Upload folder using huggingface_hub
Browse files- README.md +202 -3
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +64 -0
- tokenizer.json +0 -0
- tokenizer_config.json +357 -0
- trainer_state.json +2917 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,202 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: bigcode/starcoder2-3b
|
| 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 0.7.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bigcode/starcoder2-3b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 8,
|
| 13 |
+
"lora_dropout": 0.0,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"o_proj",
|
| 24 |
+
"c_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"c_fc"
|
| 28 |
+
],
|
| 29 |
+
"task_type": "CAUSAL_LM"
|
| 30 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61b684788a93ccb03a6350366b0c4089b434a8f744a4f645cb3cae9a2c3c081e
|
| 3 |
+
size 95402480
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a076d8d6995325de081284881685a80b45f414ac3d39e211f3a71af069a7c89a
|
| 3 |
+
size 48178804
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1d77df3252d1d2c6a10fe4f26e4855d797f6e275ac171443cbe5f2b6440ddab
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a32be996797579480b0892803dee53ceea0fc824343dad28e315bb2d27510b94
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<repo_name>",
|
| 9 |
+
"<file_sep>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<jupyter_script>",
|
| 18 |
+
"<empty_output>",
|
| 19 |
+
"<code_to_intermediate>",
|
| 20 |
+
"<intermediate_to_code>",
|
| 21 |
+
"<pr>",
|
| 22 |
+
"<pr_status>",
|
| 23 |
+
"<pr_is_merged>",
|
| 24 |
+
"<pr_base>",
|
| 25 |
+
"<pr_file>",
|
| 26 |
+
"<pr_base_code>",
|
| 27 |
+
"<pr_diff>",
|
| 28 |
+
"<pr_diff_hunk>",
|
| 29 |
+
"<pr_comment>",
|
| 30 |
+
"<pr_event_id>",
|
| 31 |
+
"<pr_review>",
|
| 32 |
+
"<pr_review_state>",
|
| 33 |
+
"<pr_review_comment>",
|
| 34 |
+
"<pr_in_reply_to_review_id>",
|
| 35 |
+
"<pr_in_reply_to_comment_id>",
|
| 36 |
+
"<pr_diff_hunk_comment_line>",
|
| 37 |
+
"<NAME>",
|
| 38 |
+
"<EMAIL>",
|
| 39 |
+
"<KEY>",
|
| 40 |
+
"<PASSWORD>"
|
| 41 |
+
],
|
| 42 |
+
"bos_token": {
|
| 43 |
+
"content": "<|endoftext|>",
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false
|
| 48 |
+
},
|
| 49 |
+
"eos_token": {
|
| 50 |
+
"content": "<|endoftext|>",
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"normalized": false,
|
| 53 |
+
"rstrip": false,
|
| 54 |
+
"single_word": false
|
| 55 |
+
},
|
| 56 |
+
"pad_token": "<|endoftext|>",
|
| 57 |
+
"unk_token": {
|
| 58 |
+
"content": "<|endoftext|>",
|
| 59 |
+
"lstrip": false,
|
| 60 |
+
"normalized": false,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"single_word": false
|
| 63 |
+
}
|
| 64 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<repo_name>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<file_sep>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_script>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<empty_output>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<code_to_intermediate>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<intermediate_to_code>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<pr>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"19": {
|
| 157 |
+
"content": "<pr_status>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"20": {
|
| 165 |
+
"content": "<pr_is_merged>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"21": {
|
| 173 |
+
"content": "<pr_base>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"22": {
|
| 181 |
+
"content": "<pr_file>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"23": {
|
| 189 |
+
"content": "<pr_base_code>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"24": {
|
| 197 |
+
"content": "<pr_diff>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"25": {
|
| 205 |
+
"content": "<pr_diff_hunk>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"26": {
|
| 213 |
+
"content": "<pr_comment>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"27": {
|
| 221 |
+
"content": "<pr_event_id>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"28": {
|
| 229 |
+
"content": "<pr_review>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"29": {
|
| 237 |
+
"content": "<pr_review_state>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"30": {
|
| 245 |
+
"content": "<pr_review_comment>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"31": {
|
| 253 |
+
"content": "<pr_in_reply_to_review_id>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32": {
|
| 261 |
+
"content": "<pr_in_reply_to_comment_id>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"33": {
|
| 269 |
+
"content": "<pr_diff_hunk_comment_line>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"34": {
|
| 277 |
+
"content": "<NAME>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"35": {
|
| 285 |
+
"content": "<EMAIL>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"36": {
|
| 293 |
+
"content": "<KEY>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"37": {
|
| 301 |
+
"content": "<PASSWORD>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
}
|
| 308 |
+
},
|
| 309 |
+
"additional_special_tokens": [
|
| 310 |
+
"<|endoftext|>",
|
| 311 |
+
"<fim_prefix>",
|
| 312 |
+
"<fim_middle>",
|
| 313 |
+
"<fim_suffix>",
|
| 314 |
+
"<fim_pad>",
|
| 315 |
+
"<repo_name>",
|
| 316 |
+
"<file_sep>",
|
| 317 |
+
"<issue_start>",
|
| 318 |
+
"<issue_comment>",
|
| 319 |
+
"<issue_closed>",
|
| 320 |
+
"<jupyter_start>",
|
| 321 |
+
"<jupyter_text>",
|
| 322 |
+
"<jupyter_code>",
|
| 323 |
+
"<jupyter_output>",
|
| 324 |
+
"<jupyter_script>",
|
| 325 |
+
"<empty_output>",
|
| 326 |
+
"<code_to_intermediate>",
|
| 327 |
+
"<intermediate_to_code>",
|
| 328 |
+
"<pr>",
|
| 329 |
+
"<pr_status>",
|
| 330 |
+
"<pr_is_merged>",
|
| 331 |
+
"<pr_base>",
|
| 332 |
+
"<pr_file>",
|
| 333 |
+
"<pr_base_code>",
|
| 334 |
+
"<pr_diff>",
|
| 335 |
+
"<pr_diff_hunk>",
|
| 336 |
+
"<pr_comment>",
|
| 337 |
+
"<pr_event_id>",
|
| 338 |
+
"<pr_review>",
|
| 339 |
+
"<pr_review_state>",
|
| 340 |
+
"<pr_review_comment>",
|
| 341 |
+
"<pr_in_reply_to_review_id>",
|
| 342 |
+
"<pr_in_reply_to_comment_id>",
|
| 343 |
+
"<pr_diff_hunk_comment_line>",
|
| 344 |
+
"<NAME>",
|
| 345 |
+
"<EMAIL>",
|
| 346 |
+
"<KEY>",
|
| 347 |
+
"<PASSWORD>"
|
| 348 |
+
],
|
| 349 |
+
"bos_token": "<|endoftext|>",
|
| 350 |
+
"clean_up_tokenization_spaces": true,
|
| 351 |
+
"eos_token": "<|endoftext|>",
|
| 352 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 353 |
+
"pad_token": "<|endoftext|>",
|
| 354 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 355 |
+
"unk_token": "<|endoftext|>",
|
| 356 |
+
"vocab_size": 49152
|
| 357 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2917 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.7491289198606275,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4125,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013937282229965157,
|
| 13 |
+
"grad_norm": 0.689270555973053,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 3.465,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.027874564459930314,
|
| 20 |
+
"grad_norm": 0.3839555084705353,
|
| 21 |
+
"learning_rate": 2e-05,
|
| 22 |
+
"loss": 3.4261,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.041811846689895474,
|
| 27 |
+
"grad_norm": 0.8513675928115845,
|
| 28 |
+
"learning_rate": 1.9999707152644143e-05,
|
| 29 |
+
"loss": 3.0148,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05574912891986063,
|
| 34 |
+
"grad_norm": 0.5808806419372559,
|
| 35 |
+
"learning_rate": 1.9998828627728483e-05,
|
| 36 |
+
"loss": 2.8815,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06968641114982578,
|
| 41 |
+
"grad_norm": 0.8429257869720459,
|
| 42 |
+
"learning_rate": 1.9997364476707765e-05,
|
| 43 |
+
"loss": 2.4359,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08362369337979095,
|
| 48 |
+
"grad_norm": 9.207444190979004,
|
| 49 |
+
"learning_rate": 1.9995314785336534e-05,
|
| 50 |
+
"loss": 2.3272,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0975609756097561,
|
| 55 |
+
"grad_norm": 0.8501074314117432,
|
| 56 |
+
"learning_rate": 1.9992679673664136e-05,
|
| 57 |
+
"loss": 2.3717,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.11149825783972125,
|
| 62 |
+
"grad_norm": 1.1296913623809814,
|
| 63 |
+
"learning_rate": 1.998945929602766e-05,
|
| 64 |
+
"loss": 1.9401,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1254355400696864,
|
| 69 |
+
"grad_norm": 0.7665435075759888,
|
| 70 |
+
"learning_rate": 1.9985653841042926e-05,
|
| 71 |
+
"loss": 2.0245,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.13937282229965156,
|
| 76 |
+
"grad_norm": 1.1252214908599854,
|
| 77 |
+
"learning_rate": 1.9981263531593422e-05,
|
| 78 |
+
"loss": 1.847,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.15331010452961671,
|
| 83 |
+
"grad_norm": 0.6236267685890198,
|
| 84 |
+
"learning_rate": 1.997628862481725e-05,
|
| 85 |
+
"loss": 1.6229,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1672473867595819,
|
| 90 |
+
"grad_norm": 0.41556432843208313,
|
| 91 |
+
"learning_rate": 1.9970729412092064e-05,
|
| 92 |
+
"loss": 1.6222,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.18118466898954705,
|
| 97 |
+
"grad_norm": 1.1682895421981812,
|
| 98 |
+
"learning_rate": 1.9964586219018018e-05,
|
| 99 |
+
"loss": 1.6162,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1951219512195122,
|
| 104 |
+
"grad_norm": 0.804908037185669,
|
| 105 |
+
"learning_rate": 1.995785940539868e-05,
|
| 106 |
+
"loss": 1.5503,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.20905923344947736,
|
| 111 |
+
"grad_norm": 0.5646180510520935,
|
| 112 |
+
"learning_rate": 1.995054936521997e-05,
|
| 113 |
+
"loss": 1.5357,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2229965156794425,
|
| 118 |
+
"grad_norm": 0.667831301689148,
|
| 119 |
+
"learning_rate": 1.994265652662707e-05,
|
| 120 |
+
"loss": 1.4177,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.23693379790940766,
|
| 125 |
+
"grad_norm": 0.6871632933616638,
|
| 126 |
+
"learning_rate": 1.9934181351899365e-05,
|
| 127 |
+
"loss": 1.4035,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2508710801393728,
|
| 132 |
+
"grad_norm": 0.5316534638404846,
|
| 133 |
+
"learning_rate": 1.9925124337423356e-05,
|
| 134 |
+
"loss": 1.3704,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.26480836236933797,
|
| 139 |
+
"grad_norm": 0.4839189946651459,
|
| 140 |
+
"learning_rate": 1.9915486013663595e-05,
|
| 141 |
+
"loss": 1.2654,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2787456445993031,
|
| 146 |
+
"grad_norm": 0.6332902908325195,
|
| 147 |
+
"learning_rate": 1.99052669451316e-05,
|
| 148 |
+
"loss": 1.341,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2926829268292683,
|
| 153 |
+
"grad_norm": 0.8837312459945679,
|
| 154 |
+
"learning_rate": 1.9894467730352817e-05,
|
| 155 |
+
"loss": 1.2951,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.30662020905923343,
|
| 160 |
+
"grad_norm": 0.5074018239974976,
|
| 161 |
+
"learning_rate": 1.9883089001831545e-05,
|
| 162 |
+
"loss": 1.2118,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3205574912891986,
|
| 167 |
+
"grad_norm": 0.4832253158092499,
|
| 168 |
+
"learning_rate": 1.9871131426013894e-05,
|
| 169 |
+
"loss": 1.1841,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3344947735191638,
|
| 174 |
+
"grad_norm": 0.593585193157196,
