Hugging Face's logo

FatCat87
/
taopanda-3_5cbd8b3f-9553-4538-beb8-e2b7bc77d242

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
custom_code
8-bit precision
bitsandbytes
Model card Files Community
FatCat87 commited on
Commit
bc1a1c2
·
verified ·
1 Parent(s): e45d937

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. checkpoint-21/README.md +202 -0
  2. checkpoint-21/adapter_config.json +34 -0
  3. checkpoint-21/adapter_model.safetensors +3 -0
  4. checkpoint-21/optimizer.pt +3 -0
  5. checkpoint-21/rng_state_0.pth +3 -0
  6. checkpoint-21/rng_state_1.pth +3 -0
  7. checkpoint-21/rng_state_2.pth +3 -0
  8. checkpoint-21/rng_state_3.pth +3 -0
  9. checkpoint-21/scheduler.pt +3 -0
  10. checkpoint-21/special_tokens_map.json +35 -0
  11. checkpoint-21/tokenizer.json +0 -0
  12. checkpoint-21/tokenizer.model +3 -0
  13. checkpoint-21/tokenizer_config.json +47 -0
  14. checkpoint-21/trainer_state.json +212 -0
  15. checkpoint-21/training_args.bin +3 -0
  16. checkpoint-42/README.md +202 -0
  17. checkpoint-42/adapter_config.json +34 -0
  18. checkpoint-42/adapter_model.safetensors +3 -0
  19. checkpoint-42/optimizer.pt +3 -0
  20. checkpoint-42/rng_state_0.pth +3 -0
  21. checkpoint-42/rng_state_1.pth +3 -0
  22. checkpoint-42/rng_state_2.pth +3 -0
  23. checkpoint-42/rng_state_3.pth +3 -0
  24. checkpoint-42/scheduler.pt +3 -0
  25. checkpoint-42/special_tokens_map.json +35 -0
  26. checkpoint-42/tokenizer.json +0 -0
  27. checkpoint-42/tokenizer.model +3 -0
  28. checkpoint-42/tokenizer_config.json +47 -0
  29. checkpoint-42/trainer_state.json +391 -0
  30. checkpoint-42/training_args.bin +3 -0
  31. merged/config.json +35 -0
  32. merged/generation_config.json +7 -0
  33. merged/pytorch_model-00001-of-00003.bin +3 -0
  34. merged/pytorch_model-00002-of-00003.bin +3 -0
  35. merged/pytorch_model-00003-of-00003.bin +3 -0
  36. merged/pytorch_model.bin.index.json +298 -0
  37. merged/special_tokens_map.json +35 -0
  38. merged/tokenizer.json +0 -0
  39. merged/tokenizer.model +3 -0
  40. merged/tokenizer_config.json +47 -0
checkpoint-21/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/Yarn-Mistral-7b-64k
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 0.11.1
checkpoint-21/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Yarn-Mistral-7b-64k",
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": 16,
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": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-21/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375909d254f0b8a268643e1ac1cc35c723225435fd028214721830e52cb1c346
3
+ size 335604696
checkpoint-21/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bcd6e55b599f91c6ae805238a430241a113db300ab3fc03740ed20b2775a253
3
+ size 168624724
checkpoint-21/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2684bc15ac0b3eadebd60c1a740cc8abb940a581e1c8c7e15b25067d802ec7e
3
+ size 14960
checkpoint-21/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6073382ef14beec365971bd56563156f8229e270e50b2e1c22a67a0fd771c4a
3
+ size 14960
checkpoint-21/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573e6fcf7b7cf83fdd9ada858d3852156f62fcf32aa7eac75f225c9288908f7f
3
+ size 14960
checkpoint-21/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4456f86560bfa75625fc170e84c81c895634ad6f3f0d4df7124e3869c178c8
3
+ size 14960
checkpoint-21/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8057116cebca6e914194f0aea4f38ed11bfeac37985745f93da3fcdb776aa9d0
3
+ size 1064
checkpoint-21/special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
checkpoint-21/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-21/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-21/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [
32
+ "<unk>",
33
+ "<s>",
34
+ "</s>"
35
+ ],
