ptoro commited on
Commit
afb6b63
1 Parent(s): 3c3c36a

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. phi-sft-out/README.md +156 -0
  2. phi-sft-out/adapter_config.json +33 -0
  3. phi-sft-out/adapter_model.bin +3 -0
  4. phi-sft-out/added_tokens.json +40 -0
  5. phi-sft-out/checkpoint-188/README.md +202 -0
  6. phi-sft-out/checkpoint-188/adapter_config.json +33 -0
  7. phi-sft-out/checkpoint-188/adapter_model.safetensors +3 -0
  8. phi-sft-out/checkpoint-188/added_tokens.json +40 -0
  9. phi-sft-out/checkpoint-188/merges.txt +0 -0
  10. phi-sft-out/checkpoint-188/optimizer.pt +3 -0
  11. phi-sft-out/checkpoint-188/rng_state.pth +3 -0
  12. phi-sft-out/checkpoint-188/scheduler.pt +3 -0
  13. phi-sft-out/checkpoint-188/special_tokens_map.json +30 -0
  14. phi-sft-out/checkpoint-188/tokenizer.json +0 -0
  15. phi-sft-out/checkpoint-188/tokenizer_config.json +325 -0
  16. phi-sft-out/checkpoint-188/trainer_state.json +1413 -0
  17. phi-sft-out/checkpoint-188/training_args.bin +3 -0
  18. phi-sft-out/checkpoint-188/vocab.json +0 -0
  19. phi-sft-out/checkpoint-282/README.md +202 -0
  20. phi-sft-out/checkpoint-282/adapter_config.json +33 -0
  21. phi-sft-out/checkpoint-282/adapter_model.safetensors +3 -0
  22. phi-sft-out/checkpoint-282/added_tokens.json +40 -0
  23. phi-sft-out/checkpoint-282/merges.txt +0 -0
  24. phi-sft-out/checkpoint-282/optimizer.pt +3 -0
  25. phi-sft-out/checkpoint-282/rng_state.pth +3 -0
  26. phi-sft-out/checkpoint-282/scheduler.pt +3 -0
  27. phi-sft-out/checkpoint-282/special_tokens_map.json +30 -0
  28. phi-sft-out/checkpoint-282/tokenizer.json +0 -0
  29. phi-sft-out/checkpoint-282/tokenizer_config.json +325 -0
  30. phi-sft-out/checkpoint-282/trainer_state.json +2103 -0
  31. phi-sft-out/checkpoint-282/training_args.bin +3 -0
  32. phi-sft-out/checkpoint-282/vocab.json +0 -0
  33. phi-sft-out/checkpoint-376/README.md +202 -0
  34. phi-sft-out/checkpoint-376/adapter_config.json +33 -0
  35. phi-sft-out/checkpoint-376/adapter_model.safetensors +3 -0
  36. phi-sft-out/checkpoint-376/added_tokens.json +40 -0
  37. phi-sft-out/checkpoint-376/merges.txt +0 -0
  38. phi-sft-out/checkpoint-376/optimizer.pt +3 -0
  39. phi-sft-out/checkpoint-376/rng_state.pth +3 -0
  40. phi-sft-out/checkpoint-376/scheduler.pt +3 -0
  41. phi-sft-out/checkpoint-376/special_tokens_map.json +30 -0
  42. phi-sft-out/checkpoint-376/tokenizer.json +0 -0
  43. phi-sft-out/checkpoint-376/tokenizer_config.json +325 -0
  44. phi-sft-out/checkpoint-376/trainer_state.json +2793 -0
  45. phi-sft-out/checkpoint-376/training_args.bin +3 -0
  46. phi-sft-out/checkpoint-376/vocab.json +0 -0
  47. phi-sft-out/checkpoint-94/README.md +202 -0
  48. phi-sft-out/checkpoint-94/adapter_config.json +33 -0
  49. phi-sft-out/checkpoint-94/adapter_model.safetensors +3 -0
  50. phi-sft-out/checkpoint-94/added_tokens.json +40 -0
phi-sft-out/README.md ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/phi-1_5
3
+ library_name: peft
4
+ license: mit
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: outputs/phi-sft-out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.1`
19
+ ```yaml
20
+ base_model: microsoft/phi-1_5
21
+ model_type: AutoModelForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+
24
+ load_in_8bit: false
25
+ load_in_4bit: true
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: ptoro/honkers-phi
30
+ type: alpaca
31
+
32
+ dataset_prepared_path:
33
+ val_set_size: 0.05
34
+ output_dir: ./outputs/phi-sft-out
35
+
36
+ sequence_len: 2048
37
+ sample_packing: true
38
+ pad_to_sequence_len: true
39
+
40
+ adapter: qlora
41
+ lora_model_dir:
42
+ lora_r: 64
43
+ lora_alpha: 32
44
+ lora_dropout: 0.05
45
+ lora_target_linear: true
46
+ lora_fan_in_fan_out:
47
+
48
+ wandb_project:
49
+ wandb_entity:
50
+ wandb_watch:
51
+ wandb_name:
52
+ wandb_log_model:
53
+
54
+ gradient_accumulation_steps: 1
55
+ micro_batch_size: 2
56
+ num_epochs: 4
57
+ optimizer: adamw_torch
58
+ adam_beta2: 0.95
59
+ adam_epsilon: 0.00001
60
+ max_grad_norm: 1.0
61
+ lr_scheduler: cosine
62
+ learning_rate: 0.000003
63
+
64
+ train_on_inputs: false
65
+ group_by_length: false
66
+ bf16: auto
67
+ fp16:
68
+ tf32: true
69
+
70
+ gradient_checkpointing: true
71
+ gradient_checkpointing_kwargs:
72
+ use_reentrant: True
73
+ early_stopping_patience:
74
+ resume_from_checkpoint:
75
+ local_rank:
76
+ logging_steps: 1
77
+ xformers_attention:
78
+ flash_attention: true
79
+
80
+ warmup_steps: 100
81
+ evals_per_epoch: 4
82
+ saves_per_epoch: 1
83
+ debug:
84
+ deepspeed:
85
+ weight_decay: 0.1
86
+ fsdp:
87
+ fsdp_config:
88
+ resize_token_embeddings_to_32x: true
89
+ special_tokens:
90
+ pad_token: "<|endoftext|>"
91
+
92
+ ```
93
+
94
+ </details><br>
95
+
96
+ # outputs/phi-sft-out
97
+
98
+ This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
99
+ It achieves the following results on the evaluation set:
100
+ - Loss: 1.5482
101
+
102
+ ## Model description
103
+
104
+ More information needed
105
+
106
+ ## Intended uses & limitations
107
+
108
+ More information needed
109
+
110
+ ## Training and evaluation data
111
+
112
+ More information needed
113
+
114
+ ## Training procedure
115
+
116
+ ### Training hyperparameters
117
+
118
+ The following hyperparameters were used during training:
119
+ - learning_rate: 3e-06
120
+ - train_batch_size: 2
121
+ - eval_batch_size: 2
122
+ - seed: 42
123
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
124
+ - lr_scheduler_type: cosine
125
+ - lr_scheduler_warmup_steps: 100
126
+ - num_epochs: 4
127
+
128
+ ### Training results
129
+
130
+ | Training Loss | Epoch | Step | Validation Loss |
131
+ |:-------------:|:------:|:----:|:---------------:|
132
+ | 1.2333 | 0.0106 | 1 | 1.5896 |
133
+ | 1.7286 | 0.2553 | 24 | 1.5891 |
134
+ | 1.2823 | 0.5106 | 48 | 1.5875 |
135
+ | 1.3856 | 0.7660 | 72 | 1.5844 |
136
+ | 1.244 | 1.0213 | 96 | 1.5804 |
137
+ | 1.2499 | 1.2447 | 120 | 1.5753 |
138
+ | 1.1656 | 1.5 | 144 | 1.5706 |
139
+ | 1.1928 | 1.7553 | 168 | 1.5656 |
140
+ | 1.1623 | 2.0106 | 192 | 1.5608 |
141
+ | 1.2679 | 2.2340 | 216 | 1.5571 |
142
+ | 1.2845 | 2.4894 | 240 | 1.5537 |
143
+ | 1.1226 | 2.7447 | 264 | 1.5516 |
144
+ | 1.2575 | 3.0 | 288 | 1.5497 |
145
+ | 1.2465 | 3.2234 | 312 | 1.5486 |
146
+ | 1.1699 | 3.4787 | 336 | 1.5483 |
147
+ | 1.2021 | 3.7340 | 360 | 1.5482 |
148
+
149
+
150
+ ### Framework versions
151
+
152
+ - PEFT 0.11.2.dev0
153
+ - Transformers 4.41.1
154
+ - Pytorch 2.1.2+cu118
155
+ - Datasets 2.19.1
156
+ - Tokenizers 0.19.1
phi-sft-out/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-1_5",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "fc1",
25
+ "v_proj",
26
+ "dense",
27
+ "fc2",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
phi-sft-out/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80368d659341cb7b3f65869a330e5c6e6b75044f4e5d77ebe3db3f76ca690793
3
+ size 226596042
phi-sft-out/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
phi-sft-out/checkpoint-188/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/phi-1_5
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.2.dev0
phi-sft-out/checkpoint-188/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-1_5",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "fc1",
25
+ "v_proj",
26
+ "dense",
27
+ "fc2",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
phi-sft-out/checkpoint-188/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b5b892feeb14c6625382251e26758b57036baa24f73e771fa848be3c7825ca
3
+ size 226530600
phi-sft-out/checkpoint-188/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
phi-sft-out/checkpoint-188/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
phi-sft-out/checkpoint-188/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25804b9697d1ed444578fee052dac516cf011d9291f2277fd863b351366b002a
3
+ size 453227642
phi-sft-out/checkpoint-188/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5f3aa316bb7d0ffb35ed58a795009860ed39f571b413f9a91ac45e187d4e37
3
+ size 14244
phi-sft-out/checkpoint-188/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a9b4e2304d4c84e1e8eaed6a1c791737dfbbd60f197668e8b439f2c5e51d0e3
3
+ size 1064
phi-sft-out/checkpoint-188/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
phi-sft-out/checkpoint-188/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
phi-sft-out/checkpoint-188/tokenizer_config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "pad_token": "<|endoftext|>",
322
+ "return_token_type_ids": false,
323
+ "tokenizer_class": "CodeGenTokenizer",
324
+ "unk_token": "<|endoftext|>"
325
+ }
phi-sft-out/checkpoint-188/trainer_state.json ADDED
@@ -0,0 +1,1413 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9680851063829787,
5
+ "eval_steps": 24,
6
+ "global_step": 188,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010638297872340425,
13
+ "grad_norm": 0.10508890450000763,
14
+ "learning_rate": 3.0000000000000004e-08,
15
+ "loss": 1.2333,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.010638297872340425,
20
+ "eval_loss": 1.5895557403564453,
21
+ "eval_runtime": 2.9603,
22
+ "eval_samples_per_second": 35.469,
23
+ "eval_steps_per_second": 17.903,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.02127659574468085,
28
+ "grad_norm": 0.12071573734283447,
29
+ "learning_rate": 6.000000000000001e-08,
30
+ "loss": 1.3986,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.031914893617021274,
35
+ "grad_norm": 0.10401547700166702,
36
+ "learning_rate": 9e-08,
37
+ "loss": 1.2058,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.0425531914893617,
42
+ "grad_norm": 0.12298297882080078,
43
+ "learning_rate": 1.2000000000000002e-07,
44
+ "loss": 1.3298,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.05319148936170213,
49
+ "grad_norm": 0.1327030211687088,
50
+ "learning_rate": 1.5000000000000002e-07,
51
+ "loss": 1.4031,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.06382978723404255,
56
+ "grad_norm": 0.12036772817373276,
57
+ "learning_rate": 1.8e-07,
58
+ "loss": 1.5335,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.07446808510638298,
63
+ "grad_norm": 0.14979703724384308,
64
+ "learning_rate": 2.1000000000000003e-07,
65
+ "loss": 1.3224,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.0851063829787234,
70
+ "grad_norm": 0.13082227110862732,
71
+ "learning_rate": 2.4000000000000003e-07,
72
+ "loss": 1.4035,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.09574468085106383,
77
+ "grad_norm": 0.09265327453613281,
78
+ "learning_rate": 2.7e-07,
79
+ "loss": 1.1546,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.10638297872340426,
84
+ "grad_norm": 0.10080434381961823,
85
+ "learning_rate": 3.0000000000000004e-07,
86
+ "loss": 1.2652,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.11702127659574468,
91
+ "grad_norm": 0.10915568470954895,
92
+ "learning_rate": 3.3e-07,
93
+ "loss": 1.1438,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.1276595744680851,
98
+ "grad_norm": 0.1307348906993866,
99
+ "learning_rate": 3.6e-07,
100
+ "loss": 1.2821,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.13829787234042554,
105
+ "grad_norm": 0.09814529865980148,
106
+ "learning_rate": 3.9e-07,
107
+ "loss": 1.3905,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.14893617021276595,
112
+ "grad_norm": 0.11842218786478043,
113
+ "learning_rate": 4.2000000000000006e-07,
114
+ "loss": 1.3085,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.1595744680851064,
119
+ "grad_norm": 0.10207124054431915,
120
+ "learning_rate": 4.5e-07,
121
+ "loss": 1.19,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.1702127659574468,
126
+ "grad_norm": 0.1150127425789833,
127
+ "learning_rate": 4.800000000000001e-07,
128
+ "loss": 1.386,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.18085106382978725,
133
+ "grad_norm": 0.11641352623701096,
134
+ "learning_rate": 5.100000000000001e-07,
135
+ "loss": 1.4357,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.19148936170212766,
140
+ "grad_norm": 0.15035435557365417,
141
+ "learning_rate": 5.4e-07,
142
+ "loss": 1.2549,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.20212765957446807,
147
+ "grad_norm": 0.0984087809920311,
148
+ "learning_rate": 5.7e-07,
149
+ "loss": 0.9723,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.2127659574468085,
154
+ "grad_norm": 0.11582670360803604,
155
+ "learning_rate": 6.000000000000001e-07,
156
+ "loss": 1.1402,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.22340425531914893,
161
+ "grad_norm": 0.10151291638612747,
162
+ "learning_rate": 6.3e-07,
163
+ "loss": 1.1533,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.23404255319148937,
168
+ "grad_norm": 0.09040653705596924,
169
+ "learning_rate": 6.6e-07,
170
+ "loss": 1.0438,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.24468085106382978,
175
+ "grad_norm": 0.10666865110397339,
176
+ "learning_rate": 6.900000000000001e-07,
177
+ "loss": 1.3195,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.2553191489361702,
182
+ "grad_norm": 0.12293969094753265,
183
+ "learning_rate": 7.2e-07,
184
+ "loss": 1.7286,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.2553191489361702,
189
+ "eval_loss": 1.5890721082687378,
190
+ "eval_runtime": 2.9908,
191
+ "eval_samples_per_second": 35.108,
192
+ "eval_steps_per_second": 17.721,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.26595744680851063,
197
+ "grad_norm": 0.11052387952804565,
198
+ "learning_rate": 7.5e-07,
199
+ "loss": 1.1413,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.2765957446808511,
204
+ "grad_norm": 0.09323304146528244,
205
+ "learning_rate": 7.8e-07,
206
+ "loss": 1.2906,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.2872340425531915,
211
+ "grad_norm": 0.12542971968650818,
212
+ "learning_rate": 8.100000000000001e-07,
213
+ "loss": 1.2809,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.2978723404255319,
218
+ "grad_norm": 0.1080215722322464,
219
+ "learning_rate": 8.400000000000001e-07,
220
+ "loss": 1.2735,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.30851063829787234,
225
+ "grad_norm": 0.11304887384176254,
226
+ "learning_rate": 8.699999999999999e-07,
227
+ "loss": 1.3767,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.3191489361702128,
232
+ "grad_norm": 0.15650290250778198,
233
+ "learning_rate": 9e-07,
234
+ "loss": 1.4713,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.32978723404255317,
239
+ "grad_norm": 0.12139321118593216,
240
+ "learning_rate": 9.3e-07,
241
+ "loss": 1.3479,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.3404255319148936,
246
+ "grad_norm": 0.10141867399215698,
247
+ "learning_rate": 9.600000000000001e-07,
248
+ "loss": 1.1512,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.35106382978723405,
253
+ "grad_norm": 0.15045498311519623,
254
+ "learning_rate": 9.9e-07,
255
+ "loss": 1.5059,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.3617021276595745,
260
+ "grad_norm": 0.12956956028938293,
261
+ "learning_rate": 1.0200000000000002e-06,
262
+ "loss": 1.2849,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.3723404255319149,
267
+ "grad_norm": 0.12963886559009552,
268
+ "learning_rate": 1.05e-06,
269
+ "loss": 1.5025,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.3829787234042553,
274
+ "grad_norm": 0.11268144845962524,
275
+ "learning_rate": 1.08e-06,
276
+ "loss": 1.2987,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.39361702127659576,
281
+ "grad_norm": 0.12941108644008636,
282
+ "learning_rate": 1.11e-06,
283
+ "loss": 1.3432,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.40425531914893614,
288
+ "grad_norm": 0.11319927126169205,
289
+ "learning_rate": 1.14e-06,
290
+ "loss": 1.1665,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.4148936170212766,
295
+ "grad_norm": 0.11748912930488586,
296
+ "learning_rate": 1.17e-06,
297
+ "loss": 1.423,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.425531914893617,
302
+ "grad_norm": 0.11666171997785568,
303
+ "learning_rate": 1.2000000000000002e-06,
304
+ "loss": 1.4391,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.43617021276595747,
309
+ "grad_norm": 0.12274409830570221,
310
+ "learning_rate": 1.2299999999999999e-06,
311
+ "loss": 1.4865,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.44680851063829785,
316
+ "grad_norm": 0.09922561049461365,
317
+ "learning_rate": 1.26e-06,
318
+ "loss": 1.2193,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.4574468085106383,
323
+ "grad_norm": 0.12003930658102036,
324
+ "learning_rate": 1.29e-06,
325
+ "loss": 1.3024,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.46808510638297873,
330
+ "grad_norm": 0.12094161659479141,
331
+ "learning_rate": 1.32e-06,
332
+ "loss": 1.4654,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.4787234042553192,
337
+ "grad_norm": 0.12934774160385132,
338
+ "learning_rate": 1.35e-06,
339
+ "loss": 1.3713,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.48936170212765956,
344
+ "grad_norm": 0.09754550457000732,
345
+ "learning_rate": 1.3800000000000001e-06,
346
+ "loss": 1.1991,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.5,
351
+ "grad_norm": 0.11549004167318344,
352
+ "learning_rate": 1.41e-06,
353
+ "loss": 1.4859,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.5106382978723404,
358
+ "grad_norm": 0.12035688012838364,
359
+ "learning_rate": 1.44e-06,
360
+ "loss": 1.2823,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.5106382978723404,
365
+ "eval_loss": 1.5874611139297485,
366
+ "eval_runtime": 2.9787,
367
+ "eval_samples_per_second": 35.251,
368
+ "eval_steps_per_second": 17.793,
369
+ "step": 48
370
+ },
371
+ {
372
+ "epoch": 0.5212765957446809,
373
+ "grad_norm": 0.12258938699960709,
374
+ "learning_rate": 1.4700000000000001e-06,
375
+ "loss": 1.2966,
376
+ "step": 49
377
+ },
378
+ {
379
+ "epoch": 0.5319148936170213,
380
+ "grad_norm": 0.12217017263174057,
381
+ "learning_rate": 1.5e-06,
382
+ "loss": 1.2988,
383
+ "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.5425531914893617,
387
+ "grad_norm": 0.12793436646461487,
388
+ "learning_rate": 1.53e-06,
389
+ "loss": 1.4233,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.5531914893617021,
394
+ "grad_norm": 0.11145548522472382,
395
+ "learning_rate": 1.56e-06,
396
+ "loss": 1.2792,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.5638297872340425,
401
+ "grad_norm": 0.13195408880710602,
402
+ "learning_rate": 1.59e-06,
403
+ "loss": 1.4481,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.574468085106383,
408
+ "grad_norm": 0.10663347691297531,
409
+ "learning_rate": 1.6200000000000002e-06,
410
+ "loss": 1.2331,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.5851063829787234,
415
+ "grad_norm": 0.10975392907857895,
416
+ "learning_rate": 1.65e-06,
417
+ "loss": 1.1839,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.5957446808510638,
422
+ "grad_norm": 0.13139477372169495,
423
+ "learning_rate": 1.6800000000000002e-06,
424
+ "loss": 1.436,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.6063829787234043,
429
+ "grad_norm": 0.0924743041396141,
430
+ "learning_rate": 1.71e-06,
431
+ "loss": 1.1291,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.6170212765957447,
436
+ "grad_norm": 0.12475109100341797,
437
+ "learning_rate": 1.7399999999999999e-06,
438
+ "loss": 1.3444,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.6276595744680851,
443
+ "grad_norm": 0.08960220962762833,
444
+ "learning_rate": 1.77e-06,
445
+ "loss": 1.2511,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.6382978723404256,
450
+ "grad_norm": 0.09909304976463318,
451
+ "learning_rate": 1.8e-06,
452
+ "loss": 1.1281,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.648936170212766,
457
+ "grad_norm": 0.11598234623670578,
458
+ "learning_rate": 1.83e-06,
459
+ "loss": 1.486,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.6595744680851063,
464
+ "grad_norm": 0.1404409557580948,
465
+ "learning_rate": 1.86e-06,
466
+ "loss": 1.4557,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.6702127659574468,
471
+ "grad_norm": 0.11349129676818848,
472
+ "learning_rate": 1.8900000000000001e-06,
473
+ "loss": 1.3969,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.6808510638297872,
478
+ "grad_norm": 0.10858353972434998,
479
+ "learning_rate": 1.9200000000000003e-06,
480
+ "loss": 1.3515,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.6914893617021277,
485
+ "grad_norm": 0.11054569482803345,
486
+ "learning_rate": 1.95e-06,
487
+ "loss": 1.248,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.7021276595744681,
492
+ "grad_norm": 0.11826737225055695,
493
+ "learning_rate": 1.98e-06,
494
+ "loss": 1.3439,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.7127659574468085,
499
+ "grad_norm": 0.12291310727596283,
500
+ "learning_rate": 2.0100000000000002e-06,
501
+ "loss": 1.4226,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.723404255319149,
506
+ "grad_norm": 0.1383126825094223,
507
+ "learning_rate": 2.0400000000000004e-06,
508
+ "loss": 1.194,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.7340425531914894,
513
+ "grad_norm": 0.10981890559196472,
514
+ "learning_rate": 2.07e-06,
515
+ "loss": 1.2502,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.7446808510638298,
520
+ "grad_norm": 0.10639657825231552,
521
+ "learning_rate": 2.1e-06,
522
+ "loss": 1.2262,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.7553191489361702,
527
+ "grad_norm": 0.46177396178245544,
528
+ "learning_rate": 2.13e-06,
529
+ "loss": 5.063,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.7659574468085106,
534
+ "grad_norm": 0.11061427742242813,
535
+ "learning_rate": 2.16e-06,
536
+ "loss": 1.3856,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.7659574468085106,
541
+ "eval_loss": 1.5843762159347534,
542
+ "eval_runtime": 2.9943,