|
| 175 |
+
"learning_rate": 1.9858595703248755e-05,
|
| 176 |
+
"loss": 1.1881,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.34843205574912894,
|
| 181 |
+
"grad_norm": 2.605353832244873,
|
| 182 |
+
"learning_rate": 1.9845482567746783e-05,
|
| 183 |
+
"loss": 1.185,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3623693379790941,
|
| 188 |
+
"grad_norm": 0.5042847990989685,
|
| 189 |
+
"learning_rate": 1.983179278753739e-05,
|
| 190 |
+
"loss": 1.1611,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.37630662020905925,
|
| 195 |
+
"grad_norm": 0.5455293655395508,
|
| 196 |
+
"learning_rate": 1.981752716442376e-05,
|
| 197 |
+
"loss": 1.1387,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3902439024390244,
|
| 202 |
+
"grad_norm": 0.5077016949653625,
|
| 203 |
+
"learning_rate": 1.9802686533935903e-05,
|
| 204 |
+
"loss": 1.1303,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.40418118466898956,
|
| 209 |
+
"grad_norm": 1.6482897996902466,
|
| 210 |
+
"learning_rate": 1.9787271765281684e-05,
|
| 211 |
+
"loss": 1.1113,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4181184668989547,
|
| 216 |
+
"grad_norm": 0.706795871257782,
|
| 217 |
+
"learning_rate": 1.9771283761295966e-05,
|
| 218 |
+
"loss": 1.2045,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.43205574912891986,
|
| 223 |
+
"grad_norm": 0.4687112867832184,
|
| 224 |
+
"learning_rate": 1.975472345838768e-05,
|
| 225 |
+
"loss": 1.1115,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.445993031358885,
|
| 230 |
+
"grad_norm": 0.6432089805603027,
|
| 231 |
+
"learning_rate": 1.9737591826485013e-05,
|
| 232 |
+
"loss": 1.0392,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.45993031358885017,
|
| 237 |
+
"grad_norm": 0.5330508351325989,
|
| 238 |
+
"learning_rate": 1.9719889868978582e-05,
|
| 239 |
+
"loss": 1.1082,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4738675958188153,
|
| 244 |
+
"grad_norm": 0.5292240381240845,
|
| 245 |
+
"learning_rate": 1.970161862266268e-05,
|
| 246 |
+
"loss": 1.0845,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4878048780487805,
|
| 251 |
+
"grad_norm": 0.5111907720565796,
|
| 252 |
+
"learning_rate": 1.968277915767454e-05,
|
| 253 |
+
"loss": 1.0763,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5017421602787456,
|
| 258 |
+
"grad_norm": 0.6637840270996094,
|
| 259 |
+
"learning_rate": 1.9663372577431663e-05,
|
| 260 |
+
"loss": 1.0727,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5156794425087108,
|
| 265 |
+
"grad_norm": 0.5857555270195007,
|
| 266 |
+
"learning_rate": 1.9643400018567195e-05,
|
| 267 |
+
"loss": 1.0431,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5296167247386759,
|
| 272 |
+
"grad_norm": 0.4895532429218292,
|
| 273 |
+
"learning_rate": 1.962286265086334e-05,
|
| 274 |
+
"loss": 1.0656,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5435540069686411,
|
| 279 |
+
"grad_norm": 0.4925576448440552,
|
| 280 |
+
"learning_rate": 1.9601761677182868e-05,
|
| 281 |
+
"loss": 1.0581,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5574912891986062,
|
| 286 |
+
"grad_norm": 0.49863460659980774,
|
| 287 |
+
"learning_rate": 1.958009833339865e-05,
|
| 288 |
+
"loss": 1.0236,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5714285714285714,
|
| 293 |
+
"grad_norm": 0.4993515610694885,
|
| 294 |
+
"learning_rate": 1.955787388832127e-05,
|
| 295 |
+
"loss": 1.0382,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5853658536585366,
|
| 300 |
+
"grad_norm": 0.5540180206298828,
|
| 301 |
+
"learning_rate": 1.953508964362473e-05,
|
| 302 |
+
"loss": 1.06,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5993031358885017,
|
| 307 |
+
"grad_norm": 0.47915443778038025,
|
| 308 |
+
"learning_rate": 1.9511746933770186e-05,
|
| 309 |
+
"loss": 1.0793,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6132404181184669,
|
| 314 |
+
"grad_norm": 0.931480348110199,
|
| 315 |
+
"learning_rate": 1.9487847125927814e-05,
|
| 316 |
+
"loss": 1.0125,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.627177700348432,
|
| 321 |
+
"grad_norm": 0.5183358192443848,
|
| 322 |
+
"learning_rate": 1.946339161989672e-05,
|
| 323 |
+
"loss": 0.9963,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6411149825783972,
|
| 328 |
+
"grad_norm": 0.4870765507221222,
|
| 329 |
+
"learning_rate": 1.943838184802296e-05,
|
| 330 |
+
"loss": 1.0556,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6550522648083623,
|
| 335 |
+
"grad_norm": 0.5741175413131714,
|
| 336 |
+
"learning_rate": 1.9412819275115648e-05,
|
| 337 |
+
"loss": 1.0337,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6689895470383276,
|
| 342 |
+
"grad_norm": 6.292229652404785,
|
| 343 |
+
"learning_rate": 1.9386705398361156e-05,
|
| 344 |
+
"loss": 1.0487,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6829268292682927,
|
| 349 |
+
"grad_norm": 0.508897602558136,
|
| 350 |
+
"learning_rate": 1.9360041747235437e-05,
|
| 351 |
+
"loss": 1.0538,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6968641114982579,
|
| 356 |
+
"grad_norm": 2.2197482585906982,
|
| 357 |
+
"learning_rate": 1.9332829883414444e-05,
|
| 358 |
+
"loss": 0.9835,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.710801393728223,
|
| 363 |
+
"grad_norm": 0.5469727516174316,
|
| 364 |
+
"learning_rate": 1.9305071400682644e-05,
|
| 365 |
+
"loss": 1.023,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7247386759581882,
|
| 370 |
+
"grad_norm": 0.5392600297927856,
|
| 371 |
+
"learning_rate": 1.9276767924839687e-05,
|
| 372 |
+
"loss": 0.9832,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7386759581881533,
|
| 377 |
+
"grad_norm": 0.5167688727378845,
|
| 378 |
+
"learning_rate": 1.9247921113605197e-05,
|
| 379 |
+
"loss": 0.9896,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7526132404181185,
|
| 384 |
+
"grad_norm": 0.622711718082428,
|
| 385 |
+
"learning_rate": 1.921853265652164e-05,
|
| 386 |
+
"loss": 0.9443,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7665505226480837,
|
| 391 |
+
"grad_norm": 0.7172455787658691,
|
| 392 |
+
"learning_rate": 1.9188604274855417e-05,
|
| 393 |
+
"loss": 1.0113,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7804878048780488,
|
| 398 |
+
"grad_norm": 0.5286630988121033,
|
| 399 |
+
"learning_rate": 1.9158137721496014e-05,
|
| 400 |
+
"loss": 1.0027,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.794425087108014,
|
| 405 |
+
"grad_norm": 0.531980037689209,
|
| 406 |
+
"learning_rate": 1.9127134780853343e-05,
|
| 407 |
+
"loss": 0.9521,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.8083623693379791,
|
| 412 |
+
"grad_norm": 0.5521572828292847,
|
| 413 |
+
"learning_rate": 1.9095597268753243e-05,
|
| 414 |
+
"loss": 1.006,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8222996515679443,
|
| 419 |
+
"grad_norm": 0.953914999961853,
|
| 420 |
+
"learning_rate": 1.9063527032331128e-05,
|
| 421 |
+
"loss": 0.9401,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8362369337979094,
|
| 426 |
+
"grad_norm": 0.6153273582458496,
|
| 427 |
+
"learning_rate": 1.9030925949923777e-05,
|
| 428 |
+
"loss": 0.9872,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8501742160278746,
|
| 433 |
+
"grad_norm": 0.7658360004425049,
|
| 434 |
+
"learning_rate": 1.899779593095935e-05,
|
| 435 |
+
"loss": 0.9842,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8641114982578397,
|
| 440 |
+
"grad_norm": 0.6273182034492493,
|
| 441 |
+
"learning_rate": 1.896413891584554e-05,
|
| 442 |
+
"loss": 0.9636,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.8780487804878049,
|
| 447 |
+
"grad_norm": 0.5916078090667725,
|
| 448 |
+
"learning_rate": 1.8929956875855913e-05,
|
| 449 |
+
"loss": 0.9845,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.89198606271777,
|
| 454 |
+
"grad_norm": 0.5227757096290588,
|
| 455 |
+
"learning_rate": 1.8895251813014486e-05,
|
| 456 |
+
"loss": 0.9813,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9059233449477352,
|
| 461 |
+
"grad_norm": 0.5434836745262146,
|
| 462 |
+
"learning_rate": 1.8860025759978436e-05,
|
| 463 |
+
"loss": 0.9522,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9198606271777003,
|
| 468 |
+
"grad_norm": 0.48904576897621155,
|
| 469 |
+
"learning_rate": 1.8824280779919055e-05,
|
| 470 |
+
"loss": 0.937,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.9337979094076655,
|
| 475 |
+
"grad_norm": 0.6036517024040222,
|
| 476 |
+
"learning_rate": 1.8788018966400923e-05,
|
| 477 |
+
"loss": 0.9587,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.9477351916376306,
|
| 482 |
+
"grad_norm": 0.5333548188209534,
|
| 483 |
+
"learning_rate": 1.8751242443259286e-05,
|
| 484 |
+
"loss": 0.9564,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9616724738675958,
|
| 489 |
+
"grad_norm": 0.6121916770935059,
|
| 490 |
+
"learning_rate": 1.8713953364475654e-05,
|
| 491 |
+
"loss": 0.9676,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.975609756097561,
|
| 496 |
+
"grad_norm": 0.5846276879310608,
|
| 497 |
+
"learning_rate": 1.8676153914051648e-05,
|
| 498 |
+
"loss": 0.9417,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.9895470383275261,
|
| 503 |
+
"grad_norm": 0.6067516207695007,
|
| 504 |
+
"learning_rate": 1.8637846305881092e-05,
|
| 505 |
+
"loss": 0.9615,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.0034843205574913,
|
| 510 |
+
"grad_norm": 0.4959181547164917,
|
| 511 |
+
"learning_rate": 1.859903278362034e-05,
|
| 512 |
+
"loss": 0.9361,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.0174216027874565,
|
| 517 |
+
"grad_norm": 0.554417073726654,
|
| 518 |
+
"learning_rate": 1.8559715620556865e-05,
|
| 519 |
+
"loss": 0.984,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.0313588850174216,
|
| 524 |
+
"grad_norm": 0.5190228223800659,
|
| 525 |
+
"learning_rate": 1.8519897119476115e-05,
|
| 526 |
+
"loss": 0.9571,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.0452961672473868,
|
| 531 |
+
"grad_norm": 0.5573728680610657,
|
| 532 |
+
"learning_rate": 1.8479579612526642e-05,
|
| 533 |
+
"loss": 0.9324,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.0592334494773519,
|
| 538 |
+
"grad_norm": 0.5803472399711609,
|
| 539 |
+
"learning_rate": 1.8438765461083504e-05,
|
| 540 |
+
"loss": 0.9274,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.0731707317073171,
|
| 545 |
+
"grad_norm": 0.5444169044494629,
|
| 546 |
+
"learning_rate": 1.8397457055609973e-05,
|
| 547 |
+
"loss": 0.9278,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.0871080139372822,
|
| 552 |
+
"grad_norm": 0.5003806352615356,
|
| 553 |
+
"learning_rate": 1.8355656815517505e-05,
|
| 554 |
+
"loss": 0.9392,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.1010452961672474,
|
| 559 |
+
"grad_norm": 1.262714147567749,
|
| 560 |
+
"learning_rate": 1.8313367189024065e-05,
|
| 561 |
+
"loss": 0.9741,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.1149825783972125,
|
| 566 |
+
"grad_norm": 0.8410710692405701,
|
| 567 |
+
"learning_rate": 1.8270590653010706e-05,
|
| 568 |
+
"loss": 0.9815,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.1289198606271778,
|
| 573 |
+
"grad_norm": 0.554559051990509,
|
| 574 |
+
"learning_rate": 1.8227329712876525e-05,
|
| 575 |
+
"loss": 0.9085,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.1428571428571428,
|
| 580 |
+
"grad_norm": 0.5503095388412476,
|
| 581 |
+
"learning_rate": 1.8183586902391905e-05,
|
