Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- config.json +73 -0
- non_lora_trainables.bin +3 -0
- trainer_state.json +1773 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: liuhaotian/llava-v1.6-mistral-7b
|
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 0.13.2
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "liuhaotian/llava-v1.6-mistral-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
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": 256,
|
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": 128,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"up_proj",
|
26 |
+
"v_proj",
|
27 |
+
"k_proj",
|
28 |
+
"down_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15cad6c13249ef14bc66999e41c8089789cc17aba74afbcb75fe910ce11da62c
|
3 |
+
size 708925520
|
config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "liuhaotian/llava-v1.6-mistral-7b",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaMistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"freeze_mm_mlp_adapter": false,
|
11 |
+
"freeze_mm_vision_resampler": false,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 4096,
|
14 |
+
"image_aspect_ratio": "pad",
|
15 |
+
"image_crop_resolution": 224,
|
16 |
+
"image_grid_pinpoints": [
|
17 |
+
[
|
18 |
+
336,
|
19 |
+
672
|
20 |
+
],
|
21 |
+
[
|
22 |
+
672,
|
23 |
+
336
|
24 |
+
],
|
25 |
+
[
|
26 |
+
672,
|
27 |
+
672
|
28 |
+
],
|
29 |
+
[
|
30 |
+
1008,
|
31 |
+
336
|
32 |
+
],
|
33 |
+
[
|
34 |
+
336,
|
35 |
+
1008
|
36 |
+
]
|
37 |
+
],
|
38 |
+
"image_split_resolution": 224,
|
39 |
+
"initializer_range": 0.02,
|
40 |
+
"intermediate_size": 14336,
|
41 |
+
"max_position_embeddings": 32768,
|
42 |
+
"mm_hidden_size": 1024,
|
43 |
+
"mm_patch_merge_type": "flat",
|
44 |
+
"mm_projector_lr": 2e-05,
|
45 |
+
"mm_projector_type": "mlp2x_gelu",
|
46 |
+
"mm_resampler_type": null,
|
47 |
+
"mm_use_im_patch_token": false,
|
48 |
+
"mm_use_im_start_end": false,
|
49 |
+
"mm_vision_select_feature": "patch",
|
50 |
+
"mm_vision_select_layer": -2,
|
51 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
52 |
+
"mm_vision_tower_lr": 2e-06,
|
53 |
+
"model_type": "llava_llama",
|
54 |
+
"num_attention_heads": 32,
|
55 |
+
"num_hidden_layers": 32,
|
56 |
+
"num_key_value_heads": 8,
|
57 |
+
"pretraining_tp": 1,
|
58 |
+
"rms_norm_eps": 1e-05,
|
59 |
+
"rope_scaling": null,
|
60 |
+
"rope_theta": 1000000.0,
|
61 |
+
"sliding_window": null,
|
62 |
+
"tie_word_embeddings": false,
|
63 |
+
"tokenizer_model_max_length": 2048,
|
64 |
+
"tokenizer_padding_side": "right",
|
65 |
+
"torch_dtype": "bfloat16",
|
66 |
+
"transformers_version": "4.39.3",
|
67 |
+
"tune_mm_mlp_adapter": false,
|
68 |
+
"tune_mm_vision_resampler": false,
|
69 |
+
"unfreeze_mm_vision_tower": true,
|
70 |
+
"use_cache": true,
|
71 |
+
"use_mm_proj": true,
|
72 |
+
"vocab_size": 32000
|
73 |
+
}
|
non_lora_trainables.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3885463ff88e1ef6530e61691e756c9a5698547c007d63c618d3680b7e604d53
|
3 |
+
size 41961648
|
trainer_state.json
ADDED
@@ -0,0 +1,1773 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 249,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 3.981182133898211,
|
14 |
+
"learning_rate": 2.5e-05,
|
15 |
+
"loss": 1.365,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01,
|
20 |
+
"grad_norm": 4.223447168750389,
|
21 |
+
"learning_rate": 5e-05,
|
22 |
+
"loss": 1.3932,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01,
|
27 |
+
"grad_norm": 2.141765750699434,
|
28 |
+
"learning_rate": 7.500000000000001e-05,
|
29 |
+
"loss": 1.1306,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.02,
|
34 |
+
"grad_norm": 2.2703951636474855,
|
35 |
+
"learning_rate": 0.0001,
|
36 |
+
"loss": 1.0787,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.02,
|
41 |
+
"grad_norm": 1.9111760478873023,
|
42 |
+
"learning_rate": 0.000125,
|
43 |
+
"loss": 1.0686,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02,
|
48 |
+
"grad_norm": 1.3499712071563628,
|
49 |
+
"learning_rate": 0.00015000000000000001,
|
50 |
+
"loss": 1.0114,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.03,
|
55 |
+
"grad_norm": 1.0911667817060011,
|
56 |
+
"learning_rate": 0.000175,
|
57 |
+
"loss": 0.9416,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.03,
|
62 |
+
"grad_norm": 1.2496043705531406,
|
63 |
+
"learning_rate": 0.0002,
|
64 |
+
"loss": 0.9286,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.04,
|
69 |
+
"grad_norm": 1.7692075337111344,
|
70 |
+
"learning_rate": 0.00019999150370633988,
|
71 |
+
"loss": 0.9074,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.04,
|
76 |
+
"grad_norm": 0.9122071484249495,
|
77 |
+
"learning_rate": 0.00019996601626909964,
|
78 |
+
"loss": 0.8867,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.04,
|
83 |
+
"grad_norm": 0.9493702949853532,
|
84 |
+
"learning_rate": 0.00019992354201925428,
|
85 |
+
"loss": 0.8814,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.05,
|
90 |
+
"grad_norm": 0.8549355244573901,
|
91 |
+
"learning_rate": 0.0001998640881742778,
|
92 |
+
"loss": 0.8887,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.05,
|
97 |
+
"grad_norm": 0.8921668257689561,
|
98 |
+
"learning_rate": 0.00019978766483691676,
|
99 |
+
"loss": 0.8542,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.06,
|
104 |
+
"grad_norm": 0.8244188073583076,
|
105 |
+
"learning_rate": 0.0001996942849934735,
|
106 |
+
"loss": 0.8412,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.06,
|
111 |
+
"grad_norm": 0.7478409595239439,
|
112 |
+
"learning_rate": 0.00019958396451159936,
|
113 |
+
"loss": 0.7793,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.06,
|
118 |
+
"grad_norm": 0.758307762850361,
|
119 |
+
"learning_rate": 0.0001994567221375987,
|
120 |
+
"loss": 0.819,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.07,
|
125 |
+
"grad_norm": 0.770947644951731,
|
126 |
+
"learning_rate": 0.00019931257949324288,
|
127 |
+
"loss": 0.8447,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.07,
|
132 |
+
"grad_norm": 0.8358253752348583,
|
133 |
+
"learning_rate": 0.00019915156107209675,
|
134 |
+