543
+ "eval_samples_per_second": 35.066,
544
+ "eval_steps_per_second": 17.7,
545
+ "step": 72
546
+ },
547
+ {
548
+ "epoch": 0.776595744680851,
549
+ "grad_norm": 0.13233324885368347,
550
+ "learning_rate": 2.19e-06,
551
+ "loss": 1.526,
552
+ "step": 73
553
+ },
554
+ {
555
+ "epoch": 0.7872340425531915,
556
+ "grad_norm": 0.14500053226947784,
557
+ "learning_rate": 2.22e-06,
558
+ "loss": 1.2554,
559
+ "step": 74
560
+ },
561
+ {
562
+ "epoch": 0.7978723404255319,
563
+ "grad_norm": 0.10629269480705261,
564
+ "learning_rate": 2.25e-06,
565
+ "loss": 1.2917,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 0.8085106382978723,
570
+ "grad_norm": 0.09674028307199478,
571
+ "learning_rate": 2.28e-06,
572
+ "loss": 1.2169,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 0.8191489361702128,
577
+ "grad_norm": 0.11965947598218918,
578
+ "learning_rate": 2.31e-06,
579
+ "loss": 1.2445,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 0.8297872340425532,
584
+ "grad_norm": 0.10441229492425919,
585
+ "learning_rate": 2.34e-06,
586
+ "loss": 1.2392,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 0.8404255319148937,
591
+ "grad_norm": 0.13795869052410126,
592
+ "learning_rate": 2.37e-06,
593
+ "loss": 1.5335,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 0.851063829787234,
598
+ "grad_norm": 0.10789927840232849,
599
+ "learning_rate": 2.4000000000000003e-06,
600
+ "loss": 1.2309,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 0.8617021276595744,
605
+ "grad_norm": 0.10697130113840103,
606
+ "learning_rate": 2.43e-06,
607
+ "loss": 1.276,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 0.8723404255319149,
612
+ "grad_norm": 0.11484125256538391,
613
+ "learning_rate": 2.4599999999999997e-06,
614
+ "loss": 1.2163,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 0.8829787234042553,
619
+ "grad_norm": 0.09692610800266266,
620
+ "learning_rate": 2.49e-06,
621
+ "loss": 1.1554,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 0.8936170212765957,
626
+ "grad_norm": 0.10697747021913528,
627
+ "learning_rate": 2.52e-06,
628
+ "loss": 1.211,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 0.9042553191489362,
633
+ "grad_norm": 0.10578318685293198,
634
+ "learning_rate": 2.55e-06,
635
+ "loss": 1.2634,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 0.9148936170212766,
640
+ "grad_norm": 0.10587752610445023,
641
+ "learning_rate": 2.58e-06,
642
+ "loss": 1.369,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 0.925531914893617,
647
+ "grad_norm": 0.11430489271879196,
648
+ "learning_rate": 2.61e-06,
649
+ "loss": 1.3048,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 0.9361702127659575,
654
+ "grad_norm": 0.11116154491901398,
655
+ "learning_rate": 2.64e-06,
656
+ "loss": 1.1883,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 0.9468085106382979,
661
+ "grad_norm": 0.12686476111412048,
662
+ "learning_rate": 2.6700000000000003e-06,
663
+ "loss": 1.2605,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 0.9574468085106383,
668
+ "grad_norm": 0.10976041853427887,
669
+ "learning_rate": 2.7e-06,
670
+ "loss": 1.2345,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 0.9680851063829787,
675
+ "grad_norm": 0.12391550838947296,
676
+ "learning_rate": 2.73e-06,
677
+ "loss": 1.2233,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 0.9787234042553191,
682
+ "grad_norm": 0.1277073174715042,
683
+ "learning_rate": 2.7600000000000003e-06,
684
+ "loss": 1.2437,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 0.9893617021276596,
689
+ "grad_norm": 0.10421616584062576,
690
+ "learning_rate": 2.7900000000000004e-06,
691
+ "loss": 1.1432,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 1.0,
696
+ "grad_norm": 0.12696842849254608,
697
+ "learning_rate": 2.82e-06,
698
+ "loss": 1.3558,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 1.0106382978723405,
703
+ "grad_norm": 0.10387945920228958,
704
+ "learning_rate": 2.85e-06,
705
+ "loss": 1.1902,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 1.0212765957446808,
710
+ "grad_norm": 0.14543002843856812,
711
+ "learning_rate": 2.88e-06,
712
+ "loss": 1.244,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 1.0212765957446808,
717
+ "eval_loss": 1.5803985595703125,
718
+ "eval_runtime": 3.0087,
719
+ "eval_samples_per_second": 34.899,
720
+ "eval_steps_per_second": 17.616,
721
+ "step": 96
722
+ },
723
+ {
724
+ "epoch": 1.0319148936170213,
725
+ "grad_norm": 0.17504040896892548,
726
+ "learning_rate": 2.91e-06,
727
+ "loss": 1.3115,
728
+ "step": 97
729
+ },
730
+ {
731
+ "epoch": 1.0106382978723405,
732
+ "grad_norm": 0.14017756283283234,
733
+ "learning_rate": 2.9400000000000002e-06,
734
+ "loss": 1.356,
735
+ "step": 98
736
+ },
737
+ {
738
+ "epoch": 1.0212765957446808,
739
+ "grad_norm": 0.11604318767786026,
740
+ "learning_rate": 2.97e-06,
741
+ "loss": 1.2806,
742
+ "step": 99
743
+ },
744
+ {
745
+ "epoch": 1.0319148936170213,
746
+ "grad_norm": 0.15116065740585327,
747
+ "learning_rate": 3e-06,
748
+ "loss": 1.3279,
749
+ "step": 100
750
+ },
751
+ {
752
+ "epoch": 1.0425531914893618,
753
+ "grad_norm": 0.10773392021656036,
754
+ "learning_rate": 2.9999028286680832e-06,
755
+ "loss": 1.3871,
756
+ "step": 101
757
+ },
758
+ {
759
+ "epoch": 1.053191489361702,
760
+ "grad_norm": 0.09363637119531631,
761
+ "learning_rate": 2.999611327262024e-06,
762
+ "loss": 1.1334,
763
+ "step": 102
764
+ },
765
+ {
766
+ "epoch": 1.0638297872340425,
767
+ "grad_norm": 0.09164439886808395,
768
+ "learning_rate": 2.999125533549261e-06,
769
+ "loss": 1.4026,
770
+ "step": 103
771
+ },
772
+ {
773
+ "epoch": 1.074468085106383,
774
+ "grad_norm": 0.12113964557647705,
775
+ "learning_rate": 2.9984455104700915e-06,
776
+ "loss": 1.2097,
777
+ "step": 104
778
+ },
779
+ {
780
+ "epoch": 1.0851063829787233,
781
+ "grad_norm": 0.10569895058870316,
782
+ "learning_rate": 2.9975713461295125e-06,
783
+ "loss": 1.3077,
784
+ "step": 105
785
+ },
786
+ {
787
+ "epoch": 1.0957446808510638,
788
+ "grad_norm": 0.11219862103462219,
789
+ "learning_rate": 2.996503153785809e-06,
790
+ "loss": 1.1923,
791
+ "step": 106
792
+ },
793
+ {
794
+ "epoch": 1.1063829787234043,
795
+ "grad_norm": 0.13474853336811066,
796
+ "learning_rate": 2.9952410718358777e-06,
797
+ "loss": 1.2729,
798
+ "step": 107
799
+ },
800
+ {
801
+ "epoch": 1.1170212765957448,
802
+ "grad_norm": 0.10451857000589371,
803
+ "learning_rate": 2.993785263797297e-06,
804
+ "loss": 1.2904,
805
+ "step": 108
806
+ },
807
+ {
808
+ "epoch": 1.127659574468085,
809
+ "grad_norm": 0.12593719363212585,
810
+ "learning_rate": 2.9921359182871422e-06,
811
+ "loss": 1.4021,
812
+ "step": 109
813
+ },
814
+ {
815
+ "epoch": 1.1382978723404256,
816
+ "grad_norm": 0.12547315657138824,
817
+ "learning_rate": 2.990293248997547e-06,
818
+ "loss": 1.2093,
819
+ "step": 110
820
+ },
821
+ {
822
+ "epoch": 1.148936170212766,
823
+ "grad_norm": 0.10086555033922195,
824
+ "learning_rate": 2.988257494668016e-06,
825
+ "loss": 1.3098,
826
+ "step": 111
827
+ },
828
+ {
829
+ "epoch": 1.1595744680851063,
830
+ "grad_norm": 0.10801573097705841,
831
+ "learning_rate": 2.9860289190544963e-06,
832
+ "loss": 1.2752,
833
+ "step": 112
834
+ },
835
+ {
836
+ "epoch": 1.1702127659574468,
837
+ "grad_norm": 0.11851054430007935,
838
+ "learning_rate": 2.9836078108952015e-06,
839
+ "loss": 1.3066,
840
+ "step": 113
841
+ },
842
+ {
843
+ "epoch": 1.1808510638297873,
844
+ "grad_norm": 0.1265188604593277,
845
+ "learning_rate": 2.9809944838732045e-06,
846
+ "loss": 1.1946,
847
+ "step": 114
848
+ },
849
+ {
850
+ "epoch": 1.1914893617021276,
851
+ "grad_norm": 0.10702725499868393,
852
+ "learning_rate": 2.9781892765757954e-06,
853
+ "loss": 1.2182,
854
+ "step": 115
855
+ },
856
+ {
857
+ "epoch": 1.202127659574468,
858
+ "grad_norm": 0.7757766842842102,
859
+ "learning_rate": 2.9751925524506135e-06,
860
+ "loss": 5.6082,
861
+ "step": 116
862
+ },
863
+ {
864
+ "epoch": 1.2127659574468086,
865
+ "grad_norm": 0.10182739049196243,
866
+ "learning_rate": 2.9720046997585577e-06,
867
+ "loss": 1.309,
868
+ "step": 117
869
+ },
870
+ {
871
+ "epoch": 1.2234042553191489,
872
+ "grad_norm": 0.14062073826789856,
873
+ "learning_rate": 2.9686261315234844e-06,
874
+ "loss": 1.3668,
875
+ "step": 118
876
+ },
877
+ {
878
+ "epoch": 1.2340425531914894,
879
+ "grad_norm": 0.1063840240240097,
880
+ "learning_rate": 2.965057285478694e-06,
881
+ "loss": 1.2247,
882
+ "step": 119
883
+ },
884
+ {
885
+ "epoch": 1.2446808510638299,
886
+ "grad_norm": 0.10701325535774231,
887
+ "learning_rate": 2.961298624010219e-06,
888
+ "loss": 1.2499,
889
+ "step": 120
890
+ },
891
+ {
892
+ "epoch": 1.2446808510638299,
893
+ "eval_loss": 1.575344204902649,
894
+ "eval_runtime": 8.2617,
895
+ "eval_samples_per_second": 12.709,
896
+ "eval_steps_per_second": 6.415,
897
+ "step": 120
898
+ },
899
+ {
900
+ "epoch": 1.2553191489361701,
901
+ "grad_norm": 0.11413375288248062,
902
+ "learning_rate": 2.957350634096912e-06,
903
+ "loss": 1.3593,
904
+ "step": 121
905
+ },
906
+ {
907
+ "epoch": 1.2659574468085106,
908
+ "grad_norm": 0.10826950520277023,
909
+ "learning_rate": 2.9532138272473597e-06,
910
+ "loss": 1.232,
911
+ "step": 122
912
+ },
913
+ {
914
+ "epoch": 1.2765957446808511,
915
+ "grad_norm": 0.10749218612909317,
916
+ "learning_rate": 2.9488887394336023e-06,
917
+ "loss": 1.401,
918
+ "step": 123
919
+ },
920
+ {
921
+ "epoch": 1.2872340425531914,
922
+ "grad_norm": 0.1175396591424942,
923
+ "learning_rate": 2.944375931021699e-06,
924
+ "loss": 1.2867,
925
+ "step": 124
926
+ },
927
+ {
928
+ "epoch": 1.297872340425532,
929
+ "grad_norm": 0.10688498616218567,
930
+ "learning_rate": 2.9396759866991214e-06,
931
+ "loss": 1.3689,
932
+ "step": 125
933
+ },
934
+ {
935
+ "epoch": 1.3085106382978724,
936
+ "grad_norm": 0.11630786955356598,
937
+ "learning_rate": 2.934789515399002e-06,
938
+ "loss": 1.2328,
939
+ "step": 126
940
+ },
941
+ {
942
+ "epoch": 1.3191489361702127,
943
+ "grad_norm": 0.11495409905910492,
944
+ "learning_rate": 2.9297171502212414e-06,
945
+ "loss": 1.1738,
946
+ "step": 127
947
+ },
948
+ {
949
+ "epoch": 1.3297872340425532,
950
+ "grad_norm": 0.10823408514261246,
951
+ "learning_rate": 2.924459548350479e-06,
952
+ "loss": 1.2318,
953
+ "step": 128
954
+ },
955
+ {
956
+ "epoch": 1.3404255319148937,
957
+ "grad_norm": 0.10759969800710678,
958
+ "learning_rate": 2.9190173909709506e-06,
959
+ "loss": 1.319,
960
+ "step": 129
961
+ },
962
+ {
963
+ "epoch": 1.351063829787234,
964
+ "grad_norm": 0.12790299952030182,
965
+ "learning_rate": 2.9133913831782307e-06,
966
+ "loss": 1.4282,
967
+ "step": 130
968
+ },
969
+ {
970
+ "epoch": 1.3617021276595744,
971
+ "grad_norm": 0.10899878293275833,
972
+ "learning_rate": 2.9075822538878805e-06,
973
+ "loss": 1.2455,
974
+ "step": 131
975
+ },
976
+ {
977
+ "epoch": 1.372340425531915,
978
+ "grad_norm": 0.12732432782649994,
979
+ "learning_rate": 2.9015907557410068e-06,
980
+ "loss": 1.2227,
981
+ "step": 132
982
+ },
983
+ {
984
+ "epoch": 1.3829787234042552,
985
+ "grad_norm": 0.10140018165111542,
986
+ "learning_rate": 2.8954176650067494e-06,
987
+ "loss": 1.0596,
988
+ "step": 133
989
+ },
990
+ {
991
+ "epoch": 1.3936170212765957,
992
+ "grad_norm": 0.12063546478748322,
993
+ "learning_rate": 2.889063781481708e-06,
994
+ "loss": 1.3321,
995
+ "step": 134
996
+ },
997
+ {
998
+ "epoch": 1.4042553191489362,
999
+ "grad_norm": 0.11323118209838867,
1000
+ "learning_rate": 2.8825299283863144e-06,
1001
+ "loss": 1.3366,
1002
+ "step": 135
1003
+ },
1004
+ {
1005
+ "epoch": 1.4148936170212765,
1006
+ "grad_norm": 0.12391477078199387,
1007
+ "learning_rate": 2.8758169522581796e-06,
1008
+ "loss": 1.2917,
1009
+ "step": 136
1010
+ },
1011
+ {
1012
+ "epoch": 1.425531914893617,
1013
+ "grad_norm": 0.12329094856977463,
1014
+ "learning_rate": 2.8689257228424125e-06,
1015
+ "loss": 1.1365,
1016
+ "step": 137
1017
+ },
1018
+ {
1019
+ "epoch": 1.4361702127659575,
1020
+ "grad_norm": 0.11298198997974396,
1021
+ "learning_rate": 2.8618571329789333e-06,
1022
+ "loss": 1.4996,
1023
+ "step": 138
1024
+ },
1025
+ {
1026
+ "epoch": 1.4468085106382977,
1027
+ "grad_norm": 0.10263165086507797,
1028
+ "learning_rate": 2.8546120984867994e-06,
1029
+ "loss": 1.199,
1030
+ "step": 139
1031
+ },
1032
+ {
1033
+ "epoch": 1.4574468085106382,
1034
+ "grad_norm": 0.13330323994159698,
1035
+ "learning_rate": 2.8471915580455442e-06,
1036
+ "loss": 1.3746,
1037
+ "step": 140
1038
+ },
1039
+ {
1040
+ "epoch": 1.4680851063829787,
1041
+ "grad_norm": 0.10694881528615952,
1042
+ "learning_rate": 2.8395964730735666e-06,
1043
+ "loss": 1.3798,
1044
+ "step": 141
1045
+ },
1046
+ {
1047
+ "epoch": 1.4787234042553192,
1048
+ "grad_norm": 0.10929003357887268,
1049
+ "learning_rate": 2.8318278276035626e-06,
1050
+ "loss": 1.2918,
1051
+ "step": 142
1052
+ },
1053
+ {
1054
+ "epoch": 1.4893617021276595,
1055
+ "grad_norm": 0.10969982296228409,
1056
+ "learning_rate": 2.8238866281550366e-06,
1057
+ "loss": 1.0444,
1058
+ "step": 143
1059
+ },
1060
+ {
1061
+ "epoch": 1.5,
1062
+ "grad_norm": 0.10668367147445679,
1063
+ "learning_rate": 2.815773903603892e-06,
1064
+ "loss": 1.1656,
1065
+ "step": 144
1066
+ },
1067
+ {
1068
+ "epoch": 1.5,
1069
+ "eval_loss": 1.5705612897872925,
1070
+ "eval_runtime": 5.6853,
1071
+ "eval_samples_per_second": 18.469,
1072
+ "eval_steps_per_second": 9.322,
1073
+ "step": 144
1074
+ },
1075
+ {
1076
+ "epoch": 1.5106382978723403,
1077
+ "grad_norm": 0.12057002633810043,
1078
+ "learning_rate": 2.807490705049127e-06,
1079
+ "loss": 1.2475,
1080
+ "step": 145
1081
+ },
1082
+ {
1083
+ "epoch": 1.521276595744681,
1084
+ "grad_norm": 0.10394139587879181,
1085
+ "learning_rate": 2.7990381056766585e-06,
1086
+ "loss": 1.3376,
1087
+ "step": 146
1088
+ },
1089
+ {
1090
+ "epoch": 1.5319148936170213,
1091
+ "grad_norm": 0.12907464802265167,
1092
+ "learning_rate": 2.7904172006202705e-06,
1093
+ "loss": 1.3509,
1094
+ "step": 147
1095
+ },
1096
+ {
1097
+ "epoch": 1.5425531914893615,
1098
+ "grad_norm": 0.1252606213092804,
1099
+ "learning_rate": 2.7816291068197328e-06,
1100
+ "loss": 1.1744,
1101
+ "step": 148
1102
+ },
1103
+ {
1104
+ "epoch": 1.5531914893617023,
1105
+ "grad_norm": 0.1514441967010498,
1106
+ "learning_rate": 2.772674962876085e-06,
1107
+ "loss": 1.9324,
1108
+ "step": 149
1109
+ },
1110
+ {
1111
+ "epoch": 1.5638297872340425,
1112
+ "grad_norm": 0.12377320230007172,
1113
+ "learning_rate": 2.7635559289041174e-06,
1114
+ "loss": 1.4511,
1115
+ "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 1.574468085106383,
1119
+ "grad_norm": 0.10629550367593765,
1120
+ "learning_rate": 2.7542731863820665e-06,
1121
+ "loss": 1.257,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 1.5851063829787235,
1126
+ "grad_norm": 0.10322704166173935,
1127
+ "learning_rate": 2.744827937998538e-06,
1128
+ "loss": 1.1796,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 1.5957446808510638,
1133
+ "grad_norm": 0.12690168619155884,
1134
+ "learning_rate": 2.735221407496686e-06,
1135
+ "loss": 1.3325,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 1.6063829787234043,
1140
+ "grad_norm": 0.0982392430305481,
1141
+ "learning_rate": 2.725454839515663e-06,
1142
+ "loss": 1.2169,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 1.6170212765957448,
1147
+ "grad_norm": 0.11184275150299072,
1148
+ "learning_rate": 2.7155294994293606e-06,
1149
+ "loss": 1.295,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 1.627659574468085,
1154
+ "grad_norm": 0.10721098631620407,
1155
+ "learning_rate": 2.7054466731824676e-06,
1156
+ "loss": 1.1945,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 1.6382978723404256,
1161
+ "grad_norm": 0.1254221498966217,
1162
+ "learning_rate": 2.695207667123857e-06,
1163
+ "loss": 1.2693,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 1.648936170212766,
1168
+ "grad_norm": 0.1157686784863472,
1169
+ "learning_rate": 2.684813807837338e-06,
1170
+ "loss": 1.1992,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 1.6595744680851063,
1175
+ "grad_norm": 0.10201229155063629,
1176
+ "learning_rate": 2.674266441969778e-06,
1177
+ "loss": 1.2401,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 1.6702127659574468,
1182
+ "grad_norm": 0.10953360050916672,
1183
+ "learning_rate": 2.6635669360566298e-06,
1184
+ "loss": 1.1627,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 1.6808510638297873,
1189
+ "grad_norm": 0.1248813271522522,
1190
+ "learning_rate": 2.652716676344881e-06,
1191
+ "loss": 1.3179,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 1.6914893617021276,
1196
+ "grad_norm": 0.09584470838308334,
1197
+ "learning_rate": 2.6417170686134472e-06,
1198
+ "loss": 1.2128,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 1.702127659574468,
1203
+ "grad_norm": 0.12864486873149872,
1204
+ "learning_rate": 2.630569537991042e-06,
1205
+ "loss": 1.1889,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 1.7127659574468086,
1210
+ "grad_norm": 0.11820186674594879,
1211
+ "learning_rate": 2.6192755287715282e-06,
1212
+ "loss": 1.2848,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 1.7234042553191489,
1217
+ "grad_norm": 0.13811764121055603,
1218
+ "learning_rate": 2.6078365042267987e-06,
1219
+ "loss": 1.2091,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 1.7340425531914894,
1224
+ "grad_norm": 0.12099539488554001,
1225
+ "learning_rate": 2.5962539464171862e-06,
1226
+ "loss": 1.2853,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 1.7446808510638299,
1231
+ "grad_norm": 0.14544783532619476,
1232
+ "learning_rate": 2.5845293559994513e-06,
1233
+ "loss": 1.1574,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 1.7553191489361701,
1238
+ "grad_norm": 0.11159494519233704,
1239
+ "learning_rate": 2.5726642520323493e-06,
1240
+ "loss": 1.1928,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 1.7553191489361701,
1245
+ "eval_loss": 1.5656005144119263,
1246
+ "eval_runtime": 3.0568,
1247
+ "eval_samples_per_second": 34.349,
1248
+ "eval_steps_per_second": 17.338,
1249
+ "step": 168
1250
+ },
1251
+ {
1252
+ "epoch": 1.7659574468085106,
1253
+ "grad_norm": 0.1385321319103241,
1254
+ "learning_rate": 2.5606601717798212e-06,
1255
+ "loss": 1.365,
1256
+ "step": 169
1257
+ },
1258
+ {
1259
+ "epoch": 1.7765957446808511,
1260
+ "grad_norm": 0.12905962765216827,
1261
+ "learning_rate": 2.548518670511823e-06,
1262
+ "loss": 1.3664,
1263
+ "step": 170
1264
+ },
1265
+ {
1266
+ "epoch": 1.7872340425531914,
1267
+ "grad_norm": 0.09589093923568726,
1268
+ "learning_rate": 2.536241321302821e-06,
1269
+ "loss": 1.1508,
1270
+ "step": 171
1271
+ },
1272
+ {
1273
+ "epoch": 1.797872340425532,
1274
+ "grad_norm": 0.12533985078334808,
1275
+ "learning_rate": 2.5238297148279814e-06,
1276
+ "loss": 1.2892,
1277
+ "step": 172
1278
+ },
1279
+ {
1280
+ "epoch": 1.8085106382978724,
1281
+ "grad_norm": 0.11337278038263321,
1282
+ "learning_rate": 2.5112854591570804e-06,
1283
+ "loss": 1.2772,
1284
+ "step": 173
1285
+ },
1286
+ {
1287
+ "epoch": 1.8191489361702127,
1288
+ "grad_norm": 0.1345362514257431,
1289
+ "learning_rate": 2.4986101795461608e-06,
1290
+ "loss": 1.3583,
1291
+ "step": 174
1292
+ },
1293
+ {
1294
+ "epoch": 1.8297872340425532,
1295
+ "grad_norm": 0.121876560151577,
1296
+ "learning_rate": 2.485805518226959e-06,
1297
+ "loss": 1.2065,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 1.8404255319148937,
1302
+ "grad_norm": 0.10669907927513123,
1303
+ "learning_rate": 2.4728731341941343e-06,
1304
+ "loss": 1.2339,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 1.851063829787234,
1309
+ "grad_norm": 0.12710174918174744,
1310
+ "learning_rate": 2.4598147029903284e-06,
1311
+ "loss": 1.4597,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 1.8617021276595744,
1316
+ "grad_norm": 0.11735282093286514,
1317
+ "learning_rate": 2.4466319164890795e-06,
1318
+ "loss": 1.2273,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 1.872340425531915,
1323
+ "grad_norm": 0.12083889544010162,
1324
+ "learning_rate": 2.4333264826756165e-06,
1325
+ "loss": 1.3051,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 1.8829787234042552,
1330
+ "grad_norm": 0.10338792204856873,
1331
+ "learning_rate": 2.4199001254255746e-06,
1332
+ "loss": 1.3827,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 1.8936170212765957,
1337
+ "grad_norm": 0.10191334784030914,
1338
+ "learning_rate": 2.406354584281642e-06,
1339
+ "loss": 1.4067,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 1.9042553191489362,
1344
+ "grad_norm": 0.10776273161172867,
1345
+ "learning_rate": 2.3926916142281846e-06,
1346
+ "loss": 1.2344,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 1.9148936170212765,
1351
+ "grad_norm": 0.1253603845834732,
1352
+ "learning_rate": 2.378912985463867e-06,
1353
+ "loss": 1.2179,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 1.925531914893617,
1358
+ "grad_norm": 0.09942696243524551,
1359
+ "learning_rate": 2.365020483172301e-06,
1360
+ "loss": 1.0613,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 1.9361702127659575,
1365
+ "grad_norm": 0.10441701859235764,
1366
+ "learning_rate": 2.351015907290755e-06,
1367
+ "loss": 1.3886,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 1.9468085106382977,
1372
+ "grad_norm": 0.10571073740720749,
1373
+ "learning_rate": 2.3369010722769502e-06,
1374
+ "loss": 1.2023,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 1.9574468085106385,
1379
+ "grad_norm": 0.12477201223373413,
1380
+ "learning_rate": 2.3226778068739783e-06,
1381
+ "loss": 1.361,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 1.9680851063829787,
1386
+ "grad_norm": 0.12106247246265411,
1387
+ "learning_rate": 2.3083479538733636e-06,
1388
+ "loss": 1.4153,
1389
+ "step": 188
1390
+ }
1391
+ ],
1392
+ "logging_steps": 1,
1393
+ "max_steps": 376,
1394