| 582 |
+
"loss": 0.9034,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.156794425087108,
|
| 587 |
+
"grad_norm": 0.5442657470703125,
|
| 588 |
+
"learning_rate": 1.8139364783550128e-05,
|
| 589 |
+
"loss": 0.9525,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.170731707317073,
|
| 594 |
+
"grad_norm": 0.5207365155220032,
|
| 595 |
+
"learning_rate": 1.8094665946417304e-05,
|
| 596 |
+
"loss": 0.9166,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.1846689895470384,
|
| 601 |
+
"grad_norm": 0.48352962732315063,
|
| 602 |
+
"learning_rate": 1.8049493008980685e-05,
|
| 603 |
+
"loss": 0.9187,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.1986062717770034,
|
| 608 |
+
"grad_norm": 0.4856855869293213,
|
| 609 |
+
"learning_rate": 1.8003848616995333e-05,
|
| 610 |
+
"loss": 0.9226,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.2125435540069687,
|
| 615 |
+
"grad_norm": 4.280817031860352,
|
| 616 |
+
"learning_rate": 1.795773544382915e-05,
|
| 617 |
+
"loss": 0.9301,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.2264808362369337,
|
| 622 |
+
"grad_norm": 0.6370670199394226,
|
| 623 |
+
"learning_rate": 1.7911156190306296e-05,
|
| 624 |
+
"loss": 0.9843,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.240418118466899,
|
| 629 |
+
"grad_norm": 0.7971873879432678,
|
| 630 |
+
"learning_rate": 1.786411358454902e-05,
|
| 631 |
+
"loss": 0.9352,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.254355400696864,
|
| 636 |
+
"grad_norm": 0.6326978802680969,
|
| 637 |
+
"learning_rate": 1.7816610381817864e-05,
|
| 638 |
+
"loss": 0.8951,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.2682926829268293,
|
| 643 |
+
"grad_norm": 0.8231450319290161,
|
| 644 |
+
"learning_rate": 1.776864936435029e-05,
|
| 645 |
+
"loss": 0.9498,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.2822299651567945,
|
| 650 |
+
"grad_norm": 0.4994203746318817,
|
| 651 |
+
"learning_rate": 1.7720233341197726e-05,
|
| 652 |
+
"loss": 0.9127,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.2961672473867596,
|
| 657 |
+
"grad_norm": 0.6145898103713989,
|
| 658 |
+
"learning_rate": 1.7671365148061053e-05,
|
| 659 |
+
"loss": 0.9249,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.3101045296167246,
|
| 664 |
+
"grad_norm": 0.5441964864730835,
|
| 665 |
+
"learning_rate": 1.7622047647124488e-05,
|
| 666 |
+
"loss": 0.9078,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.32404181184669,
|
| 671 |
+
"grad_norm": 0.5940006375312805,
|
| 672 |
+
"learning_rate": 1.757228372688799e-05,
|
| 673 |
+
"loss": 0.8937,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.3379790940766552,
|
| 678 |
+
"grad_norm": 0.6185000538825989,
|
| 679 |
+
"learning_rate": 1.7522076301998048e-05,
|
| 680 |
+
"loss": 0.8922,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.3519163763066202,
|
| 685 |
+
"grad_norm": 0.6179748773574829,
|
| 686 |
+
"learning_rate": 1.7471428313076984e-05,
|
| 687 |
+
"loss": 0.8864,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.3658536585365852,
|
| 692 |
+
"grad_norm": 0.6203311681747437,
|
| 693 |
+
"learning_rate": 1.7420342726550728e-05,
|
| 694 |
+
"loss": 0.9071,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.3797909407665505,
|
| 699 |
+
"grad_norm": 0.4726350009441376,
|
| 700 |
+
"learning_rate": 1.736882253447506e-05,
|
| 701 |
+
"loss": 0.9225,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.3937282229965158,
|
| 706 |
+
"grad_norm": 0.5029098987579346,
|
| 707 |
+
"learning_rate": 1.73168707543604e-05,
|
| 708 |
+
"loss": 0.9036,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.4076655052264808,
|
| 713 |
+
"grad_norm": 0.5293656587600708,
|
| 714 |
+
"learning_rate": 1.726449042899502e-05,
|
| 715 |
+
"loss": 0.9093,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.4216027874564459,
|
| 720 |
+
"grad_norm": 0.5243374109268188,
|
| 721 |
+
"learning_rate": 1.7211684626266887e-05,
|
| 722 |
+
"loss": 0.8831,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.4355400696864111,
|
| 727 |
+
"grad_norm": 0.5120546221733093,
|
| 728 |
+
"learning_rate": 1.7158456438983934e-05,
|
| 729 |
+
"loss": 0.9138,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.4494773519163764,
|
| 734 |
+
"grad_norm": 0.4908638596534729,
|
| 735 |
+
"learning_rate": 1.7104808984692946e-05,
|
| 736 |
+
"loss": 0.9152,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.4634146341463414,
|
| 741 |
+
"grad_norm": 0.5942572951316833,
|
| 742 |
+
"learning_rate": 1.705074540549695e-05,
|
| 743 |
+
"loss": 0.9535,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.4773519163763067,
|
| 748 |
+
"grad_norm": 0.6341879367828369,
|
| 749 |
+
"learning_rate": 1.699626886787119e-05,
|
| 750 |
+
"loss": 0.9506,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.4912891986062717,
|
| 755 |
+
"grad_norm": 0.49885329604148865,
|
| 756 |
+
"learning_rate": 1.6941382562477664e-05,
|
| 757 |
+
"loss": 0.9313,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.505226480836237,
|
| 762 |
+
"grad_norm": 0.5285991430282593,
|
| 763 |
+
"learning_rate": 1.688608970397825e-05,
|
| 764 |
+
"loss": 0.9164,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.519163763066202,
|
| 769 |
+
"grad_norm": 0.5937536358833313,
|
| 770 |
+
"learning_rate": 1.683039353084644e-05,
|
| 771 |
+
"loss": 0.8853,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.533101045296167,
|
| 776 |
+
"grad_norm": 0.5034327507019043,
|
| 777 |
+
"learning_rate": 1.677429730517763e-05,
|
| 778 |
+
"loss": 0.9081,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.5470383275261324,
|
| 783 |
+
"grad_norm": 0.48388397693634033,
|
| 784 |
+
"learning_rate": 1.67178043124981e-05,
|
| 785 |
+
"loss": 0.8786,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.5609756097560976,
|
| 790 |
+
"grad_norm": 0.6228198409080505,
|
| 791 |
+
"learning_rate": 1.666091786157255e-05,
|
| 792 |
+
"loss": 0.8607,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.5749128919860627,
|
| 797 |
+
"grad_norm": 0.4986213147640228,
|
| 798 |
+
"learning_rate": 1.6603641284210335e-05,
|
| 799 |
+
"loss": 0.8904,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.588850174216028,
|
| 804 |
+
"grad_norm": 0.4710678458213806,
|
| 805 |
+
"learning_rate": 1.6545977935070293e-05,
|
| 806 |
+
"loss": 0.8807,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.6027874564459932,
|
| 811 |
+
"grad_norm": 0.5493403673171997,
|
| 812 |
+
"learning_rate": 1.6487931191464293e-05,
|
| 813 |
+
"loss": 0.9389,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.6167247386759582,
|
| 818 |
+
"grad_norm": 0.5593530535697937,
|
| 819 |
+
"learning_rate": 1.642950445315941e-05,
|
| 820 |
+
"loss": 0.9294,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.6306620209059233,
|
| 825 |
+
"grad_norm": 0.5576480031013489,
|
| 826 |
+
"learning_rate": 1.6370701142178815e-05,
|
| 827 |
+
"loss": 0.8685,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.6445993031358885,
|
| 832 |
+
"grad_norm": 0.5916953682899475,
|
| 833 |
+
"learning_rate": 1.6311524702601328e-05,
|
| 834 |
+
"loss": 0.8794,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.6585365853658538,
|
| 839 |
+
"grad_norm": 0.49112585186958313,
|
| 840 |
+
"learning_rate": 1.6251978600359727e-05,
|
| 841 |
+
"loss": 0.8893,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.6724738675958188,
|
| 846 |
+
"grad_norm": 0.606788694858551,
|
| 847 |
+
"learning_rate": 1.6192066323037723e-05,
|
| 848 |
+
"loss": 0.9162,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.6864111498257839,
|
| 853 |
+
"grad_norm": 0.5515270829200745,
|
| 854 |
+
"learning_rate": 1.613179137966572e-05,
|
| 855 |
+
"loss": 0.9027,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.7003484320557491,
|
| 860 |
+
"grad_norm": 0.51644366979599,
|
| 861 |
+
"learning_rate": 1.6071157300515274e-05,
|
| 862 |
+
"loss": 0.9218,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.7142857142857144,
|
| 867 |
+
"grad_norm": 0.48575639724731445,
|
| 868 |
+
"learning_rate": 1.6010167636892338e-05,
|
| 869 |
+
"loss": 0.9032,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.7282229965156795,
|
| 874 |
+
"grad_norm": 0.5278819799423218,
|
| 875 |
+
"learning_rate": 1.594882596092926e-05,
|
| 876 |
+
"loss": 0.9159,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.7421602787456445,
|
| 881 |
+
"grad_norm": 0.554883599281311,
|
| 882 |
+
"learning_rate": 1.5887135865375552e-05,
|
| 883 |
+
"loss": 0.9046,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.7560975609756098,
|
| 888 |
+
"grad_norm": 0.5662369728088379,
|
| 889 |
+
"learning_rate": 1.58251009633875e-05,
|
| 890 |
+
"loss": 0.8528,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.770034843205575,
|
| 895 |
+
"grad_norm": 0.6568381786346436,
|
| 896 |
+
"learning_rate": 1.57627248883165e-05,
|
| 897 |
+
"loss": 0.8885,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.78397212543554,
|
| 902 |
+
"grad_norm": 0.7277708649635315,
|
| 903 |
+
"learning_rate": 1.5700011293496285e-05,
|
| 904 |
+
"loss": 0.9159,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.797909407665505,
|
| 909 |
+
"grad_norm": 0.5788251161575317,
|
| 910 |
+
"learning_rate": 1.5636963852028936e-05,
|
| 911 |
+
"loss": 0.9036,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.8118466898954704,
|
| 916 |
+
"grad_norm": 0.5556735396385193,
|
| 917 |
+
"learning_rate": 1.557358625656976e-05,
|
| 918 |
+
"loss": 0.9155,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.8257839721254356,
|
| 923 |
+
"grad_norm": 0.4880397319793701,
|
| 924 |
+
"learning_rate": 1.550988221911101e-05,
|
| 925 |
+
"loss": 0.8849,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.8397212543554007,
|
| 930 |
+
"grad_norm": 0.6523249745368958,
|
| 931 |
+
"learning_rate": 1.5445855470764467e-05,
|
| 932 |
+
"loss": 0.8644,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.8536585365853657,
|
| 937 |
+
"grad_norm": 0.8619920015335083,
|
| 938 |
+
"learning_rate": 1.5381509761542925e-05,
|
| 939 |
+
"loss": 0.9073,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.867595818815331,
|
| 944 |
+
"grad_norm": 0.6176061034202576,
|
| 945 |
+
"learning_rate": 1.5316848860140545e-05,
|
| 946 |
+
"loss": 0.877,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.8815331010452963,
|
| 951 |
+
"grad_norm": 0.49368295073509216,
|
| 952 |
+
"learning_rate": 1.5251876553712129e-05,
|
| 953 |
+
"loss": 0.8854,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.8954703832752613,
|
| 958 |
+
"grad_norm": 0.6543199419975281,
|
| 959 |
+
"learning_rate": 1.5186596647651299e-05,
|
| 960 |
+
"loss": 0.883,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.9094076655052263,
|
| 965 |
+
"grad_norm": 0.568365216255188,
|
| 966 |
+
"learning_rate": 1.512101296536764e-05,
|
| 967 |
+
"loss": 0.9144,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.9233449477351916,
|
| 972 |
+
"grad_norm": 0.5592637062072754,
|
| 973 |
+
"learning_rate": 1.5055129348062733e-05,
|
| 974 |
+
"loss": 0.8869,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.9372822299651569,
|
| 979 |
+
"grad_norm": 0.642049252986908,
|
| 980 |
+
"learning_rate": 1.4988949654505212e-05,
|
| 981 |
+
"loss": 0.9268,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.951219512195122,
|
| 986 |
+
"grad_norm": 0.8612108826637268,
|
| 987 |
+
"learning_rate": 1.492247776080472e-05,
|
| 988 |
+
"loss": 0.9231,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.965156794425087,