"loss": 0.772,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.08,
|
139 |
+
"grad_norm": 0.7175509358752481,
|
140 |
+
"learning_rate": 0.000198973694235356,
|
141 |
+
"loss": 0.7914,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.08,
|
146 |
+
"grad_norm": 0.7542707242255626,
|
147 |
+
"learning_rate": 0.00019877900920719827,
|
148 |
+
"loss": 0.7983,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.08,
|
153 |
+
"grad_norm": 0.7645202304094161,
|
154 |
+
"learning_rate": 0.00019856753906964686,
|
155 |
+
"loss": 0.7214,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.09,
|
160 |
+
"grad_norm": 0.7430521597063948,
|
161 |
+
"learning_rate": 0.0001983393197569497,
|
162 |
+
"loss": 0.8091,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.09,
|
167 |
+
"grad_norm": 0.7324090515929388,
|
168 |
+
"learning_rate": 0.00019809439004947268,
|
169 |
+
"loss": 0.7704,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.1,
|
174 |
+
"grad_norm": 0.6896844994612445,
|
175 |
+
"learning_rate": 0.00019783279156711022,
|
176 |
+
"loss": 0.7556,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.1,
|
181 |
+
"grad_norm": 0.6749132637574569,
|
182 |
+
"learning_rate": 0.0001975545687622129,
|
183 |
+
"loss": 0.7571,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.1,
|
188 |
+
"grad_norm": 0.7076244352514828,
|
189 |
+
"learning_rate": 0.00019725976891203376,
|
190 |
+
"loss": 0.8445,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.11,
|
195 |
+
"grad_norm": 0.6358516553573809,
|
196 |
+
"learning_rate": 0.00019694844211069477,
|
197 |
+
"loss": 0.7477,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.11,
|
202 |
+
"grad_norm": 0.6633797558960025,
|
203 |
+
"learning_rate": 0.00019662064126067452,
|
204 |
+
"loss": 0.7359,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.12,
|
209 |
+
"grad_norm": 0.7619604289470452,
|
210 |
+
"learning_rate": 0.00019627642206381863,
|
211 |
+
"loss": 0.7752,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.12,
|
216 |
+
"grad_norm": 0.6693105562777081,
|
217 |
+
"learning_rate": 0.00019591584301187478,
|
218 |
+
"loss": 0.7147,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.12,
|
223 |
+
"grad_norm": 0.6441185271339039,
|
224 |
+
"learning_rate": 0.00019553896537655318,
|
225 |
+
"loss": 0.7425,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.13,
|
230 |
+
"grad_norm": 0.6912959653338677,
|
231 |
+
"learning_rate": 0.0001951458531991151,
|
232 |
+
"loss": 0.7344,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.13,
|
237 |
+
"grad_norm": 0.6265627524452637,
|
238 |
+
"learning_rate": 0.00019473657327949054,
|
239 |
+
"loss": 0.7292,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.14,
|
244 |
+
"grad_norm": 0.8319948068621666,
|
245 |
+
"learning_rate": 0.00019431119516492726,
|
246 |
+
"loss": 0.7196,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.14,
|
251 |
+
"grad_norm": 0.6374074802429165,
|
252 |
+
"learning_rate": 0.00019386979113817282,
|
253 |
+
"loss": 0.7549,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.14,
|
258 |
+
"grad_norm": 0.6813527739244364,
|
259 |
+
"learning_rate": 0.0001934124362051919,
|
260 |
+
"loss": 0.7656,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.15,
|
265 |
+
"grad_norm": 1.6806360809140246,
|
266 |
+
"learning_rate": 0.00019293920808242083,
|
267 |
+
"loss": 0.7582,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.15,
|
272 |
+
"grad_norm": 0.66415983259972,
|
273 |
+
"learning_rate": 0.0001924501871835616,
|
274 |
+
"loss": 0.7754,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.16,
|
279 |
+
"grad_norm": 0.736768809075717,
|
280 |
+
"learning_rate": 0.00019194545660591752,
|
281 |
+
"loss": 0.6906,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.16,
|
286 |
+
"grad_norm": 1.013197406350164,
|
287 |
+
"learning_rate": 0.00019142510211627264,
|
288 |
+
"loss": 0.7464,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.16,
|
293 |
+
"grad_norm": 0.8455834245687115,
|
294 |
+
"learning_rate": 0.000190889212136318,
|
295 |
+
"loss": 0.7476,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.17,
|
300 |
+
"grad_norm": 0.8000760159918991,
|
301 |
+
"learning_rate": 0.00019033787772762645,
|
302 |
+
"loss": 0.7612,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.17,
|
307 |
+
"grad_norm": 0.7721776264489126,
|
308 |
+
"learning_rate": 0.00018977119257617878,
|
309 |
+
"loss": 0.7661,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.18,
|
314 |
+
"grad_norm": 0.7411505347014887,
|
315 |
+
"learning_rate": 0.00018918925297644416,
|
316 |
+
"loss": 0.7582,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.18,
|
321 |
+
"grad_norm": 0.6574055283176412,
|
322 |
+
"learning_rate": 0.00018859215781501725,
|
323 |
+
"loss": 0.693,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.18,
|
328 |
+
"grad_norm": 0.6252820250088373,
|
329 |
+
"learning_rate": 0.0001879800085538147,
|
330 |
+
"loss": 0.6709,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.19,
|
335 |
+
"grad_norm": 0.6283973563255442,
|
336 |
+
"learning_rate": 0.0001873529092128343,
|
337 |
+
"loss": 0.7499,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.19,
|
342 |
+
"grad_norm": 0.691088723538482,
|
343 |
+
"learning_rate": 0.00018671096635247914,
|
344 |
+
"loss": 0.7595,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.2,
|
349 |
+
"grad_norm": 0.6657667325476994,
|
350 |
+
"learning_rate": 0.00018605428905545032,
|
351 |
+
"loss": 0.7608,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.2,
|
356 |
+
"grad_norm": 0.6483390927552524,
|
357 |
+
"learning_rate": 0.0001853829889082109,
|
358 |
+
"loss": 0.7267,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.2,
|
363 |
+
"grad_norm": 0.5768376505606613,
|
364 |
+
"learning_rate": 0.00018469717998202462,
|
365 |
+
"loss": 0.7361,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.21,
|
370 |
+
"grad_norm": 0.5962362264080698,
|
371 |
+
"learning_rate": 0.00018399697881357212,
|
372 |
+
"loss": 0.7373,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.21,
|
377 |
+
"grad_norm": 0.6392264631697471,
|
378 |
+