+ "num_input_tokens_seen": 0,
1395
+ "num_train_epochs": 4,
1396
+ "save_steps": 94,
1397
+ "stateful_callbacks": {
1398
+ "TrainerControl": {
1399
+ "args": {
1400
+ "should_epoch_stop": false,
1401
+ "should_evaluate": false,
1402
+ "should_log": false,
1403
+ "should_save": true,
1404
+ "should_training_stop": false
1405
+ },
1406
+ "attributes": {}
1407
+ }
1408
+ },
1409
+ "total_flos": 6313126920192000.0,
1410
+ "train_batch_size": 2,
1411
+ "trial_name": null,
1412
+ "trial_params": null
1413
+ }
phi-sft-out/checkpoint-188/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3385717d244ba6cd34f9a94de02b9440c435857ff1e640e8a1c7255c180c1b8
3
+ size 6008
phi-sft-out/checkpoint-188/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
phi-sft-out/checkpoint-282/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/phi-1_5
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.2.dev0
phi-sft-out/checkpoint-282/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-1_5",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "fc1",
25
+ "v_proj",
26
+ "dense",
27
+ "fc2",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
phi-sft-out/checkpoint-282/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6bc85608733ba656dcea73ca548f991c037a142239296b421394fab397d592
3
+ size 226530600
phi-sft-out/checkpoint-282/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
phi-sft-out/checkpoint-282/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
phi-sft-out/checkpoint-282/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cc21951633413b444a59ca17c326286efe99637ab2c737f13d5ffe911881396
3
+ size 453227642
phi-sft-out/checkpoint-282/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca1cc74a3745d191ce868b3a77914352d382ffa7fe0b75ac3c0939bae1eb286
3
+ size 14244
phi-sft-out/checkpoint-282/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3c8b7c4f8c0543a50c7d31d5ea1723a28e5a41b54bf3786034855407ca470e
3
+ size 1064
phi-sft-out/checkpoint-282/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
phi-sft-out/checkpoint-282/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
phi-sft-out/checkpoint-282/tokenizer_config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "pad_token": "<|endoftext|>",
322
+ "return_token_type_ids": false,
323
+ "tokenizer_class": "CodeGenTokenizer",
324
+ "unk_token": "<|endoftext|>"
325
+ }
phi-sft-out/checkpoint-282/trainer_state.json ADDED
@@ -0,0 +1,2103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9361702127659575,
5
+ "eval_steps": 24,
6
+ "global_step": 282,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010638297872340425,
13
+ "grad_norm": 0.10508890450000763,
14
+ "learning_rate": 3.0000000000000004e-08,
15
+ "loss": 1.2333,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.010638297872340425,
20
+ "eval_loss": 1.5895557403564453,
21
+ "eval_runtime": 2.9603,
22
+ "eval_samples_per_second": 35.469,
23
+ "eval_steps_per_second": 17.903,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.02127659574468085,
28
+ "grad_norm": 0.12071573734283447,
29
+ "learning_rate": 6.000000000000001e-08,
30
+ "loss": 1.3986,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.031914893617021274,
35
+ "grad_norm": 0.10401547700166702,
36
+ "learning_rate": 9e-08,
37
+ "loss": 1.2058,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.0425531914893617,
42
+ "grad_norm": 0.12298297882080078,
43
+ "learning_rate": 1.2000000000000002e-07,
44
+ "loss": 1.3298,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.05319148936170213,
49
+ "grad_norm": 0.1327030211687088,
50
+ "learning_rate": 1.5000000000000002e-07,
51
+ "loss": 1.4031,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.06382978723404255,
56
+ "grad_norm": 0.12036772817373276,
57
+ "learning_rate": 1.8e-07,
58
+ "loss": 1.5335,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.07446808510638298,
63
+ "grad_norm": 0.14979703724384308,
64
+ "learning_rate": 2.1000000000000003e-07,
65
+ "loss": 1.3224,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.0851063829787234,
70
+ "grad_norm": 0.13082227110862732,
71
+ "learning_rate": 2.4000000000000003e-07,
72
+ "loss": 1.4035,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.09574468085106383,
77
+ "grad_norm": 0.09265327453613281,
78
+ "learning_rate": 2.7e-07,
79
+ "loss": 1.1546,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.10638297872340426,
84
+ "grad_norm": 0.10080434381961823,
85
+ "learning_rate": 3.0000000000000004e-07,
86
+ "loss": 1.2652,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.11702127659574468,
91
+ "grad_norm": 0.10915568470954895,
92
+ "learning_rate": 3.3e-07,
93
+ "loss": 1.1438,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.1276595744680851,
98
+ "grad_norm": 0.1307348906993866,
99
+ "learning_rate": 3.6e-07,
100
+ "loss": 1.2821,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.13829787234042554,
105
+ "grad_norm": 0.09814529865980148,
106
+ "learning_rate": 3.9e-07,
107
+ "loss": 1.3905,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.14893617021276595,
112
+ "grad_norm": 0.11842218786478043,
113
+ "learning_rate": 4.2000000000000006e-07,
114
+ "loss": 1.3085,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.1595744680851064,
119
+ "grad_norm": 0.10207124054431915,
120
+ "learning_rate": 4.5e-07,
121
+ "loss": 1.19,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.1702127659574468,
126
+ "grad_norm": 0.1150127425789833,
127
+ "learning_rate": 4.800000000000001e-07,
128
+ "loss": 1.386,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.18085106382978725,
133
+ "grad_norm": 0.11641352623701096,
134
+ "learning_rate": 5.100000000000001e-07,
135
+ "loss": 1.4357,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.19148936170212766,
140
+ "grad_norm": 0.15035435557365417,
141
+ "learning_rate": 5.4e-07,
142
+ "loss": 1.2549,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.20212765957446807,
147
+ "grad_norm": 0.0984087809920311,
148
+ "learning_rate": 5.7e-07,
149
+ "loss": 0.9723,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.2127659574468085,
154
+ "grad_norm": 0.11582670360803604,
155
+ "learning_rate": 6.000000000000001e-07,
156
+ "loss": 1.1402,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.22340425531914893,
161
+ "grad_norm": 0.10151291638612747,
162
+ "learning_rate": 6.3e-07,
163
+ "loss": 1.1533,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.23404255319148937,
168
+ "grad_norm": 0.09040653705596924,
169
+ "learning_rate": 6.6e-07,
170
+ "loss": 1.0438,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.24468085106382978,
175
+ "grad_norm": 0.10666865110397339,
176
+ "learning_rate": 6.900000000000001e-07,
177
+ "loss": 1.3195,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.2553191489361702,
182
+ "grad_norm": 0.12293969094753265,
183
+ "learning_rate": 7.2e-07,
184
+ "loss": 1.7286,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.2553191489361702,
189
+ "eval_loss": 1.5890721082687378,
190
+ "eval_runtime": 2.9908,
191
+ "eval_samples_per_second": 35.108,
192
+ "eval_steps_per_second": 17.721,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.26595744680851063,
197
+ "grad_norm": 0.11052387952804565,
198
+ "learning_rate": 7.5e-07,
199
+ "loss": 1.1413,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.2765957446808511,
204
+ "grad_norm": 0.09323304146528244,
205
+ "learning_rate": 7.8e-07,
206
+ "loss": 1.2906,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.2872340425531915,
211
+ "grad_norm": 0.12542971968650818,
212
+ "learning_rate": 8.100000000000001e-07,
213
+ "loss": 1.2809,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.2978723404255319,
218
+ "grad_norm": 0.1080215722322464,
219
+ "learning_rate": 8.400000000000001e-07,
220
+ "loss": 1.2735,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.30851063829787234,
225
+ "grad_norm": 0.11304887384176254,
226
+ "learning_rate": 8.699999999999999e-07,
227
+ "loss": 1.3767,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.3191489361702128,
232
+ "grad_norm": 0.15650290250778198,
233
+ "learning_rate": 9e-07,
234
+ "loss": 1.4713,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.32978723404255317,
239
+ "grad_norm": 0.12139321118593216,
240
+ "learning_rate": 9.3e-07,
241
+ "loss": 1.3479,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.3404255319148936,
246
+ "grad_norm": 0.10141867399215698,
247
+ "learning_rate": 9.600000000000001e-07,
248
+ "loss": 1.1512,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.35106382978723405,
253
+ "grad_norm": 0.15045498311519623,
254
+ "learning_rate": 9.9e-07,
255
+ "loss": 1.5059,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.3617021276595745,
260
+ "grad_norm": 0.12956956028938293,
261
+ "learning_rate": 1.0200000000000002e-06,
262
+ "loss": 1.2849,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.3723404255319149,
267
+ "grad_norm": 0.12963886559009552,
268
+ "learning_rate": 1.05e-06,
269
+ "loss": 1.5025,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.3829787234042553,
274
+ "grad_norm": 0.11268144845962524,
275
+ "learning_rate": 1.08e-06,
276
+ "loss": 1.2987,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.39361702127659576,
281
+ "grad_norm": 0.12941108644008636,
282
+ "learning_rate": 1.11e-06,
283
+ "loss": 1.3432,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.40425531914893614,
288
+ "grad_norm": 0.11319927126169205,
289
+ "learning_rate": 1.14e-06,
290
+ "loss": 1.1665,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.4148936170212766,
295
+ "grad_norm": 0.11748912930488586,
296
+ "learning_rate": 1.17e-06,
297
+ "loss": 1.423,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.425531914893617,
302
+ "grad_norm": 0.11666171997785568,
303
+ "learning_rate": 1.2000000000000002e-06,
304
+ "loss": 1.4391,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.43617021276595747,
309
+ "grad_norm": 0.12274409830570221,
310
+ "learning_rate": 1.2299999999999999e-06,
311
+ "loss": 1.4865,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.44680851063829785,
316
+ "grad_norm": 0.09922561049461365,
317
+ "learning_rate": 1.26e-06,
318
+ "loss": 1.2193,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.4574468085106383,
323
+ "grad_norm": 0.12003930658102036,
324
+ "learning_rate": 1.29e-06,
325
+ "loss": 1.3024,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.46808510638297873,
330
+ "grad_norm": 0.12094161659479141,
331
+ "learning_rate": 1.32e-06,
332
+ "loss": 1.4654,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.4787234042553192,
337
+ "grad_norm": 0.12934774160385132,
338
+ "learning_rate": 1.35e-06,
339
+ "loss": 1.3713,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.48936170212765956,
344
+ "grad_norm": 0.09754550457000732,
345
+ "learning_rate": 1.3800000000000001e-06,
346
+ "loss": 1.1991,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.5,
351
+ "grad_norm": 0.11549004167318344,
352
+ "learning_rate": 1.41e-06,
353
+ "loss": 1.4859,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.5106382978723404,
358
+ "grad_norm": 0.12035688012838364,
359
+ "learning_rate": 1.44e-06,
360
+ "loss": 1.2823,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.5106382978723404,
365
+ "eval_loss": 1.5874611139297485,
366
+ "eval_runtime": 2.9787,
367
+ "eval_samples_per_second": 35.251,
368
+ "eval_steps_per_second": 17.793,
369
+ "step": 48
370
+ },
371
+ {
372
+ "epoch": 0.5212765957446809,
373
+ "grad_norm": 0.12258938699960709,
374
+ "learning_rate": 1.4700000000000001e-06,
375
+ "loss": 1.2966,
376
+ "step": 49
377
+ },
378
+ {
379
+ "epoch": 0.5319148936170213,
380
+ "grad_norm": 0.12217017263174057,
381
+ "learning_rate": 1.5e-06,
382
+ "loss": 1.2988,
383
+ "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.5425531914893617,
387
+ "grad_norm": 0.12793436646461487,
388
+ "learning_rate": 1.53e-06,
389
+ "loss": 1.4233,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.5531914893617021,
394
+ "grad_norm": 0.11145548522472382,
395
+ "learning_rate": 1.56e-06,
396
+ "loss": 1.2792,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.5638297872340425,
401
+ "grad_norm": 0.13195408880710602,
402
+ "learning_rate": 1.59e-06,
403
+ "loss": 1.4481,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.574468085106383,
408
+ "grad_norm": 0.10663347691297531,
409
+ "learning_rate": 1.6200000000000002e-06,
410
+ "loss": 1.2331,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.5851063829787234,
415
+ "grad_norm": 0.10975392907857895,
416
+ "learning_rate": 1.65e-06,
417
+ "loss": 1.1839,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.5957446808510638,
422
+ "grad_norm": 0.13139477372169495,
423
+ "learning_rate": 1.6800000000000002e-06,
424
+ "loss": 1.436,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.6063829787234043,
429
+ "grad_norm": 0.0924743041396141,
430
+ "learning_rate": 1.71e-06,
431
+ "loss": 1.1291,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.6170212765957447,
436
+ "grad_norm": 0.12475109100341797,
437
+ "learning_rate": 1.7399999999999999e-06,
438
+ "loss": 1.3444,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.6276595744680851,
443
+ "grad_norm": 0.08960220962762833,
444
+ "learning_rate": 1.77e-06,
445
+ "loss": 1.2511,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.6382978723404256,
450
+ "grad_norm": 0.09909304976463318,
451
+ "learning_rate": 1.8e-06,
452
+ "loss": 1.1281,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.648936170212766,
457
+ "grad_norm": 0.11598234623670578,
458
+ "learning_rate": 1.83e-06,
459
+ "loss": 1.486,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.6595744680851063,
464
+ "grad_norm": 0.1404409557580948,
465
+ "learning_rate": 1.86e-06,
466
+ "loss": 1.4557,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.6702127659574468,
471
+ "grad_norm": 0.11349129676818848,
472
+ "learning_rate": 1.8900000000000001e-06,
473
+ "loss": 1.3969,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.6808510638297872,
478
+ "grad_norm": 0.10858353972434998,
479
+ "learning_rate": 1.9200000000000003e-06,
480
+ "loss": 1.3515,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.6914893617021277,
485
+ "grad_norm": 0.11054569482803345,
486
+ "learning_rate": 1.95e-06,
487
+ "loss": 1.248,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.7021276595744681,
492
+ "grad_norm": 0.11826737225055695,
493
+ "learning_rate": 1.98e-06,
494
+ "loss": 1.3439,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.7127659574468085,
499
+ "grad_norm": 0.12291310727596283,
500
+ "learning_rate": 2.0100000000000002e-06,
501
+ "loss": 1.4226,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.723404255319149,
506
+ "grad_norm": 0.1383126825094223,
507
+ "learning_rate": 2.0400000000000004e-06,
508
+ "loss": 1.194,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.7340425531914894,
513
+ "grad_norm": 0.10981890559196472,
514
+ "learning_rate": 2.07e-06,
515
+ "loss": 1.2502,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.7446808510638298,
520
+ "grad_norm": 0.10639657825231552,
521
+ "learning_rate": 2.1e-06,
522
+ "loss": 1.2262,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.7553191489361702,
527
+ "grad_norm": 0.46177396178245544,
528
+ "learning_rate": 2.13e-06,
529
+ "loss": 5.063,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.7659574468085106,
534
+ "grad_norm": 0.11061427742242813,
535
+ "learning_rate": 2.16e-06,
536
+ "loss": 1.3856,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.7659574468085106,
541
+ "eval_loss": 1.5843762159347534,
542
+ "eval_runtime": 2.9943,
543
+ "eval_samples_per_second": 35.066,
544
+ "eval_steps_per_second": 17.7,
545
+ "step": 72
546
+ },
547
+ {
548
+ "epoch": 0.776595744680851,
549
+ "grad_norm": 0.13233324885368347,
550
+ "learning_rate": 2.19e-06,
551
+ "loss": 1.526,
552
+ "step": 73
553
+ },
554
+ {
555
+ "epoch": 0.7872340425531915,
556
+ "grad_norm": 0.14500053226947784,
557
+ "learning_rate": 2.22e-06,
558
+ "loss": 1.2554,
559
+ "step": 74
560
+ },
561
+ {
562
+ "epoch": 0.7978723404255319,
563
+ "grad_norm": 0.10629269480705261,
564
+ "learning_rate": 2.25e-06,
565
+ "loss": 1.2917,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 0.8085106382978723,
570
+ "grad_norm": 0.09674028307199478,
571
+ "learning_rate": 2.28e-06,
572
+ "loss": 1.2169,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 0.8191489361702128,
577
+ "grad_norm": 0.11965947598218918,
578
+ "learning_rate": 2.31e-06,
579
+ "loss": 1.2445,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 0.8297872340425532,
584
+ "grad_norm": 0.10441229492425919,
585
+ "learning_rate": 2.34e-06,
586
+ "loss": 1.2392,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 0.8404255319148937,
591
+ "grad_norm": 0.13795869052410126,
592
+ "learning_rate": 2.37e-06,
593
+ "loss": 1.5335,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 0.851063829787234,
598
+ "grad_norm": 0.10789927840232849,
599
+ "learning_rate": 2.4000000000000003e-06,
600
+ "loss": 1.2309,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 0.8617021276595744,
605
+ "grad_norm": 0.10697130113840103,
606
+ "learning_rate": 2.43e-06,
607
+ "loss": 1.276,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 0.8723404255319149,
612
+ "grad_norm": 0.11484125256538391,
613
+ "learning_rate": 2.4599999999999997e-06,
614
+ "loss": 1.2163,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 0.8829787234042553,
619
+ "grad_norm": 0.09692610800266266,
620
+ "learning_rate": 2.49e-06,
621
+ "loss": 1.1554,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 0.8936170212765957,
626
+ "grad_norm": 0.10697747021913528,
627
+ "learning_rate": 2.52e-06,
628
+ "loss": 1.211,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 0.9042553191489362,
633
+ "grad_norm": 0.10578318685293198,
634
+ "learning_rate": 2.55e-06,
635
+ "loss": 1.2634,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 0.9148936170212766,
640
+ "grad_norm": 0.10587752610445023,
641
+ "learning_rate": 2.58e-06,
642
+ "loss": 1.369,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 0.925531914893617,
647
+ "grad_norm": 0.11430489271879196,
648
+ "learning_rate": 2.61e-06,
649
+ "loss": 1.3048,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 0.9361702127659575,
654
+ "grad_norm": 0.11116154491901398,
655
+ "learning_rate": 2.64e-06,
656
+ "loss": 1.1883,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 0.9468085106382979,
661
+ "grad_norm": 0.12686476111412048,
662
+ "learning_rate": 2.6700000000000003e-06,
663
+ "loss": 1.2605,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 0.9574468085106383,
668
+ "grad_norm": 0.10976041853427887,
669
+ "learning_rate": 2.7e-06,
670
+ "loss": 1.2345,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 0.9680851063829787,
675
+ "grad_norm": 0.12391550838947296,
676
+ "learning_rate": 2.73e-06,
677
+ "loss": 1.2233,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 0.9787234042553191,
682
+ "grad_norm": 0.1277073174715042,
683
+ "learning_rate": 2.7600000000000003e-06,
684
+ "loss": 1.2437,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 0.9893617021276596,
689
+ "grad_norm": 0.10421616584062576,
690
+ "learning_rate": 2.7900000000000004e-06,
691
+ "loss": 1.1432,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 1.0,
696
+ "grad_norm": 0.12696842849254608,
697
+ "learning_rate": 2.82e-06,
698
+ "loss": 1.3558,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 1.0106382978723405,
703
+ "grad_norm": 0.10387945920228958,
704
+ "learning_rate": 2.85e-06,
705
+ "loss": 1.1902,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 1.0212765957446808,
710
+ "grad_norm": 0.14543002843856812,
711
+ "learning_rate": 2.88e-06,
712
+ "loss": 1.244,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 1.0212765957446808,
717
+ "eval_loss": 1.5803985595703125,
718
+ "eval_runtime": 3.0087,
719
+ "eval_samples_per_second": 34.899,
720
+ "eval_steps_per_second": 17.616,
721
+ "step": 96
722
+ },
723
+ {
724
+ "epoch": 1.0319148936170213,
725
+ "grad_norm": 0.17504040896892548,
726
+ "learning_rate": 2.91e-06,
727
+ "loss": 1.3115,
728
+ "step": 97
729
+ },
730
+ {
731
+ "epoch": 1.0106382978723405,
732
+ "grad_norm": 0.14017756283283234,
733
+ "learning_rate": 2.9400000000000002e-06,
734
+ "loss": 1.356,
735
+ "step": 98
736
+ },
737
+ {
738
+ "epoch": 1.0212765957446808,
739
+ "grad_norm": 0.11604318767786026,
740
+ "learning_rate": 2.97e-06,
741
+ "loss": 1.2806,
742
+ "step": 99
743
+ },
744
+ {
745
+ "epoch": 1.0319148936170213,
746
+ "grad_norm": 0.15116065740585327,
747
+ "learning_rate": 3e-06,
748
+ "loss": 1.3279,
749
+ "step": 100
750
+ },
751
+ {
752
+ "epoch": 1.0425531914893618,
753
+ "grad_norm": 0.10773392021656036,
754
+ "learning_rate": 2.9999028286680832e-06,
755
+ "loss": 1.3871,
756
+ "step": 101
757
+ },
758
+ {
759
+ "epoch": 1.053191489361702,
760
+ "grad_norm": 0.09363637119531631,
761
+ "learning_rate": 2.999611327262024e-06,
762
+ "loss": 1.1334,
763
+ "step": 102
764
+ },
765
+ {
766
+ "epoch": 1.0638297872340425,
767
+ "grad_norm": 0.09164439886808395,
768
+ "learning_rate": 2.999125533549261e-06,
769
+ "loss": 1.4026,
770
+ "step": 103
771
+ },
772
+ {
773
+ "epoch": 1.074468085106383,
774
+ "grad_norm": 0.12113964557647705,
775
+ "learning_rate": 2.9984455104700915e-06,
776
+ "loss": 1.2097,
777
+ "step": 104
778
+ },
779
+ {
780
+ "epoch": 1.0851063829787233,
781
+ "grad_norm": 0.10569895058870316,
782
+ "learning_rate": 2.9975713461295125e-06,
783
+ "loss": 1.3077,
784
+ "step": 105
785
+ },
786
+ {
787
+ "epoch": 1.0957446808510638,
788
+ "grad_norm": 0.11219862103462219,
789
+ "learning_rate": 2.996503153785809e-06,
790
+ "loss": 1.1923,
791
+ "step": 106
792
+ },
793
+ {
794
+ "epoch": 1.1063829787234043,
795
+ "grad_norm": 0.13474853336811066,