|
| 993 |
+
"grad_norm": 0.5690594911575317,
|
| 994 |
+
"learning_rate": 1.4855717560184925e-05,
|
| 995 |
+
"loss": 0.8862,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.9790940766550522,
|
| 1000 |
+
"grad_norm": 0.5545530915260315,
|
| 1001 |
+
"learning_rate": 1.4788672962755474e-05,
|
| 1002 |
+
"loss": 0.8777,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.9930313588850175,
|
| 1007 |
+
"grad_norm": 0.5686807036399841,
|
| 1008 |
+
"learning_rate": 1.4721347895282977e-05,
|
| 1009 |
+
"loss": 0.867,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.0069686411149825,
|
| 1014 |
+
"grad_norm": 0.49507030844688416,
|
| 1015 |
+
"learning_rate": 1.4653746300961037e-05,
|
| 1016 |
+
"loss": 0.8879,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.0209059233449476,
|
| 1021 |
+
"grad_norm": 0.5000828504562378,
|
| 1022 |
+
"learning_rate": 1.4585872139179284e-05,
|
| 1023 |
+
"loss": 0.8951,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.034843205574913,
|
| 1028 |
+
"grad_norm": 0.5445813536643982,
|
| 1029 |
+
"learning_rate": 1.4517729385291479e-05,
|
| 1030 |
+
"loss": 0.8741,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.048780487804878,
|
| 1035 |
+
"grad_norm": 0.5599672198295593,
|
| 1036 |
+
"learning_rate": 1.4449322030382681e-05,
|
| 1037 |
+
"loss": 0.8956,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.062717770034843,
|
| 1042 |
+
"grad_norm": 0.579526424407959,
|
| 1043 |
+
"learning_rate": 1.4380654081035492e-05,
|
| 1044 |
+
"loss": 0.8655,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.076655052264808,
|
| 1049 |
+
"grad_norm": 0.5371329188346863,
|
| 1050 |
+
"learning_rate": 1.4311729559095391e-05,
|
| 1051 |
+
"loss": 0.8916,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.0905923344947737,
|
| 1056 |
+
"grad_norm": 0.5372903943061829,
|
| 1057 |
+
"learning_rate": 1.424255250143518e-05,
|
| 1058 |
+
"loss": 0.9006,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.1045296167247387,
|
| 1063 |
+
"grad_norm": 0.5461590886116028,
|
| 1064 |
+
"learning_rate": 1.4173126959718542e-05,
|
| 1065 |
+
"loss": 0.8981,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.1184668989547037,
|
| 1070 |
+
"grad_norm": 0.5336124897003174,
|
| 1071 |
+
"learning_rate": 1.410345700016274e-05,
|
| 1072 |
+
"loss": 0.8979,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.132404181184669,
|
| 1077 |
+
"grad_norm": 0.512737512588501,
|
| 1078 |
+
"learning_rate": 1.4033546703300465e-05,
|
| 1079 |
+
"loss": 0.8549,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.1463414634146343,
|
| 1084 |
+
"grad_norm": 0.5914519429206848,
|
| 1085 |
+
"learning_rate": 1.3963400163740828e-05,
|
| 1086 |
+
"loss": 0.8807,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.1602787456445993,
|
| 1091 |
+
"grad_norm": 0.6203148365020752,
|
| 1092 |
+
"learning_rate": 1.3893021489929564e-05,
|
| 1093 |
+
"loss": 0.9025,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.1742160278745644,
|
| 1098 |
+
"grad_norm": 0.47906365990638733,
|
| 1099 |
+
"learning_rate": 1.382241480390837e-05,
|
| 1100 |
+
"loss": 0.9091,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.1881533101045294,
|
| 1105 |
+
"grad_norm": 1.1542456150054932,
|
| 1106 |
+
"learning_rate": 1.3751584241073517e-05,
|
| 1107 |
+
"loss": 0.8571,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.202090592334495,
|
| 1112 |
+
"grad_norm": 0.778533935546875,
|
| 1113 |
+
"learning_rate": 1.3680533949933607e-05,
|
| 1114 |
+
"loss": 0.8534,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.21602787456446,
|
| 1119 |
+
"grad_norm": 0.5771265625953674,
|
| 1120 |
+
"learning_rate": 1.3609268091866621e-05,
|
| 1121 |
+
"loss": 0.8709,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.229965156794425,
|
| 1126 |
+
"grad_norm": 0.5153730511665344,
|
| 1127 |
+
"learning_rate": 1.3537790840876179e-05,
|
| 1128 |
+
"loss": 0.8865,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.2439024390243905,
|
| 1133 |
+
"grad_norm": 0.5823934674263,
|
| 1134 |
+
"learning_rate": 1.346610638334707e-05,
|
| 1135 |
+
"loss": 0.8608,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.2578397212543555,
|
| 1140 |
+
"grad_norm": 0.4887414872646332,
|
| 1141 |
+
"learning_rate": 1.3394218917800064e-05,
|
| 1142 |
+
"loss": 0.8661,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.2717770034843205,
|
| 1147 |
+
"grad_norm": 0.5397761464118958,
|
| 1148 |
+
"learning_rate": 1.3322132654646003e-05,
|
| 1149 |
+
"loss": 0.8719,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.2857142857142856,
|
| 1154 |
+
"grad_norm": 0.7656607627868652,
|
| 1155 |
+
"learning_rate": 1.3249851815939197e-05,
|
| 1156 |
+
"loss": 0.8857,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.2996515679442506,
|
| 1161 |
+
"grad_norm": 0.5524553060531616,
|
| 1162 |
+
"learning_rate": 1.3177380635130144e-05,
|
| 1163 |
+
"loss": 0.8957,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.313588850174216,
|
| 1168 |
+
"grad_norm": 0.7648917436599731,
|
| 1169 |
+
"learning_rate": 1.3104723356817582e-05,
|
| 1170 |
+
"loss": 0.8746,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.327526132404181,
|
| 1175 |
+
"grad_norm": 0.696306049823761,
|
| 1176 |
+
"learning_rate": 1.3031884236499877e-05,
|
| 1177 |
+
"loss": 0.8732,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.341463414634146,
|
| 1182 |
+
"grad_norm": 0.5518249273300171,
|
| 1183 |
+
"learning_rate": 1.2958867540325785e-05,
|
| 1184 |
+
"loss": 0.8641,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.3554006968641117,
|
| 1189 |
+
"grad_norm": 0.5839936137199402,
|
| 1190 |
+
"learning_rate": 1.2885677544844592e-05,
|
| 1191 |
+
"loss": 0.8317,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.3693379790940767,
|
| 1196 |
+
"grad_norm": 0.5415021777153015,
|
| 1197 |
+
"learning_rate": 1.2812318536755624e-05,
|
| 1198 |
+
"loss": 0.8815,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.3832752613240418,
|
| 1203 |
+
"grad_norm": 0.5816763639450073,
|
| 1204 |
+
"learning_rate": 1.2738794812657194e-05,
|
| 1205 |
+
"loss": 0.8682,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.397212543554007,
|
| 1210 |
+
"grad_norm": 0.5739949941635132,
|
| 1211 |
+
"learning_rate": 1.266511067879494e-05,
|
| 1212 |
+
"loss": 0.8928,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.4111498257839723,
|
| 1217 |
+
"grad_norm": 0.5285424590110779,
|
| 1218 |
+
"learning_rate": 1.2591270450809612e-05,
|
| 1219 |
+
"loss": 0.9042,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.4250871080139373,
|
| 1224 |
+
"grad_norm": 0.67451012134552,
|
| 1225 |
+
"learning_rate": 1.251727845348432e-05,
|
| 1226 |
+
"loss": 0.9084,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.4390243902439024,
|
| 1231 |
+
"grad_norm": 0.6238117218017578,
|
| 1232 |
+
"learning_rate": 1.2443139020491216e-05,
|
| 1233 |
+
"loss": 0.8828,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.4529616724738674,
|
| 1238 |
+
"grad_norm": 0.527727484703064,
|
| 1239 |
+
"learning_rate": 1.236885649413768e-05,
|
| 1240 |
+
"loss": 0.8348,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.466898954703833,
|
| 1245 |
+
"grad_norm": 0.6208236813545227,
|
| 1246 |
+
"learning_rate": 1.2294435225112005e-05,
|
| 1247 |
+
"loss": 0.8976,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.480836236933798,
|
| 1252 |
+
"grad_norm": 0.6415792107582092,
|
| 1253 |
+
"learning_rate": 1.2219879572228555e-05,
|
| 1254 |
+
"loss": 0.853,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.494773519163763,
|
| 1259 |
+
"grad_norm": 0.5672902464866638,
|
| 1260 |
+
"learning_rate": 1.2145193902172496e-05,
|
| 1261 |
+
"loss": 0.8624,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.508710801393728,
|
| 1266 |
+
"grad_norm": 0.5251675248146057,
|
| 1267 |
+
"learning_rate": 1.2070382589244026e-05,
|
| 1268 |
+
"loss": 0.8919,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.5226480836236935,
|
| 1273 |
+
"grad_norm": 0.6049728989601135,
|
| 1274 |
+
"learning_rate": 1.199545001510218e-05,
|
| 1275 |
+
"loss": 0.8417,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.5365853658536586,
|
| 1280 |
+
"grad_norm": 0.5997565984725952,
|
| 1281 |
+
"learning_rate": 1.1920400568508201e-05,
|
| 1282 |
+
"loss": 0.8831,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.5505226480836236,
|
| 1287 |
+
"grad_norm": 0.5272901058197021,
|
| 1288 |
+
"learning_rate": 1.184523864506849e-05,
|
| 1289 |
+
"loss": 0.8773,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.564459930313589,
|
| 1294 |
+
"grad_norm": 0.567862331867218,
|
| 1295 |
+
"learning_rate": 1.1769968646977148e-05,
|
| 1296 |
+
"loss": 0.8595,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.578397212543554,
|
| 1301 |
+
"grad_norm": 0.5373286008834839,
|
| 1302 |
+
"learning_rate": 1.1694594982758164e-05,
|
| 1303 |
+
"loss": 0.8896,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.592334494773519,
|
| 1308 |
+
"grad_norm": 0.5112028121948242,
|
| 1309 |
+
"learning_rate": 1.161912206700719e-05,
|
| 1310 |
+
"loss": 0.8882,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.6062717770034842,
|
| 1315 |
+
"grad_norm": 0.4764540493488312,
|
| 1316 |
+
"learning_rate": 1.154355432013299e-05,
|
| 1317 |
+
"loss": 0.8381,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.6202090592334493,
|
| 1322 |
+
"grad_norm": 0.7286739349365234,
|
| 1323 |
+
"learning_rate": 1.1467896168098533e-05,
|
| 1324 |
+
"loss": 0.8502,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.6341463414634148,
|
| 1329 |
+
"grad_norm": 0.5751617550849915,
|
| 1330 |
+
"learning_rate": 1.1392152042161774e-05,
|
| 1331 |
+
"loss": 0.8631,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.64808362369338,
|
| 1336 |
+
"grad_norm": 0.5550952553749084,
|
| 1337 |
+
"learning_rate": 1.1316326378616121e-05,
|
| 1338 |
+
"loss": 0.9055,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.662020905923345,
|
| 1343 |
+
"grad_norm": 0.5390698909759521,
|
| 1344 |
+
"learning_rate": 1.1240423618530578e-05,
|
| 1345 |
+
"loss": 0.8586,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.6759581881533103,
|
| 1350 |
+
"grad_norm": 0.5401940941810608,
|
| 1351 |
+
"learning_rate": 1.1164448207489673e-05,
|
| 1352 |
+
"loss": 0.873,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.6898954703832754,
|
| 1357 |
+
"grad_norm": 0.7127025723457336,
|
| 1358 |
+
"learning_rate": 1.1088404595333046e-05,
|
| 1359 |
+
"loss": 0.8753,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.7038327526132404,
|
| 1364 |
+
"grad_norm": 0.6411701440811157,
|
| 1365 |
+
"learning_rate": 1.101229723589485e-05,
|
| 1366 |
+
"loss": 0.8814,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.7177700348432055,
|
| 1371 |
+
"grad_norm": 0.5122844576835632,
|
| 1372 |
+
"learning_rate": 1.0936130586742881e-05,
|
| 1373 |
+
"loss": 0.8509,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.7317073170731705,
|
| 1378 |
+
"grad_norm": 2.784543514251709,
|
| 1379 |
+
"learning_rate": 1.0859909108917497e-05,
|
| 1380 |
+
"loss": 0.8112,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.745644599303136,
|
| 1385 |
+
"grad_norm": 0.533532977104187,
|
| 1386 |
+
"learning_rate": 1.0783637266670348e-05,
|
| 1387 |
+
"loss": 0.8479,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.759581881533101,
|
| 1392 |
+
"grad_norm": 0.5365408062934875,
|