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "</s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
47
+ }
checkpoint-21/trainer_state.json ADDED
@@ -0,0 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9655172413793104,
5
+ "eval_steps": 6,
6
+ "global_step": 21,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04597701149425287,
13
+ "grad_norm": 2.537923574447632,
14
+ "learning_rate": 0.0001,
15
+ "loss": 1.4151,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.04597701149425287,
20
+ "eval_loss": 0.6549283862113953,
21
+ "eval_runtime": 59.8262,
22
+ "eval_samples_per_second": 3.31,
23
+ "eval_steps_per_second": 0.418,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.09195402298850575,
28
+ "grad_norm": 2.5883562564849854,
29
+ "learning_rate": 0.0002,
30
+ "loss": 1.3772,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.13793103448275862,
35
+ "grad_norm": 2.2641923427581787,
36
+ "learning_rate": 0.0001996917333733128,
37
+ "loss": 1.3153,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.1839080459770115,
42
+ "grad_norm": 5.304536819458008,
43
+ "learning_rate": 0.00019876883405951377,
44
+ "loss": 1.1035,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.22988505747126436,
49
+ "grad_norm": 1.074016809463501,
50
+ "learning_rate": 0.00019723699203976766,
51
+ "loss": 0.9059,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.27586206896551724,
56
+ "grad_norm": 0.8219733834266663,
57
+ "learning_rate": 0.00019510565162951537,
58
+ "loss": 0.8678,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.27586206896551724,
63
+ "eval_loss": 0.6351205706596375,
64
+ "eval_runtime": 59.9835,
65
+ "eval_samples_per_second": 3.301,
66
+ "eval_steps_per_second": 0.417,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.3218390804597701,
71
+ "grad_norm": 1.478880524635315,
72
+ "learning_rate": 0.0001923879532511287,
73
+ "loss": 0.8782,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.367816091954023,
78
+ "grad_norm": 0.7757106423377991,
79
+ "learning_rate": 0.0001891006524188368,
80
+ "loss": 0.7993,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.41379310344827586,
85
+ "grad_norm": 0.5512004494667053,
86
+ "learning_rate": 0.00018526401643540922,
87
+ "loss": 0.7126,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.45977011494252873,
92
+ "grad_norm": 1.5733872652053833,
93
+ "learning_rate": 0.00018090169943749476,
94
+ "loss": 0.685,
95
+ "step": 10
96
+ },
97
+ {
98
+ "epoch": 0.5057471264367817,
99
+ "grad_norm": 0.34443506598472595,
100
+ "learning_rate": 0.0001760405965600031,
101
+ "loss": 0.653,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.5517241379310345,
106
+ "grad_norm": 0.5645097494125366,
107
+ "learning_rate": 0.00017071067811865476,
108
+ "loss": 0.6408,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.5517241379310345,
113
+ "eval_loss": 0.6028693318367004,
114
+ "eval_runtime": 59.4134,
115
+ "eval_samples_per_second": 3.333,
116
+ "eval_steps_per_second": 0.421,
117
+ "step": 12
118
+ },
119
+ {
120
+ "epoch": 0.5977011494252874,
121
+ "grad_norm": 0.5011037588119507,
122
+ "learning_rate": 0.00016494480483301836,
123
+ "loss": 0.6326,
124
+ "step": 13
125
+ },
126
+ {
127
+ "epoch": 0.6436781609195402,
128
+ "grad_norm": 0.2876424789428711,
129
+ "learning_rate": 0.00015877852522924732,
130
+ "loss": 0.6937,
131
+ "step": 14
132
+ },
133
+ {
134
+ "epoch": 0.6896551724137931,
135
+ "grad_norm": 0.47212648391723633,
136
+ "learning_rate": 0.0001522498564715949,
137
+ "loss": 0.6298,
138
+ "step": 15
139
+ },
140
+ {
141
+ "epoch": 0.735632183908046,
142
+ "grad_norm": 0.6836615800857544,
143
+ "learning_rate": 0.00014539904997395468,
144
+ "loss": 0.5569,
145
+ "step": 16
146
+ },
147
+ {
148
+ "epoch": 0.7816091954022989,
149
+ "grad_norm": 0.26638293266296387,
150
+ "learning_rate": 0.000138268343236509,