796
+ "learning_rate": 2.9952410718358777e-06,
797
+ "loss": 1.2729,
798
+ "step": 107
799
+ },
800
+ {
801
+ "epoch": 1.1170212765957448,
802
+ "grad_norm": 0.10451857000589371,
803
+ "learning_rate": 2.993785263797297e-06,
804
+ "loss": 1.2904,
805
+ "step": 108
806
+ },
807
+ {
808
+ "epoch": 1.127659574468085,
809
+ "grad_norm": 0.12593719363212585,
810
+ "learning_rate": 2.9921359182871422e-06,
811
+ "loss": 1.4021,
812
+ "step": 109
813
+ },
814
+ {
815
+ "epoch": 1.1382978723404256,
816
+ "grad_norm": 0.12547315657138824,
817
+ "learning_rate": 2.990293248997547e-06,
818
+ "loss": 1.2093,
819
+ "step": 110
820
+ },
821
+ {
822
+ "epoch": 1.148936170212766,
823
+ "grad_norm": 0.10086555033922195,
824
+ "learning_rate": 2.988257494668016e-06,
825
+ "loss": 1.3098,
826
+ "step": 111
827
+ },
828
+ {
829
+ "epoch": 1.1595744680851063,
830
+ "grad_norm": 0.10801573097705841,
831
+ "learning_rate": 2.9860289190544963e-06,
832
+ "loss": 1.2752,
833
+ "step": 112
834
+ },
835
+ {
836
+ "epoch": 1.1702127659574468,
837
+ "grad_norm": 0.11851054430007935,
838
+ "learning_rate": 2.9836078108952015e-06,
839
+ "loss": 1.3066,
840
+ "step": 113
841
+ },
842
+ {
843
+ "epoch": 1.1808510638297873,
844
+ "grad_norm": 0.1265188604593277,
845
+ "learning_rate": 2.9809944838732045e-06,
846
+ "loss": 1.1946,
847
+ "step": 114
848
+ },
849
+ {
850
+ "epoch": 1.1914893617021276,
851
+ "grad_norm": 0.10702725499868393,
852
+ "learning_rate": 2.9781892765757954e-06,
853
+ "loss": 1.2182,
854
+ "step": 115
855
+ },
856
+ {
857
+ "epoch": 1.202127659574468,
858
+ "grad_norm": 0.7757766842842102,
859
+ "learning_rate": 2.9751925524506135e-06,
860
+ "loss": 5.6082,
861
+ "step": 116
862
+ },
863
+ {
864
+ "epoch": 1.2127659574468086,
865
+ "grad_norm": 0.10182739049196243,
866
+ "learning_rate": 2.9720046997585577e-06,
867
+ "loss": 1.309,
868
+ "step": 117
869
+ },
870
+ {
871
+ "epoch": 1.2234042553191489,
872
+ "grad_norm": 0.14062073826789856,
873
+ "learning_rate": 2.9686261315234844e-06,
874
+ "loss": 1.3668,
875
+ "step": 118
876
+ },
877
+ {
878
+ "epoch": 1.2340425531914894,
879
+ "grad_norm": 0.1063840240240097,
880
+ "learning_rate": 2.965057285478694e-06,
881
+ "loss": 1.2247,
882
+ "step": 119
883
+ },
884
+ {
885
+ "epoch": 1.2446808510638299,
886
+ "grad_norm": 0.10701325535774231,
887
+ "learning_rate": 2.961298624010219e-06,
888
+ "loss": 1.2499,
889
+ "step": 120
890
+ },
891
+ {
892
+ "epoch": 1.2446808510638299,
893
+ "eval_loss": 1.575344204902649,
894
+ "eval_runtime": 8.2617,
895
+ "eval_samples_per_second": 12.709,
896
+ "eval_steps_per_second": 6.415,
897
+ "step": 120
898
+ },
899
+ {
900
+ "epoch": 1.2553191489361701,
901
+ "grad_norm": 0.11413375288248062,
902
+ "learning_rate": 2.957350634096912e-06,
903
+ "loss": 1.3593,
904
+ "step": 121
905
+ },
906
+ {
907
+ "epoch": 1.2659574468085106,
908
+ "grad_norm": 0.10826950520277023,
909
+ "learning_rate": 2.9532138272473597e-06,
910
+ "loss": 1.232,
911
+ "step": 122
912
+ },
913
+ {
914
+ "epoch": 1.2765957446808511,
915
+ "grad_norm": 0.10749218612909317,
916
+ "learning_rate": 2.9488887394336023e-06,
917
+ "loss": 1.401,
918
+ "step": 123
919
+ },
920
+ {
921
+ "epoch": 1.2872340425531914,
922
+ "grad_norm": 0.1175396591424942,
923
+ "learning_rate": 2.944375931021699e-06,
924
+ "loss": 1.2867,
925
+ "step": 124
926
+ },
927
+ {
928
+ "epoch": 1.297872340425532,
929
+ "grad_norm": 0.10688498616218567,
930
+ "learning_rate": 2.9396759866991214e-06,
931
+ "loss": 1.3689,
932
+ "step": 125
933
+ },
934
+ {
935
+ "epoch": 1.3085106382978724,
936
+ "grad_norm": 0.11630786955356598,
937
+ "learning_rate": 2.934789515399002e-06,
938
+ "loss": 1.2328,
939
+ "step": 126
940
+ },
941
+ {
942
+ "epoch": 1.3191489361702127,
943
+ "grad_norm": 0.11495409905910492,
944
+ "learning_rate": 2.9297171502212414e-06,
945
+ "loss": 1.1738,
946
+ "step": 127
947
+ },
948
+ {
949
+ "epoch": 1.3297872340425532,
950
+ "grad_norm": 0.10823408514261246,
951
+ "learning_rate": 2.924459548350479e-06,
952
+ "loss": 1.2318,
953
+ "step": 128
954
+ },
955
+ {
956
+ "epoch": 1.3404255319148937,
957
+ "grad_norm": 0.10759969800710678,
958
+ "learning_rate": 2.9190173909709506e-06,
959
+ "loss": 1.319,
960
+ "step": 129
961
+ },
962
+ {
963
+ "epoch": 1.351063829787234,
964
+ "grad_norm": 0.12790299952030182,
965
+ "learning_rate": 2.9133913831782307e-06,
966
+ "loss": 1.4282,
967
+ "step": 130
968
+ },
969
+ {
970
+ "epoch": 1.3617021276595744,
971
+ "grad_norm": 0.10899878293275833,
972
+ "learning_rate": 2.9075822538878805e-06,
973
+ "loss": 1.2455,
974
+ "step": 131
975
+ },
976
+ {
977
+ "epoch": 1.372340425531915,
978
+ "grad_norm": 0.12732432782649994,
979
+ "learning_rate": 2.9015907557410068e-06,
980
+ "loss": 1.2227,
981
+ "step": 132
982
+ },
983
+ {
984
+ "epoch": 1.3829787234042552,
985
+ "grad_norm": 0.10140018165111542,
986
+ "learning_rate": 2.8954176650067494e-06,
987
+ "loss": 1.0596,
988
+ "step": 133
989
+ },
990
+ {
991
+ "epoch": 1.3936170212765957,
992
+ "grad_norm": 0.12063546478748322,
993
+ "learning_rate": 2.889063781481708e-06,
994
+ "loss": 1.3321,
995
+ "step": 134
996
+ },
997
+ {
998
+ "epoch": 1.4042553191489362,
999
+ "grad_norm": 0.11323118209838867,
1000
+ "learning_rate": 2.8825299283863144e-06,
1001
+ "loss": 1.3366,
1002
+ "step": 135
1003
+ },
1004
+ {
1005
+ "epoch": 1.4148936170212765,
1006
+ "grad_norm": 0.12391477078199387,
1007
+ "learning_rate": 2.8758169522581796e-06,
1008
+ "loss": 1.2917,
1009
+ "step": 136
1010
+ },
1011
+ {
1012
+ "epoch": 1.425531914893617,
1013
+ "grad_norm": 0.12329094856977463,
1014
+ "learning_rate": 2.8689257228424125e-06,
1015
+ "loss": 1.1365,
1016
+ "step": 137
1017
+ },
1018
+ {
1019
+ "epoch": 1.4361702127659575,
1020
+ "grad_norm": 0.11298198997974396,
1021
+ "learning_rate": 2.8618571329789333e-06,
1022
+ "loss": 1.4996,
1023
+ "step": 138
1024
+ },
1025
+ {
1026
+ "epoch": 1.4468085106382977,
1027
+ "grad_norm": 0.10263165086507797,
1028
+ "learning_rate": 2.8546120984867994e-06,
1029
+ "loss": 1.199,
1030
+ "step": 139
1031
+ },
1032
+ {
1033
+ "epoch": 1.4574468085106382,
1034
+ "grad_norm": 0.13330323994159698,
1035
+ "learning_rate": 2.8471915580455442e-06,
1036
+ "loss": 1.3746,
1037
+ "step": 140
1038
+ },
1039
+ {
1040
+ "epoch": 1.4680851063829787,
1041
+ "grad_norm": 0.10694881528615952,
1042
+ "learning_rate": 2.8395964730735666e-06,
1043
+ "loss": 1.3798,
1044
+ "step": 141
1045
+ },
1046
+ {
1047
+ "epoch": 1.4787234042553192,
1048
+ "grad_norm": 0.10929003357887268,
1049
+ "learning_rate": 2.8318278276035626e-06,
1050
+ "loss": 1.2918,
1051
+ "step": 142
1052
+ },
1053
+ {
1054
+ "epoch": 1.4893617021276595,
1055
+ "grad_norm": 0.10969982296228409,
1056
+ "learning_rate": 2.8238866281550366e-06,
1057
+ "loss": 1.0444,
1058
+ "step": 143
1059
+ },
1060
+ {
1061
+ "epoch": 1.5,
1062
+ "grad_norm": 0.10668367147445679,
1063
+ "learning_rate": 2.815773903603892e-06,
1064
+ "loss": 1.1656,
1065
+ "step": 144
1066
+ },
1067
+ {
1068
+ "epoch": 1.5,
1069
+ "eval_loss": 1.5705612897872925,
1070
+ "eval_runtime": 5.6853,
1071
+ "eval_samples_per_second": 18.469,
1072
+ "eval_steps_per_second": 9.322,
1073
+ "step": 144
1074
+ },
1075
+ {
1076
+ "epoch": 1.5106382978723403,
1077
+ "grad_norm": 0.12057002633810043,
1078
+ "learning_rate": 2.807490705049127e-06,
1079
+ "loss": 1.2475,
1080
+ "step": 145
1081
+ },
1082
+ {
1083
+ "epoch": 1.521276595744681,
1084
+ "grad_norm": 0.10394139587879181,
1085
+ "learning_rate": 2.7990381056766585e-06,
1086
+ "loss": 1.3376,
1087
+ "step": 146
1088
+ },
1089
+ {
1090
+ "epoch": 1.5319148936170213,
1091
+ "grad_norm": 0.12907464802265167,
1092
+ "learning_rate": 2.7904172006202705e-06,
1093
+ "loss": 1.3509,
1094
+ "step": 147
1095
+ },
1096
+ {
1097
+ "epoch": 1.5425531914893615,
1098
+ "grad_norm": 0.1252606213092804,
1099
+ "learning_rate": 2.7816291068197328e-06,
1100
+ "loss": 1.1744,
1101
+ "step": 148
1102
+ },
1103
+ {
1104
+ "epoch": 1.5531914893617023,
1105
+ "grad_norm": 0.1514441967010498,
1106
+ "learning_rate": 2.772674962876085e-06,
1107
+ "loss": 1.9324,
1108
+ "step": 149
1109
+ },
1110
+ {
1111
+ "epoch": 1.5638297872340425,
1112
+ "grad_norm": 0.12377320230007172,
1113
+ "learning_rate": 2.7635559289041174e-06,
1114
+ "loss": 1.4511,
1115
+ "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 1.574468085106383,
1119
+ "grad_norm": 0.10629550367593765,
1120
+ "learning_rate": 2.7542731863820665e-06,
1121
+ "loss": 1.257,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 1.5851063829787235,
1126
+ "grad_norm": 0.10322704166173935,
1127
+ "learning_rate": 2.744827937998538e-06,
1128
+ "loss": 1.1796,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 1.5957446808510638,
1133
+ "grad_norm": 0.12690168619155884,
1134
+ "learning_rate": 2.735221407496686e-06,
1135
+ "loss": 1.3325,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 1.6063829787234043,
1140
+ "grad_norm": 0.0982392430305481,
1141
+ "learning_rate": 2.725454839515663e-06,
1142
+ "loss": 1.2169,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 1.6170212765957448,
1147
+ "grad_norm": 0.11184275150299072,
1148
+ "learning_rate": 2.7155294994293606e-06,
1149
+ "loss": 1.295,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 1.627659574468085,
1154
+ "grad_norm": 0.10721098631620407,
1155
+ "learning_rate": 2.7054466731824676e-06,
1156
+ "loss": 1.1945,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 1.6382978723404256,
1161
+ "grad_norm": 0.1254221498966217,
1162
+ "learning_rate": 2.695207667123857e-06,
1163
+ "loss": 1.2693,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 1.648936170212766,
1168
+ "grad_norm": 0.1157686784863472,
1169
+ "learning_rate": 2.684813807837338e-06,
1170
+ "loss": 1.1992,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 1.6595744680851063,
1175
+ "grad_norm": 0.10201229155063629,
1176
+ "learning_rate": 2.674266441969778e-06,
1177
+ "loss": 1.2401,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 1.6702127659574468,
1182
+ "grad_norm": 0.10953360050916672,
1183
+ "learning_rate": 2.6635669360566298e-06,
1184
+ "loss": 1.1627,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 1.6808510638297873,
1189
+ "grad_norm": 0.1248813271522522,
1190
+ "learning_rate": 2.652716676344881e-06,
1191
+ "loss": 1.3179,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 1.6914893617021276,
1196
+ "grad_norm": 0.09584470838308334,
1197
+ "learning_rate": 2.6417170686134472e-06,
1198
+ "loss": 1.2128,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 1.702127659574468,
1203
+ "grad_norm": 0.12864486873149872,
1204
+ "learning_rate": 2.630569537991042e-06,
1205
+ "loss": 1.1889,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 1.7127659574468086,
1210
+ "grad_norm": 0.11820186674594879,
1211
+ "learning_rate": 2.6192755287715282e-06,
1212
+ "loss": 1.2848,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 1.7234042553191489,
1217
+ "grad_norm": 0.13811764121055603,
1218
+ "learning_rate": 2.6078365042267987e-06,
1219
+ "loss": 1.2091,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 1.7340425531914894,
1224
+ "grad_norm": 0.12099539488554001,
1225
+ "learning_rate": 2.5962539464171862e-06,
1226
+ "loss": 1.2853,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 1.7446808510638299,
1231
+ "grad_norm": 0.14544783532619476,
1232
+ "learning_rate": 2.5845293559994513e-06,
1233
+ "loss": 1.1574,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 1.7553191489361701,
1238
+ "grad_norm": 0.11159494519233704,
1239
+ "learning_rate": 2.5726642520323493e-06,
1240
+ "loss": 1.1928,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 1.7553191489361701,
1245
+ "eval_loss": 1.5656005144119263,
1246
+ "eval_runtime": 3.0568,
1247
+ "eval_samples_per_second": 34.349,
1248
+ "eval_steps_per_second": 17.338,
1249
+ "step": 168
1250
+ },
1251
+ {
1252
+ "epoch": 1.7659574468085106,
1253
+ "grad_norm": 0.1385321319103241,
1254
+ "learning_rate": 2.5606601717798212e-06,
1255
+ "loss": 1.365,
1256
+ "step": 169
1257
+ },
1258
+ {
1259
+ "epoch": 1.7765957446808511,
1260
+ "grad_norm": 0.12905962765216827,
1261
+ "learning_rate": 2.548518670511823e-06,
1262
+ "loss": 1.3664,
1263
+ "step": 170
1264
+ },
1265
+ {
1266
+ "epoch": 1.7872340425531914,
1267
+ "grad_norm": 0.09589093923568726,
1268
+ "learning_rate": 2.536241321302821e-06,
1269
+ "loss": 1.1508,
1270
+ "step": 171
1271
+ },
1272
+ {
1273
+ "epoch": 1.797872340425532,
1274
+ "grad_norm": 0.12533985078334808,
1275
+ "learning_rate": 2.5238297148279814e-06,
1276
+ "loss": 1.2892,
1277
+ "step": 172
1278
+ },
1279
+ {
1280
+ "epoch": 1.8085106382978724,
1281
+ "grad_norm": 0.11337278038263321,
1282
+ "learning_rate": 2.5112854591570804e-06,
1283
+ "loss": 1.2772,
1284
+ "step": 173
1285
+ },
1286
+ {
1287
+ "epoch": 1.8191489361702127,
1288
+ "grad_norm": 0.1345362514257431,
1289
+ "learning_rate": 2.4986101795461608e-06,
1290
+ "loss": 1.3583,
1291
+ "step": 174
1292
+ },
1293
+ {
1294
+ "epoch": 1.8297872340425532,
1295
+ "grad_norm": 0.121876560151577,
1296
+ "learning_rate": 2.485805518226959e-06,
1297
+ "loss": 1.2065,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 1.8404255319148937,
1302
+ "grad_norm": 0.10669907927513123,
1303
+ "learning_rate": 2.4728731341941343e-06,
1304
+ "loss": 1.2339,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 1.851063829787234,
1309
+ "grad_norm": 0.12710174918174744,
1310
+ "learning_rate": 2.4598147029903284e-06,
1311
+ "loss": 1.4597,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 1.8617021276595744,
1316
+ "grad_norm": 0.11735282093286514,
1317
+ "learning_rate": 2.4466319164890795e-06,
1318
+ "loss": 1.2273,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 1.872340425531915,
1323
+ "grad_norm": 0.12083889544010162,
1324
+ "learning_rate": 2.4333264826756165e-06,
1325
+ "loss": 1.3051,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 1.8829787234042552,
1330
+ "grad_norm": 0.10338792204856873,
1331
+ "learning_rate": 2.4199001254255746e-06,
1332
+ "loss": 1.3827,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 1.8936170212765957,
1337
+ "grad_norm": 0.10191334784030914,
1338
+ "learning_rate": 2.406354584281642e-06,
1339
+ "loss": 1.4067,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 1.9042553191489362,
1344
+ "grad_norm": 0.10776273161172867,
1345
+ "learning_rate": 2.3926916142281846e-06,
1346
+ "loss": 1.2344,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 1.9148936170212765,
1351
+ "grad_norm": 0.1253603845834732,
1352
+ "learning_rate": 2.378912985463867e-06,
1353
+ "loss": 1.2179,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 1.925531914893617,
1358
+ "grad_norm": 0.09942696243524551,
1359
+ "learning_rate": 2.365020483172301e-06,
1360
+ "loss": 1.0613,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 1.9361702127659575,
1365
+ "grad_norm": 0.10441701859235764,
1366
+ "learning_rate": 2.351015907290755e-06,
1367
+ "loss": 1.3886,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 1.9468085106382977,
1372
+ "grad_norm": 0.10571073740720749,
1373
+ "learning_rate": 2.3369010722769502e-06,
1374
+ "loss": 1.2023,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 1.9574468085106385,
1379
+ "grad_norm": 0.12477201223373413,
1380
+ "learning_rate": 2.3226778068739783e-06,
1381
+ "loss": 1.361,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 1.9680851063829787,
1386
+ "grad_norm": 0.12106247246265411,
1387
+ "learning_rate": 2.3083479538733636e-06,
1388
+ "loss": 1.4153,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 1.978723404255319,
1393
+ "grad_norm": 0.17261436581611633,
1394
+ "learning_rate": 2.2939133698763084e-06,
1395
+ "loss": 1.45,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 1.9893617021276597,
1400
+ "grad_norm": 0.12172568589448929,
1401
+ "learning_rate": 2.2793759250531504e-06,
1402
+ "loss": 1.1764,
1403
+ "step": 190
1404
+ },
1405
+ {
1406
+ "epoch": 2.0,
1407
+ "grad_norm": 0.11111535131931305,
1408
+ "learning_rate": 2.2647375029010575e-06,
1409
+ "loss": 1.1347,
1410
+ "step": 191
1411
+ },
1412
+ {
1413
+ "epoch": 2.0106382978723403,
1414
+ "grad_norm": 0.10596352070569992,
1415
+ "learning_rate": 2.25e-06,
1416
+ "loss": 1.1623,
1417
+ "step": 192
1418
+ },
1419
+ {
1420
+ "epoch": 2.0106382978723403,
1421
+ "eval_loss": 1.560809850692749,
1422
+ "eval_runtime": 4.8693,
1423
+ "eval_samples_per_second": 21.564,
1424
+ "eval_steps_per_second": 10.885,
1425
+ "step": 192
1426
+ },
1427
+ {
1428
+ "epoch": 2.0212765957446805,
1429
+ "grad_norm": 0.08630727976560593,
1430
+ "learning_rate": 2.235165325767026e-06,
1431
+ "loss": 1.1733,
1432
+ "step": 193
1433
+ },
1434
+ {
1435
+ "epoch": 2.0319148936170213,
1436
+ "grad_norm": 0.3629175126552582,
1437
+ "learning_rate": 2.2202354022088735e-06,
1438
+ "loss": 1.1114,
1439
+ "step": 194
1440
+ },
1441
+ {
1442
+ "epoch": 2.0106382978723403,
1443
+ "grad_norm": 0.12061420828104019,
1444
+ "learning_rate": 2.2052121636729527e-06,
1445
+ "loss": 1.1813,
1446
+ "step": 195
1447
+ },
1448
+ {
1449
+ "epoch": 2.021276595744681,
1450
+ "grad_norm": 0.12194402515888214,
1451
+ "learning_rate": 2.1900975565967284e-06,
1452
+ "loss": 1.4466,
1453
+ "step": 196
1454
+ },
1455
+ {
1456
+ "epoch": 2.0319148936170213,
1457
+ "grad_norm": 0.09581239521503448,
1458
+ "learning_rate": 2.1748935392555347e-06,
1459
+ "loss": 1.1863,
1460
+ "step": 197
1461
+ },
1462
+ {
1463
+ "epoch": 2.0425531914893615,
1464
+ "grad_norm": 0.12056192755699158,
1465
+ "learning_rate": 2.1596020815088587e-06,
1466
+ "loss": 1.5781,
1467
+ "step": 198
1468
+ },
1469
+ {
1470
+ "epoch": 2.0531914893617023,
1471
+ "grad_norm": 0.10989479720592499,
1472
+ "learning_rate": 2.1442251645451233e-06,
1473
+ "loss": 1.2638,
1474
+ "step": 199
1475
+ },
1476
+ {
1477
+ "epoch": 2.0638297872340425,
1478
+ "grad_norm": 0.1273481398820877,
1479
+ "learning_rate": 2.1287647806249964e-06,
1480
+ "loss": 1.1346,
1481
+ "step": 200
1482
+ },
1483
+ {
1484
+ "epoch": 2.074468085106383,
1485
+ "grad_norm": 0.11547158658504486,
1486
+ "learning_rate": 2.1132229328232755e-06,
1487
+ "loss": 1.124,
1488
+ "step": 201
1489
+ },
1490
+ {
1491
+ "epoch": 2.0851063829787235,
1492
+ "grad_norm": 0.12033279985189438,
1493
+ "learning_rate": 2.0976016347693624e-06,
1494
+ "loss": 1.2695,
1495
+ "step": 202
1496
+ },
1497
+ {
1498
+ "epoch": 2.095744680851064,
1499
+ "grad_norm": 0.11929858475923538,
1500
+ "learning_rate": 2.0819029103863746e-06,
1501
+ "loss": 1.1885,
1502
+ "step": 203
1503
+ },
1504
+ {
1505
+ "epoch": 2.106382978723404,
1506
+ "grad_norm": 0.10733456164598465,
1507
+ "learning_rate": 2.0661287936289213e-06,
1508
+ "loss": 1.3742,
1509
+ "step": 204
1510
+ },
1511
+ {
1512
+ "epoch": 2.117021276595745,
1513
+ "grad_norm": 0.12037491053342819,
1514
+ "learning_rate": 2.050281328219585e-06,
1515
+ "loss": 1.1911,
1516
+ "step": 205
1517
+ },
1518
+ {
1519
+ "epoch": 2.127659574468085,
1520
+ "grad_norm": 0.12621213495731354,
1521
+ "learning_rate": 2.0343625673841254e-06,
1522
+ "loss": 1.1241,
1523
+ "step": 206
1524
+ },
1525
+ {
1526
+ "epoch": 2.1382978723404253,
1527
+ "grad_norm": 0.15265725553035736,
1528
+ "learning_rate": 2.018374573585467e-06,
1529
+ "loss": 1.4419,
1530
+ "step": 207
1531
+ },
1532
+ {
1533
+ "epoch": 2.148936170212766,
1534
+ "grad_norm": 0.10528834164142609,
1535
+ "learning_rate": 2.0023194182564793e-06,
1536
+ "loss": 1.2211,
1537
+ "step": 208
1538
+ },
1539
+ {
1540
+ "epoch": 2.1595744680851063,
1541
+ "grad_norm": 0.11791864037513733,
1542
+ "learning_rate": 1.986199181531599e-06,
1543
+ "loss": 1.2159,
1544
+ "step": 209
1545
+ },
1546
+ {
1547
+ "epoch": 2.1702127659574466,
1548
+ "grad_norm": 0.1230137050151825,
1549
+ "learning_rate": 1.9700159519773233e-06,
1550
+ "loss": 1.2687,
1551
+ "step": 210
1552
+ },
1553
+ {
1554
+ "epoch": 2.1808510638297873,
1555
+ "grad_norm": 0.11243241280317307,
1556
+ "learning_rate": 1.9537718263216137e-06,
1557
+ "loss": 1.2008,
1558
+ "step": 211
1559
+ },
1560
+ {
1561
+ "epoch": 2.1914893617021276,
1562
+ "grad_norm": 0.13040384650230408,
1563
+ "learning_rate": 1.9374689091822377e-06,
1564
+ "loss": 1.2937,
1565
+ "step": 212
1566
+ },
1567
+ {
1568
+ "epoch": 2.202127659574468,
1569
+ "grad_norm": 0.096621572971344,
1570
+ "learning_rate": 1.9211093127940917e-06,
1571
+ "loss": 1.1315,
1572
+ "step": 213
1573
+ },
1574
+ {
1575
+ "epoch": 2.2127659574468086,
1576
+ "grad_norm": 0.10366329550743103,
1577
+ "learning_rate": 1.9046951567355363e-06,
1578
+ "loss": 1.1998,
1579
+ "step": 214
1580
+ },
1581
+ {
1582
+ "epoch": 2.223404255319149,
1583
+ "grad_norm": 0.13266436755657196,
1584
+ "learning_rate": 1.888228567653781e-06,
1585
+ "loss": 1.2169,
1586
+ "step": 215
1587
+ },
1588
+ {
1589
+ "epoch": 2.2340425531914896,
1590
+ "grad_norm": 0.12041480094194412,
1591
+ "learning_rate": 1.87171167898935e-06,
1592
+ "loss": 1.2679,
1593
+ "step": 216
1594
+ },
1595
+ {
1596
+ "epoch": 2.2340425531914896,
1597
+ "eval_loss": 1.557094931602478,
1598
+ "eval_runtime": 3.8276,
1599
+ "eval_samples_per_second": 27.432,
1600
+ "eval_steps_per_second": 13.847,
1601
+ "step": 216
1602
+ },
1603
+ {
1604
+ "epoch": 2.24468085106383,
1605
+ "grad_norm": 0.11926256865262985,
1606
+ "learning_rate": 1.8551466306996702e-06,
1607
+ "loss": 1.2496,
1608
+ "step": 217
1609
+ },
1610
+ {
1611
+ "epoch": 2.25531914893617,
1612
+ "grad_norm": 0.11768142879009247,
1613
+ "learning_rate": 1.838535568981816e-06,
1614
+ "loss": 1.2793,
1615
+ "step": 218
1616
+ },
1617
+ {
1618
+ "epoch": 2.2659574468085104,
1619
+ "grad_norm": 0.09850093722343445,
1620
+ "learning_rate": 1.821880645994443e-06,
1621
+ "loss": 1.1712,
1622
+ "step": 219
1623
+ },
1624
+ {
1625
+ "epoch": 2.276595744680851,
1626
+ "grad_norm": 0.11399635672569275,
1627
+ "learning_rate": 1.8051840195789509e-06,