| 1393 |
+
"learning_rate": 1.0707319527202902e-05,
|
| 1394 |
+
"loss": 0.8281,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.773519163763066,
|
| 1399 |
+
"grad_norm": 0.45295801758766174,
|
| 1400 |
+
"learning_rate": 1.0630960360404793e-05,
|
| 1401 |
+
"loss": 0.9046,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.7874564459930316,
|
| 1406 |
+
"grad_norm": 0.656039834022522,
|
| 1407 |
+
"learning_rate": 1.0554564238592051e-05,
|
| 1408 |
+
"loss": 0.8305,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.8013937282229966,
|
| 1413 |
+
"grad_norm": 0.5675934553146362,
|
| 1414 |
+
"learning_rate": 1.0478135636245122e-05,
|
| 1415 |
+
"loss": 0.8633,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.8153310104529616,
|
| 1420 |
+
"grad_norm": 0.5480667948722839,
|
| 1421 |
+
"learning_rate": 1.0401679029746828e-05,
|
| 1422 |
+
"loss": 0.8756,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.8292682926829267,
|
| 1427 |
+
"grad_norm": 0.5900964736938477,
|
| 1428 |
+
"learning_rate": 1.0325198897120183e-05,
|
| 1429 |
+
"loss": 0.8737,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.8432055749128917,
|
| 1434 |
+
"grad_norm": 0.688490092754364,
|
| 1435 |
+
"learning_rate": 1.0248699717766107e-05,
|
| 1436 |
+
"loss": 0.8425,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.857142857142857,
|
| 1441 |
+
"grad_norm": 0.5785161256790161,
|
| 1442 |
+
"learning_rate": 1.0172185972201082e-05,
|
| 1443 |
+
"loss": 0.902,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.8710801393728222,
|
| 1448 |
+
"grad_norm": 0.5259153246879578,
|
| 1449 |
+
"learning_rate": 1.0095662141794725e-05,
|
| 1450 |
+
"loss": 0.8793,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.8850174216027873,
|
| 1455 |
+
"grad_norm": 0.5888857841491699,
|
| 1456 |
+
"learning_rate": 1.0019132708507307e-05,
|
| 1457 |
+
"loss": 0.8665,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.8989547038327528,
|
| 1462 |
+
"grad_norm": 0.6237362027168274,
|
| 1463 |
+
"learning_rate": 9.94260215462727e-06,
|
| 1464 |
+
"loss": 0.8647,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.912891986062718,
|
| 1469 |
+
"grad_norm": 0.5640315413475037,
|
| 1470 |
+
"learning_rate": 9.866074962508684e-06,
|
| 1471 |
+
"loss": 0.8659,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.926829268292683,
|
| 1476 |
+
"grad_norm": 0.4334649443626404,
|
| 1477 |
+
"learning_rate": 9.789555614308721e-06,
|
| 1478 |
+
"loss": 0.8566,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.940766550522648,
|
| 1483 |
+
"grad_norm": 0.5068169832229614,
|
| 1484 |
+
"learning_rate": 9.713048591725138e-06,
|
| 1485 |
+
"loss": 0.8712,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.9547038327526134,
|
| 1490 |
+
"grad_norm": 0.5684682726860046,
|
| 1491 |
+
"learning_rate": 9.63655837573379e-06,
|
| 1492 |
+
"loss": 0.8217,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.9686411149825784,
|
| 1497 |
+
"grad_norm": 0.6925583481788635,
|
| 1498 |
+
"learning_rate": 9.560089446326175e-06,
|
| 1499 |
+
"loss": 0.8675,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.9825783972125435,
|
| 1504 |
+
"grad_norm": 0.7573685050010681,
|
| 1505 |
+
"learning_rate": 9.483646282247056e-06,
|
| 1506 |
+
"loss": 0.8369,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.996515679442509,
|
| 1511 |
+
"grad_norm": 0.598778486251831,
|
| 1512 |
+
"learning_rate": 9.407233360732119e-06,
|
| 1513 |
+
"loss": 0.8434,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 3.010452961672474,
|
| 1518 |
+
"grad_norm": 114.71971893310547,
|
| 1519 |
+
"learning_rate": 9.330855157245776e-06,
|
| 1520 |
+
"loss": 0.8841,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 3.024390243902439,
|
| 1525 |
+
"grad_norm": 0.5424976348876953,
|
| 1526 |
+
"learning_rate": 9.254516145219006e-06,
|
| 1527 |
+
"loss": 0.8653,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 3.038327526132404,
|
| 1532 |
+
"grad_norm": 0.48183199763298035,
|
| 1533 |
+
"learning_rate": 9.17822079578738e-06,
|
| 1534 |
+
"loss": 0.8402,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 3.052264808362369,
|
| 1539 |
+
"grad_norm": 0.5667704343795776,
|
| 1540 |
+
"learning_rate": 9.101973577529164e-06,
|
| 1541 |
+
"loss": 0.8357,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 3.0662020905923346,
|
| 1546 |
+
"grad_norm": 0.5843963027000427,
|
| 1547 |
+
"learning_rate": 9.025778956203611e-06,
|
| 1548 |
+
"loss": 0.8538,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 3.0801393728222997,
|
| 1553 |
+
"grad_norm": 0.5097166895866394,
|
| 1554 |
+
"learning_rate": 8.949641394489399e-06,
|
| 1555 |
+
"loss": 0.8208,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 3.0940766550522647,
|
| 1560 |
+
"grad_norm": 0.5178412795066833,
|
| 1561 |
+
"learning_rate": 8.873565351723249e-06,
|
| 1562 |
+
"loss": 0.9026,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 3.10801393728223,
|
| 1567 |
+
"grad_norm": 0.6717800498008728,
|
| 1568 |
+
"learning_rate": 8.79755528363876e-06,
|
| 1569 |
+
"loss": 0.8002,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 3.1219512195121952,
|
| 1574 |
+
"grad_norm": 0.81369549036026,
|
| 1575 |
+
"learning_rate": 8.721615642105417e-06,
|
| 1576 |
+
"loss": 0.8757,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 3.1358885017421603,
|
| 1581 |
+
"grad_norm": 0.574155867099762,
|
| 1582 |
+
"learning_rate": 8.645750874867876e-06,
|
| 1583 |
+
"loss": 0.8411,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 3.1498257839721253,
|
| 1588 |
+
"grad_norm": 0.4896714985370636,
|
| 1589 |
+
"learning_rate": 8.56996542528542e-06,
|
| 1590 |
+
"loss": 0.8671,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 3.1637630662020904,
|
| 1595 |
+
"grad_norm": 0.5032427906990051,
|
| 1596 |
+
"learning_rate": 8.494263732071772e-06,
|
| 1597 |
+
"loss": 0.8521,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 3.177700348432056,
|
| 1602 |
+
"grad_norm": 0.5645169615745544,
|
| 1603 |
+
"learning_rate": 8.418650229035054e-06,
|
| 1604 |
+
"loss": 0.8407,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 3.191637630662021,
|
| 1609 |
+
"grad_norm": 0.5049313306808472,
|
| 1610 |
+
"learning_rate": 8.343129344818162e-06,
|
| 1611 |
+
"loss": 0.853,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 3.205574912891986,
|
| 1616 |
+
"grad_norm": 0.5244989991188049,
|
| 1617 |
+
"learning_rate": 8.267705502639342e-06,
|
| 1618 |
+
"loss": 0.8546,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 3.2195121951219514,
|
| 1623 |
+
"grad_norm": 0.6323722004890442,
|
| 1624 |
+
"learning_rate": 8.192383120033147e-06,
|
| 1625 |
+
"loss": 0.8408,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 3.2334494773519165,
|
| 1630 |
+
"grad_norm": 0.5894546508789062,
|
| 1631 |
+
"learning_rate": 8.117166608591693e-06,
|
| 1632 |
+
"loss": 0.865,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 3.2473867595818815,
|
| 1637 |
+
"grad_norm": 1.284786343574524,
|
| 1638 |
+
"learning_rate": 8.042060373706275e-06,
|
| 1639 |
+
"loss": 0.8596,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 3.2613240418118465,
|
| 1644 |
+
"grad_norm": 0.5084718465805054,
|
| 1645 |
+
"learning_rate": 7.967068814309359e-06,
|
| 1646 |
+
"loss": 0.8377,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 3.275261324041812,
|
| 1651 |
+
"grad_norm": 0.5845734477043152,
|
| 1652 |
+
"learning_rate": 7.892196322616912e-06,
|
| 1653 |
+
"loss": 0.8597,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 3.289198606271777,
|
| 1658 |
+
"grad_norm": 0.5465214252471924,
|
| 1659 |
+
"learning_rate": 7.817447283871187e-06,
|
| 1660 |
+
"loss": 0.8584,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 3.303135888501742,
|
| 1665 |
+
"grad_norm": 0.5865809917449951,
|
| 1666 |
+
"learning_rate": 7.742826076083848e-06,
|
| 1667 |
+
"loss": 0.843,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 3.317073170731707,
|
| 1672 |
+
"grad_norm": 0.455839604139328,
|
| 1673 |
+
"learning_rate": 7.668337069779577e-06,
|
| 1674 |
+
"loss": 0.8599,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 3.3310104529616726,
|
| 1679 |
+
"grad_norm": 0.48517608642578125,
|
| 1680 |
+
"learning_rate": 7.593984627740075e-06,
|
| 1681 |
+
"loss": 0.8592,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 3.3449477351916377,
|
| 1686 |
+
"grad_norm": 0.5980703830718994,
|
| 1687 |
+
"learning_rate": 7.519773104748562e-06,
|
| 1688 |
+
"loss": 0.8673,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 3.3588850174216027,
|
| 1693 |
+
"grad_norm": 0.5855985879898071,
|
| 1694 |
+
"learning_rate": 7.4457068473346836e-06,
|
| 1695 |
+
"loss": 0.8518,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 3.3728222996515678,
|
| 1700 |
+
"grad_norm": 0.4601869583129883,
|
| 1701 |
+
"learning_rate": 7.371790193519979e-06,
|
| 1702 |
+
"loss": 0.8457,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 3.3867595818815333,
|
| 1707 |
+
"grad_norm": 0.5327535271644592,
|
| 1708 |
+
"learning_rate": 7.298027472563768e-06,
|
| 1709 |
+
"loss": 0.8373,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 3.4006968641114983,
|
| 1714 |
+
"grad_norm": 0.5465139746665955,
|
| 1715 |
+
"learning_rate": 7.224423004709607e-06,
|
| 1716 |
+
"loss": 0.8515,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 3.4146341463414633,
|
| 1721 |
+
"grad_norm": 0.5567154884338379,
|
| 1722 |
+
"learning_rate": 7.1509811009322574e-06,
|
| 1723 |
+
"loss": 0.8541,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 3.4285714285714284,
|
| 1728 |
+
"grad_norm": 0.5773440599441528,
|
| 1729 |
+
"learning_rate": 7.077706062685181e-06,
|
| 1730 |
+
"loss": 0.849,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 3.442508710801394,
|
| 1735 |
+
"grad_norm": 0.5186436176300049,
|
| 1736 |
+
"learning_rate": 7.004602181648626e-06,
|
| 1737 |
+
"loss": 0.8857,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 3.456445993031359,
|
| 1742 |
+
"grad_norm": 0.647905707359314,
|
| 1743 |
+
"learning_rate": 6.931673739478235e-06,
|
| 1744 |
+
"loss": 0.8486,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 3.470383275261324,
|
| 1749 |
+
"grad_norm": 0.7109155058860779,
|
| 1750 |
+
"learning_rate": 6.858925007554308e-06,
|
| 1751 |
+
"loss": 0.8703,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 3.484320557491289,
|
| 1756 |
+
"grad_norm": 0.5457651019096375,
|
| 1757 |
+
"learning_rate": 6.786360246731595e-06,
|
| 1758 |
+
"loss": 0.8494,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 3.4982578397212545,
|
| 1763 |
+
"grad_norm": 0.49579504132270813,
|
| 1764 |
+
"learning_rate": 6.713983707089773e-06,
|
| 1765 |
+
"loss": 0.848,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 3.5121951219512195,
|
| 1770 |
+
"grad_norm": 0.472918838262558,
|
| 1771 |
+
"learning_rate": 6.641799627684481e-06,
|
| 1772 |
+
"loss": 0.8633,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 3.5261324041811846,
|
| 1777 |
+
"grad_norm": 0.6405051946640015,
|
| 1778 |
+
"learning_rate": 6.569812236299089e-06,
|
| 1779 |
+
"loss": 0.8672,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 3.54006968641115,
|
| 1784 |
+
"grad_norm": 0.5040938258171082,
|
| 1785 |
+
"learning_rate": 6.498025749197036e-06,
|
| 1786 |
+
"loss": 0.847,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 3.554006968641115,
|
| 1791 |
+
"grad_norm": 0.5406576991081238,
|
| 1792 |
+
"learning_rate": 6.426444370874906e-06,
|
| 1793 |
+
"loss": 0.8291,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 3.56794425087108,
|
| 1798 |
+
"grad_norm": 0.47771602869033813,
|
| 1799 |
+
"learning_rate": 6.355072293816178e-06,
|
| 1800 |
+
"loss": 0.8522,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 3.581881533101045,
|
| 1805 |
+
"grad_norm": 0.5669821500778198,
|
| 1806 |
+
"learning_rate": 6.283913698245659e-06,
|
| 1807 |
+
"loss": 0.8316,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 3.59581881533101,
|
| 1812 |
+
"grad_norm": 0.6127913594245911,
|
| 1813 |
+
"learning_rate": 6.212972751884663e-06,
|
| 1814 |
+
"loss": 0.8686,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.6097560975609757,
|
| 1819 |
+
"grad_norm": 0.5714460015296936,
|
| 1820 |
+
"learning_rate": 6.142253609706898e-06,
|
| 1821 |
+
"loss": 0.8493,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.6236933797909407,
|
| 1826 |
+
"grad_norm": 0.5862120389938354,
|
| 1827 |
+
"learning_rate": 6.0717604136951315e-06,
|
| 1828 |
+
"loss": 0.8962,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.637630662020906,
|
| 1833 |
+
"grad_norm": 0.5323344469070435,
|
| 1834 |
+
"learning_rate": 6.001497292598566e-06,
|
| 1835 |
+
"loss": 0.8615,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.6515679442508713,
|
| 1840 |
+
"grad_norm": 0.5613053441047668,
|
| 1841 |
+
"learning_rate": 5.931468361691053e-06,
|
| 1842 |
+
"loss": 0.8823,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.6655052264808363,
|
| 1847 |
+
"grad_norm": 0.512625515460968,
|
| 1848 |
+
"learning_rate": 5.861677722530037e-06,
|
| 1849 |
+
"loss": 0.8505,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.6794425087108014,
|
| 1854 |
+
"grad_norm": 0.5254554152488708,
|
| 1855 |
+
"learning_rate": 5.792129462716355e-06,
|
| 1856 |
+
"loss": 0.8456,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 3.6933797909407664,
|
| 1861 |
+
"grad_norm": 0.5453774929046631,
|
| 1862 |
+
"learning_rate": 5.722827655654801e-06,
|
| 1863 |
+
"loss": 0.862,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 3.7073170731707314,
|
| 1868 |
+
"grad_norm": 0.5125150680541992,
|
| 1869 |
+
"learning_rate": 5.653776360315562e-06,
|
| 1870 |
+
"loss": 0.8497,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 3.721254355400697,
|
| 1875 |
+
"grad_norm": 0.5420352816581726,
|
| 1876 |
+
"learning_rate": 5.584979620996491e-06,
|
| 1877 |
+
"loss": 0.8507,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 3.735191637630662,
|
| 1882 |
+
"grad_norm": 0.6987497210502625,
|
| 1883 |
+
"learning_rate": 5.516441467086231e-06,
|
| 1884 |
+
"loss": 0.8596,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 3.749128919860627,
|
| 1889 |
+
"grad_norm": 0.6294048428535461,
|
| 1890 |
+
"learning_rate": 5.448165912828214e-06,
|
| 1891 |
+
"loss": 0.8402,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 3.7630662020905925,
|
| 1896 |
+
"grad_norm": 0.4914676547050476,
|
| 1897 |
+
"learning_rate": 5.380156957085536e-06,
|
| 1898 |
+
"loss": 0.8544,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 3.7770034843205575,
|
| 1903 |
+
"grad_norm": 0.46825504302978516,
|
| 1904 |
+
"learning_rate": 5.312418583106784e-06,
|
| 1905 |
+
"loss": 0.8307,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 3.7909407665505226,
|
| 1910 |
+
"grad_norm": 0.6263434290885925,
|
| 1911 |
+
"learning_rate": 5.244954758292691e-06,
|
| 1912 |
+
"loss": 0.8472,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 3.8048780487804876,
|
| 1917 |
+
"grad_norm": 0.6025940179824829,
|
| 1918 |
+
"learning_rate": 5.177769433963801e-06,
|
| 1919 |
+
"loss": 0.8388,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 3.818815331010453,
|
| 1924 |
+
"grad_norm": 0.6129311919212341,
|
| 1925 |
+
"learning_rate": 5.110866545129031e-06,
|
| 1926 |
+
"loss": 0.8647,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 3.832752613240418,
|
| 1931 |
+
"grad_norm": 0.5434401035308838,
|
| 1932 |
+
"learning_rate": 5.044250010255202e-06,
|
| 1933 |
+
"loss": 0.8224,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 3.846689895470383,
|
| 1938 |
+
"grad_norm": 0.5361849069595337,
|
| 1939 |
+
"learning_rate": 4.97792373103753e-06,
|
| 1940 |
+
"loss": 0.8677,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 3.8606271777003487,
|
| 1945 |
+
"grad_norm": 0.5294119715690613,
|
| 1946 |
+
"learning_rate": 4.911891592171113e-06,
|
| 1947 |
+
"loss": 0.8471,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 3.8745644599303137,
|
| 1952 |
+
"grad_norm": 0.3936956524848938,
|
| 1953 |
+
"learning_rate": 4.846157461123411e-06,
|
| 1954 |
+
"loss": 0.8718,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 3.8885017421602788,
|
| 1959 |
+
"grad_norm": 0.5664070844650269,
|
| 1960 |
+
"learning_rate": 4.780725187907707e-06,
|
| 1961 |
+
"loss": 0.8424,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 3.902439024390244,
|
| 1966 |
+
"grad_norm": 0.6031394600868225,
|
| 1967 |
+
"learning_rate": 4.715598604857648e-06,
|
| 1968 |
+
"loss": 0.8469,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 3.916376306620209,
|
| 1973 |
+
"grad_norm": 0.5560880899429321,
|
| 1974 |
+
"learning_rate": 4.65078152640276e-06,
|
| 1975 |
+
"loss": 0.8626,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 3.9303135888501743,
|
| 1980 |
+
"grad_norm": 0.5566712021827698,
|
| 1981 |
+
"learning_rate": 4.586277748845055e-06,
|
| 1982 |
+
"loss": 0.9251,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 3.9442508710801394,
|
| 1987 |
+
"grad_norm": 0.5782540440559387,
|
| 1988 |
+
"learning_rate": 4.5220910501366635e-06,
|
| 1989 |
+
"loss": 0.8321,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 3.9581881533101044,
|
| 1994 |
+
"grad_norm": 0.5216631889343262,
|
| 1995 |
+
"learning_rate": 4.458225189658598e-06,
|
| 1996 |
+
"loss": 0.8293,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 3.97212543554007,
|
| 2001 |
+
"grad_norm": 0.511968195438385,
|
| 2002 |
+
"learning_rate": 4.3946839080005236e-06,
|
| 2003 |
+
"loss": 0.8238,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 3.986062717770035,
|
| 2008 |
+
"grad_norm": 0.49393701553344727,
|
| 2009 |
+
"learning_rate": 4.331470926741707e-06,
|
| 2010 |
+
"loss": 0.885,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 4.0,
|
| 2015 |
+
"grad_norm": 0.4580581486225128,
|
| 2016 |
+
"learning_rate": 4.268589948233034e-06,
|
| 2017 |
+
"loss": 0.8487,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 4.013937282229965,
|
| 2022 |
+
"grad_norm": 0.4895112216472626,
|
| 2023 |
+
"learning_rate": 4.2060446553801585e-06,
|
| 2024 |
+
"loss": 0.8222,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 4.02787456445993,
|
| 2029 |
+
"grad_norm": 0.5034216046333313,
|
| 2030 |
+
"learning_rate": 4.143838711427808e-06,
|
| 2031 |
+
"loss": 0.8645,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 4.041811846689895,
|
| 2036 |
+
"grad_norm": 0.5985310673713684,
|
| 2037 |
+
"learning_rate": 4.0819757597452246e-06,
|
| 2038 |
+
"loss": 0.8652,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 4.055749128919861,
|
| 2043 |
+
"grad_norm": 0.4828563332557678,
|
| 2044 |
+
"learning_rate": 4.020459423612777e-06,
|
| 2045 |
+
"loss": 0.8602,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 4.069686411149826,
|
| 2050 |
+
"grad_norm": 0.48318225145339966,
|
| 2051 |
+
"learning_rate": 3.959293306009734e-06,
|
| 2052 |
+
"loss": 0.8541,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 4.083623693379791,
|
| 2057 |
+
"grad_norm": 0.5043054223060608,
|
| 2058 |
+
"learning_rate": 3.89848098940326e-06,
|
| 2059 |
+
"loss": 0.857,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 4.097560975609756,
|
| 2064 |
+
"grad_norm": 0.5322110652923584,
|
| 2065 |
+
"learning_rate": 3.838026035538581e-06,
|
| 2066 |
+
"loss": 0.8419,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 4.111498257839721,
|
| 2071 |
+
"grad_norm": 0.7655691504478455,
|
| 2072 |
+
"learning_rate": 3.7779319852303766e-06,
|
| 2073 |
+
"loss": 0.8551,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 4.125435540069686,
|
| 2078 |
+
"grad_norm": 0.5095774531364441,
|
| 2079 |
+
"learning_rate": 3.718202358155384e-06,
|
| 2080 |
+
"loss": 0.838,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 4.139372822299651,
|
| 2085 |
+
"grad_norm": 0.5320903658866882,
|
| 2086 |
+
"learning_rate": 3.658840652646287e-06,
|
| 2087 |
+
"loss": 0.8044,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 4.153310104529616,
|
| 2092 |
+
"grad_norm": 0.5706301927566528,
|
| 2093 |
+
"learning_rate": 3.5998503454867807e-06,
|
| 2094 |
+
"loss": 0.858,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 4.167247386759582,
|
| 2099 |
+
"grad_norm": 1.014062523841858,
|
| 2100 |
+
"learning_rate": 3.5412348917079507e-06,
|
| 2101 |
+
"loss": 0.8739,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 4.181184668989547,
|
| 2106 |
+
"grad_norm": 0.5381621718406677,
|
| 2107 |
+
"learning_rate": 3.4829977243859414e-06,
|
| 2108 |
+
"loss": 0.8082,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 4.195121951219512,
|
| 2113 |
+
"grad_norm": 0.48279663920402527,
|
| 2114 |
+
"learning_rate": 3.425142254440835e-06,
|
| 2115 |
+
"loss": 0.8335,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 4.209059233449477,
|
| 2120 |
+
"grad_norm": 0.6682676076889038,
|
| 2121 |
+
"learning_rate": 3.367671870436915e-06,
|
| 2122 |
+
"loss": 0.8484,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 4.2229965156794425,
|
| 2127 |
+
"grad_norm": 0.5164760947227478,
|
| 2128 |
+
"learning_rate": 3.310589938384179e-06,
|
| 2129 |
+
"loss": 0.8228,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 4.2369337979094075,
|
| 2134 |
+
"grad_norm": 0.5330147743225098,
|
| 2135 |
+
"learning_rate": 3.253899801541206e-06,
|
| 2136 |
+
"loss": 0.8475,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 4.2508710801393725,
|
| 2141 |
+
"grad_norm": 0.5183762907981873,
|
| 2142 |
+
"learning_rate": 3.197604780219323e-06,
|
| 2143 |
+
"loss": 0.8228,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 4.264808362369338,
|
| 2148 |
+
"grad_norm": 0.5862233638763428,
|
| 2149 |
+
"learning_rate": 3.1417081715881623e-06,
|
| 2150 |
+
"loss": 0.8419,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 4.2787456445993035,
|
| 2155 |
+
"grad_norm": 0.5445356369018555,
|
| 2156 |
+
"learning_rate": 3.0862132494825325e-06,
|
| 2157 |
+
"loss": 0.875,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 4.2926829268292686,
|
| 2162 |
+
"grad_norm": 0.5905585885047913,
|
| 2163 |
+
"learning_rate": 3.0311232642106768e-06,
|
| 2164 |
+
"loss": 0.8548,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 4.306620209059234,
|
| 2169 |
+
"grad_norm": 0.5876056551933289,
|
| 2170 |
+
"learning_rate": 2.976441442363893e-06,
|
| 2171 |
+
"loss": 0.8812,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 4.320557491289199,
|
| 2176 |
+
"grad_norm": 0.5916198492050171,
|
| 2177 |
+
"learning_rate": 2.922170986627573e-06,
|
| 2178 |
+
"loss": 0.8289,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 4.334494773519164,
|
| 2183 |
+
"grad_norm": 0.555949866771698,
|
| 2184 |
+
"learning_rate": 2.8683150755936107e-06,
|
| 2185 |
+
"loss": 0.8822,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 4.348432055749129,
|
| 2190 |
+
"grad_norm": 0.5823965668678284,
|
| 2191 |
+
"learning_rate": 2.8148768635742286e-06,
|
| 2192 |
+