151
+ "loss": 0.6057,
152
+ "step": 17
153
+ },
154
+ {
155
+ "epoch": 0.8275862068965517,
156
+ "grad_norm": 0.5527795553207397,
157
+ "learning_rate": 0.00013090169943749476,
158
+ "loss": 0.6546,
159
+ "step": 18
160
+ },
161
+ {
162
+ "epoch": 0.8275862068965517,
163
+ "eval_loss": 0.5754240155220032,
164
+ "eval_runtime": 59.3448,
165
+ "eval_samples_per_second": 3.336,
166
+ "eval_steps_per_second": 0.421,
167
+ "step": 18
168
+ },
169
+ {
170
+ "epoch": 0.8735632183908046,
171
+ "grad_norm": 0.3253306746482849,
172
+ "learning_rate": 0.00012334453638559057,
173
+ "loss": 0.5521,
174
+ "step": 19
175
+ },
176
+ {
177
+ "epoch": 0.9195402298850575,
178
+ "grad_norm": 0.17234736680984497,
179
+ "learning_rate": 0.0001156434465040231,
180
+ "loss": 0.5802,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.9655172413793104,
185
+ "grad_norm": 0.2543017864227295,
186
+ "learning_rate": 0.0001078459095727845,
187
+ "loss": 0.5579,
188
+ "step": 21
189
+ }
190
+ ],
191
+ "logging_steps": 1,
192
+ "max_steps": 42,
193
+ "num_input_tokens_seen": 0,
194
+ "num_train_epochs": 2,
195
+ "save_steps": 21,
196
+ "stateful_callbacks": {
197
+ "TrainerControl": {
198
+ "args": {
199
+ "should_epoch_stop": false,
200
+ "should_evaluate": false,
201
+ "should_log": false,
202
+ "should_save": true,
203
+ "should_training_stop": false
204
+ },
205
+ "attributes": {}
206
+ }
207
+ },
208
+ "total_flos": 1.1881844810396467e+17,
209
+ "train_batch_size": 2,
210
+ "trial_name": null,
211
+ "trial_params": null
212
+ }
checkpoint-21/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7597b9398cd5a80ae99530d1801ba0bdb201f15ee1f1b3ae6442df8bd1d62d0
3
+ size 6200
checkpoint-42/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/Yarn-Mistral-7b-64k
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 0.11.1
checkpoint-42/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Yarn-Mistral-7b-64k",
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": 16,
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": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-42/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e47b5d8ddd70d39b37d280c3af27514e07cf1a7f72078b7d37bfda8479c74d
3
+ size 335604696
checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c125dd1aafa5e7583d4c20081726039e1cb69f66c81bfa920f2136f15b63ff5
3
+ size 168624724
checkpoint-42/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:254239861923df0d7f8a0b2c4b0af95b72ea41a4cefe224f8734022aa686bbc3
3
+ size 14960
checkpoint-42/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cabb2a184bccf68c43275a0ee3c601cc65cce9c9fb494736c57136f56e14b39b
3
+ size 14960
checkpoint-42/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd024cba4fb79b42561cdebaad820564bc22220e5fe20fb905f21934324add4
3
+ size 14960
checkpoint-42/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:730583047ac80431a59a707690c52653caca27c3936faa3a515bd38baf1b0908
3
+ size 14960
checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da2e7edae03699c1cd9559730363e2f67d4336103b5fded6865a5437f817ac2d
3
+ size 1064
checkpoint-42/special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
checkpoint-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-42/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-42/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [
32
+ "<unk>",
33
+ "<s>",
34
+ "</s>"
35
+ ],
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "</s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
47
+ }
checkpoint-42/trainer_state.json ADDED
@@ -0,0 +1,391 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.8850574712643677,
5
+ "eval_steps": 6,
6
+ "global_step": 42,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04597701149425287,
13
+ "grad_norm": 2.537923574447632,
14
+ "learning_rate": 0.0001,
15