1628
+ "loss": 1.3151,
1629
+ "step": 220
1630
+ },
1631
+ {
1632
+ "epoch": 2.2872340425531914,
1633
+ "grad_norm": 0.10654745250940323,
1634
+ "learning_rate": 1.788447852979909e-06,
1635
+ "loss": 1.1726,
1636
+ "step": 221
1637
+ },
1638
+ {
1639
+ "epoch": 2.297872340425532,
1640
+ "grad_norm": 0.12983720004558563,
1641
+ "learning_rate": 1.7716743145647837e-06,
1642
+ "loss": 1.2158,
1643
+ "step": 222
1644
+ },
1645
+ {
1646
+ "epoch": 2.3085106382978724,
1647
+ "grad_norm": 0.08331640809774399,
1648
+ "learning_rate": 1.754865577543e-06,
1649
+ "loss": 0.8472,
1650
+ "step": 223
1651
+ },
1652
+ {
1653
+ "epoch": 2.3191489361702127,
1654
+ "grad_norm": 0.11662207543849945,
1655
+ "learning_rate": 1.738023819684377e-06,
1656
+ "loss": 1.2938,
1657
+ "step": 224
1658
+ },
1659
+ {
1660
+ "epoch": 2.329787234042553,
1661
+ "grad_norm": 0.13265132904052734,
1662
+ "learning_rate": 1.7211512230369716e-06,
1663
+ "loss": 1.3288,
1664
+ "step": 225
1665
+ },
1666
+ {
1667
+ "epoch": 2.3404255319148937,
1668
+ "grad_norm": 0.10342156141996384,
1669
+ "learning_rate": 1.7042499736443702e-06,
1670
+ "loss": 1.2352,
1671
+ "step": 226
1672
+ },
1673
+ {
1674
+ "epoch": 2.351063829787234,
1675
+ "grad_norm": 0.10495639592409134,
1676
+ "learning_rate": 1.6873222612624575e-06,
1677
+ "loss": 1.1748,
1678
+ "step": 227
1679
+ },
1680
+ {
1681
+ "epoch": 2.3617021276595747,
1682
+ "grad_norm": 0.1564377248287201,
1683
+ "learning_rate": 1.6703702790757123e-06,
1684
+ "loss": 1.4071,
1685
+ "step": 228
1686
+ },
1687
+ {
1688
+ "epoch": 2.372340425531915,
1689
+ "grad_norm": 0.11000990867614746,
1690
+ "learning_rate": 1.6533962234130513e-06,
1691
+ "loss": 1.2102,
1692
+ "step": 229
1693
+ },
1694
+ {
1695
+ "epoch": 2.382978723404255,
1696
+ "grad_norm": 0.12565018236637115,
1697
+ "learning_rate": 1.6364022934632706e-06,
1698
+ "loss": 1.4047,
1699
+ "step": 230
1700
+ },
1701
+ {
1702
+ "epoch": 2.393617021276596,
1703
+ "grad_norm": 0.11519981920719147,
1704
+ "learning_rate": 1.6193906909901133e-06,
1705
+ "loss": 1.3905,
1706
+ "step": 231
1707
+ },
1708
+ {
1709
+ "epoch": 2.404255319148936,
1710
+ "grad_norm": 0.12704767286777496,
1711
+ "learning_rate": 1.6023636200470066e-06,
1712
+ "loss": 1.0632,
1713
+ "step": 232
1714
+ },
1715
+ {
1716
+ "epoch": 2.4148936170212765,
1717
+ "grad_norm": 0.11226076632738113,
1718
+ "learning_rate": 1.5853232866915004e-06,
1719
+ "loss": 1.2448,
1720
+ "step": 233
1721
+ },
1722
+ {
1723
+ "epoch": 2.425531914893617,
1724
+ "grad_norm": 0.11282170563936234,
1725
+ "learning_rate": 1.5682718986994457e-06,
1726
+ "loss": 1.5068,
1727
+ "step": 234
1728
+ },
1729
+ {
1730
+ "epoch": 2.4361702127659575,
1731
+ "grad_norm": 0.09763903170824051,
1732
+ "learning_rate": 1.5512116652789518e-06,
1733
+ "loss": 1.2398,
1734
+ "step": 235
1735
+ },
1736
+ {
1737
+ "epoch": 2.4468085106382977,
1738
+ "grad_norm": 0.11640322953462601,
1739
+ "learning_rate": 1.5341447967841585e-06,
1740
+ "loss": 1.3176,
1741
+ "step": 236
1742
+ },
1743
+ {
1744
+ "epoch": 2.4574468085106385,
1745
+ "grad_norm": 0.12292848527431488,
1746
+ "learning_rate": 1.5170735044288565e-06,
1747
+ "loss": 1.8823,
1748
+ "step": 237
1749
+ },
1750
+ {
1751
+ "epoch": 2.4680851063829787,
1752
+ "grad_norm": 0.12308197468519211,
1753
+ "learning_rate": 1.5e-06,
1754
+ "loss": 1.14,
1755
+ "step": 238
1756
+ },
1757
+ {
1758
+ "epoch": 2.478723404255319,
1759
+ "grad_norm": 0.11871509999036789,
1760
+ "learning_rate": 1.4829264955711436e-06,
1761
+ "loss": 1.2753,
1762
+ "step": 239
1763
+ },
1764
+ {
1765
+ "epoch": 2.4893617021276597,
1766
+ "grad_norm": 0.14034831523895264,
1767
+ "learning_rate": 1.4658552032158414e-06,
1768
+ "loss": 1.2845,
1769
+ "step": 240
1770
+ },
1771
+ {
1772
+ "epoch": 2.4893617021276597,
1773
+ "eval_loss": 1.5537203550338745,
1774
+ "eval_runtime": 5.1489,
1775
+ "eval_samples_per_second": 20.393,
1776
+ "eval_steps_per_second": 10.294,
1777
+ "step": 240
1778
+ },
1779
+ {
1780
+ "epoch": 2.5,
1781
+ "grad_norm": 0.12317660450935364,
1782
+ "learning_rate": 1.4487883347210483e-06,
1783
+ "loss": 1.2742,
1784
+ "step": 241
1785
+ },
1786
+ {
1787
+ "epoch": 2.5106382978723403,
1788
+ "grad_norm": 0.11180029809474945,
1789
+ "learning_rate": 1.431728101300555e-06,
1790
+ "loss": 1.3743,
1791
+ "step": 242
1792
+ },
1793
+ {
1794
+ "epoch": 2.521276595744681,
1795
+ "grad_norm": 0.12544095516204834,
1796
+ "learning_rate": 1.4146767133085e-06,
1797
+ "loss": 1.2935,
1798
+ "step": 243
1799
+ },
1800
+ {
1801
+ "epoch": 2.5319148936170213,
1802
+ "grad_norm": 0.12283220142126083,
1803
+ "learning_rate": 1.3976363799529937e-06,
1804
+ "loss": 1.2529,
1805
+ "step": 244
1806
+ },
1807
+ {
1808
+ "epoch": 2.5425531914893615,
1809
+ "grad_norm": 0.1375051885843277,
1810
+ "learning_rate": 1.3806093090098872e-06,
1811
+ "loss": 1.2907,
1812
+ "step": 245
1813
+ },
1814
+ {
1815
+ "epoch": 2.5531914893617023,
1816
+ "grad_norm": 0.10762558877468109,
1817
+ "learning_rate": 1.3635977065367295e-06,
1818
+ "loss": 1.1548,
1819
+ "step": 246
1820
+ },
1821
+ {
1822
+ "epoch": 2.5638297872340425,
1823
+ "grad_norm": 0.12075044959783554,
1824
+ "learning_rate": 1.3466037765869486e-06,
1825
+ "loss": 1.2208,
1826
+ "step": 247
1827
+ },
1828
+ {
1829
+ "epoch": 2.574468085106383,
1830
+ "grad_norm": 0.11484728753566742,
1831
+ "learning_rate": 1.3296297209242874e-06,
1832
+ "loss": 1.1182,
1833
+ "step": 248
1834
+ },
1835
+ {
1836
+ "epoch": 2.5851063829787235,
1837
+ "grad_norm": 0.11546777188777924,
1838
+ "learning_rate": 1.312677738737543e-06,
1839
+ "loss": 1.4478,
1840
+ "step": 249
1841
+ },
1842
+ {
1843
+ "epoch": 2.595744680851064,
1844
+ "grad_norm": 0.12128724902868271,
1845
+ "learning_rate": 1.2957500263556303e-06,
1846
+ "loss": 1.3132,
1847
+ "step": 250
1848
+ },
1849
+ {
1850
+ "epoch": 2.6063829787234045,
1851
+ "grad_norm": 0.09233469516038895,
1852
+ "learning_rate": 1.2788487769630284e-06,
1853
+ "loss": 1.0863,
1854
+ "step": 251
1855
+ },
1856
+ {
1857
+ "epoch": 2.617021276595745,
1858
+ "grad_norm": 0.12085112929344177,
1859
+ "learning_rate": 1.261976180315623e-06,
1860
+ "loss": 1.2855,
1861
+ "step": 252
1862
+ },
1863
+ {
1864
+ "epoch": 2.627659574468085,
1865
+ "grad_norm": 0.12655006349086761,
1866
+ "learning_rate": 1.2451344224570002e-06,
1867
+ "loss": 1.2691,
1868
+ "step": 253
1869
+ },
1870
+ {
1871
+ "epoch": 2.6382978723404253,
1872
+ "grad_norm": 0.12646865844726562,
1873
+ "learning_rate": 1.2283256854352162e-06,
1874
+ "loss": 1.2194,
1875
+ "step": 254
1876
+ },
1877
+ {
1878
+ "epoch": 2.648936170212766,
1879
+ "grad_norm": 0.1081186905503273,
1880
+ "learning_rate": 1.2115521470200911e-06,
1881
+ "loss": 1.2551,
1882
+ "step": 255
1883
+ },
1884
+ {
1885
+ "epoch": 2.6595744680851063,
1886
+ "grad_norm": 0.12278001755475998,
1887
+ "learning_rate": 1.1948159804210496e-06,
1888
+ "loss": 1.3049,
1889
+ "step": 256
1890
+ },
1891
+ {
1892
+ "epoch": 2.670212765957447,
1893
+ "grad_norm": 0.09346724301576614,
1894
+ "learning_rate": 1.1781193540055573e-06,
1895
+ "loss": 1.1507,
1896
+ "step": 257
1897
+ },
1898
+ {
1899
+ "epoch": 2.6808510638297873,
1900
+ "grad_norm": 0.10679617524147034,
1901
+ "learning_rate": 1.1614644310181842e-06,
1902
+ "loss": 1.2971,
1903
+ "step": 258
1904
+ },
1905
+ {
1906
+ "epoch": 2.6914893617021276,
1907
+ "grad_norm": 0.11394444108009338,
1908
+ "learning_rate": 1.14485336930033e-06,
1909
+ "loss": 1.2133,
1910
+ "step": 259
1911
+ },
1912
+ {
1913
+ "epoch": 2.702127659574468,
1914
+ "grad_norm": 0.1416221708059311,
1915
+ "learning_rate": 1.1282883210106503e-06,
1916
+ "loss": 1.2132,
1917
+ "step": 260
1918
+ },
1919
+ {
1920
+ "epoch": 2.7127659574468086,
1921
+ "grad_norm": 0.09133229404687881,
1922
+ "learning_rate": 1.1117714323462188e-06,
1923
+ "loss": 1.17,
1924
+ "step": 261
1925
+ },
1926
+ {
1927
+ "epoch": 2.723404255319149,
1928
+ "grad_norm": 0.10997346043586731,
1929
+ "learning_rate": 1.0953048432644634e-06,
1930
+ "loss": 1.1443,
1931
+ "step": 262
1932
+ },
1933
+ {
1934
+ "epoch": 2.7340425531914896,
1935
+ "grad_norm": 0.11233331263065338,
1936
+ "learning_rate": 1.0788906872059088e-06,
1937
+ "loss": 1.3383,
1938
+ "step": 263
1939
+ },
1940
+ {
1941
+ "epoch": 2.74468085106383,
1942
+ "grad_norm": 0.11798594146966934,
1943
+ "learning_rate": 1.0625310908177626e-06,
1944
+ "loss": 1.1226,
1945
+ "step": 264
1946
+ },
1947
+ {
1948
+ "epoch": 2.74468085106383,
1949
+ "eval_loss": 1.5516207218170166,
1950
+ "eval_runtime": 4.7557,
1951
+ "eval_samples_per_second": 22.079,
1952
+ "eval_steps_per_second": 11.145,
1953
+ "step": 264
1954
+ },
1955
+ {
1956
+ "epoch": 2.75531914893617,
1957
+ "grad_norm": 0.12637464702129364,
1958
+ "learning_rate": 1.0462281736783864e-06,
1959
+ "loss": 1.4182,
1960
+ "step": 265
1961
+ },
1962
+ {
1963
+ "epoch": 2.7659574468085104,
1964
+ "grad_norm": 0.11374552547931671,
1965
+ "learning_rate": 1.0299840480226768e-06,
1966
+ "loss": 1.2926,
1967
+ "step": 266
1968
+ },
1969
+ {
1970
+ "epoch": 2.776595744680851,
1971
+ "grad_norm": 0.13765357434749603,
1972
+ "learning_rate": 1.0138008184684011e-06,
1973
+ "loss": 1.3036,
1974
+ "step": 267
1975
+ },
1976
+ {
1977
+ "epoch": 2.7872340425531914,
1978
+ "grad_norm": 0.1168639063835144,
1979
+ "learning_rate": 9.976805817435208e-07,
1980
+ "loss": 1.2854,
1981
+ "step": 268
1982
+ },
1983
+ {
1984
+ "epoch": 2.797872340425532,
1985
+ "grad_norm": 0.11609431356191635,
1986
+ "learning_rate": 9.816254264145328e-07,
1987
+ "loss": 1.2832,
1988
+ "step": 269
1989
+ },
1990
+ {
1991
+ "epoch": 2.8085106382978724,
1992
+ "grad_norm": 0.11090860515832901,
1993
+ "learning_rate": 9.656374326158753e-07,
1994
+ "loss": 1.4098,
1995
+ "step": 270
1996
+ },
1997
+ {
1998
+ "epoch": 2.8191489361702127,
1999
+ "grad_norm": 0.12376827001571655,
2000
+ "learning_rate": 9.497186717804155e-07,
2001
+ "loss": 1.2335,
2002
+ "step": 271
2003
+ },
2004
+ {
2005
+ "epoch": 2.829787234042553,
2006
+ "grad_norm": 0.11905582994222641,
2007
+ "learning_rate": 9.338712063710786e-07,
2008
+ "loss": 1.1991,
2009
+ "step": 272
2010
+ },
2011
+ {
2012
+ "epoch": 2.8404255319148937,
2013
+ "grad_norm": 0.09383586794137955,
2014
+ "learning_rate": 9.180970896136258e-07,
2015
+ "loss": 1.1715,
2016
+ "step": 273
2017
+ },
2018
+ {
2019
+ "epoch": 2.851063829787234,
2020
+ "grad_norm": 0.14080052077770233,
2021
+ "learning_rate": 9.023983652306379e-07,
2022
+ "loss": 1.3227,
2023
+ "step": 274
2024
+ },
2025
+ {
2026
+ "epoch": 2.8617021276595747,
2027
+ "grad_norm": 0.10943106561899185,
2028
+ "learning_rate": 8.867770671767246e-07,
2029
+ "loss": 0.9774,
2030
+ "step": 275
2031
+ },
2032
+ {
2033
+ "epoch": 2.872340425531915,
2034
+ "grad_norm": 0.093683160841465,
2035
+ "learning_rate": 8.712352193750043e-07,
2036
+ "loss": 1.053,
2037
+ "step": 276
2038
+ },
2039
+ {
2040
+ "epoch": 2.882978723404255,
2041
+ "grad_norm": 0.1352389007806778,
2042
+ "learning_rate": 8.557748354548773e-07,
2043
+ "loss": 1.2713,
2044
+ "step": 277
2045
+ },
2046
+ {
2047
+ "epoch": 2.8936170212765955,
2048
+ "grad_norm": 0.09906943887472153,
2049
+ "learning_rate": 8.403979184911411e-07,
2050
+ "loss": 1.3128,
2051
+ "step": 278
2052
+ },
2053
+ {
2054
+ "epoch": 2.904255319148936,
2055
+ "grad_norm": 0.13467717170715332,
2056
+ "learning_rate": 8.251064607444658e-07,
2057
+ "loss": 1.4274,
2058
+ "step": 279
2059
+ },
2060
+ {
2061
+ "epoch": 2.9148936170212765,
2062
+ "grad_norm": 0.11490917205810547,
2063
+ "learning_rate": 8.099024434032718e-07,
2064
+ "loss": 1.307,
2065
+ "step": 280
2066
+ },
2067
+ {
2068
+ "epoch": 2.925531914893617,
2069
+ "grad_norm": 0.10982628166675568,
2070
+ "learning_rate": 7.947878363270472e-07,
2071
+ "loss": 1.0661,
2072
+ "step": 281
2073
+ },
2074
+ {
2075
+ "epoch": 2.9361702127659575,
2076
+ "grad_norm": 0.13426214456558228,
2077
+ "learning_rate": 7.797645977911268e-07,
2078
+ "loss": 1.3296,
2079
+ "step": 282
2080
+ }
2081
+ ],
2082
+ "logging_steps": 1,
2083
+ "max_steps": 376,
2084
+ "num_input_tokens_seen": 0,
2085
+ "num_train_epochs": 4,
2086
+ "save_steps": 94,
2087
+ "stateful_callbacks": {
2088
+ "TrainerControl": {
2089
+ "args": {
2090
+ "should_epoch_stop": false,
2091
+ "should_evaluate": false,
2092
+ "should_log": false,
2093
+ "should_save": true,
2094
+ "should_training_stop": false
2095
+ },
2096
+ "attributes": {}
2097
+ }
2098
+ },
2099
+ "total_flos": 9461272877727744.0,
2100
+ "train_batch_size": 2,
2101
+ "trial_name": null,
2102
+ "trial_params": null
2103
+ }
phi-sft-out/checkpoint-282/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3385717d244ba6cd34f9a94de02b9440c435857ff1e640e8a1c7255c180c1b8
3
+ size 6008
phi-sft-out/checkpoint-282/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
phi-sft-out/checkpoint-376/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/phi-1_5
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.2.dev0
phi-sft-out/checkpoint-376/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-1_5",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "fc1",
25
+ "v_proj",
26
+ "dense",
27
+ "fc2",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
phi-sft-out/checkpoint-376/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241c6c3044862c027dd4a5b884dc64b710af34d4af3be69795a4ff3186febd29
3
+ size 226530600
phi-sft-out/checkpoint-376/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
phi-sft-out/checkpoint-376/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
phi-sft-out/checkpoint-376/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a48dcc1cdca3fafb26844cd4b2fce4583f597e3b9ded8785d1613bc12d2bf011
3
+ size 453227642
phi-sft-out/checkpoint-376/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b8dbab6f3f0b4ec0a2aa7cd20a8f0b4e43beeb74cc71cab5d67dec19630101
3
+ size 14244
phi-sft-out/checkpoint-376/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fba535709d4b8515923331226da9aae9dad13bc2e531b0585c7d05f01f21f87
3
+ size 1064
phi-sft-out/checkpoint-376/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
phi-sft-out/checkpoint-376/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
phi-sft-out/checkpoint-376/tokenizer_config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "pad_token": "<|endoftext|>",
322
+ "return_token_type_ids": false,
323
+ "tokenizer_class": "CodeGenTokenizer",
324
+ "unk_token": "<|endoftext|>"
325
+ }
phi-sft-out/checkpoint-376/trainer_state.json ADDED
@@ -0,0 +1,2793 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.904255319148936,
5
+ "eval_steps": 24,
6
+ "global_step": 376,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010638297872340425,
13
+ "grad_norm": 0.10508890450000763,
14
+ "learning_rate": 3.0000000000000004e-08,
15
+ "loss": 1.2333,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.010638297872340425,
20
+ "eval_loss": 1.5895557403564453,
21
+ "eval_runtime": 2.9603,
22
+ "eval_samples_per_second": 35.469,
23
+ "eval_steps_per_second": 17.903,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.02127659574468085,
28
+ "grad_norm": 0.12071573734283447,
29
+ "learning_rate": 6.000000000000001e-08,
30
+ "loss": 1.3986,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.031914893617021274,
35
+ "grad_norm": 0.10401547700166702,
36
+ "learning_rate": 9e-08,
37
+ "loss": 1.2058,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.0425531914893617,
42
+ "grad_norm": 0.12298297882080078,
43
+ "learning_rate": 1.2000000000000002e-07,
44
+ "loss": 1.3298,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.05319148936170213,
49
+ "grad_norm": 0.1327030211687088,
50
+ "learning_rate": 1.5000000000000002e-07,
51
+ "loss": 1.4031,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.06382978723404255,
56
+ "grad_norm": 0.12036772817373276,
57
+ "learning_rate": 1.8e-07,
58
+ "loss": 1.5335,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.07446808510638298,
63
+ "grad_norm": 0.14979703724384308,
64
+ "learning_rate": 2.1000000000000003e-07,
65
+ "loss": 1.3224,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.0851063829787234,
70
+ "grad_norm": 0.13082227110862732,
71
+ "learning_rate": 2.4000000000000003e-07,
72
+ "loss": 1.4035,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.09574468085106383,
77
+ "grad_norm": 0.09265327453613281,
78
+ "learning_rate": 2.7e-07,
79
+ "loss": 1.1546,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.10638297872340426,
84
+ "grad_norm": 0.10080434381961823,
85
+ "learning_rate": 3.0000000000000004e-07,
86
+ "loss": 1.2652,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.11702127659574468,
91
+ "grad_norm": 0.10915568470954895,
92
+ "learning_rate": 3.3e-07,
93
+ "loss": 1.1438,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.1276595744680851,
98
+ "grad_norm": 0.1307348906993866,
99
+ "learning_rate": 3.6e-07,
100
+ "loss": 1.2821,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.13829787234042554,
105
+ "grad_norm": 0.09814529865980148,
106
+ "learning_rate": 3.9e-07,
107
+ "loss": 1.3905,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.14893617021276595,
112
+ "grad_norm": 0.11842218786478043,
113
+ "learning_rate": 4.2000000000000006e-07,
114
+ "loss": 1.3085,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.1595744680851064,
119
+ "grad_norm": 0.10207124054431915,
120
+ "learning_rate": 4.5e-07,
121
+ "loss": 1.19,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.1702127659574468,
126
+ "grad_norm": 0.1150127425789833,
127
+ "learning_rate": 4.800000000000001e-07,
128
+ "loss": 1.386,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.18085106382978725,
133
+ "grad_norm": 0.11641352623701096,
134
+ "learning_rate": 5.100000000000001e-07,
135
+ "loss": 1.4357,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.19148936170212766,
140
+ "grad_norm": 0.15035435557365417,
141
+ "learning_rate": 5.4e-07,
142
+ "loss": 1.2549,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.20212765957446807,
147
+ "grad_norm": 0.0984087809920311,
148
+ "learning_rate": 5.7e-07,
149
+ "loss": 0.9723,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.2127659574468085,
154
+ "grad_norm": 0.11582670360803604,
155
+ "learning_rate": 6.000000000000001e-07,
156
+ "loss": 1.1402,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.22340425531914893,
161
+ "grad_norm": 0.10151291638612747,
162
+ "learning_rate": 6.3e-07,
163
+ "loss": 1.1533,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.23404255319148937,
168
+ "grad_norm": 0.09040653705596924,
169
+ "learning_rate": 6.6e-07,
170
+ "loss": 1.0438,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.24468085106382978,
175
+ "grad_norm": 0.10666865110397339,
176
+ "learning_rate": 6.900000000000001e-07,
177
+ "loss": 1.3195,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.2553191489361702,
182
+ "grad_norm": 0.12293969094753265,
183
+ "learning_rate": 7.2e-07,
184
+ "loss": 1.7286,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.2553191489361702,
189
+ "eval_loss": 1.5890721082687378,
190
+ "eval_runtime": 2.9908,
191
+ "eval_samples_per_second": 35.108,
192
+ "eval_steps_per_second": 17.721,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.26595744680851063,
197
+ "grad_norm": 0.11052387952804565,
198
+ "learning_rate": 7.5e-07,
199
+ "loss": 1.1413,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.2765957446808511,
204
+ "grad_norm": 0.09323304146528244,
205
+ "learning_rate": 7.8e-07,
206
+ "loss": 1.2906,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.2872340425531915,
211
+ "grad_norm": 0.12542971968650818,
212
+ "learning_rate": 8.100000000000001e-07,
213
+ "loss": 1.2809,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.2978723404255319,
218
+ "grad_norm": 0.1080215722322464,
219
+ "learning_rate": 8.400000000000001e-07,
220
+ "loss": 1.2735,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.30851063829787234,
225
+ "grad_norm": 0.11304887384176254,
226
+ "learning_rate": 8.699999999999999e-07,
227
+ "loss": 1.3767,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.3191489361702128,
232
+ "grad_norm": 0.15650290250778198,
233
+ "learning_rate": 9e-07,
234
+ "loss": 1.4713,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.32978723404255317,
239
+ "grad_norm": 0.12139321118593216,
240
+ "learning_rate": 9.3e-07,
241
+ "loss": 1.3479,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.3404255319148936,
246
+ "grad_norm": 0.10141867399215698,
247
+ "learning_rate": 9.600000000000001e-07,
248
+ "loss": 1.1512,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.35106382978723405,
253
+ "grad_norm": 0.15045498311519623,
254
+ "learning_rate": 9.9e-07,
255
+ "loss": 1.5059,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.3617021276595745,
260
+ "grad_norm": 0.12956956028938293,
261
+ "learning_rate": 1.0200000000000002e-06,
262
+ "loss": 1.2849,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.3723404255319149,
267
+ "grad_norm": 0.12963886559009552,
268
+ "learning_rate": 1.05e-06,
269
+ "loss": 1.5025,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.3829787234042553,
274
+ "grad_norm": 0.11268144845962524,
275
+ "learning_rate": 1.08e-06,
276
+ "loss": 1.2987,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.39361702127659576,
281
+ "grad_norm": 0.12941108644008636,
282
+ "learning_rate": 1.11e-06,
283
+ "loss": 1.3432,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.40425531914893614,
288
+ "grad_norm": 0.11319927126169205,
289
+ "learning_rate": 1.14e-06,
290
+ "loss": 1.1665,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.4148936170212766,
295
+ "grad_norm": 0.11748912930488586,
296
+ "learning_rate": 1.17e-06,
297
+ "loss": 1.423,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.425531914893617,
302
+ "grad_norm": 0.11666171997785568,
303
+ "learning_rate": 1.2000000000000002e-06,