"learning_rate": 0.00018328250438514836,
|
379 |
+
"loss": 0.7005,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.22,
|
384 |
+
"grad_norm": 0.6242411219574141,
|
385 |
+
"learning_rate": 0.00018255387810444448,
|
386 |
+
"loss": 0.7522,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.22,
|
391 |
+
"grad_norm": 0.5870527031664319,
|
392 |
+
"learning_rate": 0.0001818112237839174,
|
393 |
+
"loss": 0.7118,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.22,
|
398 |
+
"grad_norm": 0.6066047817906325,
|
399 |
+
"learning_rate": 0.00018105466761975109,
|
400 |
+
"loss": 0.7058,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.23,
|
405 |
+
"grad_norm": 0.6038141699713118,
|
406 |
+
"learning_rate": 0.00018028433817041236,
|
407 |
+
"loss": 0.7219,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.23,
|
412 |
+
"grad_norm": 0.5847345831142737,
|
413 |
+
"learning_rate": 0.00017950036633480556,
|
414 |
+
"loss": 0.7147,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.24,
|
419 |
+
"grad_norm": 0.6312111783082757,
|
420 |
+
"learning_rate": 0.00017870288533002938,
|
421 |
+
"loss": 0.6963,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.24,
|
426 |
+
"grad_norm": 0.5966959070900965,
|
427 |
+
"learning_rate": 0.00017789203066873998,
|
428 |
+
"loss": 0.7307,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.24,
|
433 |
+
"grad_norm": 0.5798593347176144,
|
434 |
+
"learning_rate": 0.00017706794013612364,
|
435 |
+
"loss": 0.7303,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.25,
|
440 |
+
"grad_norm": 0.6100699019983455,
|
441 |
+
"learning_rate": 0.00017623075376648376,
|
442 |
+
"loss": 0.7122,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.25,
|
447 |
+
"grad_norm": 0.6150446745513377,
|
448 |
+
"learning_rate": 0.00017538061381944524,
|
449 |
+
"loss": 0.7282,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.26,
|
454 |
+
"grad_norm": 0.5839828703861961,
|
455 |
+
"learning_rate": 0.0001745176647557809,
|
456 |
+
"loss": 0.6841,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.26,
|
461 |
+
"grad_norm": 0.5832617502478282,
|
462 |
+
"learning_rate": 0.00017364205321286394,
|
463 |
+
"loss": 0.7088,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.27,
|
468 |
+
"grad_norm": 0.6117567542213321,
|
469 |
+
"learning_rate": 0.00017275392797975032,
|
470 |
+
"loss": 0.781,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.27,
|
475 |
+
"grad_norm": 0.6332126002995662,
|
476 |
+
"learning_rate": 0.00017185343997189588,
|
477 |
+
"loss": 0.7346,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.27,
|
482 |
+
"grad_norm": 0.5617477585453899,
|
483 |
+
"learning_rate": 0.00017094074220551158,
|
484 |
+
"loss": 0.7114,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.28,
|
489 |
+
"grad_norm": 0.5820274703305921,
|
490 |
+
"learning_rate": 0.0001700159897715624,
|
491 |
+
"loss": 0.742,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.28,
|
496 |
+
"grad_norm": 0.580367538119296,
|
497 |
+
"learning_rate": 0.00016907933980941312,
|
498 |
+
"loss": 0.6663,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.29,
|
503 |
+
"grad_norm": 0.5652333172835816,
|
504 |
+
"learning_rate": 0.0001681309514801265,
|
505 |
+
"loss": 0.678,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.29,
|
510 |
+
"grad_norm": 0.5604822769679129,
|
511 |
+
"learning_rate": 0.00016717098593941752,
|
512 |
+
"loss": 0.7027,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.29,
|
517 |
+
"grad_norm": 0.5443005590527936,
|
518 |
+
"learning_rate": 0.00016619960631026888,
|
519 |
+
"loss": 0.7235,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.3,
|
524 |
+
"grad_norm": 0.5648289749630883,
|
525 |
+
"learning_rate": 0.0001652169776552123,
|
526 |
+
"loss": 0.6966,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.3,
|
531 |
+
"grad_norm": 0.5511612101503145,
|
532 |
+
"learning_rate": 0.00016422326694828007,
|
533 |
+
"loss": 0.6716,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.31,
|
538 |
+
"grad_norm": 0.5652818087038983,
|
539 |
+
"learning_rate": 0.00016321864304663173,
|
540 |
+
"loss": 0.6964,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.31,
|
545 |
+
"grad_norm": 0.5873059772542137,
|
546 |
+
"learning_rate": 0.000162203276661861,
|
547 |
+
"loss": 0.7268,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.31,
|
552 |
+
"grad_norm": 0.584440156512384,
|
553 |
+
"learning_rate": 0.00016117734033098744,
|
554 |
+
"loss": 0.7183,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.32,
|
559 |
+
"grad_norm": 0.5476205992100533,
|
560 |
+
"learning_rate": 0.00016014100838713797,
|
561 |
+
"loss": 0.7063,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.32,
|
566 |
+
"grad_norm": 0.6013346658704335,
|
567 |
+
"learning_rate": 0.000159094456929923,
|
568 |
+
"loss": 0.6893,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.33,
|
573 |
+
"grad_norm": 0.5525643324311199,
|
574 |
+
"learning_rate": 0.0001580378637955128,
|
575 |
+
"loss": 0.6691,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.33,
|
580 |
+
"grad_norm": 0.5889885232500072,
|
581 |
+
"learning_rate": 0.00015697140852641834,
|
582 |
+
"loss": 0.6944,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.33,
|
587 |
+
"grad_norm": 0.6105160593879608,
|
588 |
+
"learning_rate": 0.00015589527234098247,
|
589 |
+
"loss": 0.7328,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.34,
|
594 |
+
"grad_norm": 0.580479859109292,
|
595 |
+
"learning_rate": 0.00015480963810258613,
|
596 |
+
"loss": 0.6913,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.34,
|
601 |
+
"grad_norm": 0.5618974771825274,
|
602 |
+
"learning_rate": 0.00015371469028857532,
|
603 |
+
"loss": 0.724,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.35,
|
608 |
+
"grad_norm": 0.560525959205613,
|
609 |
+
"learning_rate": 0.00015261061495891345,
|
610 |
+
"loss": 0.7048,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.35,
|
615 |
+
"grad_norm": 0.6212802766603819,
|
616 |
+
"learning_rate": 0.0001514975997245649,
|
617 |
+
"loss": 0.6858,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.35,
|
622 |
+