"loss": 0.8308,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 4.362369337979094,
|
| 2197 |
+
"grad_norm": 0.6472144722938538,
|
| 2198 |
+
"learning_rate": 2.761859480417255e-06,
|
| 2199 |
+
"loss": 0.8368,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 4.376306620209059,
|
| 2204 |
+
"grad_norm": 0.5416210293769836,
|
| 2205 |
+
"learning_rate": 2.7092660313227748e-06,
|
| 2206 |
+
"loss": 0.8655,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 4.390243902439025,
|
| 2211 |
+
"grad_norm": 0.5069013833999634,
|
| 2212 |
+
"learning_rate": 2.6570995966612945e-06,
|
| 2213 |
+
"loss": 0.8657,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 4.40418118466899,
|
| 2218 |
+
"grad_norm": 0.4444841146469116,
|
| 2219 |
+
"learning_rate": 2.605363231793302e-06,
|
| 2220 |
+
"loss": 0.8362,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 4.418118466898955,
|
| 2225 |
+
"grad_norm": 0.5552143454551697,
|
| 2226 |
+
"learning_rate": 2.554059966890332e-06,
|
| 2227 |
+
"loss": 0.8027,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 4.43205574912892,
|
| 2232 |
+
"grad_norm": 0.7829400897026062,
|
| 2233 |
+
"learning_rate": 2.503192806757474e-06,
|
| 2234 |
+
"loss": 0.8351,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 4.445993031358885,
|
| 2239 |
+
"grad_norm": 0.477295458316803,
|
| 2240 |
+
"learning_rate": 2.4527647306574e-06,
|
| 2241 |
+
"loss": 0.8102,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 4.45993031358885,
|
| 2246 |
+
"grad_norm": 0.5426877737045288,
|
| 2247 |
+
"learning_rate": 2.402778692135861e-06,
|
| 2248 |
+
"loss": 0.8406,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 4.473867595818815,
|
| 2253 |
+
"grad_norm": 0.5670856237411499,
|
| 2254 |
+
"learning_rate": 2.353237618848695e-06,
|
| 2255 |
+
"loss": 0.8258,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 4.487804878048781,
|
| 2260 |
+
"grad_norm": 0.4924805462360382,
|
| 2261 |
+
"learning_rate": 2.304144412390367e-06,
|
| 2262 |
+
"loss": 0.8303,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 4.501742160278746,
|
| 2267 |
+
"grad_norm": 0.5142589807510376,
|
| 2268 |
+
"learning_rate": 2.255501948124017e-06,
|
| 2269 |
+
"loss": 0.8714,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 4.515679442508711,
|
| 2274 |
+
"grad_norm": 0.546807587146759,
|
| 2275 |
+
"learning_rate": 2.207313075013059e-06,
|
| 2276 |
+
"loss": 0.8221,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 4.529616724738676,
|
| 2281 |
+
"grad_norm": 0.5798578858375549,
|
| 2282 |
+
"learning_rate": 2.1595806154542965e-06,
|
| 2283 |
+
"loss": 0.8625,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 4.543554006968641,
|
| 2288 |
+
"grad_norm": 0.567733108997345,
|
| 2289 |
+
"learning_rate": 2.112307365112657e-06,
|
| 2290 |
+
"loss": 0.8242,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 4.557491289198606,
|
| 2295 |
+
"grad_norm": 0.5294705033302307,
|
| 2296 |
+
"learning_rate": 2.065496092757403e-06,
|
| 2297 |
+
"loss": 0.8721,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 4.571428571428571,
|
| 2302 |
+
"grad_norm": 0.49266737699508667,
|
| 2303 |
+
"learning_rate": 2.019149540100005e-06,
|
| 2304 |
+
"loss": 0.8576,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 4.585365853658536,
|
| 2309 |
+
"grad_norm": 0.5400304198265076,
|
| 2310 |
+
"learning_rate": 1.973270421633543e-06,
|
| 2311 |
+
"loss": 0.8899,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 4.599303135888501,
|
| 2316 |
+
"grad_norm": 0.5392309427261353,
|
| 2317 |
+
"learning_rate": 1.927861424473726e-06,
|
| 2318 |
+
"loss": 0.8227,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 4.613240418118467,
|
| 2323 |
+
"grad_norm": 0.5385839343070984,
|
| 2324 |
+
"learning_rate": 1.882925208201498e-06,
|
| 2325 |
+
"loss": 0.838,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 4.627177700348432,
|
| 2330 |
+
"grad_norm": 0.5418098568916321,
|
| 2331 |
+
"learning_rate": 1.8384644047072864e-06,
|
| 2332 |
+
"loss": 0.8612,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 4.641114982578397,
|
| 2337 |
+
"grad_norm": 0.5207215547561646,
|
| 2338 |
+
"learning_rate": 1.7944816180368408e-06,
|
| 2339 |
+
"loss": 0.8356,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 4.655052264808362,
|
| 2344 |
+
"grad_norm": 0.9076542854309082,
|
| 2345 |
+
"learning_rate": 1.7509794242387135e-06,
|
| 2346 |
+
"loss": 0.8224,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 4.668989547038327,
|
| 2351 |
+
"grad_norm": 0.4973151385784149,
|
| 2352 |
+
"learning_rate": 1.7079603712133908e-06,
|
| 2353 |
+
"loss": 0.8678,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 4.682926829268292,
|
| 2358 |
+
"grad_norm": 0.5431068539619446,
|
| 2359 |
+
"learning_rate": 1.6654269785640608e-06,
|
| 2360 |
+
"loss": 0.8467,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 4.696864111498257,
|
| 2365 |
+
"grad_norm": 0.4680764079093933,
|
| 2366 |
+
"learning_rate": 1.623381737449038e-06,
|
| 2367 |
+
"loss": 0.8364,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 4.710801393728223,
|
| 2372 |
+
"grad_norm": 0.507692813873291,
|
| 2373 |
+
"learning_rate": 1.5818271104358574e-06,
|
| 2374 |
+
"loss": 0.8854,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 4.724738675958188,
|
| 2379 |
+
"grad_norm": 0.758124828338623,
|
| 2380 |
+
"learning_rate": 1.5407655313570525e-06,
|
| 2381 |
+
"loss": 0.8534,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 4.7386759581881535,
|
| 2386 |
+
"grad_norm": 0.6623209118843079,
|
| 2387 |
+
"learning_rate": 1.5001994051675894e-06,
|
| 2388 |
+
"loss": 0.8814,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 4.7526132404181185,
|
| 2393 |
+
"grad_norm": 0.5073679089546204,
|
| 2394 |
+
"learning_rate": 1.4601311078040304e-06,
|
| 2395 |
+
"loss": 0.8457,
|
| 2396 |
+
"step": 3410
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 4.7665505226480835,
|
| 2400 |
+
"grad_norm": 0.500339150428772,
|
| 2401 |
+
"learning_rate": 1.4205629860453641e-06,
|
| 2402 |
+
"loss": 0.842,
|
| 2403 |
+
"step": 3420
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 4.780487804878049,
|
| 2407 |
+
"grad_norm": 0.8517163395881653,
|
| 2408 |
+
"learning_rate": 1.3814973573755518e-06,
|
| 2409 |
+
"loss": 0.8982,
|
| 2410 |
+
"step": 3430
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 4.794425087108014,
|
| 2414 |
+
"grad_norm": 0.5409610867500305,
|
| 2415 |
+
"learning_rate": 1.3429365098478087e-06,
|
| 2416 |
+
"loss": 0.8492,
|
| 2417 |
+
"step": 3440
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 4.80836236933798,
|
| 2421 |
+
"grad_norm": 0.5923708081245422,
|
| 2422 |
+
"learning_rate": 1.3048827019505828e-06,
|
| 2423 |
+
"loss": 0.8548,
|
| 2424 |
+
"step": 3450
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 4.822299651567945,
|
| 2428 |
+
"grad_norm": 0.4563385844230652,
|
| 2429 |
+
"learning_rate": 1.2673381624752813e-06,
|
| 2430 |
+
"loss": 0.8518,
|
| 2431 |
+
"step": 3460
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 4.83623693379791,
|
| 2435 |
+
"grad_norm": 0.89119553565979,
|
| 2436 |
+
"learning_rate": 1.2303050903857195e-06,
|
| 2437 |
+
"loss": 0.8355,
|
| 2438 |
+
"step": 3470
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 4.850174216027875,
|
| 2442 |
+
"grad_norm": 0.5999810695648193,
|
| 2443 |
+
"learning_rate": 1.1937856546893533e-06,
|
| 2444 |
+
"loss": 0.8347,
|
| 2445 |
+
"step": 3480
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 4.86411149825784,
|
| 2449 |
+
"grad_norm": 0.6495084166526794,
|
| 2450 |
+
"learning_rate": 1.1577819943102132e-06,
|
| 2451 |
+
"loss": 0.7981,
|
| 2452 |
+
"step": 3490
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 4.878048780487805,
|
| 2456 |
+
"grad_norm": 0.5115063190460205,
|
| 2457 |
+
"learning_rate": 1.122296217963651e-06,
|
| 2458 |
+
"loss": 0.8321,
|
| 2459 |
+
"step": 3500
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 4.89198606271777,
|
| 2463 |
+
"grad_norm": 0.5369818806648254,
|
| 2464 |
+
"learning_rate": 1.0873304040328193e-06,
|
| 2465 |
+
"loss": 0.8499,
|
| 2466 |
+
"step": 3510
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 4.905923344947735,
|
| 2470 |
+
"grad_norm": 0.523055374622345,
|
| 2471 |
+
"learning_rate": 1.052886600446954e-06,
|
| 2472 |
+
"loss": 0.8561,
|
| 2473 |
+
"step": 3520
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 4.9198606271777,
|
| 2477 |
+
"grad_norm": 0.6084771156311035,
|
| 2478 |
+
"learning_rate": 1.0189668245614092e-06,
|
| 2479 |
+
"loss": 0.854,
|
| 2480 |
+
"step": 3530
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 4.933797909407666,
|
| 2484 |
+
"grad_norm": 0.4877120852470398,
|
| 2485 |
+
"learning_rate": 9.855730630395244e-07,
|
| 2486 |
+
"loss": 0.8161,
|
| 2487 |
+
"step": 3540
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 4.947735191637631,
|
| 2491 |
+
"grad_norm": 0.6254660487174988,
|
| 2492 |
+
"learning_rate": 9.52707271736254e-07,
|
| 2493 |
+
"loss": 0.8705,
|
| 2494 |
+
"step": 3550
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 4.961672473867596,
|
| 2498 |
+
"grad_norm": 0.6138275861740112,
|
| 2499 |
+
"learning_rate": 9.203713755836108e-07,
|
| 2500 |
+
"loss": 0.8599,
|
| 2501 |
+
"step": 3560
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 4.975609756097561,
|
| 2505 |
+
"grad_norm": 0.5839621424674988,
|
| 2506 |
+
"learning_rate": 8.885672684779345e-07,
|
| 2507 |
+
"loss": 0.8536,
|
| 2508 |
+
"step": 3570
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 4.989547038327526,
|
| 2512 |
+
"grad_norm": 0.544059157371521,
|
| 2513 |
+
"learning_rate": 8.572968131689585e-07,
|
| 2514 |
+
"loss": 0.8536,
|
| 2515 |
+
"step": 3580
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 5.003484320557491,
|
| 2519 |
+
"grad_norm": 0.5101696848869324,
|
| 2520 |
+
"learning_rate": 8.265618411507148e-07,
|
| 2521 |
+
"loss": 0.84,
|
| 2522 |
+
"step": 3590
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 5.017421602787456,
|
| 2526 |
+
"grad_norm": 0.5106877684593201,
|
| 2527 |
+
"learning_rate": 7.963641525542564e-07,
|
| 2528 |
+
"loss": 0.8752,
|
| 2529 |
+
"step": 3600
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 5.031358885017422,
|
| 2533 |
+
"grad_norm": 0.5784628391265869,
|
| 2534 |
+
"learning_rate": 7.667055160422432e-07,
|
| 2535 |
+
"loss": 0.8417,
|
| 2536 |
+
"step": 3610
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 5.045296167247387,
|
| 2540 |
+
"grad_norm": 0.5501140356063843,
|
| 2541 |
+
"learning_rate": 7.375876687053252e-07,
|
| 2542 |
+
"loss": 0.8473,
|
| 2543 |
+
"step": 3620
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 5.059233449477352,
|
| 2547 |
+
"grad_norm": 0.4966902434825897,
|
| 2548 |
+
"learning_rate": 7.090123159604234e-07,
|
| 2549 |
+
"loss": 0.8414,
|
| 2550 |
+
"step": 3630
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 5.073170731707317,
|
| 2554 |
+
"grad_norm": 0.769673764705658,
|
| 2555 |
+
"learning_rate": 6.809811314508386e-07,
|
| 2556 |
+
"loss": 0.8604,
|
| 2557 |
+
"step": 3640
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 5.087108013937282,
|
| 2561 |
+
"grad_norm": 0.55353182554245,
|
| 2562 |
+
"learning_rate": 6.534957569482214e-07,
|
| 2563 |
+
"loss": 0.8601,
|
| 2564 |
+
"step": 3650
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 5.101045296167247,
|
| 2568 |
+
"grad_norm": 0.6018425822257996,
|
| 2569 |
+
"learning_rate": 6.265578022564233e-07,