304
+ "loss": 1.4391,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.43617021276595747,
309
+ "grad_norm": 0.12274409830570221,
310
+ "learning_rate": 1.2299999999999999e-06,
311
+ "loss": 1.4865,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.44680851063829785,
316
+ "grad_norm": 0.09922561049461365,
317
+ "learning_rate": 1.26e-06,
318
+ "loss": 1.2193,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.4574468085106383,
323
+ "grad_norm": 0.12003930658102036,
324
+ "learning_rate": 1.29e-06,
325
+ "loss": 1.3024,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.46808510638297873,
330
+ "grad_norm": 0.12094161659479141,
331
+ "learning_rate": 1.32e-06,
332
+ "loss": 1.4654,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.4787234042553192,
337
+ "grad_norm": 0.12934774160385132,
338
+ "learning_rate": 1.35e-06,
339
+ "loss": 1.3713,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.48936170212765956,
344
+ "grad_norm": 0.09754550457000732,
345
+ "learning_rate": 1.3800000000000001e-06,
346
+ "loss": 1.1991,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.5,
351
+ "grad_norm": 0.11549004167318344,
352
+ "learning_rate": 1.41e-06,
353
+ "loss": 1.4859,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.5106382978723404,
358
+ "grad_norm": 0.12035688012838364,
359
+ "learning_rate": 1.44e-06,
360
+ "loss": 1.2823,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.5106382978723404,
365
+ "eval_loss": 1.5874611139297485,
366
+ "eval_runtime": 2.9787,
367
+ "eval_samples_per_second": 35.251,
368
+ "eval_steps_per_second": 17.793,
369
+ "step": 48
370
+ },
371
+ {
372
+ "epoch": 0.5212765957446809,
373
+ "grad_norm": 0.12258938699960709,
374
+ "learning_rate": 1.4700000000000001e-06,
375
+ "loss": 1.2966,
376
+ "step": 49
377
+ },
378
+ {
379
+ "epoch": 0.5319148936170213,
380
+ "grad_norm": 0.12217017263174057,
381
+ "learning_rate": 1.5e-06,
382
+ "loss": 1.2988,
383
+ "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.5425531914893617,
387
+ "grad_norm": 0.12793436646461487,
388
+ "learning_rate": 1.53e-06,
389
+ "loss": 1.4233,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.5531914893617021,
394
+ "grad_norm": 0.11145548522472382,
395
+ "learning_rate": 1.56e-06,
396
+ "loss": 1.2792,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.5638297872340425,
401
+ "grad_norm": 0.13195408880710602,
402
+ "learning_rate": 1.59e-06,
403
+ "loss": 1.4481,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.574468085106383,
408
+ "grad_norm": 0.10663347691297531,
409
+ "learning_rate": 1.6200000000000002e-06,
410
+ "loss": 1.2331,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.5851063829787234,
415
+ "grad_norm": 0.10975392907857895,
416
+ "learning_rate": 1.65e-06,
417
+ "loss": 1.1839,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.5957446808510638,
422
+ "grad_norm": 0.13139477372169495,
423
+ "learning_rate": 1.6800000000000002e-06,
424
+ "loss": 1.436,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.6063829787234043,
429
+ "grad_norm": 0.0924743041396141,
430
+ "learning_rate": 1.71e-06,
431
+ "loss": 1.1291,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.6170212765957447,
436
+ "grad_norm": 0.12475109100341797,
437
+ "learning_rate": 1.7399999999999999e-06,
438
+ "loss": 1.3444,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.6276595744680851,
443
+ "grad_norm": 0.08960220962762833,
444
+ "learning_rate": 1.77e-06,
445
+ "loss": 1.2511,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.6382978723404256,
450
+ "grad_norm": 0.09909304976463318,
451
+ "learning_rate": 1.8e-06,
452
+ "loss": 1.1281,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.648936170212766,
457
+ "grad_norm": 0.11598234623670578,
458
+ "learning_rate": 1.83e-06,
459
+ "loss": 1.486,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.6595744680851063,
464
+ "grad_norm": 0.1404409557580948,
465
+ "learning_rate": 1.86e-06,
466
+ "loss": 1.4557,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.6702127659574468,
471
+ "grad_norm": 0.11349129676818848,
472
+ "learning_rate": 1.8900000000000001e-06,
473
+ "loss": 1.3969,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.6808510638297872,
478
+ "grad_norm": 0.10858353972434998,
479
+ "learning_rate": 1.9200000000000003e-06,
480
+ "loss": 1.3515,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.6914893617021277,
485
+ "grad_norm": 0.11054569482803345,
486
+ "learning_rate": 1.95e-06,
487
+ "loss": 1.248,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.7021276595744681,
492
+ "grad_norm": 0.11826737225055695,
493
+ "learning_rate": 1.98e-06,
494
+ "loss": 1.3439,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.7127659574468085,
499
+ "grad_norm": 0.12291310727596283,
500
+ "learning_rate": 2.0100000000000002e-06,
501
+ "loss": 1.4226,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.723404255319149,
506
+ "grad_norm": 0.1383126825094223,
507
+ "learning_rate": 2.0400000000000004e-06,
508
+ "loss": 1.194,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.7340425531914894,
513
+ "grad_norm": 0.10981890559196472,
514
+ "learning_rate": 2.07e-06,
515
+ "loss": 1.2502,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.7446808510638298,
520
+ "grad_norm": 0.10639657825231552,
521
+ "learning_rate": 2.1e-06,
522
+ "loss": 1.2262,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.7553191489361702,
527
+ "grad_norm": 0.46177396178245544,
528
+ "learning_rate": 2.13e-06,
529
+ "loss": 5.063,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.7659574468085106,
534
+ "grad_norm": 0.11061427742242813,
535
+ "learning_rate": 2.16e-06,
536
+ "loss": 1.3856,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.7659574468085106,
541
+ "eval_loss": 1.5843762159347534,
542
+ "eval_runtime": 2.9943,
543
+ "eval_samples_per_second": 35.066,
544
+ "eval_steps_per_second": 17.7,
545
+ "step": 72
546
+ },
547
+ {
548
+ "epoch": 0.776595744680851,
549
+ "grad_norm": 0.13233324885368347,
550
+ "learning_rate": 2.19e-06,
551
+ "loss": 1.526,
552
+ "step": 73
553
+ },
554
+ {
555
+ "epoch": 0.7872340425531915,
556
+ "grad_norm": 0.14500053226947784,
557
+ "learning_rate": 2.22e-06,
558
+ "loss": 1.2554,
559
+ "step": 74
560
+ },
561
+ {
562
+ "epoch": 0.7978723404255319,
563
+ "grad_norm": 0.10629269480705261,
564
+ "learning_rate": 2.25e-06,
565
+ "loss": 1.2917,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 0.8085106382978723,
570
+ "grad_norm": 0.09674028307199478,
571
+ "learning_rate": 2.28e-06,
572
+ "loss": 1.2169,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 0.8191489361702128,
577
+ "grad_norm": 0.11965947598218918,
578
+ "learning_rate": 2.31e-06,
579
+ "loss": 1.2445,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 0.8297872340425532,
584
+ "grad_norm": 0.10441229492425919,
585
+ "learning_rate": 2.34e-06,
586
+ "loss": 1.2392,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 0.8404255319148937,
591
+ "grad_norm": 0.13795869052410126,
592
+ "learning_rate": 2.37e-06,
593
+ "loss": 1.5335,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 0.851063829787234,
598
+ "grad_norm": 0.10789927840232849,
599
+ "learning_rate": 2.4000000000000003e-06,
600
+ "loss": 1.2309,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 0.8617021276595744,
605
+ "grad_norm": 0.10697130113840103,
606
+ "learning_rate": 2.43e-06,
607
+ "loss": 1.276,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 0.8723404255319149,
612
+ "grad_norm": 0.11484125256538391,
613
+ "learning_rate": 2.4599999999999997e-06,
614
+ "loss": 1.2163,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 0.8829787234042553,
619
+ "grad_norm": 0.09692610800266266,
620
+ "learning_rate": 2.49e-06,
621
+ "loss": 1.1554,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 0.8936170212765957,
626
+ "grad_norm": 0.10697747021913528,
627
+ "learning_rate": 2.52e-06,
628
+ "loss": 1.211,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 0.9042553191489362,
633
+ "grad_norm": 0.10578318685293198,
634
+ "learning_rate": 2.55e-06,
635
+ "loss": 1.2634,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 0.9148936170212766,
640
+ "grad_norm": 0.10587752610445023,
641
+ "learning_rate": 2.58e-06,
642
+ "loss": 1.369,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 0.925531914893617,
647
+ "grad_norm": 0.11430489271879196,
648
+ "learning_rate": 2.61e-06,
649
+ "loss": 1.3048,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 0.9361702127659575,
654
+ "grad_norm": 0.11116154491901398,
655
+ "learning_rate": 2.64e-06,
656
+ "loss": 1.1883,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 0.9468085106382979,
661
+ "grad_norm": 0.12686476111412048,
662
+ "learning_rate": 2.6700000000000003e-06,
663
+ "loss": 1.2605,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 0.9574468085106383,
668
+ "grad_norm": 0.10976041853427887,
669
+ "learning_rate": 2.7e-06,
670
+ "loss": 1.2345,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 0.9680851063829787,
675
+ "grad_norm": 0.12391550838947296,
676
+ "learning_rate": 2.73e-06,
677
+ "loss": 1.2233,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 0.9787234042553191,
682
+ "grad_norm": 0.1277073174715042,
683
+ "learning_rate": 2.7600000000000003e-06,
684
+ "loss": 1.2437,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 0.9893617021276596,
689
+ "grad_norm": 0.10421616584062576,
690
+ "learning_rate": 2.7900000000000004e-06,
691
+ "loss": 1.1432,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 1.0,
696
+ "grad_norm": 0.12696842849254608,
697
+ "learning_rate": 2.82e-06,
698
+ "loss": 1.3558,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 1.0106382978723405,
703
+ "grad_norm": 0.10387945920228958,
704
+ "learning_rate": 2.85e-06,
705
+ "loss": 1.1902,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 1.0212765957446808,
710
+ "grad_norm": 0.14543002843856812,
711
+ "learning_rate": 2.88e-06,
712
+ "loss": 1.244,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 1.0212765957446808,
717
+ "eval_loss": 1.5803985595703125,
718
+ "eval_runtime": 3.0087,
719
+ "eval_samples_per_second": 34.899,
720
+ "eval_steps_per_second": 17.616,
721
+ "step": 96
722
+ },
723
+ {
724
+ "epoch": 1.0319148936170213,
725
+ "grad_norm": 0.17504040896892548,
726
+ "learning_rate": 2.91e-06,
727
+ "loss": 1.3115,
728
+ "step": 97
729
+ },
730
+ {
731
+ "epoch": 1.0106382978723405,
732
+ "grad_norm": 0.14017756283283234,
733
+ "learning_rate": 2.9400000000000002e-06,
734
+ "loss": 1.356,
735
+ "step": 98
736
+ },
737
+ {
738
+ "epoch": 1.0212765957446808,
739
+ "grad_norm": 0.11604318767786026,
740
+ "learning_rate": 2.97e-06,
741
+ "loss": 1.2806,
742
+ "step": 99
743
+ },
744
+ {
745
+ "epoch": 1.0319148936170213,
746
+ "grad_norm": 0.15116065740585327,
747
+ "learning_rate": 3e-06,
748
+ "loss": 1.3279,
749
+ "step": 100
750
+ },
751
+ {
752
+ "epoch": 1.0425531914893618,
753
+ "grad_norm": 0.10773392021656036,
754
+ "learning_rate": 2.9999028286680832e-06,
755
+ "loss": 1.3871,
756
+ "step": 101
757
+ },
758
+ {
759
+ "epoch": 1.053191489361702,
760
+ "grad_norm": 0.09363637119531631,
761
+ "learning_rate": 2.999611327262024e-06,
762
+ "loss": 1.1334,
763
+ "step": 102
764
+ },
765
+ {
766
+ "epoch": 1.0638297872340425,
767
+ "grad_norm": 0.09164439886808395,
768
+ "learning_rate": 2.999125533549261e-06,
769
+ "loss": 1.4026,
770
+ "step": 103
771
+ },
772
+ {
773
+ "epoch": 1.074468085106383,
774
+ "grad_norm": 0.12113964557647705,
775
+ "learning_rate": 2.9984455104700915e-06,
776
+ "loss": 1.2097,
777
+ "step": 104
778
+ },
779
+ {
780
+ "epoch": 1.0851063829787233,
781
+ "grad_norm": 0.10569895058870316,
782
+ "learning_rate": 2.9975713461295125e-06,
783
+ "loss": 1.3077,
784
+ "step": 105
785
+ },
786
+ {
787
+ "epoch": 1.0957446808510638,
788
+ "grad_norm": 0.11219862103462219,
789
+ "learning_rate": 2.996503153785809e-06,
790
+ "loss": 1.1923,
791
+ "step": 106
792
+ },
793
+ {
794
+ "epoch": 1.1063829787234043,
795
+ "grad_norm": 0.13474853336811066,
796
+ "learning_rate": 2.9952410718358777e-06,
797
+ "loss": 1.2729,
798
+ "step": 107
799
+ },
800
+ {
801
+ "epoch": 1.1170212765957448,
802
+ "grad_norm": 0.10451857000589371,
803
+ "learning_rate": 2.993785263797297e-06,
804
+ "loss": 1.2904,
805
+ "step": 108
806
+ },
807
+ {
808
+ "epoch": 1.127659574468085,
809
+ "grad_norm": 0.12593719363212585,
810
+ "learning_rate": 2.9921359182871422e-06,
811
+ "loss": 1.4021,
812
+ "step": 109
813
+ },
814
+ {
815
+ "epoch": 1.1382978723404256,
816
+ "grad_norm": 0.12547315657138824,
817
+ "learning_rate": 2.990293248997547e-06,
818
+ "loss": 1.2093,
819
+ "step": 110
820
+ },
821
+ {
822
+ "epoch": 1.148936170212766,
823
+ "grad_norm": 0.10086555033922195,
824
+ "learning_rate": 2.988257494668016e-06,
825
+ "loss": 1.3098,
826
+ "step": 111
827
+ },
828
+ {
829
+ "epoch": 1.1595744680851063,
830
+ "grad_norm": 0.10801573097705841,
831
+ "learning_rate": 2.9860289190544963e-06,
832
+ "loss": 1.2752,
833
+ "step": 112
834
+ },
835
+ {
836
+ "epoch": 1.1702127659574468,
837
+ "grad_norm": 0.11851054430007935,
838
+ "learning_rate": 2.9836078108952015e-06,
839
+ "loss": 1.3066,
840
+ "step": 113
841
+ },
842
+ {
843
+ "epoch": 1.1808510638297873,
844
+ "grad_norm": 0.1265188604593277,
845
+ "learning_rate": 2.9809944838732045e-06,
846
+ "loss": 1.1946,
847
+ "step": 114
848
+ },
849
+ {
850
+ "epoch": 1.1914893617021276,
851
+ "grad_norm": 0.10702725499868393,
852
+ "learning_rate": 2.9781892765757954e-06,
853
+ "loss": 1.2182,
854
+ "step": 115
855
+ },
856
+ {
857
+ "epoch": 1.202127659574468,
858
+ "grad_norm": 0.7757766842842102,
859
+ "learning_rate": 2.9751925524506135e-06,
860
+ "loss": 5.6082,
861
+ "step": 116
862
+ },
863
+ {
864
+ "epoch": 1.2127659574468086,
865
+ "grad_norm": 0.10182739049196243,
866
+ "learning_rate": 2.9720046997585577e-06,
867
+ "loss": 1.309,
868
+ "step": 117
869
+ },
870
+ {
871
+ "epoch": 1.2234042553191489,
872
+ "grad_norm": 0.14062073826789856,
873
+ "learning_rate": 2.9686261315234844e-06,
874
+ "loss": 1.3668,
875
+ "step": 118
876
+ },
877
+ {
878
+ "epoch": 1.2340425531914894,
879
+ "grad_norm": 0.1063840240240097,
880
+ "learning_rate": 2.965057285478694e-06,
881
+ "loss": 1.2247,
882
+ "step": 119
883
+ },
884
+ {
885
+ "epoch": 1.2446808510638299,
886
+ "grad_norm": 0.10701325535774231,
887
+ "learning_rate": 2.961298624010219e-06,
888
+ "loss": 1.2499,
889
+ "step": 120
890
+ },
891
+ {
892
+ "epoch": 1.2446808510638299,
893
+ "eval_loss": 1.575344204902649,
894
+ "eval_runtime": 8.2617,
895
+ "eval_samples_per_second": 12.709,
896
+ "eval_steps_per_second": 6.415,
897
+ "step": 120
898
+ },
899
+ {
900
+ "epoch": 1.2553191489361701,
901
+ "grad_norm": 0.11413375288248062,
902
+ "learning_rate": 2.957350634096912e-06,
903
+ "loss": 1.3593,
904
+ "step": 121
905
+ },
906
+ {
907
+ "epoch": 1.2659574468085106,
908
+ "grad_norm": 0.10826950520277023,
909
+ "learning_rate": 2.9532138272473597e-06,
910
+ "loss": 1.232,
911
+ "step": 122
912
+ },
913
+ {
914
+ "epoch": 1.2765957446808511,
915
+ "grad_norm": 0.10749218612909317,
916
+ "learning_rate": 2.9488887394336023e-06,
917
+ "loss": 1.401,
918
+ "step": 123
919
+ },
920
+ {
921
+ "epoch": 1.2872340425531914,
922
+ "grad_norm": 0.1175396591424942,
923
+ "learning_rate": 2.944375931021699e-06,
924
+ "loss": 1.2867,
925
+ "step": 124
926
+ },
927
+ {
928
+ "epoch": 1.297872340425532,
929
+ "grad_norm": 0.10688498616218567,
930
+ "learning_rate": 2.9396759866991214e-06,
931
+ "loss": 1.3689,
932
+ "step": 125
933
+ },
934
+ {
935
+ "epoch": 1.3085106382978724,
936
+ "grad_norm": 0.11630786955356598,
937
+ "learning_rate": 2.934789515399002e-06,
938
+ "loss": 1.2328,
939
+ "step": 126
940
+ },
941
+ {
942
+ "epoch": 1.3191489361702127,
943
+ "grad_norm": 0.11495409905910492,
944
+ "learning_rate": 2.9297171502212414e-06,
945
+ "loss": 1.1738,
946
+ "step": 127
947
+ },
948
+ {
949
+ "epoch": 1.3297872340425532,
950
+ "grad_norm": 0.10823408514261246,
951
+ "learning_rate": 2.924459548350479e-06,
952
+ "loss": 1.2318,
953
+ "step": 128
954
+ },
955
+ {
956
+ "epoch": 1.3404255319148937,
957
+ "grad_norm": 0.10759969800710678,
958
+ "learning_rate": 2.9190173909709506e-06,
959
+ "loss": 1.319,
960
+ "step": 129
961
+ },
962
+ {
963
+ "epoch": 1.351063829787234,
964
+ "grad_norm": 0.12790299952030182,
965
+ "learning_rate": 2.9133913831782307e-06,
966
+ "loss": 1.4282,
967
+ "step": 130
968
+ },
969
+ {
970
+ "epoch": 1.3617021276595744,
971
+ "grad_norm": 0.10899878293275833,
972
+ "learning_rate": 2.9075822538878805e-06,
973
+ "loss": 1.2455,
974
+ "step": 131
975
+ },
976
+ {
977
+ "epoch": 1.372340425531915,
978
+ "grad_norm": 0.12732432782649994,
979
+ "learning_rate": 2.9015907557410068e-06,
980
+ "loss": 1.2227,
981
+ "step": 132
982
+ },
983
+ {
984
+ "epoch": 1.3829787234042552,
985
+ "grad_norm": 0.10140018165111542,
986
+ "learning_rate": 2.8954176650067494e-06,
987
+ "loss": 1.0596,
988
+ "step": 133
989
+ },
990
+ {
991
+ "epoch": 1.3936170212765957,
992
+ "grad_norm": 0.12063546478748322,
993
+ "learning_rate": 2.889063781481708e-06,
994
+ "loss": 1.3321,
995
+ "step": 134
996
+ },
997
+ {
998
+ "epoch": 1.4042553191489362,
999
+ "grad_norm": 0.11323118209838867,
1000
+ "learning_rate": 2.8825299283863144e-06,
1001
+ "loss": 1.3366,
1002
+ "step": 135
1003
+ },
1004
+ {
1005
+ "epoch": 1.4148936170212765,
1006
+ "grad_norm": 0.12391477078199387,
1007
+ "learning_rate": 2.8758169522581796e-06,
1008
+ "loss": 1.2917,
1009
+ "step": 136
1010
+ },
1011
+ {
1012
+ "epoch": 1.425531914893617,
1013
+ "grad_norm": 0.12329094856977463,
1014
+ "learning_rate": 2.8689257228424125e-06,
1015
+ "loss": 1.1365,
1016
+ "step": 137
1017
+ },
1018
+ {
1019
+ "epoch": 1.4361702127659575,
1020
+ "grad_norm": 0.11298198997974396,
1021
+ "learning_rate": 2.8618571329789333e-06,
1022
+ "loss": 1.4996,
1023
+ "step": 138
1024
+ },
1025
+ {
1026
+ "epoch": 1.4468085106382977,
1027
+ "grad_norm": 0.10263165086507797,
1028
+ "learning_rate": 2.8546120984867994e-06,
1029
+ "loss": 1.199,
1030
+ "step": 139
1031
+ },
1032
+ {
1033
+ "epoch": 1.4574468085106382,
1034
+ "grad_norm": 0.13330323994159698,
1035
+ "learning_rate": 2.8471915580455442e-06,
1036
+ "loss": 1.3746,
1037
+ "step": 140
1038
+ },
1039
+ {
1040
+ "epoch": 1.4680851063829787,
1041
+ "grad_norm": 0.10694881528615952,
1042
+ "learning_rate": 2.8395964730735666e-06,
1043
+ "loss": 1.3798,
1044
+ "step": 141
1045
+ },
1046
+ {
1047
+ "epoch": 1.4787234042553192,
1048
+ "grad_norm": 0.10929003357887268,
1049
+ "learning_rate": 2.8318278276035626e-06,
1050
+ "loss": 1.2918,
1051
+ "step": 142
1052
+ },
1053
+ {
1054
+ "epoch": 1.4893617021276595,
1055
+ "grad_norm": 0.10969982296228409,
1056
+ "learning_rate": 2.8238866281550366e-06,
1057
+ "loss": 1.0444,
1058
+ "step": 143
1059
+ },
1060
+ {
1061
+ "epoch": 1.5,
1062
+ "grad_norm": 0.10668367147445679,
1063
+ "learning_rate": 2.815773903603892e-06,
1064
+ "loss": 1.1656,
1065
+ "step": 144
1066
+ },
1067
+ {
1068
+ "epoch": 1.5,
1069
+ "eval_loss": 1.5705612897872925,
1070
+ "eval_runtime": 5.6853,
1071
+ "eval_samples_per_second": 18.469,
1072
+ "eval_steps_per_second": 9.322,
1073
+ "step": 144
1074
+ },
1075
+ {
1076
+ "epoch": 1.5106382978723403,
1077
+ "grad_norm": 0.12057002633810043,
1078
+ "learning_rate": 2.807490705049127e-06,
1079
+ "loss": 1.2475,
1080
+ "step": 145
1081
+ },
1082
+ {
1083
+ "epoch": 1.521276595744681,
1084
+ "grad_norm": 0.10394139587879181,
1085
+ "learning_rate": 2.7990381056766585e-06,
1086
+ "loss": 1.3376,
1087
+ "step": 146
1088
+ },
1089
+ {
1090
+ "epoch": 1.5319148936170213,
1091
+ "grad_norm": 0.12907464802265167,
1092
+ "learning_rate": 2.7904172006202705e-06,
1093
+ "loss": 1.3509,
1094
+ "step": 147
1095
+ },
1096
+ {
1097
+ "epoch": 1.5425531914893615,
1098
+ "grad_norm": 0.1252606213092804,
1099
+ "learning_rate": 2.7816291068197328e-06,
1100
+ "loss": 1.1744,
1101
+ "step": 148
1102
+ },
1103
+ {
1104
+ "epoch": 1.5531914893617023,
1105
+ "grad_norm": 0.1514441967010498,
1106
+ "learning_rate": 2.772674962876085e-06,
1107
+ "loss": 1.9324,
1108
+ "step": 149
1109
+ },
1110
+ {
1111
+ "epoch": 1.5638297872340425,
1112
+ "grad_norm": 0.12377320230007172,
1113
+ "learning_rate": 2.7635559289041174e-06,
1114
+ "loss": 1.4511,
1115
+ "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 1.574468085106383,
1119
+ "grad_norm": 0.10629550367593765,
1120
+ "learning_rate": 2.7542731863820665e-06,
1121
+ "loss": 1.257,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 1.5851063829787235,
1126
+ "grad_norm": 0.10322704166173935,
1127
+ "learning_rate": 2.744827937998538e-06,
1128
+ "loss": 1.1796,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 1.5957446808510638,
1133
+ "grad_norm": 0.12690168619155884,
1134
+ "learning_rate": 2.735221407496686e-06,
1135
+ "loss": 1.3325,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 1.6063829787234043,
1140
+ "grad_norm": 0.0982392430305481,
1141
+ "learning_rate": 2.725454839515663e-06,
1142
+ "loss": 1.2169,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 1.6170212765957448,
1147
+ "grad_norm": 0.11184275150299072,
1148
+ "learning_rate": 2.7155294994293606e-06,
1149
+ "loss": 1.295,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 1.627659574468085,
1154
+ "grad_norm": 0.10721098631620407,
1155
+ "learning_rate": 2.7054466731824676e-06,
1156
+ "loss": 1.1945,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 1.6382978723404256,
1161
+ "grad_norm": 0.1254221498966217,
1162
+ "learning_rate": 2.695207667123857e-06,
1163
+ "loss": 1.2693,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 1.648936170212766,
1168
+ "grad_norm": 0.1157686784863472,
1169
+ "learning_rate": 2.684813807837338e-06,
1170
+ "loss": 1.1992,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 1.6595744680851063,