"grad_norm": 0.570889967163218,
|
623 |
+
"learning_rate": 0.00015037583371561535,
|
624 |
+
"loss": 0.696,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.36,
|
629 |
+
"grad_norm": 0.5568747400044114,
|
630 |
+
"learning_rate": 0.0001492455075491334,
|
631 |
+
"loss": 0.693,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.36,
|
636 |
+
"grad_norm": 0.5563715707732911,
|
637 |
+
"learning_rate": 0.00014810681329677987,
|
638 |
+
"loss": 0.6806,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.37,
|
643 |
+
"grad_norm": 0.568992451570255,
|
644 |
+
"learning_rate": 0.00014695994445216985,
|
645 |
+
"loss": 0.7074,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.37,
|
650 |
+
"grad_norm": 0.5767587218056255,
|
651 |
+
"learning_rate": 0.00014580509589799329,
|
652 |
+
"loss": 0.7094,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.37,
|
657 |
+
"grad_norm": 0.5425009774160251,
|
658 |
+
"learning_rate": 0.00014464246387289913,
|
659 |
+
"loss": 0.6781,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.38,
|
664 |
+
"grad_norm": 0.5513859545077572,
|
665 |
+
"learning_rate": 0.00014347224593814944,
|
666 |
+
"loss": 0.7234,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.38,
|
671 |
+
"grad_norm": 0.5339051729787517,
|
672 |
+
"learning_rate": 0.00014229464094404865,
|
673 |
+
"loss": 0.6931,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.39,
|
678 |
+
"grad_norm": 0.5549045365561713,
|
679 |
+
"learning_rate": 0.00014110984899615367,
|
680 |
+
"loss": 0.6962,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.39,
|
685 |
+
"grad_norm": 0.5395797162975184,
|
686 |
+
"learning_rate": 0.0001399180714212708,
|
687 |
+
"loss": 0.6832,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.39,
|
692 |
+
"grad_norm": 0.5393020282422275,
|
693 |
+
"learning_rate": 0.00013871951073324507,
|
694 |
+
"loss": 0.7212,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.4,
|
699 |
+
"grad_norm": 0.5406971945004404,
|
700 |
+
"learning_rate": 0.0001375143705985481,
|
701 |
+
"loss": 0.6878,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.4,
|
706 |
+
"grad_norm": 0.5741985470318297,
|
707 |
+
"learning_rate": 0.00013630285580166945,
|
708 |
+
"loss": 0.6725,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.41,
|
713 |
+
"grad_norm": 0.6087387724460733,
|
714 |
+
"learning_rate": 0.000135085172210319,
|
715 |
+
"loss": 0.6876,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.41,
|
720 |
+
"grad_norm": 0.5202304228310284,
|
721 |
+
"learning_rate": 0.00013386152674044422,
|
722 |
+
"loss": 0.6652,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.41,
|
727 |
+
"grad_norm": 0.5660298147339341,
|
728 |
+
"learning_rate": 0.00013263212732107012,
|
729 |
+
"loss": 0.693,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.42,
|
734 |
+
"grad_norm": 0.546774134041922,
|
735 |
+
"learning_rate": 0.00013139718285896655,
|
736 |
+
"loss": 0.6464,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.42,
|
741 |
+
"grad_norm": 0.5338303600632187,
|
742 |
+
"learning_rate": 0.00013015690320314954,
|
743 |
+
"loss": 0.7009,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.43,
|
748 |
+
"grad_norm": 0.5396484507008162,
|
749 |
+
"learning_rate": 0.00012891149910922267,
|
750 |
+
"loss": 0.696,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.43,
|
755 |
+
"grad_norm": 0.5185373681304583,
|
756 |
+
"learning_rate": 0.00012766118220356408,
|
757 |
+
"loss": 0.687,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.43,
|
762 |
+
"grad_norm": 0.5102091277266492,
|
763 |
+
"learning_rate": 0.0001264061649473657,
|
764 |
+
"loss": 0.6648,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.44,
|
769 |
+
"grad_norm": 0.5727613881928513,
|
770 |
+
"learning_rate": 0.00012514666060053076,
|
771 |
+
"loss": 0.6777,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.44,
|
776 |
+
"grad_norm": 0.5165707891231989,
|
777 |
+
"learning_rate": 0.00012388288318543512,
|
778 |
+
"loss": 0.6454,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.45,
|
783 |
+
"grad_norm": 0.5463906044314786,
|
784 |
+
"learning_rate": 0.00012261504745055964,
|
785 |
+
"loss": 0.6463,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.45,
|
790 |
+
"grad_norm": 0.5150747138759594,
|
791 |
+
"learning_rate": 0.00012134336883399855,
|
792 |
+
"loss": 0.6436,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.45,
|
797 |
+
"grad_norm": 0.5268166681458911,
|
798 |
+
"learning_rate": 0.00012006806342685126,
|
799 |
+
"loss": 0.7139,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.46,
|
804 |
+
"grad_norm": 0.5797636370362743,
|
805 |
+
"learning_rate": 0.00011878934793650273,
|
806 |
+
"loss": 0.5959,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.46,
|
811 |
+
"grad_norm": 0.5168654595529651,
|
812 |
+
"learning_rate": 0.00011750743964979918,
|
813 |
+
"loss": 0.6465,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.47,
|
818 |
+
"grad_norm": 0.5586505025432532,
|
819 |
+
"learning_rate": 0.00011622255639612554,
|
820 |
+
"loss": 0.6954,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.47,
|
825 |
+
"grad_norm": 0.5733109224839272,
|
826 |
+
"learning_rate": 0.00011493491651039077,
|
827 |
+
"loss": 0.6951,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.47,
|
832 |
+
"grad_norm": 0.5798484006098489,
|
833 |
+
"learning_rate": 0.00011364473879592674,
|
834 |
+
"loss": 0.6713,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.48,
|
839 |
+
"grad_norm": 0.5558404867313713,
|
840 |
+
"learning_rate": 0.0001123522424873082,
|
841 |
+
"loss": 0.6627,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.48,
|
846 |
+
"grad_norm": 0.564370632395679,
|
847 |
+
"learning_rate": 0.000111057647213099,
|
848 |
+
"loss": 0.6582,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.49,
|
853 |
+
"grad_norm": 0.5247546019655245,
|
854 |
+
"learning_rate": 0.00010976117295853154,
|
855 |
+
"loss": 0.6274,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.49,
|
860 |
+
"grad_norm": 0.5043366815729828,
|
861 |
+
"learning_rate": 0.00010846304002812564,
|
862 |
+
"loss": 0.663,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.49,