|
| 2570 |
+
"loss": 0.8661,
|
| 2571 |
+
"step": 3660
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 5.114982578397212,
|
| 2575 |
+
"grad_norm": 0.534132182598114,
|
| 2576 |
+
"learning_rate": 6.001688451172027e-07,
|
| 2577 |
+
"loss": 0.8218,
|
| 2578 |
+
"step": 3670
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 5.128919860627177,
|
| 2582 |
+
"grad_norm": 0.5793606042861938,
|
| 2583 |
+
"learning_rate": 5.743304311178289e-07,
|
| 2584 |
+
"loss": 0.8399,
|
| 2585 |
+
"step": 3680
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 5.142857142857143,
|
| 2589 |
+
"grad_norm": 0.6463719010353088,
|
| 2590 |
+
"learning_rate": 5.490440736005397e-07,
|
| 2591 |
+
"loss": 0.8249,
|
| 2592 |
+
"step": 3690
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 5.156794425087108,
|
| 2596 |
+
"grad_norm": 0.5509739518165588,
|
| 2597 |
+
"learning_rate": 5.24311253573927e-07,
|
| 2598 |
+
"loss": 0.8125,
|
| 2599 |
+
"step": 3700
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 5.170731707317073,
|
| 2603 |
+
"grad_norm": 0.4920913279056549,
|
| 2604 |
+
"learning_rate": 5.001334196261776e-07,
|
| 2605 |
+
"loss": 0.8701,
|
| 2606 |
+
"step": 3710
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 5.184668989547038,
|
| 2610 |
+
"grad_norm": 0.5054136514663696,
|
| 2611 |
+
"learning_rate": 4.765119878402424e-07,
|
| 2612 |
+
"loss": 0.8548,
|
| 2613 |
+
"step": 3720
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 5.198606271777003,
|
| 2617 |
+
"grad_norm": 0.5016888380050659,
|
| 2618 |
+
"learning_rate": 4.5344834171088594e-07,
|
| 2619 |
+
"loss": 0.837,
|
| 2620 |
+
"step": 3730
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 5.2125435540069684,
|
| 2624 |
+
"grad_norm": 0.5839513540267944,
|
| 2625 |
+
"learning_rate": 4.309438320636705e-07,
|
| 2626 |
+
"loss": 0.8781,
|
| 2627 |
+
"step": 3740
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 5.2264808362369335,
|
| 2631 |
+
"grad_norm": 0.5476316213607788,
|
| 2632 |
+
"learning_rate": 4.089997769758225e-07,
|
| 2633 |
+
"loss": 0.8616,
|
| 2634 |
+
"step": 3750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 5.2404181184668985,
|
| 2638 |
+
"grad_norm": 0.562765896320343,
|
| 2639 |
+
"learning_rate": 3.876174616990402e-07,
|
| 2640 |
+
"loss": 0.8614,
|
| 2641 |
+
"step": 3760
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 5.2543554006968645,
|
| 2645 |
+
"grad_norm": 0.5283138751983643,
|
| 2646 |
+
"learning_rate": 3.6679813858422673e-07,
|
| 2647 |
+
"loss": 0.8013,
|
| 2648 |
+
"step": 3770
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 5.2682926829268295,
|
| 2652 |
+
"grad_norm": 0.4689981937408447,
|
| 2653 |
+
"learning_rate": 3.46543027008126e-07,
|
| 2654 |
+
"loss": 0.7839,
|
| 2655 |
+
"step": 3780
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 5.2822299651567945,
|
| 2659 |
+
"grad_norm": 0.46892431378364563,
|
| 2660 |
+
"learning_rate": 3.2685331330190916e-07,
|
| 2661 |
+
"loss": 0.8268,
|
| 2662 |
+
"step": 3790
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 5.29616724738676,
|
| 2666 |
+
"grad_norm": 0.5027751326560974,
|
| 2667 |
+
"learning_rate": 3.0773015068169876e-07,
|
| 2668 |
+
"loss": 0.8209,
|
| 2669 |
+
"step": 3800
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 5.310104529616725,
|
| 2673 |
+
"grad_norm": 0.6267147660255432,
|
| 2674 |
+
"learning_rate": 2.891746591810152e-07,
|
| 2675 |
+
"loss": 0.8121,
|
| 2676 |
+
"step": 3810
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 5.32404181184669,
|
| 2680 |
+
"grad_norm": 0.5063154697418213,
|
| 2681 |
+
"learning_rate": 2.7118792558518237e-07,
|
| 2682 |
+
"loss": 0.8622,
|
| 2683 |
+
"step": 3820
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 5.337979094076655,
|
| 2687 |
+
"grad_norm": 0.5375659465789795,
|
| 2688 |
+
"learning_rate": 2.5377100336767547e-07,
|
| 2689 |
+
"loss": 0.8033,
|
| 2690 |
+
"step": 3830
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 5.351916376306621,
|
| 2694 |
+
"grad_norm": 0.5449223518371582,
|
| 2695 |
+
"learning_rate": 2.3692491262841788e-07,
|
| 2696 |
+
"loss": 0.848,
|
| 2697 |
+
"step": 3840
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 5.365853658536586,
|
| 2701 |
+
"grad_norm": 0.5025774240493774,
|
| 2702 |
+
"learning_rate": 2.206506400340369e-07,
|
| 2703 |
+
"loss": 0.8403,
|
| 2704 |
+
"step": 3850
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 5.379790940766551,
|
| 2708 |
+
"grad_norm": 0.4367560148239136,
|
| 2709 |
+
"learning_rate": 2.0494913876007105e-07,
|
| 2710 |
+
"loss": 0.8539,
|
| 2711 |
+
"step": 3860
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 5.393728222996516,
|
| 2715 |
+
"grad_norm": 0.5829946994781494,
|
| 2716 |
+
"learning_rate": 1.8982132843514577e-07,
|
| 2717 |
+
"loss": 0.8371,
|
| 2718 |
+
"step": 3870
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 5.407665505226481,
|
| 2722 |
+
"grad_norm": 0.5280970931053162,
|
| 2723 |
+
"learning_rate": 1.752680950871144e-07,
|
| 2724 |
+
"loss": 0.8705,
|
| 2725 |
+
"step": 3880
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 5.421602787456446,
|
| 2729 |
+
"grad_norm": 0.5541146993637085,
|
| 2730 |
+
"learning_rate": 1.6129029109115401e-07,
|
| 2731 |
+
"loss": 0.8514,
|
| 2732 |
+
"step": 3890
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 5.435540069686411,
|
| 2736 |
+
"grad_norm": 0.5944886207580566,
|
| 2737 |
+
"learning_rate": 1.4788873511985656e-07,
|
| 2738 |
+
"loss": 0.8545,
|
| 2739 |
+
"step": 3900
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 5.449477351916376,
|
| 2743 |
+
"grad_norm": 0.5219863653182983,
|
| 2744 |
+
"learning_rate": 1.350642120952661e-07,
|
| 2745 |
+
"loss": 0.9,
|
| 2746 |
+
"step": 3910
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 5.463414634146342,
|
| 2750 |
+
"grad_norm": 0.5505541563034058,
|
| 2751 |
+
"learning_rate": 1.2281747314291437e-07,
|
| 2752 |
+
"loss": 0.8239,
|
| 2753 |
+
"step": 3920
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 5.477351916376307,
|
| 2757 |
+
"grad_norm": 0.551377534866333,
|
| 2758 |
+
"learning_rate": 1.1114923554782608e-07,
|
| 2759 |
+
"loss": 0.8817,
|
| 2760 |
+
"step": 3930
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 5.491289198606272,
|
| 2764 |
+
"grad_norm": 0.5536546111106873,
|
| 2765 |
+
"learning_rate": 1.0006018271250695e-07,
|
| 2766 |
+
"loss": 0.8719,
|
| 2767 |
+
"step": 3940
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 5.505226480836237,
|
| 2771 |
+
"grad_norm": 0.48071563243865967,
|
| 2772 |
+
"learning_rate": 8.955096411691566e-08,
|
| 2773 |
+
"loss": 0.8517,
|
| 2774 |
+
"step": 3950
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 5.519163763066202,
|
| 2778 |
+
"grad_norm": 0.5239782929420471,
|
| 2779 |
+
"learning_rate": 7.962219528042991e-08,
|
| 2780 |
+
"loss": 0.8284,
|
| 2781 |
+
"step": 3960
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 5.533101045296167,
|
| 2785 |
+
"grad_norm": 0.5262070298194885,
|
| 2786 |
+
"learning_rate": 7.027445772578856e-08,
|
| 2787 |
+
"loss": 0.8277,
|
| 2788 |
+
"step": 3970
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 5.547038327526132,
|
| 2792 |
+
"grad_norm": 0.5303363800048828,
|
| 2793 |
+
"learning_rate": 6.150829894503662e-08,
|
| 2794 |
+
"loss": 0.8648,
|
| 2795 |
+
"step": 3980
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 5.560975609756097,
|
| 2799 |
+
"grad_norm": 0.5235099196434021,
|
| 2800 |
+
"learning_rate": 5.332423236745765e-08,
|
| 2801 |
+
"loss": 0.8722,
|
| 2802 |
+
"step": 3990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 5.574912891986063,
|
| 2806 |
+
"grad_norm": 0.5281161665916443,
|
| 2807 |
+
"learning_rate": 4.5722737329505495e-08,
|
| 2808 |
+
"loss": 0.8452,
|
| 2809 |
+
"step": 4000
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 5.588850174216028,
|
| 2813 |
+
"grad_norm": 0.6809967756271362,
|
| 2814 |
+
"learning_rate": 3.870425904672237e-08,
|
| 2815 |
+
"loss": 0.8571,
|
| 2816 |
+
"step": 4010
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 5.602787456445993,
|
| 2820 |
+
"grad_norm": 0.5919767618179321,
|
| 2821 |
+
"learning_rate": 3.22692085876708e-08,
|
| 2822 |
+
"loss": 0.8392,
|
| 2823 |
+
"step": 4020
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 5.616724738675958,
|
| 2827 |
+
"grad_norm": 0.5929062962532043,
|
| 2828 |
+
"learning_rate": 2.6417962849852875e-08,
|
| 2829 |
+
"loss": 0.7991,
|
| 2830 |
+
"step": 4030
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 5.630662020905923,
|
| 2834 |
+
"grad_norm": 85.85006713867188,
|
| 2835 |
+
"learning_rate": 2.1150864537636817e-08,
|
| 2836 |
+
"loss": 0.8357,
|
| 2837 |
+
"step": 4040
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 5.644599303135888,
|
| 2841 |
+
"grad_norm": 0.5508357286453247,
|
| 2842 |
+
"learning_rate": 1.646822214218524e-08,
|
| 2843 |
+
"loss": 0.8502,
|
| 2844 |
+
"step": 4050
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 5.658536585365853,
|
| 2848 |
+
"grad_norm": 0.5149642825126648,
|
| 2849 |
+
"learning_rate": 1.2370309923388501e-08,
|
| 2850 |
+
"loss": 0.8546,
|
| 2851 |
+
"step": 4060
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 5.672473867595819,
|
| 2855 |
+
"grad_norm": 0.601134181022644,
|
| 2856 |
+
"learning_rate": 8.857367893796431e-09,
|
| 2857 |
+
"loss": 0.8809,
|
| 2858 |
+
"step": 4070
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 5.686411149825784,
|
| 2862 |
+
"grad_norm": 0.6303636431694031,
|
| 2863 |
+
"learning_rate": 5.929601804566254e-09,
|
| 2864 |
+
"loss": 0.8678,
|
| 2865 |
+
"step": 4080
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 5.700348432055749,
|
| 2869 |
+
"grad_norm": 0.5462765097618103,
|
| 2870 |
+
"learning_rate": 3.5871831334099992e-09,
|
| 2871 |
+
"loss": 0.843,
|
| 2872 |
+
"step": 4090
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 5.714285714285714,
|
| 2876 |
+
"grad_norm": 0.6144183278083801,
|
| 2877 |
+
"learning_rate": 1.8302490745503166e-09,
|
| 2878 |
+
"loss": 0.8146,
|
| 2879 |
+
"step": 4100
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 5.7282229965156795,
|
| 2883 |
+
"grad_norm": 0.5314708352088928,
|
| 2884 |
+
"learning_rate": 6.589025306869002e-10,
|
| 2885 |
+
"loss": 0.8237,
|
| 2886 |
+
"step": 4110
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 5.7421602787456445,
|
| 2890 |
+
"grad_norm": 0.56773841381073,
|
| 2891 |
+
"learning_rate": 7.321210696464853e-11,
|
| 2892 |
+
"loss": 0.8358,
|
| 2893 |
+
"step": 4120
|
| 2894 |
+
}
|
| 2895 |
+
],
|
| 2896 |
+
"logging_steps": 10,
|
| 2897 |
+
"max_steps": 4125,
|
| 2898 |
+
"num_input_tokens_seen": 0,
|
| 2899 |
+
"num_train_epochs": 6,
|
| 2900 |
+
"save_steps": 500,
|
| 2901 |
+
"stateful_callbacks": {
|
| 2902 |
+
"TrainerControl": {
|
| 2903 |
+
"args": {
|
| 2904 |
+
"should_epoch_stop": false,
|
| 2905 |
+
"should_evaluate": false,
|
| 2906 |
+
"should_log": false,
|
| 2907 |
+
"should_save": true,
|
| 2908 |
+
"should_training_stop": true
|
| 2909 |
+
},
|
| 2910 |
+
"attributes": {}
|
| 2911 |
+
}
|
| 2912 |
+
},
|
| 2913 |
+
"total_flos": 5.88632668766208e+17,
|
| 2914 |
+
"train_batch_size": 4,
|
| 2915 |
+
"trial_name": null,
|
| 2916 |
+
"trial_params": null
|
| 2917 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df79fcd387c99ec36e4fb46d3b7fbec33def1dd3949e7e2efe71a888f080570d
|
| 3 |
+
size 5496
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|