1175
+ "grad_norm": 0.10201229155063629,
1176
+ "learning_rate": 2.674266441969778e-06,
1177
+ "loss": 1.2401,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 1.6702127659574468,
1182
+ "grad_norm": 0.10953360050916672,
1183
+ "learning_rate": 2.6635669360566298e-06,
1184
+ "loss": 1.1627,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 1.6808510638297873,
1189
+ "grad_norm": 0.1248813271522522,
1190
+ "learning_rate": 2.652716676344881e-06,
1191
+ "loss": 1.3179,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 1.6914893617021276,
1196
+ "grad_norm": 0.09584470838308334,
1197
+ "learning_rate": 2.6417170686134472e-06,
1198
+ "loss": 1.2128,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 1.702127659574468,
1203
+ "grad_norm": 0.12864486873149872,
1204
+ "learning_rate": 2.630569537991042e-06,
1205
+ "loss": 1.1889,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 1.7127659574468086,
1210
+ "grad_norm": 0.11820186674594879,
1211
+ "learning_rate": 2.6192755287715282e-06,
1212
+ "loss": 1.2848,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 1.7234042553191489,
1217
+ "grad_norm": 0.13811764121055603,
1218
+ "learning_rate": 2.6078365042267987e-06,
1219
+ "loss": 1.2091,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 1.7340425531914894,
1224
+ "grad_norm": 0.12099539488554001,
1225
+ "learning_rate": 2.5962539464171862e-06,
1226
+ "loss": 1.2853,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 1.7446808510638299,
1231
+ "grad_norm": 0.14544783532619476,
1232
+ "learning_rate": 2.5845293559994513e-06,
1233
+ "loss": 1.1574,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 1.7553191489361701,
1238
+ "grad_norm": 0.11159494519233704,
1239
+ "learning_rate": 2.5726642520323493e-06,
1240
+ "loss": 1.1928,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 1.7553191489361701,
1245
+ "eval_loss": 1.5656005144119263,
1246
+ "eval_runtime": 3.0568,
1247
+ "eval_samples_per_second": 34.349,
1248
+ "eval_steps_per_second": 17.338,
1249
+ "step": 168
1250
+ },
1251
+ {
1252
+ "epoch": 1.7659574468085106,
1253
+ "grad_norm": 0.1385321319103241,
1254
+ "learning_rate": 2.5606601717798212e-06,
1255
+ "loss": 1.365,
1256
+ "step": 169
1257
+ },
1258
+ {
1259
+ "epoch": 1.7765957446808511,
1260
+ "grad_norm": 0.12905962765216827,
1261
+ "learning_rate": 2.548518670511823e-06,
1262
+ "loss": 1.3664,
1263
+ "step": 170
1264
+ },
1265
+ {
1266
+ "epoch": 1.7872340425531914,
1267
+ "grad_norm": 0.09589093923568726,
1268
+ "learning_rate": 2.536241321302821e-06,
1269
+ "loss": 1.1508,
1270
+ "step": 171
1271
+ },
1272
+ {
1273
+ "epoch": 1.797872340425532,
1274
+ "grad_norm": 0.12533985078334808,
1275
+ "learning_rate": 2.5238297148279814e-06,
1276
+ "loss": 1.2892,
1277
+ "step": 172
1278
+ },
1279
+ {
1280
+ "epoch": 1.8085106382978724,
1281
+ "grad_norm": 0.11337278038263321,
1282
+ "learning_rate": 2.5112854591570804e-06,
1283
+ "loss": 1.2772,
1284
+ "step": 173
1285
+ },
1286
+ {
1287
+ "epoch": 1.8191489361702127,
1288
+ "grad_norm": 0.1345362514257431,
1289
+ "learning_rate": 2.4986101795461608e-06,
1290
+ "loss": 1.3583,
1291
+ "step": 174
1292
+ },
1293
+ {
1294
+ "epoch": 1.8297872340425532,
1295
+ "grad_norm": 0.121876560151577,
1296
+ "learning_rate": 2.485805518226959e-06,
1297
+ "loss": 1.2065,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 1.8404255319148937,
1302
+ "grad_norm": 0.10669907927513123,
1303
+ "learning_rate": 2.4728731341941343e-06,
1304
+ "loss": 1.2339,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 1.851063829787234,
1309
+ "grad_norm": 0.12710174918174744,
1310
+ "learning_rate": 2.4598147029903284e-06,
1311
+ "loss": 1.4597,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 1.8617021276595744,
1316
+ "grad_norm": 0.11735282093286514,
1317
+ "learning_rate": 2.4466319164890795e-06,
1318
+ "loss": 1.2273,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 1.872340425531915,
1323
+ "grad_norm": 0.12083889544010162,
1324
+ "learning_rate": 2.4333264826756165e-06,
1325
+ "loss": 1.3051,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 1.8829787234042552,
1330
+ "grad_norm": 0.10338792204856873,
1331
+ "learning_rate": 2.4199001254255746e-06,
1332
+ "loss": 1.3827,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 1.8936170212765957,
1337
+ "grad_norm": 0.10191334784030914,
1338
+ "learning_rate": 2.406354584281642e-06,
1339
+ "loss": 1.4067,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 1.9042553191489362,
1344
+ "grad_norm": 0.10776273161172867,
1345
+ "learning_rate": 2.3926916142281846e-06,
1346
+ "loss": 1.2344,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 1.9148936170212765,
1351
+ "grad_norm": 0.1253603845834732,
1352
+ "learning_rate": 2.378912985463867e-06,
1353
+ "loss": 1.2179,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 1.925531914893617,
1358
+ "grad_norm": 0.09942696243524551,
1359
+ "learning_rate": 2.365020483172301e-06,
1360
+ "loss": 1.0613,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 1.9361702127659575,
1365
+ "grad_norm": 0.10441701859235764,
1366
+ "learning_rate": 2.351015907290755e-06,
1367
+ "loss": 1.3886,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 1.9468085106382977,
1372
+ "grad_norm": 0.10571073740720749,
1373
+ "learning_rate": 2.3369010722769502e-06,
1374
+ "loss": 1.2023,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 1.9574468085106385,
1379
+ "grad_norm": 0.12477201223373413,
1380
+ "learning_rate": 2.3226778068739783e-06,
1381
+ "loss": 1.361,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 1.9680851063829787,
1386
+ "grad_norm": 0.12106247246265411,
1387
+ "learning_rate": 2.3083479538733636e-06,
1388
+ "loss": 1.4153,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 1.978723404255319,
1393
+ "grad_norm": 0.17261436581611633,
1394
+ "learning_rate": 2.2939133698763084e-06,
1395
+ "loss": 1.45,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 1.9893617021276597,
1400
+ "grad_norm": 0.12172568589448929,
1401
+ "learning_rate": 2.2793759250531504e-06,
1402
+ "loss": 1.1764,
1403
+ "step": 190
1404
+ },
1405
+ {
1406
+ "epoch": 2.0,
1407
+ "grad_norm": 0.11111535131931305,
1408
+ "learning_rate": 2.2647375029010575e-06,
1409
+ "loss": 1.1347,
1410
+ "step": 191
1411
+ },
1412
+ {
1413
+ "epoch": 2.0106382978723403,
1414
+ "grad_norm": 0.10596352070569992,
1415
+ "learning_rate": 2.25e-06,
1416
+ "loss": 1.1623,
1417
+ "step": 192
1418
+ },
1419
+ {
1420
+ "epoch": 2.0106382978723403,
1421
+ "eval_loss": 1.560809850692749,
1422
+ "eval_runtime": 4.8693,
1423
+ "eval_samples_per_second": 21.564,
1424
+ "eval_steps_per_second": 10.885,
1425
+ "step": 192
1426
+ },
1427
+ {
1428
+ "epoch": 2.0212765957446805,
1429
+ "grad_norm": 0.08630727976560593,
1430
+ "learning_rate": 2.235165325767026e-06,
1431
+ "loss": 1.1733,
1432
+ "step": 193
1433
+ },
1434
+ {
1435
+ "epoch": 2.0319148936170213,
1436
+ "grad_norm": 0.3629175126552582,
1437
+ "learning_rate": 2.2202354022088735e-06,
1438
+ "loss": 1.1114,
1439
+ "step": 194
1440
+ },
1441
+ {
1442
+ "epoch": 2.0106382978723403,
1443
+ "grad_norm": 0.12061420828104019,
1444
+ "learning_rate": 2.2052121636729527e-06,
1445
+ "loss": 1.1813,
1446
+ "step": 195
1447
+ },
1448
+ {
1449
+ "epoch": 2.021276595744681,
1450
+ "grad_norm": 0.12194402515888214,
1451
+ "learning_rate": 2.1900975565967284e-06,
1452
+ "loss": 1.4466,
1453
+ "step": 196
1454
+ },
1455
+ {
1456
+ "epoch": 2.0319148936170213,
1457
+ "grad_norm": 0.09581239521503448,
1458
+ "learning_rate": 2.1748935392555347e-06,
1459
+ "loss": 1.1863,
1460
+ "step": 197
1461
+ },
1462
+ {
1463
+ "epoch": 2.0425531914893615,
1464
+ "grad_norm": 0.12056192755699158,
1465
+ "learning_rate": 2.1596020815088587e-06,
1466
+ "loss": 1.5781,
1467
+ "step": 198
1468
+ },
1469
+ {
1470
+ "epoch": 2.0531914893617023,
1471
+ "grad_norm": 0.10989479720592499,
1472
+ "learning_rate": 2.1442251645451233e-06,
1473
+ "loss": 1.2638,
1474
+ "step": 199
1475
+ },
1476
+ {
1477
+ "epoch": 2.0638297872340425,
1478
+ "grad_norm": 0.1273481398820877,
1479
+ "learning_rate": 2.1287647806249964e-06,
1480
+ "loss": 1.1346,
1481
+ "step": 200
1482
+ },
1483
+ {
1484
+ "epoch": 2.074468085106383,
1485
+ "grad_norm": 0.11547158658504486,
1486
+ "learning_rate": 2.1132229328232755e-06,
1487
+ "loss": 1.124,
1488
+ "step": 201
1489
+ },
1490
+ {
1491
+ "epoch": 2.0851063829787235,
1492
+ "grad_norm": 0.12033279985189438,
1493
+ "learning_rate": 2.0976016347693624e-06,
1494
+ "loss": 1.2695,
1495
+ "step": 202
1496
+ },
1497
+ {
1498
+ "epoch": 2.095744680851064,
1499
+ "grad_norm": 0.11929858475923538,
1500
+ "learning_rate": 2.0819029103863746e-06,
1501
+ "loss": 1.1885,
1502
+ "step": 203
1503
+ },
1504
+ {
1505
+ "epoch": 2.106382978723404,
1506
+ "grad_norm": 0.10733456164598465,
1507
+ "learning_rate": 2.0661287936289213e-06,
1508
+ "loss": 1.3742,
1509
+ "step": 204
1510
+ },
1511
+ {
1512
+ "epoch": 2.117021276595745,
1513
+ "grad_norm": 0.12037491053342819,
1514
+ "learning_rate": 2.050281328219585e-06,
1515
+ "loss": 1.1911,
1516
+ "step": 205
1517
+ },
1518
+ {
1519
+ "epoch": 2.127659574468085,
1520
+ "grad_norm": 0.12621213495731354,
1521
+ "learning_rate": 2.0343625673841254e-06,
1522
+ "loss": 1.1241,
1523
+ "step": 206
1524
+ },
1525
+ {
1526
+ "epoch": 2.1382978723404253,
1527
+ "grad_norm": 0.15265725553035736,
1528
+ "learning_rate": 2.018374573585467e-06,
1529
+ "loss": 1.4419,
1530
+ "step": 207
1531
+ },
1532
+ {
1533
+ "epoch": 2.148936170212766,
1534
+ "grad_norm": 0.10528834164142609,
1535
+ "learning_rate": 2.0023194182564793e-06,
1536
+ "loss": 1.2211,
1537
+ "step": 208
1538
+ },
1539
+ {
1540
+ "epoch": 2.1595744680851063,
1541
+ "grad_norm": 0.11791864037513733,
1542
+ "learning_rate": 1.986199181531599e-06,
1543
+ "loss": 1.2159,
1544
+ "step": 209
1545
+ },
1546
+ {
1547
+ "epoch": 2.1702127659574466,
1548
+ "grad_norm": 0.1230137050151825,
1549
+ "learning_rate": 1.9700159519773233e-06,
1550
+ "loss": 1.2687,
1551
+ "step": 210
1552
+ },
1553
+ {
1554
+ "epoch": 2.1808510638297873,
1555
+ "grad_norm": 0.11243241280317307,
1556
+ "learning_rate": 1.9537718263216137e-06,
1557
+ "loss": 1.2008,
1558
+ "step": 211
1559
+ },
1560
+ {
1561
+ "epoch": 2.1914893617021276,
1562
+ "grad_norm": 0.13040384650230408,
1563
+ "learning_rate": 1.9374689091822377e-06,
1564
+ "loss": 1.2937,
1565
+ "step": 212
1566
+ },
1567
+ {
1568
+ "epoch": 2.202127659574468,
1569
+ "grad_norm": 0.096621572971344,
1570
+ "learning_rate": 1.9211093127940917e-06,
1571
+ "loss": 1.1315,
1572
+ "step": 213
1573
+ },
1574
+ {
1575
+ "epoch": 2.2127659574468086,
1576
+ "grad_norm": 0.10366329550743103,
1577
+ "learning_rate": 1.9046951567355363e-06,
1578
+ "loss": 1.1998,
1579
+ "step": 214
1580
+ },
1581
+ {
1582
+ "epoch": 2.223404255319149,
1583
+ "grad_norm": 0.13266436755657196,
1584
+ "learning_rate": 1.888228567653781e-06,
1585
+ "loss": 1.2169,
1586
+ "step": 215
1587
+ },
1588
+ {
1589
+ "epoch": 2.2340425531914896,
1590
+ "grad_norm": 0.12041480094194412,
1591
+ "learning_rate": 1.87171167898935e-06,
1592
+ "loss": 1.2679,
1593
+ "step": 216
1594
+ },
1595
+ {
1596
+ "epoch": 2.2340425531914896,
1597
+ "eval_loss": 1.557094931602478,
1598
+ "eval_runtime": 3.8276,
1599
+ "eval_samples_per_second": 27.432,
1600
+ "eval_steps_per_second": 13.847,
1601
+ "step": 216
1602
+ },
1603
+ {
1604
+ "epoch": 2.24468085106383,
1605
+ "grad_norm": 0.11926256865262985,
1606
+ "learning_rate": 1.8551466306996702e-06,
1607
+ "loss": 1.2496,
1608
+ "step": 217
1609
+ },
1610
+ {
1611
+ "epoch": 2.25531914893617,
1612
+ "grad_norm": 0.11768142879009247,
1613
+ "learning_rate": 1.838535568981816e-06,
1614
+ "loss": 1.2793,
1615
+ "step": 218
1616
+ },
1617
+ {
1618
+ "epoch": 2.2659574468085104,
1619
+ "grad_norm": 0.09850093722343445,
1620
+ "learning_rate": 1.821880645994443e-06,
1621
+ "loss": 1.1712,
1622
+ "step": 219
1623
+ },
1624
+ {
1625
+ "epoch": 2.276595744680851,
1626
+ "grad_norm": 0.11399635672569275,
1627
+ "learning_rate": 1.8051840195789509e-06,
1628
+ "loss": 1.3151,
1629
+ "step": 220
1630
+ },
1631
+ {
1632
+ "epoch": 2.2872340425531914,
1633
+ "grad_norm": 0.10654745250940323,
1634
+ "learning_rate": 1.788447852979909e-06,
1635
+ "loss": 1.1726,
1636
+ "step": 221
1637
+ },
1638
+ {
1639
+ "epoch": 2.297872340425532,
1640
+ "grad_norm": 0.12983720004558563,
1641
+ "learning_rate": 1.7716743145647837e-06,
1642
+ "loss": 1.2158,
1643
+ "step": 222
1644
+ },
1645
+ {
1646
+ "epoch": 2.3085106382978724,
1647
+ "grad_norm": 0.08331640809774399,
1648
+ "learning_rate": 1.754865577543e-06,
1649
+ "loss": 0.8472,
1650
+ "step": 223
1651
+ },
1652
+ {
1653
+ "epoch": 2.3191489361702127,
1654
+ "grad_norm": 0.11662207543849945,
1655
+ "learning_rate": 1.738023819684377e-06,
1656
+ "loss": 1.2938,
1657
+ "step": 224
1658
+ },
1659
+ {
1660
+ "epoch": 2.329787234042553,
1661
+ "grad_norm": 0.13265132904052734,
1662
+ "learning_rate": 1.7211512230369716e-06,
1663
+ "loss": 1.3288,
1664
+ "step": 225
1665
+ },
1666
+ {
1667
+ "epoch": 2.3404255319148937,
1668
+ "grad_norm": 0.10342156141996384,
1669
+ "learning_rate": 1.7042499736443702e-06,
1670
+ "loss": 1.2352,
1671
+ "step": 226
1672
+ },
1673
+ {
1674
+ "epoch": 2.351063829787234,
1675
+ "grad_norm": 0.10495639592409134,
1676
+ "learning_rate": 1.6873222612624575e-06,
1677
+ "loss": 1.1748,
1678
+ "step": 227
1679
+ },
1680
+ {
1681
+ "epoch": 2.3617021276595747,
1682
+ "grad_norm": 0.1564377248287201,
1683
+ "learning_rate": 1.6703702790757123e-06,
1684
+ "loss": 1.4071,
1685
+ "step": 228
1686
+ },
1687
+ {
1688
+ "epoch": 2.372340425531915,
1689
+ "grad_norm": 0.11000990867614746,
1690
+ "learning_rate": 1.6533962234130513e-06,
1691
+ "loss": 1.2102,
1692
+ "step": 229
1693
+ },
1694
+ {
1695
+ "epoch": 2.382978723404255,
1696
+ "grad_norm": 0.12565018236637115,
1697
+ "learning_rate": 1.6364022934632706e-06,
1698
+ "loss": 1.4047,
1699
+ "step": 230
1700
+ },
1701
+ {
1702
+ "epoch": 2.393617021276596,
1703
+ "grad_norm": 0.11519981920719147,
1704
+ "learning_rate": 1.6193906909901133e-06,
1705
+ "loss": 1.3905,
1706
+ "step": 231
1707
+ },
1708
+ {
1709
+ "epoch": 2.404255319148936,
1710
+ "grad_norm": 0.12704767286777496,
1711
+ "learning_rate": 1.6023636200470066e-06,
1712
+ "loss": 1.0632,
1713
+ "step": 232
1714
+ },
1715
+ {
1716
+ "epoch": 2.4148936170212765,
1717
+ "grad_norm": 0.11226076632738113,
1718
+ "learning_rate": 1.5853232866915004e-06,
1719
+ "loss": 1.2448,
1720
+ "step": 233
1721
+ },
1722
+ {
1723
+ "epoch": 2.425531914893617,
1724
+ "grad_norm": 0.11282170563936234,
1725
+ "learning_rate": 1.5682718986994457e-06,
1726
+ "loss": 1.5068,
1727
+ "step": 234
1728
+ },
1729
+ {
1730
+ "epoch": 2.4361702127659575,
1731
+ "grad_norm": 0.09763903170824051,
1732
+ "learning_rate": 1.5512116652789518e-06,
1733
+ "loss": 1.2398,
1734
+ "step": 235
1735
+ },
1736
+ {
1737
+ "epoch": 2.4468085106382977,
1738
+ "grad_norm": 0.11640322953462601,
1739
+ "learning_rate": 1.5341447967841585e-06,
1740
+ "loss": 1.3176,
1741
+ "step": 236
1742
+ },
1743
+ {
1744
+ "epoch": 2.4574468085106385,
1745
+ "grad_norm": 0.12292848527431488,
1746
+ "learning_rate": 1.5170735044288565e-06,
1747
+ "loss": 1.8823,
1748
+ "step": 237
1749
+ },
1750
+ {
1751
+ "epoch": 2.4680851063829787,
1752
+ "grad_norm": 0.12308197468519211,
1753
+ "learning_rate": 1.5e-06,
1754
+ "loss": 1.14,
1755
+ "step": 238
1756
+ },
1757
+ {
1758
+ "epoch": 2.478723404255319,
1759
+ "grad_norm": 0.11871509999036789,
1760
+ "learning_rate": 1.4829264955711436e-06,
1761
+ "loss": 1.2753,
1762
+ "step": 239
1763
+ },
1764
+ {
1765
+ "epoch": 2.4893617021276597,
1766
+ "grad_norm": 0.14034831523895264,
1767
+ "learning_rate": 1.4658552032158414e-06,
1768
+ "loss": 1.2845,
1769
+ "step": 240
1770
+ },
1771
+ {
1772
+ "epoch": 2.4893617021276597,
1773
+ "eval_loss": 1.5537203550338745,
1774
+ "eval_runtime": 5.1489,
1775
+ "eval_samples_per_second": 20.393,
1776
+ "eval_steps_per_second": 10.294,
1777
+ "step": 240
1778
+ },
1779
+ {
1780
+ "epoch": 2.5,
1781
+ "grad_norm": 0.12317660450935364,
1782
+ "learning_rate": 1.4487883347210483e-06,
1783
+ "loss": 1.2742,
1784
+ "step": 241
1785
+ },
1786
+ {
1787
+ "epoch": 2.5106382978723403,
1788
+ "grad_norm": 0.11180029809474945,
1789
+ "learning_rate": 1.431728101300555e-06,
1790
+ "loss": 1.3743,
1791
+ "step": 242
1792
+ },
1793
+ {
1794
+ "epoch": 2.521276595744681,
1795
+ "grad_norm": 0.12544095516204834,
1796
+ "learning_rate": 1.4146767133085e-06,
1797
+ "loss": 1.2935,
1798
+ "step": 243
1799
+ },
1800
+ {
1801
+ "epoch": 2.5319148936170213,
1802
+ "grad_norm": 0.12283220142126083,
1803
+ "learning_rate": 1.3976363799529937e-06,
1804
+ "loss": 1.2529,
1805
+ "step": 244
1806
+ },
1807
+ {
1808
+ "epoch": 2.5425531914893615,
1809
+ "grad_norm": 0.1375051885843277,
1810
+ "learning_rate": 1.3806093090098872e-06,
1811
+ "loss": 1.2907,
1812
+ "step": 245
1813
+ },
1814
+ {
1815
+ "epoch": 2.5531914893617023,
1816
+ "grad_norm": 0.10762558877468109,
1817
+ "learning_rate": 1.3635977065367295e-06,
1818
+ "loss": 1.1548,
1819
+ "step": 246
1820
+ },
1821
+ {
1822
+ "epoch": 2.5638297872340425,
1823
+ "grad_norm": 0.12075044959783554,
1824
+ "learning_rate": 1.3466037765869486e-06,
1825
+ "loss": 1.2208,
1826
+ "step": 247
1827
+ },
1828
+ {
1829
+ "epoch": 2.574468085106383,
1830
+ "grad_norm": 0.11484728753566742,
1831
+ "learning_rate": 1.3296297209242874e-06,
1832
+ "loss": 1.1182,
1833
+ "step": 248
1834
+ },
1835
+ {
1836
+ "epoch": 2.5851063829787235,
1837
+ "grad_norm": 0.11546777188777924,
1838
+ "learning_rate": 1.312677738737543e-06,
1839
+ "loss": 1.4478,
1840
+ "step": 249
1841
+ },
1842
+ {
1843
+ "epoch": 2.595744680851064,
1844
+ "grad_norm": 0.12128724902868271,
1845
+ "learning_rate": 1.2957500263556303e-06,
1846
+ "loss": 1.3132,
1847
+ "step": 250
1848
+ },
1849
+ {
1850
+ "epoch": 2.6063829787234045,
1851
+ "grad_norm": 0.09233469516038895,
1852
+ "learning_rate": 1.2788487769630284e-06,
1853
+ "loss": 1.0863,
1854
+ "step": 251
1855
+ },
1856
+ {
1857
+ "epoch": 2.617021276595745,
1858
+ "grad_norm": 0.12085112929344177,
1859
+ "learning_rate": 1.261976180315623e-06,
1860
+ "loss": 1.2855,
1861
+ "step": 252
1862
+ },
1863
+ {
1864
+ "epoch": 2.627659574468085,
1865
+ "grad_norm": 0.12655006349086761,
1866
+ "learning_rate": 1.2451344224570002e-06,
1867
+ "loss": 1.2691,
1868
+ "step": 253
1869
+ },
1870
+ {
1871
+ "epoch": 2.6382978723404253,
1872
+ "grad_norm": 0.12646865844726562,
1873
+ "learning_rate": 1.2283256854352162e-06,
1874
+ "loss": 1.2194,
1875
+ "step": 254
1876
+ },
1877
+ {
1878
+ "epoch": 2.648936170212766,
1879
+ "grad_norm": 0.1081186905503273,
1880
+ "learning_rate": 1.2115521470200911e-06,
1881
+ "loss": 1.2551,
1882
+ "step": 255
1883
+ },
1884
+ {
1885
+ "epoch": 2.6595744680851063,
1886
+ "grad_norm": 0.12278001755475998,
1887
+ "learning_rate": 1.1948159804210496e-06,
1888
+ "loss": 1.3049,
1889
+ "step": 256
1890
+ },
1891
+ {
1892
+ "epoch": 2.670212765957447,
1893
+ "grad_norm": 0.09346724301576614,
1894
+ "learning_rate": 1.1781193540055573e-06,
1895
+ "loss": 1.1507,
1896
+ "step": 257
1897
+ },
1898
+ {
1899
+ "epoch": 2.6808510638297873,
1900
+ "grad_norm": 0.10679617524147034,
1901
+ "learning_rate": 1.1614644310181842e-06,
1902
+ "loss": 1.2971,
1903
+ "step": 258
1904
+ },
1905
+ {
1906
+ "epoch": 2.6914893617021276,
1907
+ "grad_norm": 0.11394444108009338,
1908
+ "learning_rate": 1.14485336930033e-06,
1909
+ "loss": 1.2133,
1910
+ "step": 259
1911
+ },
1912
+ {
1913
+ "epoch": 2.702127659574468,
1914
+ "grad_norm": 0.1416221708059311,
1915
+ "learning_rate": 1.1282883210106503e-06,
1916
+ "loss": 1.2132,
1917
+ "step": 260
1918
+ },
1919
+ {
1920
+ "epoch": 2.7127659574468086,
1921
+ "grad_norm": 0.09133229404687881,
1922
+ "learning_rate": 1.1117714323462188e-06,
1923
+ "loss": 1.17,
1924
+ "step": 261
1925
+ },
1926
+ {
1927
+ "epoch": 2.723404255319149,
1928
+ "grad_norm": 0.10997346043586731,
1929
+ "learning_rate": 1.0953048432644634e-06,
1930
+ "loss": 1.1443,
1931
+ "step": 262
1932
+ },
1933
+ {
1934
+ "epoch": 2.7340425531914896,
1935
+ "grad_norm": 0.11233331263065338,
1936
+ "learning_rate": 1.0788906872059088e-06,
1937
+ "loss": 1.3383,
1938
+ "step": 263
1939
+ },
1940
+ {
1941
+ "epoch": 2.74468085106383,
1942
+ "grad_norm": 0.11798594146966934,
1943
+ "learning_rate": 1.0625310908177626e-06,
1944
+ "loss": 1.1226,
1945
+ "step": 264
1946
+ },
1947
+ {
1948
+ "epoch": 2.74468085106383,
1949
+ "eval_loss": 1.5516207218170166,
1950
+ "eval_runtime": 4.7557,
1951
+ "eval_samples_per_second": 22.079,
1952
+ "eval_steps_per_second": 11.145,
1953
+ "step": 264
1954
+ },
1955
+ {
1956
+ "epoch": 2.75531914893617,
1957
+ "grad_norm": 0.12637464702129364,
1958
+ "learning_rate": 1.0462281736783864e-06,
1959
+ "loss": 1.4182,
1960
+ "step": 265
1961
+ },
1962
+ {
1963
+ "epoch": 2.7659574468085104,
1964
+ "grad_norm": 0.11374552547931671,
1965
+ "learning_rate": 1.0299840480226768e-06,
1966
+ "loss": 1.2926,
1967
+ "step": 266
1968
+ },
1969
+ {
1970
+ "epoch": 2.776595744680851,
1971
+ "grad_norm": 0.13765357434749603,
1972
+ "learning_rate": 1.0138008184684011e-06,
1973
+ "loss": 1.3036,
1974
+ "step": 267
1975
+ },
1976
+ {
1977
+ "epoch": 2.7872340425531914,
1978
+ "grad_norm": 0.1168639063835144,
1979
+ "learning_rate": 9.976805817435208e-07,
1980
+ "loss": 1.2854,
1981
+ "step": 268
1982
+ },
1983
+ {
1984
+ "epoch": 2.797872340425532,
1985
+ "grad_norm": 0.11609431356191635,
1986
+ "learning_rate": 9.816254264145328e-07,
1987
+ "loss": 1.2832,
1988
+ "step": 269
1989
+ },
1990
+ {
1991
+ "epoch": 2.8085106382978724,
1992
+ "grad_norm": 0.11090860515832901,
1993
+ "learning_rate": 9.656374326158753e-07,
1994
+ "loss": 1.4098,
1995
+ "step": 270
1996
+ },
1997
+ {
1998
+ "epoch": 2.8191489361702127,