+ "loss": 1.4151,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.04597701149425287,
20
+ "eval_loss": 0.6549283862113953,
21
+ "eval_runtime": 59.8262,
22
+ "eval_samples_per_second": 3.31,
23
+ "eval_steps_per_second": 0.418,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.09195402298850575,
28
+ "grad_norm": 2.5883562564849854,
29
+ "learning_rate": 0.0002,
30
+ "loss": 1.3772,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.13793103448275862,
35
+ "grad_norm": 2.2641923427581787,
36
+ "learning_rate": 0.0001996917333733128,
37
+ "loss": 1.3153,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.1839080459770115,
42
+ "grad_norm": 5.304536819458008,
43
+ "learning_rate": 0.00019876883405951377,
44
+ "loss": 1.1035,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.22988505747126436,
49
+ "grad_norm": 1.074016809463501,
50
+ "learning_rate": 0.00019723699203976766,
51
+ "loss": 0.9059,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.27586206896551724,
56
+ "grad_norm": 0.8219733834266663,
57
+ "learning_rate": 0.00019510565162951537,
58
+ "loss": 0.8678,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.27586206896551724,
63
+ "eval_loss": 0.6351205706596375,
64
+ "eval_runtime": 59.9835,
65
+ "eval_samples_per_second": 3.301,
66
+ "eval_steps_per_second": 0.417,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.3218390804597701,
71
+ "grad_norm": 1.478880524635315,
72
+ "learning_rate": 0.0001923879532511287,
73
+ "loss": 0.8782,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.367816091954023,
78
+ "grad_norm": 0.7757106423377991,
79
+ "learning_rate": 0.0001891006524188368,
80
+ "loss": 0.7993,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.41379310344827586,
85
+ "grad_norm": 0.5512004494667053,
86
+ "learning_rate": 0.00018526401643540922,
87
+ "loss": 0.7126,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.45977011494252873,
92
+ "grad_norm": 1.5733872652053833,
93
+ "learning_rate": 0.00018090169943749476,
94
+ "loss": 0.685,
95
+ "step": 10
96
+ },
97
+ {
98
+ "epoch": 0.5057471264367817,
99
+ "grad_norm": 0.34443506598472595,
100
+ "learning_rate": 0.0001760405965600031,
101
+ "loss": 0.653,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.5517241379310345,
106
+ "grad_norm": 0.5645097494125366,
107
+ "learning_rate": 0.00017071067811865476,
108
+ "loss": 0.6408,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.5517241379310345,
113
+ "eval_loss": 0.6028693318367004,
114
+ "eval_runtime": 59.4134,
115
+ "eval_samples_per_second": 3.333,
116
+ "eval_steps_per_second": 0.421,
117
+ "step": 12
118
+ },
119
+ {
120
+ "epoch": 0.5977011494252874,
121
+ "grad_norm": 0.5011037588119507,
122
+ "learning_rate": 0.00016494480483301836,
123
+ "loss": 0.6326,
124
+ "step": 13
125
+ },
126
+ {
127
+ "epoch": 0.6436781609195402,
128
+ "grad_norm": 0.2876424789428711,
129
+ "learning_rate": 0.00015877852522924732,
130
+ "loss": 0.6937,
131
+ "step": 14
132
+ },
133
+ {
134
+ "epoch": 0.6896551724137931,
135
+ "grad_norm": 0.47212648391723633,
136
+ "learning_rate": 0.0001522498564715949,
137
+ "loss": 0.6298,
138
+ "step": 15
139
+ },
140
+ {
141
+ "epoch": 0.735632183908046,
142
+ "grad_norm": 0.6836615800857544,
143
+ "learning_rate": 0.00014539904997395468,
144
+ "loss": 0.5569,
145
+ "step": 16
146
+ },
147
+ {
148
+ "epoch": 0.7816091954022989,
149
+ "grad_norm": 0.26638293266296387,
150
+ "learning_rate": 0.000138268343236509,
151
+ "loss": 0.6057,
152
+ "step": 17
153
+ },
154
+ {
155
+ "epoch": 0.8275862068965517,
156
+ "grad_norm": 0.5527795553207397,
157
+ "learning_rate": 0.00013090169943749476,
158
+ "loss": 0.6546,
159
+ "step": 18
160
+ },
161
+ {
162
+ "epoch": 0.8275862068965517,
163
+ "eval_loss": 0.5754240155220032,
164
+ "eval_runtime": 59.3448,
165
+ "eval_samples_per_second": 3.336,
166
+ "eval_steps_per_second": 0.421,
167
+ "step": 18
168
+ },
169
+ {
170
+ "epoch": 0.8735632183908046,
171
+ "grad_norm": 0.3253306746482849,
172
+ "learning_rate": 0.00012334453638559057,
173
+ "loss": 0.5521,
174
+ "step": 19
175
+ },
176
+ {
177
+ "epoch": 0.9195402298850575,
178
+ "grad_norm": 0.17234736680984497,
179
+ "learning_rate": 0.0001156434465040231,
180
+ "loss": 0.5802,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.9655172413793104,
185
+ "grad_norm": 0.2543017864227295,
186
+ "learning_rate": 0.0001078459095727845,
187
+ "loss": 0.5579,
188
+ "step": 21
189
+ },
190
+ {
191
+ "epoch": 1.0114942528735633,
192
+ "grad_norm": 0.8507859706878662,
193
+ "learning_rate": 0.0001,
194
+ "loss": 0.5795,
195
+ "step": 22
196
+ },
197
+ {
198
+ "epoch": 1.0114942528735633,
199
+ "grad_norm": 0.29268795251846313,
200
+ "learning_rate": 9.215409042721552e-05,
201
+ "loss": 0.6311,
202
+ "step": 23
203
+ },
204
+ {
205
+ "epoch": 1.0574712643678161,
206
+ "grad_norm": 0.18724839389324188,
207
+ "learning_rate": 8.435655349597689e-05,
208
+ "loss": 0.574,
209
+ "step": 24
210
+ },
211
+ {
212
+ "epoch": 1.0574712643678161,
213
+ "eval_loss": 0.5620841979980469,
214
+ "eval_runtime": 59.4173,
215
+ "eval_samples_per_second": 3.332,
216
+ "eval_steps_per_second": 0.421,
217
+ "step": 24
218
+ },
219
+ {
220
+ "epoch": 1.103448275862069,
221
+ "grad_norm": 0.21775011718273163,
222
+ "learning_rate": 7.66554636144095e-05,
223
+ "loss": 0.5818,
224
+ "step": 25
225
+ },
226
+ {
227
+ "epoch": 1.1494252873563218,
228
+ "grad_norm": 0.24518676102161407,
229
+ "learning_rate": 6.909830056250527e-05,
230
+ "loss": 0.5618,
231
+ "step": 26
232
+ },
233
+ {
234
+ "epoch": 1.1954022988505748,
235
+ "grad_norm": 0.24137045443058014,
236
+ "learning_rate": 6.173165676349103e-05,
237
+ "loss": 0.6078,
238
+ "step": 27
239
+ },
240
+ {
241
+ "epoch": 1.2413793103448276,
242
+ "grad_norm": 0.17265664041042328,
243
+ "learning_rate": 5.4600950026045326e-05,
244
+ "loss": 0.5907,
245
+ "step": 28
246
+ },
247
+ {
248
+ "epoch": 1.2873563218390804,
249
+ "grad_norm": 0.1558091938495636,
250
+ "learning_rate": 4.7750143528405126e-05,
251
+ "loss": 0.553,
252
+ "step": 29
253
+ },
254
+ {
255
+ "epoch": 1.3333333333333333,
256
+ "grad_norm": 0.15223024785518646,
257
+ "learning_rate": 4.12214747707527e-05,
258
+ "loss": 0.5518,
259
+ "step": 30
260
+ },
261
+ {
262
+ "epoch": 1.3333333333333333,
263
+ "eval_loss": 0.5595065951347351,
264
+ "eval_runtime": 59.4325,
265
+ "eval_samples_per_second": 3.332,
266
+ "eval_steps_per_second": 0.421,
267
+ "step": 30
268
+ },
269
+ {
270
+ "epoch": 1.3793103448275863,
271
+ "grad_norm": 0.25727611780166626,
272
+ "learning_rate": 3.5055195166981645e-05,
273
+ "loss": 0.5463,
274
+ "step": 31
275
+ },
276
+ {
277
+ "epoch": 1.4252873563218391,
278
+ "grad_norm": 0.13202741742134094,
279
+ "learning_rate": 2.9289321881345254e-05,
280
+ "loss": 0.5598,
281
+ "step": 32
282
+ },
283
+ {
284
+ "epoch": 1.471264367816092,
285
+ "grad_norm": 0.20626722276210785,
286
+ "learning_rate": 2.3959403439996907e-05,
287
+ "loss": 0.5242,
288
+ "step": 33
289
+ },
290
+ {
291
+ "epoch": 1.5172413793103448,
292
+ "grad_norm": 0.16128551959991455,
293
+ "learning_rate": 1.9098300562505266e-05,
294
+ "loss": 0.5715,
295
+ "step": 34
296
+ },
297
+ {
298
+ "epoch": 1.5632183908045976,
299
+ "grad_norm": 0.346206396818161,
300
+ "learning_rate": 1.4735983564590783e-05,
301
+ "loss": 0.5265,
302
+ "step": 35
303
+ },
304
+ {
305
+ "epoch": 1.6091954022988506,
306
+ "grad_norm": 0.1324978768825531,
307
+ "learning_rate": 1.0899347581163221e-05,
308
+ "loss": 0.5446,
309
+ "step": 36
310
+ },
311
+ {
312
+ "epoch": 1.6091954022988506,
313
+ "eval_loss": 0.5576122403144836,
314
+ "eval_runtime": 59.5124,
315
+ "eval_samples_per_second": 3.327,
316
+ "eval_steps_per_second": 0.42,
317
+ "step": 36
318
+ },
319
+ {
320
+ "epoch": 1.6551724137931034,
321
+ "grad_norm": 0.1254015415906906,
322
+ "learning_rate": 7.612046748871327e-06,
323
+ "loss": 0.5739,
324
+ "step": 37
325
+ },
326
+ {
327
+ "epoch": 1.7011494252873565,
328
+ "grad_norm": 0.18170268833637238,
329
+ "learning_rate": 4.8943483704846475e-06,
330
+ "loss": 0.5717,
331
+ "step": 38
332
+ },
333
+ {
334
+ "epoch": 1.7471264367816093,
335
+ "grad_norm": 0.12662401795387268,
336
+ "learning_rate": 2.7630079602323442e-06,
337
+ "loss": 0.5424,
338
+ "step": 39
339
+ },
340
+ {
341
+ "epoch": 1.793103448275862,
342
+ "grad_norm": 0.1479385495185852,
343
+ "learning_rate": 1.231165940486234e-06,
344
+ "loss": 0.563,
345
+ "step": 40
346
+ },
347
+ {
348
+ "epoch": 1.839080459770115,
349
+ "grad_norm": 0.13152529299259186,
350
+ "learning_rate": 3.0826662668720364e-07,
351
+ "loss": 0.5698,
352
+ "step": 41
353
+ },
354
+ {
355
+ "epoch": 1.8850574712643677,
356
+ "grad_norm": 0.17284046113491058,
357
+ "learning_rate": 0.0,
358
+ "loss": 0.6227,
359
+ "step": 42
360
+ },
361
+ {
362
+ "epoch": 1.8850574712643677,
363
+ "eval_loss": 0.5568149089813232,
364
+ "eval_runtime": 59.8384,
365
+ "eval_samples_per_second": 3.309,
366
+ "eval_steps_per_second": 0.418,
367
+ "step": 42
368
+ }
369
+ ],
370
+ "logging_steps": 1,
371
+ "max_steps": 42,
372
+ "num_input_tokens_seen": 0,
373
+ "num_train_epochs": 2,
374
+ "save_steps": 21,
375
+ "stateful_callbacks": {
376
+ "TrainerControl": {
377
+ "args": {
378
+ "should_epoch_stop": false,
379
+ "should_evaluate": false,
380
+ "should_log": false,
381
+ "should_save": true,
382
+ "should_training_stop": true
383
+ },
384
+ "attributes": {}
385
+ }
386
+ },
387
+ "total_flos": 2.3746008314177126e+17,
388
+ "train_batch_size": 2,
389
+ "trial_name": null,
390
+ "trial_params": null
391
+ }
checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7597b9398cd5a80ae99530d1801ba0bdb201f15ee1f1b3ae6442df8bd1d62d0
3
+ size 6200
merged/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NousResearch/Yarn-Mistral-7b-64k",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "NousResearch/Yarn-Mistral-7b-64k--configuration_mistral.MistralConfig",
8
+ "AutoModelForCausalLM": "NousResearch/Yarn-Mistral-7b-64k--modeling_mistral_yarn.MistralForCausalLM"
9
+ },
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 14336,
16
+ "max_position_embeddings": 32768,
17
+ "model_type": "mistral",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "finetuned": true,
25
+ "original_max_position_embeddings": 8192,
26
+ "type": "yarn"
27
+ },
28
+ "rope_theta": 10000.0,
29
+ "sliding_window": 65536,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.42.3",
33
+ "use_cache": false,
34
+ "vocab_size": 32000
35
+ }
merged/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.42.3"
7
+ }
merged/pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67dd4fc16babff489884f4f1c1bb3132c12ccd10d1aaa82e6e07e5e25d2c4ae6
3
+ size 4943184288
merged/pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe27a44b38acb4f7ae0c94b145864da4aff40d7f53c8df28da1199d0498dcc74
3
+ size 4999843272
merged/pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4abda7ec763df491e5b4ca6c7d2c9af4f36b35724bb07e77592f074f0268cf8
3
+ size 4540536134
merged/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
296
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
297
+ }
298
+ }
merged/special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
merged/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
merged/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
merged/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [
32
+ "<unk>",
33
+ "<s>",
34
+ "</s>"
35
+ ],
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "</s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
47
+ }