|
867 |
+
"grad_norm": 0.5377570953262834,
|
868 |
+
"learning_rate": 0.00010716346900825299,
|
869 |
+
"loss": 0.6879,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.5,
|
874 |
+
"grad_norm": 0.5316530391582156,
|
875 |
+
"learning_rate": 0.00010586268072965396,
|
876 |
+
"loss": 0.6812,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.5,
|
881 |
+
"grad_norm": 0.5309847868667069,
|
882 |
+
"learning_rate": 0.00010456089622991263,
|
883 |
+
"loss": 0.6378,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.51,
|
888 |
+
"grad_norm": 0.49952898047881455,
|
889 |
+
"learning_rate": 0.00010325833671589687,
|
890 |
+
"loss": 0.7031,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.51,
|
895 |
+
"grad_norm": 0.513186855879022,
|
896 |
+
"learning_rate": 0.00010195522352616943,
|
897 |
+
"loss": 0.6346,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.51,
|
902 |
+
"grad_norm": 0.5624215177016363,
|
903 |
+
"learning_rate": 0.00010065177809337702,
|
904 |
+
"loss": 0.7014,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.52,
|
909 |
+
"grad_norm": 0.5339748834208153,
|
910 |
+
"learning_rate": 9.934822190662299e-05,
|
911 |
+
"loss": 0.7169,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.52,
|
916 |
+
"grad_norm": 0.5298864830864823,
|
917 |
+
"learning_rate": 9.80447764738306e-05,
|
918 |
+
"loss": 0.6419,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.53,
|
923 |
+
"grad_norm": 0.49790603329053645,
|
924 |
+
"learning_rate": 9.674166328410318e-05,
|
925 |
+
"loss": 0.6277,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.53,
|
930 |
+
"grad_norm": 0.5222038396293899,
|
931 |
+
"learning_rate": 9.543910377008742e-05,
|
932 |
+
"loss": 0.6617,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.53,
|
937 |
+
"grad_norm": 0.5076737199539593,
|
938 |
+
"learning_rate": 9.413731927034605e-05,
|
939 |
+
"loss": 0.6315,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.54,
|
944 |
+
"grad_norm": 0.540367448084855,
|
945 |
+
"learning_rate": 9.283653099174704e-05,
|
946 |
+
"loss": 0.637,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.54,
|
951 |
+
"grad_norm": 0.5259754962695676,
|
952 |
+
"learning_rate": 9.15369599718744e-05,
|
953 |
+
"loss": 0.6564,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.55,
|
958 |
+
"grad_norm": 0.5297038847994276,
|
959 |
+
"learning_rate": 9.023882704146848e-05,
|
960 |
+
"loss": 0.6174,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.55,
|
965 |
+
"grad_norm": 0.5175810600475641,
|
966 |
+
"learning_rate": 8.894235278690104e-05,
|
967 |
+
"loss": 0.6885,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.55,
|
972 |
+
"grad_norm": 0.49466775844805594,
|
973 |
+
"learning_rate": 8.764775751269182e-05,
|
974 |
+
"loss": 0.6264,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.56,
|
979 |
+
"grad_norm": 0.5468376014397491,
|
980 |
+
"learning_rate": 8.635526120407329e-05,
|
981 |
+
"loss": 0.6293,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.56,
|
986 |
+
"grad_norm": 0.5266499924056278,
|
987 |
+
"learning_rate": 8.506508348960924e-05,
|
988 |
+
"loss": 0.6672,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.57,
|
993 |
+
"grad_norm": 0.5125354022430374,
|
994 |
+
"learning_rate": 8.377744360387447e-05,
|
995 |
+
"loss": 0.6289,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.57,
|
1000 |
+
"grad_norm": 0.508760796232234,
|
1001 |
+
"learning_rate": 8.249256035020086e-05,
|
1002 |
+
"loss": 0.6311,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.57,
|
1007 |
+
"grad_norm": 0.5021864887346997,
|
1008 |
+
"learning_rate": 8.121065206349729e-05,
|
1009 |
+
"loss": 0.6594,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.58,
|
1014 |
+
"grad_norm": 0.5355896437675315,
|
1015 |
+
"learning_rate": 7.993193657314875e-05,
|
1016 |
+
"loss": 0.6224,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.58,
|
1021 |
+
"grad_norm": 0.5488326374985829,
|
1022 |
+
"learning_rate": 7.865663116600148e-05,
|
1023 |
+
"loss": 0.6465,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.59,
|
1028 |
+
"grad_norm": 0.6071274038365753,
|
1029 |
+
"learning_rate": 7.738495254944042e-05,
|
1030 |
+
"loss": 0.6576,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.59,
|
1035 |
+
"grad_norm": 0.5212237290379841,
|
1036 |
+
"learning_rate": 7.611711681456493e-05,
|
1037 |
+
"loss": 0.6286,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.59,
|
1042 |
+
"grad_norm": 0.5361821341032351,
|
1043 |
+
"learning_rate": 7.485333939946926e-05,
|
1044 |
+
"loss": 0.6436,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.6,
|
1049 |
+
"grad_norm": 0.5328445664549779,
|
1050 |
+
"learning_rate": 7.359383505263431e-05,
|
1051 |
+
"loss": 0.6805,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.6,
|
1056 |
+
"grad_norm": 0.5169478911375548,
|
1057 |
+
"learning_rate": 7.233881779643594e-05,
|
1058 |
+
"loss": 0.6351,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.61,
|
1063 |
+
"grad_norm": 0.4942190213678014,
|
1064 |
+
"learning_rate": 7.108850089077735e-05,
|
1065 |
+
"loss": 0.6645,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.61,
|
1070 |
+
"grad_norm": 0.4777490402143269,
|
1071 |
+
"learning_rate": 6.98430967968505e-05,
|
1072 |
+
"loss": 0.6646,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.61,
|
1077 |
+
"grad_norm": 0.5203792217543509,
|
1078 |
+
"learning_rate": 6.86028171410335e-05,
|
1079 |
+
"loss": 0.6264,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.62,
|
1084 |
+
"grad_norm": 0.5295673373178881,
|
1085 |
+
"learning_rate": 6.736787267892991e-05,
|
1086 |
+
"loss": 0.6574,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.62,
|
1091 |
+
"grad_norm": 0.5054007800089361,
|
1092 |
+
"learning_rate": 6.613847325955578e-05,
|
1093 |
+
"loss": 0.6463,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.63,
|
1098 |
+
"grad_norm": 0.5328764157075438,
|
1099 |
+
"learning_rate": 6.491482778968104e-05,
|
1100 |
+
"loss": 0.6542,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.63,
|
1105 |
+
"grad_norm": 0.518388232442327,
|
1106 |
+
"learning_rate": 6.369714419833056e-05,
|
1107 |
+
"loss": 0.6266,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.63,
|
1112 |
+
"grad_norm": 0.6119309470927382,
|
1113 |
+
"learning_rate": 6.248562940145195e-05,
|
1114 |
+
"loss": 0.6336,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.64,
|
1119 |
+
"grad_norm": 0.4963434899391007,
|
1120 |
+
"learning_rate": 6.128048926675494e-05,
|
1121 |
+
"loss": 0.6718,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.64,
|
1126 |
+
"grad_norm": 0.5095621401572632,
|
1127 |
+
"learning_rate": 6.008192857872923e-05,
|
1128 |
+
"loss": 0.637,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.65,
|
1133 |
+
"grad_norm": 0.5093440110600602,
|
1134 |
+
"learning_rate": 5.889015100384636e-05,
|
1135 |
+
"loss": 0.6307,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.65,
|
1140 |
+
"grad_norm": 0.5082532966773227,
|
1141 |
+
"learning_rate": 5.770535905595138e-05,
|
1142 |
+
"loss": 0.6382,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.65,
|
1147 |
+
"grad_norm": 0.5305244284181049,
|
1148 |
+
"learning_rate": 5.6527754061850554e-05,
|
1149 |
+
"loss": 0.6424,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.66,
|
1154 |
+
"grad_norm": 0.5234971513196092,
|
1155 |
+
"learning_rate": 5.5357536127100904e-05,
|
1156 |
+
"loss": 0.6485,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.66,
|
1161 |
+
"grad_norm": 0.5035050904882836,
|
1162 |
+
"learning_rate": 5.419490410200675e-05,
|
1163 |
+
"loss": 0.6037,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.67,
|
1168 |
+
"grad_norm": 0.4979993303718048,
|
1169 |
+
"learning_rate": 5.304005554783015e-05,
|
1170 |
+
"loss": 0.6394,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.67,
|
1175 |
+
"grad_norm": 0.4822032608918998,
|
1176 |
+
"learning_rate": 5.1893186703220165e-05,
|
1177 |
+
"loss": 0.6107,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.67,
|
1182 |
+
"grad_norm": 0.47831076024478025,
|
1183 |
+
"learning_rate": 5.0754492450866607e-05,
|
1184 |
+
"loss": 0.6171,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.68,
|
1189 |
+
"grad_norm": 0.5217479864900989,
|
1190 |
+
"learning_rate": 4.9624166284384656e-05,
|
1191 |
+
"loss": 0.6039,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.68,
|
1196 |
+
"grad_norm": 0.4966800853562241,
|
1197 |
+
"learning_rate": 4.850240027543509e-05,
|
1198 |
+
"loss": 0.6399,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.69,
|
1203 |
+
"grad_norm": 0.48803795748690887,
|
1204 |
+
"learning_rate": 4.738938504108659e-05,
|
1205 |
+
"loss": 0.6182,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.69,
|
1210 |
+
"grad_norm": 0.5080270857045189,
|
1211 |
+
"learning_rate": 4.628530971142471e-05,
|
1212 |
+
"loss": 0.6141,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.69,
|
1217 |
+
"grad_norm": 0.47913685117930593,
|
1218 |
+
"learning_rate": 4.519036189741386e-05,
|
1219 |
+
"loss": 0.6386,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.7,
|
1224 |
+
"grad_norm": 0.5026651678612354,
|
1225 |
+
"learning_rate": 4.410472765901755e-05,
|
1226 |
+
"loss": 0.6185,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.7,
|
1231 |
+
"grad_norm": 0.5224312932610757,
|
1232 |
+
"learning_rate": 4.302859147358168e-05,
|
1233 |
+
"loss": 0.5824,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.71,
|
1238 |
+
"grad_norm": 0.5178862834267116,
|
1239 |
+
"learning_rate": 4.196213620448723e-05,
|
1240 |
+
"loss": 0.6329,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.71,
|
1245 |
+
"grad_norm": 0.5323664753651522,
|
1246 |
+
"learning_rate": 4.0905543070077036e-05,
|
1247 |
+
"loss": 0.6317,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.71,
|
1252 |
+
"grad_norm": 0.5216091278689122,
|
1253 |
+
"learning_rate": 3.985899161286205e-05,
|
1254 |
+
"loss": 0.6487,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.72,
|
1259 |
+
"grad_norm": 0.4968974338551305,
|
1260 |
+
"learning_rate": 3.882265966901257e-05,
|
1261 |
+
"loss": 0.6692,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.72,
|
1266 |
+
"grad_norm": 0.4904223105734582,
|
1267 |
+
"learning_rate": 3.7796723338138995e-05,
|
1268 |
+
"loss": 0.5781,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.73,
|
1273 |
+
"grad_norm": 0.47447489519607455,
|
1274 |
+
"learning_rate": 3.6781356953368284e-05,
|
1275 |
+
"loss": 0.6254,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.73,
|
1280 |
+
"grad_norm": 0.5197591426247571,
|
1281 |
+
"learning_rate": 3.5776733051719936e-05,
|
1282 |
+
"loss": 0.6023,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.73,
|
1287 |
+
"grad_norm": 0.49832288681418657,
|
1288 |
+
"learning_rate": 3.47830223447877e-05,
|
1289 |
+
"loss": 0.6551,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.74,
|
1294 |
+
"grad_norm": 0.5129531748899837,
|
1295 |
+
"learning_rate": 3.3800393689731146e-05,
|
1296 |
+
"loss": 0.6196,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.74,
|
1301 |
+
"grad_norm": 0.5036518056972021,
|
1302 |
+
"learning_rate": 3.28290140605825e-05,
|
1303 |
+
"loss": 0.6175,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.75,
|
1308 |
+
"grad_norm": 0.480187816135646,
|
1309 |
+
"learning_rate": 3.186904851987351e-05,
|
1310 |
+
"loss": 0.5996,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.75,
|
1315 |
+
"grad_norm": 0.5242700195547425,
|
1316 |
+
"learning_rate": 3.092066019058689e-05,
|
1317 |
+
"loss": 0.61,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.76,
|
1322 |
+
"grad_norm": 0.5152846503044708,
|
1323 |
+
"learning_rate": 2.998401022843761e-05,
|
1324 |
+
"loss": 0.6404,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.76,
|
1329 |
+
"grad_norm": 0.513298219609548,
|
1330 |
+
"learning_rate": 2.9059257794488424e-05,
|
1331 |
+
"loss": 0.557,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.76,
|
1336 |
+
"grad_norm": 0.5021252812027022,
|
1337 |
+
"learning_rate": 2.8146560028104153e-05,
|
1338 |
+
"loss": 0.6634,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.77,
|
1343 |
+
"grad_norm": 0.519800671516665,
|
1344 |
+
"learning_rate": 2.724607202024969e-05,
|
1345 |
+
"loss": 0.6121,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.77,
|
1350 |
+
"grad_norm": 0.5385204988477328,
|
1351 |
+
"learning_rate": 2.6357946787136113e-05,
|
1352 |
+
"loss": 0.6334,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.78,
|
1357 |
+
"grad_norm": 0.4878184839311098,
|
1358 |
+
"learning_rate": 2.548233524421911e-05,
|
1359 |
+
"loss": 0.6267,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.78,
|
1364 |
+
"grad_norm": 0.5220934509633983,
|
1365 |
+
"learning_rate": 2.461938618055478e-05,
|
1366 |
+
"loss": 0.6391,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.78,
|
1371 |
+
"grad_norm": 0.49114273229478017,
|
1372 |
+
"learning_rate": 2.3769246233516242e-05,
|
1373 |
+
"loss": 0.5895,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.79,
|
1378 |
+
"grad_norm": 0.4886291762205353,
|
1379 |
+
"learning_rate": 2.2932059863876365e-05,
|
1380 |
+
"loss": 0.6325,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.79,
|
1385 |
+
"grad_norm": 0.4939232885896318,
|
1386 |
+
"learning_rate": 2.2107969331260048e-05,
|
1387 |
+
"loss": 0.6165,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.8,
|
1392 |
+
"grad_norm": 0.5320372697561206,
|
1393 |
+
"learning_rate": 2.1297114669970618e-05,
|
1394 |
+
"loss": 0.585,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.8,
|
1399 |
+
"grad_norm": 0.4897381232694001,
|
1400 |
+
"learning_rate": 2.049963366519446e-05,
|
1401 |
+
"loss": 0.6132,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.8,
|
1406 |
+
"grad_norm": 0.5063086712780054,
|
1407 |
+
"learning_rate": 1.971566182958765e-05,
|
1408 |
+
"loss": 0.5857,
|
1409 |
+
"step": 200
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.81,
|
1413 |
+
"grad_norm": 0.49709180074211373,
|
1414 |
+
"learning_rate": 1.8945332380248913e-05,
|
1415 |
+
"loss": 0.5934,
|
1416 |
+
"step": 201
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.81,
|
1420 |
+
"grad_norm": 0.5013514907900145,
|
1421 |
+
"learning_rate": 1.8188776216082603e-05,
|
1422 |
+
"loss": 0.6079,
|
1423 |
+
"step": 202
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.82,
|
1427 |
+
"grad_norm": 0.4846234378658167,
|
1428 |
+
"learning_rate": 1.7446121895555555e-05,
|
1429 |
+
"loss": 0.6238,
|
1430 |
+
"step": 203
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.82,
|
1434 |
+
"grad_norm": 0.5159176854303504,
|
1435 |
+
"learning_rate": 1.6717495614851652e-05,
|
1436 |
+
"loss": 0.618,
|
1437 |
+
"step": 204
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.82,
|
1441 |
+
"grad_norm": 0.48388369881041865,
|
1442 |
+
"learning_rate": 1.6003021186427893e-05,
|
1443 |
+
"loss": 0.6115,
|
1444 |
+
"step": 205
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.83,
|
1448 |
+
"grad_norm": 0.4972352579200309,
|
1449 |
+
"learning_rate": 1.5302820017975394e-05,
|
1450 |
+
"loss": 0.6129,
|
1451 |
+
"step": 206
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.83,
|
1455 |
+
"grad_norm": 0.48184028854019717,
|
1456 |
+
"learning_rate": 1.4617011091789135e-05,
|
1457 |
+
"loss": 0.6016,
|
1458 |
+
"step": 207
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.84,
|
1462 |
+
"grad_norm": 0.4693368878966723,
|
1463 |
+
"learning_rate": 1.3945710944549706e-05,
|
1464 |
+
"loss": 0.6055,
|
1465 |
+
"step": 208
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.84,
|
1469 |
+
"grad_norm": 0.49328037858750934,
|
1470 |
+
"learning_rate": 1.3289033647520877e-05,
|
1471 |
+
"loss": 0.5841,
|
1472 |
+
"step": 209
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.84,
|
1476 |
+
"grad_norm": 0.4887185175626592,
|
1477 |
+
"learning_rate": 1.2647090787165694e-05,
|
1478 |
+
"loss": 0.6118,
|
1479 |
+
"step": 210
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.85,
|
1483 |
+
"grad_norm": 0.5275529498494832,
|
1484 |
+
"learning_rate": 1.2019991446185309e-05,
|
1485 |
+
"loss": 0.6056,
|
1486 |
+
"step": 211
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.85,
|
1490 |
+
"grad_norm": 0.5139820604569797,
|
1491 |
+
"learning_rate": 1.1407842184982786e-05,
|
1492 |
+
"loss": 0.6033,
|
1493 |
+
"step": 212
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.86,
|
1497 |
+
"grad_norm": 0.5018443059475605,
|
1498 |
+
"learning_rate": 1.0810747023555878e-05,
|
1499 |
+
"loss": 0.5949,
|
1500 |
+
"step": 213
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.86,
|
1504 |
+
"grad_norm": 0.48214911033187263,
|
1505 |
+
"learning_rate": 1.0228807423821263e-05,
|
1506 |
+
"loss": 0.5889,
|
1507 |
+
"step": 214
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.86,
|
1511 |
+
"grad_norm": 0.48428681987465205,
|
1512 |
+
"learning_rate": 9.662122272373575e-06,
|
1513 |
+
"loss": 0.5819,
|
1514 |
+
"step": 215
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.87,
|
1518 |
+
"grad_norm": 0.528477861467508,
|
1519 |
+
"learning_rate": 9.110787863682002e-06,
|
1520 |
+
"loss": 0.5819,
|
1521 |
+
"step": 216
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.87,
|
1525 |
+
"grad_norm": 0.542081152492008,
|
1526 |
+
"learning_rate": 8.574897883727384e-06,
|
1527 |
+
"loss": 0.6237,
|
1528 |
+
"step": 217
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.88,
|
1532 |
+
"grad_norm": 0.5087137996746921,
|
1533 |
+
"learning_rate": 8.054543394082504e-06,
|
1534 |
+
"loss": 0.6057,
|
1535 |
+
"step": 218
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.88,
|
1539 |
+
"grad_norm": 0.504565281502016,
|
1540 |
+
"learning_rate": 7.5498128164383955e-06,
|
1541 |
+
"loss": 0.5934,
|
1542 |
+
"step": 219
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.88,
|
1546 |
+
"grad_norm": 0.4973612377357542,
|
1547 |
+
"learning_rate": 7.0607919175791796e-06,
|
1548 |
+
"loss": 0.6008,
|
1549 |
+
"step": 220
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.89,
|
1553 |
+
"grad_norm": 0.4569327819305099,
|
1554 |
+
"learning_rate": 6.587563794808127e-06,
|
1555 |
+
"loss": 0.6257,
|
1556 |
+
"step": 221
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.89,
|
1560 |
+
"grad_norm": 0.5013818574659203,
|
1561 |
+
"learning_rate": 6.130208861827202e-06,
|
1562 |
+
"loss": 0.6111,
|
1563 |
+
"step": 222
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.9,
|
1567 |
+
"grad_norm": 0.5396029754257269,
|
1568 |
+
"learning_rate": 5.688804835072748e-06,
|
1569 |
+
"loss": 0.6049,
|
1570 |
+
"step": 223
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.9,
|
1574 |
+
"grad_norm": 0.4941288037270458,
|
1575 |
+
"learning_rate": 5.263426720509468e-06,
|
1576 |
+
"loss": 0.5498,
|
1577 |
+
"step": 224
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.9,
|
1581 |
+
"grad_norm": 0.5221213240498462,
|
1582 |
+
"learning_rate": 4.8541468008849285e-06,
|
1583 |
+
"loss": 0.5939,
|
1584 |
+
"step": 225
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.91,
|
1588 |
+
"grad_norm": 0.5148521707210466,
|
1589 |
+
"learning_rate": 4.461034623446847e-06,
|
1590 |
+
"loss": 0.5773,
|
1591 |
+
"step": 226
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.91,
|
1595 |
+
"grad_norm": 0.4933400691524689,
|
1596 |
+
"learning_rate": 4.084156988125231e-06,
|
1597 |
+
"loss": 0.6078,
|
1598 |
+
"step": 227
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.92,
|
1602 |
+
"grad_norm": 0.4882090112322451,
|
1603 |
+
"learning_rate": 3.723577936181366e-06,
|
1604 |
+
"loss": 0.6044,
|
1605 |
+
"step": 228
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.92,
|
1609 |
+
"grad_norm": 0.4899230526737377,
|
1610 |
+
"learning_rate": 3.3793587393255e-06,
|
1611 |
+
"loss": 0.5841,
|
1612 |
+
"step": 229
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.92,
|
1616 |
+
"grad_norm": 0.48341263558623804,
|
1617 |
+
"learning_rate": 3.0515578893052344e-06,
|
1618 |
+
"loss": 0.5636,
|
1619 |
+
"step": 230
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.93,
|
1623 |
+
"grad_norm": 0.45580749261782566,
|
1624 |
+
"learning_rate": 2.7402310879662497e-06,
|
1625 |
+
"loss": 0.6148,
|
1626 |
+
"step": 231
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.93,
|
1630 |
+
"grad_norm": 0.5090083434022111,
|
1631 |
+
"learning_rate": 2.44543123778711e-06,
|
1632 |
+
"loss": 0.6169,
|
1633 |
+
"step": 232
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.94,
|
1637 |
+
"grad_norm": 0.4909526042662716,
|
1638 |
+
"learning_rate": 2.167208432889789e-06,
|
1639 |
+
"loss": 0.61,
|
1640 |
+
"step": 233
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.94,
|
1644 |
+
"grad_norm": 0.4915614072461919,
|
1645 |
+
"learning_rate": 1.9056099505273427e-06,
|
1646 |
+
"loss": 0.5589,
|
1647 |
+
"step": 234
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.94,
|
1651 |
+
"grad_norm": 0.4967849394301577,
|
1652 |
+
"learning_rate": 1.6606802430503166e-06,
|
1653 |
+
"loss": 0.6148,
|
1654 |
+
"step": 235
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.95,
|
1658 |
+
"grad_norm": 0.49008026008002525,
|
1659 |
+
"learning_rate": 1.43246093035313e-06,
|
1660 |
+
"loss": 0.5432,
|
1661 |
+
"step": 236
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.95,
|
1665 |
+
"grad_norm": 0.47910645199801954,
|
1666 |
+
"learning_rate": 1.2209907928017795e-06,
|
1667 |
+
"loss": 0.6306,
|
1668 |
+
"step": 237
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.96,
|
1672 |
+
"grad_norm": 0.47354206064914267,
|
1673 |
+
"learning_rate": 1.0263057646440199e-06,
|
1674 |
+
"loss": 0.6149,
|
1675 |
+
"step": 238
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.96,
|
1679 |
+
"grad_norm": 0.48080154743346765,
|
1680 |
+
"learning_rate": 8.484389279032834e-07,
|
1681 |
+
"loss": 0.6118,
|
1682 |
+
"step": 239
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.96,
|
1686 |
+
"grad_norm": 0.5000613082596329,
|
1687 |
+
"learning_rate": 6.874205067571083e-07,
|
1688 |
+
"loss": 0.6344,
|
1689 |
+
"step": 240
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.97,
|
1693 |
+
"grad_norm": 0.5161518232153531,
|
1694 |
+
"learning_rate": 5.432778624013257e-07,
|
1695 |
+
"loss": 0.6341,
|
1696 |
+
"step": 241
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.97,
|
1700 |
+
"grad_norm": 0.5360018159046693,
|
1701 |
+
"learning_rate": 4.1603548840062345e-07,
|
1702 |
+
"loss": 0.6191,
|
1703 |
+
"step": 242
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.98,
|
1707 |
+
"grad_norm": 0.5403903928320288,
|
1708 |
+
"learning_rate": 3.0571500652651907e-07,
|
1709 |
+
"loss": 0.6069,
|
1710 |
+
"step": 243
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.98,
|
1714 |
+
"grad_norm": 0.480958206210995,
|
1715 |
+
"learning_rate": 2.1233516308323264e-07,
|
1716 |
+
"loss": 0.6041,
|
1717 |
+
"step": 244
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.98,
|
1721 |
+
"grad_norm": 0.46018947114009656,
|
1722 |
+
"learning_rate": 1.359118257221903e-07,
|
1723 |
+
"loss": 0.5822,
|
1724 |
+
"step": 245
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.99,
|
1728 |
+
"grad_norm": 0.5297015912922861,
|
1729 |
+
"learning_rate": 7.645798074572552e-08,
|
1730 |
+
"loss": 0.6451,
|
1731 |
+
"step": 246
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.99,
|
1735 |
+
"grad_norm": 0.4867081187971182,
|
1736 |
+
"learning_rate": 3.3983730900377655e-08,
|
1737 |
+
"loss": 0.5977,
|
1738 |
+
"step": 247
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 1.0,
|
1742 |
+
"grad_norm": 0.5439247812896818,
|
1743 |
+
"learning_rate": 8.496293660120724e-09,
|
1744 |
+
"loss": 0.659,
|
1745 |
+
"step": 248
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 1.0,
|
1749 |
+
"grad_norm": 0.5183819113313861,
|
1750 |
+
"learning_rate": 0.0,
|
1751 |
+
"loss": 0.5523,
|
1752 |
+
"step": 249
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 1.0,
|
1756 |
+
"step": 249,
|
1757 |
+
"total_flos": 37334311403520.0,
|
1758 |
+
"train_loss": 0.6850855740677401,
|
1759 |
+
"train_runtime": 4182.855,
|
1760 |
+
"train_samples_per_second": 3.802,
|
1761 |
+
"train_steps_per_second": 0.06
|
1762 |
+
}
|
1763 |
+
],
|
1764 |
+
"logging_steps": 1.0,
|
1765 |
+
"max_steps": 249,
|
1766 |
+
"num_input_tokens_seen": 0,
|
1767 |
+
"num_train_epochs": 1,
|
1768 |
+
"save_steps": 50,
|
1769 |
+
"total_flos": 37334311403520.0,
|
1770 |
+
"train_batch_size": 16,
|
1771 |
+
"trial_name": null,
|
1772 |
+
"trial_params": null
|
1773 |
+
}
|