1999
+ "grad_norm": 0.12376827001571655,
2000
+ "learning_rate": 9.497186717804155e-07,
2001
+ "loss": 1.2335,
2002
+ "step": 271
2003
+ },
2004
+ {
2005
+ "epoch": 2.829787234042553,
2006
+ "grad_norm": 0.11905582994222641,
2007
+ "learning_rate": 9.338712063710786e-07,
2008
+ "loss": 1.1991,
2009
+ "step": 272
2010
+ },
2011
+ {
2012
+ "epoch": 2.8404255319148937,
2013
+ "grad_norm": 0.09383586794137955,
2014
+ "learning_rate": 9.180970896136258e-07,
2015
+ "loss": 1.1715,
2016
+ "step": 273
2017
+ },
2018
+ {
2019
+ "epoch": 2.851063829787234,
2020
+ "grad_norm": 0.14080052077770233,
2021
+ "learning_rate": 9.023983652306379e-07,
2022
+ "loss": 1.3227,
2023
+ "step": 274
2024
+ },
2025
+ {
2026
+ "epoch": 2.8617021276595747,
2027
+ "grad_norm": 0.10943106561899185,
2028
+ "learning_rate": 8.867770671767246e-07,
2029
+ "loss": 0.9774,
2030
+ "step": 275
2031
+ },
2032
+ {
2033
+ "epoch": 2.872340425531915,
2034
+ "grad_norm": 0.093683160841465,
2035
+ "learning_rate": 8.712352193750043e-07,
2036
+ "loss": 1.053,
2037
+ "step": 276
2038
+ },
2039
+ {
2040
+ "epoch": 2.882978723404255,
2041
+ "grad_norm": 0.1352389007806778,
2042
+ "learning_rate": 8.557748354548773e-07,
2043
+ "loss": 1.2713,
2044
+ "step": 277
2045
+ },
2046
+ {
2047
+ "epoch": 2.8936170212765955,
2048
+ "grad_norm": 0.09906943887472153,
2049
+ "learning_rate": 8.403979184911411e-07,
2050
+ "loss": 1.3128,
2051
+ "step": 278
2052
+ },
2053
+ {
2054
+ "epoch": 2.904255319148936,
2055
+ "grad_norm": 0.13467717170715332,
2056
+ "learning_rate": 8.251064607444658e-07,
2057
+ "loss": 1.4274,
2058
+ "step": 279
2059
+ },
2060
+ {
2061
+ "epoch": 2.9148936170212765,
2062
+ "grad_norm": 0.11490917205810547,
2063
+ "learning_rate": 8.099024434032718e-07,
2064
+ "loss": 1.307,
2065
+ "step": 280
2066
+ },
2067
+ {
2068
+ "epoch": 2.925531914893617,
2069
+ "grad_norm": 0.10982628166675568,
2070
+ "learning_rate": 7.947878363270472e-07,
2071
+ "loss": 1.0661,
2072
+ "step": 281
2073
+ },
2074
+ {
2075
+ "epoch": 2.9361702127659575,
2076
+ "grad_norm": 0.13426214456558228,
2077
+ "learning_rate": 7.797645977911268e-07,
2078
+ "loss": 1.3296,
2079
+ "step": 282
2080
+ },
2081
+ {
2082
+ "epoch": 2.9468085106382977,
2083
+ "grad_norm": 0.5615570545196533,
2084
+ "learning_rate": 7.648346742329746e-07,
2085
+ "loss": 5.321,
2086
+ "step": 283
2087
+ },
2088
+ {
2089
+ "epoch": 2.9574468085106385,
2090
+ "grad_norm": 0.12761859595775604,
2091
+ "learning_rate": 7.500000000000003e-07,
2092
+ "loss": 1.2247,
2093
+ "step": 284
2094
+ },
2095
+ {
2096
+ "epoch": 2.9680851063829787,
2097
+ "grad_norm": 0.12587665021419525,
2098
+ "learning_rate": 7.352624970989425e-07,
2099
+ "loss": 1.2634,
2100
+ "step": 285
2101
+ },
2102
+ {
2103
+ "epoch": 2.978723404255319,
2104
+ "grad_norm": 0.09242536127567291,
2105
+ "learning_rate": 7.2062407494685e-07,
2106
+ "loss": 1.2181,
2107
+ "step": 286
2108
+ },
2109
+ {
2110
+ "epoch": 2.9893617021276597,
2111
+ "grad_norm": 0.1055845320224762,
2112
+ "learning_rate": 7.06086630123692e-07,
2113
+ "loss": 1.3458,
2114
+ "step": 287
2115
+ },
2116
+ {
2117
+ "epoch": 3.0,
2118
+ "grad_norm": 0.10968521237373352,
2119
+ "learning_rate": 6.916520461266367e-07,
2120
+ "loss": 1.2575,
2121
+ "step": 288
2122
+ },
2123
+ {
2124
+ "epoch": 3.0,
2125
+ "eval_loss": 1.5497299432754517,
2126
+ "eval_runtime": 3.0359,
2127
+ "eval_samples_per_second": 34.586,
2128
+ "eval_steps_per_second": 17.458,
2129
+ "step": 288
2130
+ },
2131
+ {
2132
+ "epoch": 3.0106382978723403,
2133
+ "grad_norm": 0.12890629470348358,
2134
+ "learning_rate": 6.773221931260217e-07,
2135
+ "loss": 1.2357,
2136
+ "step": 289
2137
+ },
2138
+ {
2139
+ "epoch": 3.0212765957446805,
2140
+ "grad_norm": 0.11267005652189255,
2141
+ "learning_rate": 6.630989277230501e-07,
2142
+ "loss": 1.352,
2143
+ "step": 290
2144
+ },
2145
+ {
2146
+ "epoch": 3.0319148936170213,
2147
+ "grad_norm": 0.16483013331890106,
2148
+ "learning_rate": 6.489840927092458e-07,
2149
+ "loss": 1.121,
2150
+ "step": 291
2151
+ },
2152
+ {
2153
+ "epoch": 3.0106382978723403,
2154
+ "grad_norm": 0.11686303466558456,
2155
+ "learning_rate": 6.349795168276994e-07,
2156
+ "loss": 1.3244,
2157
+ "step": 292
2158
+ },
2159
+ {
2160
+ "epoch": 3.021276595744681,
2161
+ "grad_norm": 0.11969567835330963,
2162
+ "learning_rate": 6.210870145361331e-07,
2163
+ "loss": 1.4993,
2164
+ "step": 293
2165
+ },
2166
+ {
2167
+ "epoch": 3.0319148936170213,
2168
+ "grad_norm": 0.09593074023723602,
2169
+ "learning_rate": 6.073083857718157e-07,
2170
+ "loss": 1.1972,
2171
+ "step": 294
2172
+ },
2173
+ {
2174
+ "epoch": 3.0425531914893615,
2175
+ "grad_norm": 0.1114688366651535,
2176
+ "learning_rate": 5.936454157183583e-07,
2177
+ "loss": 1.3017,
2178
+ "step": 295
2179
+ },
2180
+ {
2181
+ "epoch": 3.0531914893617023,
2182
+ "grad_norm": 0.1574050486087799,
2183
+ "learning_rate": 5.800998745744253e-07,
2184
+ "loss": 1.131,
2185
+ "step": 296
2186
+ },
2187
+ {
2188
+ "epoch": 3.0638297872340425,
2189
+ "grad_norm": 0.09848689287900925,
2190
+ "learning_rate": 5.666735173243836e-07,
2191
+ "loss": 1.2648,
2192
+ "step": 297
2193
+ },
2194
+ {
2195
+ "epoch": 3.074468085106383,
2196
+ "grad_norm": 0.12783421576023102,
2197
+ "learning_rate": 5.533680835109212e-07,
2198
+ "loss": 1.3503,
2199
+ "step": 298
2200
+ },
2201
+ {
2202
+ "epoch": 3.0851063829787235,
2203
+ "grad_norm": 0.16221453249454498,
2204
+ "learning_rate": 5.401852970096719e-07,
2205
+ "loss": 1.3837,
2206
+ "step": 299
2207
+ },
2208
+ {
2209
+ "epoch": 3.095744680851064,
2210
+ "grad_norm": 0.13070747256278992,
2211
+ "learning_rate": 5.27126865805866e-07,
2212
+ "loss": 1.844,
2213
+ "step": 300
2214
+ },
2215
+ {
2216
+ "epoch": 3.106382978723404,
2217
+ "grad_norm": 0.10077214986085892,
2218
+ "learning_rate": 5.141944817730411e-07,
2219
+ "loss": 1.1528,
2220
+ "step": 301
2221
+ },
2222
+ {
2223
+ "epoch": 3.117021276595745,
2224
+ "grad_norm": 0.10629620403051376,
2225
+ "learning_rate": 5.013898204538392e-07,
2226
+ "loss": 1.3626,
2227
+ "step": 302
2228
+ },
2229
+ {
2230
+ "epoch": 3.127659574468085,
2231
+ "grad_norm": 0.11176397651433945,
2232
+ "learning_rate": 4.887145408429194e-07,
2233
+ "loss": 1.401,
2234
+ "step": 303
2235
+ },
2236
+ {
2237
+ "epoch": 3.1382978723404253,
2238
+ "grad_norm": 0.11966844648122787,
2239
+ "learning_rate": 4.7617028517201914e-07,
2240
+ "loss": 1.4937,
2241
+ "step": 304
2242
+ },
2243
+ {
2244
+ "epoch": 3.148936170212766,
2245
+ "grad_norm": 0.09916877746582031,
2246
+ "learning_rate": 4.6375867869717915e-07,
2247
+ "loss": 1.1892,
2248
+ "step": 305
2249
+ },
2250
+ {
2251
+ "epoch": 3.1595744680851063,
2252
+ "grad_norm": 0.14531613886356354,
2253
+ "learning_rate": 4.514813294881772e-07,
2254
+ "loss": 1.4487,
2255
+ "step": 306
2256
+ },
2257
+ {
2258
+ "epoch": 3.1702127659574466,
2259
+ "grad_norm": 0.11752136796712875,
2260
+ "learning_rate": 4.3933982822017883e-07,
2261
+ "loss": 1.1079,
2262
+ "step": 307
2263
+ },
2264
+ {
2265
+ "epoch": 3.1808510638297873,
2266
+ "grad_norm": 0.11633948236703873,
2267
+ "learning_rate": 4.273357479676508e-07,
2268
+ "loss": 1.2957,
2269
+ "step": 308
2270
+ },
2271
+ {
2272
+ "epoch": 3.1914893617021276,
2273
+ "grad_norm": 0.10776685178279877,
2274
+ "learning_rate": 4.154706440005491e-07,
2275
+ "loss": 1.2521,
2276
+ "step": 309
2277
+ },
2278
+ {
2279
+ "epoch": 3.202127659574468,
2280
+ "grad_norm": 0.10373863577842712,
2281
+ "learning_rate": 4.037460535828138e-07,
2282
+ "loss": 1.1982,
2283
+ "step": 310
2284
+ },
2285
+ {
2286
+ "epoch": 3.2127659574468086,
2287
+ "grad_norm": 0.10363980382680893,
2288
+ "learning_rate": 3.921634957732019e-07,
2289
+ "loss": 1.2003,
2290
+ "step": 311
2291
+ },
2292
+ {
2293
+ "epoch": 3.223404255319149,
2294
+ "grad_norm": 0.1123185008764267,
2295
+ "learning_rate": 3.8072447122847184e-07,
2296
+ "loss": 1.2465,
2297
+ "step": 312
2298
+ },
2299
+ {
2300
+ "epoch": 3.223404255319149,
2301
+ "eval_loss": 1.548577070236206,
2302
+ "eval_runtime": 3.0417,
2303
+ "eval_samples_per_second": 34.52,
2304
+ "eval_steps_per_second": 17.425,
2305
+ "step": 312
2306
+ },
2307
+ {
2308
+ "epoch": 3.2340425531914896,
2309
+ "grad_norm": 0.0931960716843605,
2310
+ "learning_rate": 3.694304620089587e-07,
2311
+ "loss": 1.1363,
2312
+ "step": 313
2313
+ },
2314
+ {
2315
+ "epoch": 3.24468085106383,
2316
+ "grad_norm": 0.09377090632915497,
2317
+ "learning_rate": 3.5828293138655306e-07,
2318
+ "loss": 1.2143,
2319
+ "step": 314
2320
+ },
2321
+ {
2322
+ "epoch": 3.25531914893617,
2323
+ "grad_norm": 0.13445159792900085,
2324
+ "learning_rate": 3.4728332365511953e-07,
2325
+ "loss": 1.3706,
2326
+ "step": 315
2327
+ },
2328
+ {
2329
+ "epoch": 3.2659574468085104,
2330
+ "grad_norm": 0.11298293620347977,
2331
+ "learning_rate": 3.3643306394337013e-07,
2332
+ "loss": 1.2664,
2333
+ "step": 316
2334
+ },
2335
+ {
2336
+ "epoch": 3.276595744680851,
2337
+ "grad_norm": 0.10045924782752991,
2338
+ "learning_rate": 3.2573355803022206e-07,
2339
+ "loss": 1.2612,
2340
+ "step": 317
2341
+ },
2342
+ {
2343
+ "epoch": 3.2872340425531914,
2344
+ "grad_norm": 0.13584546744823456,
2345
+ "learning_rate": 3.151861921626624e-07,
2346
+ "loss": 1.2384,
2347
+ "step": 318
2348
+ },
2349
+ {
2350
+ "epoch": 3.297872340425532,
2351
+ "grad_norm": 0.11470676213502884,
2352
+ "learning_rate": 3.0479233287614325e-07,
2353
+ "loss": 1.2728,
2354
+ "step": 319
2355
+ },
2356
+ {
2357
+ "epoch": 3.3085106382978724,
2358
+ "grad_norm": 0.12791061401367188,
2359
+ "learning_rate": 2.9455332681753264e-07,
2360
+ "loss": 1.2408,
2361
+ "step": 320
2362
+ },
2363
+ {
2364
+ "epoch": 3.3191489361702127,
2365
+ "grad_norm": 0.1361236423254013,
2366
+ "learning_rate": 2.844705005706394e-07,
2367
+ "loss": 1.3287,
2368
+ "step": 321
2369
+ },
2370
+ {
2371
+ "epoch": 3.329787234042553,
2372
+ "grad_norm": 0.11060075461864471,
2373
+ "learning_rate": 2.7454516048433704e-07,
2374
+ "loss": 1.4066,
2375
+ "step": 322
2376
+ },
2377
+ {
2378
+ "epoch": 3.3404255319148937,
2379
+ "grad_norm": 0.12533032894134521,
2380
+ "learning_rate": 2.64778592503314e-07,
2381
+ "loss": 1.3182,
2382
+ "step": 323
2383
+ },
2384
+ {
2385
+ "epoch": 3.351063829787234,
2386
+ "grad_norm": 0.10592247545719147,
2387
+ "learning_rate": 2.5517206200146245e-07,
2388
+ "loss": 1.137,
2389
+ "step": 324
2390
+ },
2391
+ {
2392
+ "epoch": 3.3617021276595747,
2393
+ "grad_norm": 0.10802777856588364,
2394
+ "learning_rate": 2.457268136179341e-07,
2395
+ "loss": 1.1359,
2396
+ "step": 325
2397
+ },
2398
+ {
2399
+ "epoch": 3.372340425531915,
2400
+ "grad_norm": 0.12638698518276215,
2401
+ "learning_rate": 2.364440710958828e-07,
2402
+ "loss": 1.1918,
2403
+ "step": 326
2404
+ },
2405
+ {
2406
+ "epoch": 3.382978723404255,
2407
+ "grad_norm": 1.0334383249282837,
2408
+ "learning_rate": 2.2732503712391524e-07,
2409
+ "loss": 6.2297,
2410
+ "step": 327
2411
+ },
2412
+ {
2413
+ "epoch": 3.393617021276596,
2414
+ "grad_norm": 0.13448600471019745,
2415
+ "learning_rate": 2.1837089318026714e-07,
2416
+ "loss": 1.3724,
2417
+ "step": 328
2418
+ },
2419
+ {
2420
+ "epoch": 3.404255319148936,
2421
+ "grad_norm": 0.12653769552707672,
2422
+ "learning_rate": 2.0958279937972978e-07,
2423
+ "loss": 1.2918,
2424
+ "step": 329
2425
+ },
2426
+ {
2427
+ "epoch": 3.4148936170212765,
2428
+ "grad_norm": 0.0998699963092804,
2429
+ "learning_rate": 2.0096189432334195e-07,
2430
+ "loss": 1.2476,
2431
+ "step": 330
2432
+ },
2433
+ {
2434
+ "epoch": 3.425531914893617,
2435
+ "grad_norm": 0.12127155810594559,
2436
+ "learning_rate": 1.9250929495087294e-07,
2437
+ "loss": 1.4288,
2438
+ "step": 331
2439
+ },
2440
+ {
2441
+ "epoch": 3.4361702127659575,
2442
+ "grad_norm": 0.1191040650010109,
2443
+ "learning_rate": 1.842260963961086e-07,
2444
+ "loss": 1.2145,
2445
+ "step": 332
2446
+ },
2447
+ {
2448
+ "epoch": 3.4468085106382977,
2449
+ "grad_norm": 0.13884760439395905,
2450
+ "learning_rate": 1.761133718449634e-07,
2451
+ "loss": 1.2676,
2452
+ "step": 333
2453
+ },
2454
+ {
2455
+ "epoch": 3.4574468085106385,
2456
+ "grad_norm": 0.13023029267787933,
2457
+ "learning_rate": 1.6817217239643717e-07,
2458
+ "loss": 1.326,
2459
+ "step": 334
2460
+ },
2461
+ {
2462
+ "epoch": 3.4680851063829787,
2463
+ "grad_norm": 0.1026253029704094,
2464
+ "learning_rate": 1.6040352692643356e-07,
2465
+ "loss": 1.2225,
2466
+ "step": 335
2467
+ },
2468
+ {
2469
+ "epoch": 3.478723404255319,
2470
+ "grad_norm": 0.11566822230815887,
2471
+ "learning_rate": 1.5280844195445598e-07,
2472
+ "loss": 1.1699,
2473
+ "step": 336
2474
+ },
2475
+ {
2476
+ "epoch": 3.478723404255319,
2477
+ "eval_loss": 1.5482865571975708,
2478
+ "eval_runtime": 8.2306,
2479
+ "eval_samples_per_second": 12.757,
2480
+ "eval_steps_per_second": 6.439,
2481
+ "step": 336
2482
+ },
2483
+ {
2484
+ "epoch": 3.4893617021276597,
2485
+ "grad_norm": 0.11099603772163391,
2486
+ "learning_rate": 1.4538790151320092e-07,
2487
+ "loss": 1.1752,
2488
+ "step": 337
2489
+ },
2490
+ {
2491
+ "epoch": 3.5,
2492
+ "grad_norm": 0.10131604224443436,
2493
+ "learning_rate": 1.3814286702106644e-07,
2494
+ "loss": 1.2082,
2495
+ "step": 338
2496
+ },
2497
+ {
2498
+ "epoch": 3.5106382978723403,
2499
+ "grad_norm": 0.1052994355559349,
2500
+ "learning_rate": 1.3107427715758796e-07,
2501
+ "loss": 1.1038,
2502
+ "step": 339
2503
+ },
2504
+ {
2505
+ "epoch": 3.521276595744681,
2506
+ "grad_norm": 0.11623264849185944,
2507
+ "learning_rate": 1.2418304774182077e-07,
2508
+ "loss": 1.1679,
2509
+ "step": 340
2510
+ },
2511
+ {
2512
+ "epoch": 3.5319148936170213,
2513
+ "grad_norm": 0.10955728590488434,
2514
+ "learning_rate": 1.1747007161368584e-07,
2515
+ "loss": 1.198,
2516
+ "step": 341
2517
+ },
2518
+ {
2519
+ "epoch": 3.5425531914893615,
2520
+ "grad_norm": 0.13709692656993866,
2521
+ "learning_rate": 1.1093621851829211e-07,
2522
+ "loss": 1.3202,
2523
+ "step": 342
2524
+ },
2525
+ {
2526
+ "epoch": 3.5531914893617023,
2527
+ "grad_norm": 0.1269705444574356,
2528
+ "learning_rate": 1.0458233499325026e-07,
2529
+ "loss": 1.1253,
2530
+ "step": 343
2531
+ },
2532
+ {
2533
+ "epoch": 3.5638297872340425,
2534
+ "grad_norm": 0.12783360481262207,
2535
+ "learning_rate": 9.840924425899344e-08,
2536
+ "loss": 1.3489,
2537
+ "step": 344
2538
+ },
2539
+ {
2540
+ "epoch": 3.574468085106383,
2541
+ "grad_norm": 0.1359439641237259,
2542
+ "learning_rate": 9.241774611211979e-08,
2543
+ "loss": 1.3248,
2544
+ "step": 345
2545
+ },
2546
+ {
2547
+ "epoch": 3.5851063829787235,
2548
+ "grad_norm": 0.13286209106445312,
2549
+ "learning_rate": 8.660861682176941e-08,
2550
+ "loss": 1.0637,
2551
+ "step": 346
2552
+ },
2553
+ {
2554
+ "epoch": 3.595744680851064,
2555
+ "grad_norm": 0.13463550806045532,
2556
+ "learning_rate": 8.098260902904942e-08,
2557
+ "loss": 1.4834,
2558
+ "step": 347
2559
+ },
2560
+ {
2561
+ "epoch": 3.6063829787234045,
2562
+ "grad_norm": 0.11620105803012848,
2563
+ "learning_rate": 7.554045164952123e-08,
2564
+ "loss": 1.1721,
2565
+ "step": 348
2566
+ },
2567
+ {
2568
+ "epoch": 3.617021276595745,
2569
+ "grad_norm": 0.11728944629430771,
2570
+ "learning_rate": 7.028284977875876e-08,
2571
+ "loss": 1.0798,
2572
+ "step": 349
2573
+ },
2574
+ {
2575
+ "epoch": 3.627659574468085,
2576
+ "grad_norm": 0.10178694874048233,
2577
+ "learning_rate": 6.521048460099788e-08,
2578
+ "loss": 1.1834,
2579
+ "step": 350
2580
+ },
2581
+ {
2582
+ "epoch": 3.6382978723404253,
2583
+ "grad_norm": 0.12597782909870148,
2584
+ "learning_rate": 6.032401330087894e-08,
2585
+ "loss": 1.1844,
2586
+ "step": 351
2587
+ },
2588
+ {
2589
+ "epoch": 3.648936170212766,
2590
+ "grad_norm": 0.12270310521125793,
2591
+ "learning_rate": 5.56240689783013e-08,
2592
+ "loss": 1.2313,
2593
+ "step": 352
2594
+ },
2595
+ {
2596
+ "epoch": 3.6595744680851063,
2597
+ "grad_norm": 0.10874566435813904,
2598
+ "learning_rate": 5.11112605663977e-08,
2599
+ "loss": 1.018,
2600
+ "step": 353
2601
+ },
2602
+ {
2603
+ "epoch": 3.670212765957447,
2604
+ "grad_norm": 0.11302437633275986,
2605
+ "learning_rate": 4.6786172752640576e-08,
2606
+ "loss": 1.304,
2607
+ "step": 354
2608
+ },
2609
+ {
2610
+ "epoch": 3.6808510638297873,
2611
+ "grad_norm": 0.15053825080394745,
2612
+ "learning_rate": 4.264936590308782e-08,
2613
+ "loss": 1.3825,
2614
+ "step": 355
2615
+ },
2616
+ {
2617
+ "epoch": 3.6914893617021276,
2618
+ "grad_norm": 0.12475212663412094,
2619
+ "learning_rate": 3.870137598978152e-08,
2620
+ "loss": 1.1793,
2621
+ "step": 356
2622
+ },
2623
+ {
2624
+ "epoch": 3.702127659574468,
2625
+ "grad_norm": 0.0818130299448967,
2626
+ "learning_rate": 3.494271452130582e-08,
2627
+ "loss": 1.0666,
2628
+ "step": 357
2629
+ },
2630
+ {
2631
+ "epoch": 3.7127659574468086,
2632
+ "grad_norm": 0.0952049046754837,
2633
+ "learning_rate": 3.1373868476515634e-08,
2634
+ "loss": 1.1753,
2635
+ "step": 358
2636
+ },
2637
+ {
2638
+ "epoch": 3.723404255319149,
2639
+ "grad_norm": 0.11639692634344101,
2640
+ "learning_rate": 2.799530024144259e-08,
2641
+ "loss": 1.2072,
2642
+ "step": 359
2643
+ },
2644
+ {
2645
+ "epoch": 3.7340425531914896,
2646
+ "grad_norm": 0.09965858608484268,
2647
+ "learning_rate": 2.4807447549386964e-08,
2648
+ "loss": 1.2021,
2649
+ "step": 360
2650
+ },
2651
+ {
2652
+ "epoch": 3.7340425531914896,
2653
+ "eval_loss": 1.5481599569320679,
2654
+ "eval_runtime": 6.0038,
2655
+ "eval_samples_per_second": 17.489,
2656
+ "eval_steps_per_second": 8.828,
2657
+ "step": 360
2658
+ },
2659
+ {
2660
+ "epoch": 3.74468085106383,
2661
+ "grad_norm": 0.10187926143407822,
2662
+ "learning_rate": 2.1810723424204705e-08,
2663
+ "loss": 1.2199,
2664
+ "step": 361
2665
+ },
2666
+ {
2667
+ "epoch": 3.75531914893617,
2668
+ "grad_norm": 0.1356193870306015,
2669
+ "learning_rate": 1.9005516126795574e-08,
2670
+ "loss": 1.3415,
2671
+ "step": 362
2672
+ },
2673
+ {
2674
+ "epoch": 3.7659574468085104,
2675
+ "grad_norm": 0.10562197864055634,
2676
+ "learning_rate": 1.6392189104798727e-08,
2677
+ "loss": 1.2226,
2678
+ "step": 363
2679
+ },
2680
+ {
2681
+ "epoch": 3.776595744680851,
2682
+ "grad_norm": 0.12549865245819092,
2683
+ "learning_rate": 1.3971080945503866e-08,
2684
+ "loss": 1.2114,
2685
+ "step": 364
2686
+ },
2687
+ {
2688
+ "epoch": 3.7872340425531914,
2689
+ "grad_norm": 0.1090317815542221,
2690
+ "learning_rate": 1.174250533198401e-08,
2691
+ "loss": 1.1658,
2692
+ "step": 365
2693
+ },
2694
+ {
2695
+ "epoch": 3.797872340425532,
2696
+ "grad_norm": 0.11821944266557693,
2697
+ "learning_rate": 9.706751002453329e-09,
2698
+ "loss": 1.1497,
2699
+ "step": 366
2700
+ },
2701
+ {
2702
+ "epoch": 3.8085106382978724,
2703
+ "grad_norm": 0.11243613809347153,
2704
+ "learning_rate": 7.86408171285774e-09,
2705
+ "loss": 1.0885,
2706
+ "step": 367
2707
+ },
2708
+ {
2709
+ "epoch": 3.8191489361702127,
2710
+ "grad_norm": 0.12863968312740326,
2711
+ "learning_rate": 6.214736202703075e-09,
2712
+ "loss": 1.1333,
2713
+ "step": 368
2714
+ },
2715
+ {
2716
+ "epoch": 3.829787234042553,
2717
+ "grad_norm": 0.10371046513319016,
2718
+ "learning_rate": 4.758928164122656e-09,
2719
+ "loss": 1.3754,
2720
+ "step": 369
2721
+ },
2722
+ {
2723
+ "epoch": 3.8404255319148937,
2724
+ "grad_norm": 0.11500074714422226,
2725
+ "learning_rate": 3.4968462141911073e-09,
2726
+ "loss": 1.3089,
2727
+ "step": 370
2728
+ },
2729
+ {
2730
+ "epoch": 3.851063829787234,
2731
+ "grad_norm": 0.10779456794261932,
2732
+ "learning_rate": 2.4286538704875737e-09,
2733
+ "loss": 1.2216,
2734
+ "step": 371
2735
+ },
2736
+ {
2737
+ "epoch": 3.8617021276595747,
2738
+ "grad_norm": 0.11587704718112946,
2739
+ "learning_rate": 1.5544895299086648e-09,
2740
+ "loss": 1.201,
2741
+ "step": 372
2742
+ },
2743
+ {
2744
+ "epoch": 3.872340425531915,
2745
+ "grad_norm": 0.11766841262578964,
2746
+ "learning_rate": 8.744664507389644e-10,
2747
+ "loss": 1.2929,
2748
+ "step": 373
2749
+ },
2750
+ {
2751
+ "epoch": 3.882978723404255,
2752
+ "grad_norm": 0.1037261113524437,
2753
+ "learning_rate": 3.8867273797627003e-10,
2754
+ "loss": 1.0566,
2755
+ "step": 374
2756
+ },
2757
+ {
2758
+ "epoch": 3.8936170212765955,
2759
+ "grad_norm": 0.1192815825343132,
2760
+ "learning_rate": 9.717133191672334e-11,
2761
+ "loss": 1.46,
2762
+ "step": 375
2763
+ },
2764
+ {
2765
+ "epoch": 3.904255319148936,
2766
+ "grad_norm": 0.10904623568058014,
2767
+ "learning_rate": 0.0,
2768
+ "loss": 1.1985,
2769
+ "step": 376
2770
+ }
2771
+ ],
2772
+ "logging_steps": 1,
2773
+ "max_steps": 376,
2774
+ "num_input_tokens_seen": 0,
2775
+ "num_train_epochs": 4,
2776
+ "save_steps": 94,
2777
+ "stateful_callbacks": {
2778
+ "TrainerControl": {
2779
+ "args": {
2780
+ "should_epoch_stop": false,
2781
+ "should_evaluate": false,
2782
+ "should_log": false,
2783
+ "should_save": true,
2784
+ "should_training_stop": true
2785
+ },
2786
+ "attributes": {}
2787
+ }
2788
+ },
2789
+ "total_flos": 1.2609418835263488e+16,
2790
+ "train_batch_size": 2,
2791
+ "trial_name": null,
2792
+ "trial_params": null
2793
+ }
phi-sft-out/checkpoint-376/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3385717d244ba6cd34f9a94de02b9440c435857ff1e640e8a1c7255c180c1b8
3
+ size 6008
phi-sft-out/checkpoint-376/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
phi-sft-out/checkpoint-94/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/phi-1_5
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.2.dev0
phi-sft-out/checkpoint-94/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-1_5",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "fc1",
25
+ "v_proj",
26
+ "dense",
27
+ "fc2",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
phi-sft-out/checkpoint-94/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998c27a23a6e4a4353f50ca70b9e421e6839ab7c37219765c9ea1bde19655020
3
+ size 226530600
phi-sft-out/checkpoint-94/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }