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 +2175 -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 |
+
"c_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"c_fc",
|
| 27 |
+
"v_proj"
|
| 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:bca4fb25f82da786bf5f8d089b0b8419a488ac56531063a48b729a63d8ac4cc5
|
| 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:e35b5274e0b5e1cc9879557d80c0ec5452566d92b7445b9ef1f3310aba607f3e
|
| 3 |
+
size 48178804
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:424aec6bf77bb5921313e399a43b664a7ce0aeecfbf7df5c85ef40b5aadfbec1
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6df558548f6ec422f2c36743b38b770987c99e6b4c06510c760cda47ac1ef901
|
| 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 +1,2175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.462025316455696,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3063,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02109704641350211,
|
| 13 |
+
"grad_norm": 0.47141513228416443,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 3.0389,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04219409282700422,
|
| 20 |
+
"grad_norm": 0.701974093914032,
|
| 21 |
+
"learning_rate": 2e-05,
|
| 22 |
+
"loss": 3.2294,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06329113924050633,
|
| 27 |
+
"grad_norm": 0.5129281878471375,
|
| 28 |
+
"learning_rate": 1.9999467080038847e-05,
|
| 29 |
+
"loss": 2.8774,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08438818565400844,
|
| 34 |
+
"grad_norm": 0.5039157867431641,
|
| 35 |
+
"learning_rate": 1.9997868376956112e-05,
|
| 36 |
+
"loss": 2.8694,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10548523206751055,
|
| 41 |
+
"grad_norm": 0.6525703072547913,
|
| 42 |
+
"learning_rate": 1.9995204061147954e-05,
|
| 43 |
+
"loss": 2.549,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12658227848101267,
|
| 48 |
+
"grad_norm": 0.7681527137756348,
|
| 49 |
+
"learning_rate": 1.9991474416587794e-05,
|
| 50 |
+
"loss": 2.4746,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14767932489451477,
|
| 55 |
+
"grad_norm": 0.909417450428009,
|
| 56 |
+
"learning_rate": 1.9986679840796036e-05,
|
| 57 |
+
"loss": 2.2414,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16877637130801687,
|
| 62 |
+
"grad_norm": 1.059488296508789,
|
| 63 |
+
"learning_rate": 1.998082084479771e-05,
|
| 64 |
+
"loss": 2.1423,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.189873417721519,
|
| 69 |
+
"grad_norm": 0.5037703514099121,
|
| 70 |
+
"learning_rate": 1.9973898053067996e-05,
|
| 71 |
+
"loss": 1.9704,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2109704641350211,
|
| 76 |
+
"grad_norm": 1.0699340105056763,
|
| 77 |
+
"learning_rate": 1.996591220346568e-05,
|
| 78 |
+
"loss": 1.9176,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2320675105485232,
|
| 83 |
+
"grad_norm": 0.5377259850502014,
|
| 84 |
+
"learning_rate": 1.995686414715449e-05,
|
| 85 |
+
"loss": 1.6842,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.25316455696202533,
|
| 90 |
+
"grad_norm": 0.4896199107170105,
|
| 91 |
+
"learning_rate": 1.994675484851239e-05,
|
| 92 |
+
"loss": 1.8138,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2742616033755274,
|
| 97 |
+
"grad_norm": 0.85350102186203,
|
| 98 |
+
"learning_rate": 1.9935585385028786e-05,
|
| 99 |
+
"loss": 1.6322,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.29535864978902954,
|
| 104 |
+
"grad_norm": 0.7110411524772644,
|
| 105 |
+
"learning_rate": 1.992335694718969e-05,
|
| 106 |
+
"loss": 1.6378,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.31645569620253167,
|
| 111 |
+
"grad_norm": 7.485868453979492,
|
| 112 |
+
"learning_rate": 1.9910070838350828e-05,
|
| 113 |
+
"loss": 1.5367,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.33755274261603374,
|
| 118 |
+
"grad_norm": 0.6181347370147705,
|
| 119 |
+
"learning_rate": 1.9895728474598713e-05,
|
| 120 |
+
"loss": 1.5012,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.35864978902953587,
|
| 125 |
+
"grad_norm": 0.609489917755127,
|
| 126 |
+
"learning_rate": 1.9880331384599743e-05,
|
| 127 |
+
"loss": 1.4693,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.379746835443038,
|
| 132 |
+
"grad_norm": 0.4934925138950348,
|
| 133 |
+
"learning_rate": 1.986388120943723e-05,
|
| 134 |
+
"loss": 1.411,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4008438818565401,
|
| 139 |
+
"grad_norm": 0.5047251582145691,
|
| 140 |
+
"learning_rate": 1.9846379702436518e-05,
|
| 141 |
+
"loss": 1.389,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4219409282700422,
|
| 146 |
+
"grad_norm": 0.558677077293396,
|
| 147 |
+
"learning_rate": 1.9827828728978096e-05,
|
| 148 |
+
"loss": 1.3247,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.4430379746835443,
|
| 153 |
+
"grad_norm": 0.6455519199371338,
|
| 154 |
+
"learning_rate": 1.980823026629877e-05,
|
| 155 |
+
"loss": 1.4037,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4641350210970464,
|
| 160 |
+
"grad_norm": 0.54356849193573,
|
| 161 |
+
"learning_rate": 1.978758640328094e-05,
|
| 162 |
+
"loss": 1.2992,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.48523206751054854,
|
| 167 |
+
"grad_norm": 0.569212794303894,
|
| 168 |
+
"learning_rate": 1.9765899340229934e-05,
|
| 169 |
+
"loss": 1.3177,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5063291139240507,
|
| 174 |
+
"grad_norm": 0.525545060634613,
|
| 175 |
+
"learning_rate": 1.9743171388639518e-05,
|
| 176 |
+
"loss": 1.2712,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5274261603375527,
|
| 181 |
+
"grad_norm": 0.53231281042099,
|
| 182 |
+
"learning_rate": 1.9719404970945506e-05,
|
| 183 |
+
"loss": 1.249,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5485232067510548,
|
| 188 |
+
"grad_norm": 0.8335980176925659,
|
| 189 |
+
"learning_rate": 1.9694602620267575e-05,
|
| 190 |
+
"loss": 1.2184,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.569620253164557,
|
| 195 |
+
"grad_norm": 0.48649874329566956,
|
| 196 |
+
"learning_rate": 1.9668766980139283e-05,
|
| 197 |
+
"loss": 1.2538,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5907172995780591,
|
| 202 |
+
"grad_norm": 0.5631985068321228,
|
| 203 |
+
"learning_rate": 1.9641900804226286e-05,
|
| 204 |
+
"loss": 1.2088,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6118143459915611,
|
| 209 |
+
"grad_norm": 0.5892934799194336,
|
| 210 |
+
"learning_rate": 1.961400695603288e-05,
|
| 211 |
+
"loss": 1.189,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6329113924050633,
|
| 216 |
+
"grad_norm": 0.9515223503112793,
|
| 217 |
+
"learning_rate": 1.9585088408596758e-05,
|
| 218 |
+
"loss": 1.2768,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6540084388185654,
|
| 223 |
+
"grad_norm": 0.4848034679889679,
|
| 224 |
+
"learning_rate": 1.9555148244172155e-05,
|
| 225 |
+
"loss": 1.1582,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6751054852320675,
|
| 230 |
+
"grad_norm": 0.8658956289291382,
|
| 231 |
+
"learning_rate": 1.9524189653901326e-05,
|
| 232 |
+
"loss": 1.1797,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6962025316455697,
|
| 237 |
+
"grad_norm": 0.5689557194709778,
|
| 238 |
+
"learning_rate": 1.9492215937474416e-05,
|
| 239 |
+
"loss": 1.2036,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7172995780590717,
|
| 244 |
+
"grad_norm": 0.47713547945022583,
|
| 245 |
+
"learning_rate": 1.9459230502777765e-05,
|
| 246 |
+
"loss": 1.1822,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7383966244725738,
|
| 251 |
+
"grad_norm": 0.5391554832458496,
|
| 252 |
+
"learning_rate": 1.9425236865530693e-05,
|
| 253 |
+
"loss": 1.1276,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.759493670886076,
|
| 258 |
+
"grad_norm": 0.4558831751346588,
|
| 259 |
+
"learning_rate": 1.9390238648910765e-05,
|
| 260 |
+
"loss": 1.1413,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7805907172995781,
|
| 265 |
+
"grad_norm": 0.6209776401519775,
|
| 266 |
+
"learning_rate": 1.935423958316763e-05,
|
| 267 |
+
"loss": 1.1602,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8016877637130801,
|
| 272 |
+
"grad_norm": 3.7902824878692627,
|
| 273 |
+
"learning_rate": 1.9317243505225432e-05,
|
| 274 |
+
"loss": 1.1335,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8227848101265823,
|
| 279 |
+
"grad_norm": 0.46277958154678345,
|
| 280 |
+
"learning_rate": 1.9279254358273857e-05,
|
| 281 |
+
"loss": 1.0967,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8438818565400844,
|
| 286 |
+
"grad_norm": 0.5270448327064514,
|
| 287 |
+
"learning_rate": 1.9240276191347843e-05,
|
| 288 |
+
"loss": 1.1255,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8649789029535865,
|
| 293 |
+
"grad_norm": 0.5431308150291443,
|
| 294 |
+
"learning_rate": 1.9200313158896034e-05,
|
| 295 |
+
"loss": 1.1804,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8860759493670886,
|
| 300 |
+
"grad_norm": 0.5265894532203674,
|
| 301 |
+
"learning_rate": 1.915936952033797e-05,
|
| 302 |
+
"loss": 1.1411,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.9071729957805907,
|
| 307 |
+
"grad_norm": 0.4602664113044739,
|
| 308 |
+
"learning_rate": 1.9117449639610105e-05,
|
| 309 |
+
"loss": 1.1545,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9282700421940928,
|
| 314 |
+
"grad_norm": 0.5221014618873596,
|
| 315 |
+
"learning_rate": 1.9074557984700685e-05,
|
| 316 |
+
"loss": 1.098,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9493670886075949,
|
| 321 |
+
"grad_norm": 0.45506101846694946,
|
| 322 |
+
"learning_rate": 1.9030699127173518e-05,
|
| 323 |
+
"loss": 1.1323,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9704641350210971,
|
| 328 |
+
"grad_norm": 0.6054735779762268,
|
| 329 |
+
"learning_rate": 1.8985877741680735e-05,
|
| 330 |
+
"loss": 1.1156,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.9915611814345991,
|
| 335 |
+
"grad_norm": 0.5910170078277588,
|
| 336 |
+
"learning_rate": 1.8940098605464544e-05,
|
| 337 |
+
"loss": 1.0949,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.0126582278481013,
|
| 342 |
+
"grad_norm": 0.5487635135650635,
|
| 343 |
+
"learning_rate": 1.8893366597848036e-05,
|
| 344 |
+
"loss": 1.1163,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.0337552742616034,
|
| 349 |
+
"grad_norm": 0.78420090675354,
|
| 350 |
+
"learning_rate": 1.884568669971515e-05,
|
| 351 |
+
"loss": 1.1012,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.0548523206751055,
|
| 356 |
+
"grad_norm": 0.5282578468322754,
|
| 357 |
+
"learning_rate": 1.8797063992979786e-05,
|
| 358 |
+
"loss": 1.0687,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.0759493670886076,
|
| 363 |
+
"grad_norm": 0.5505881309509277,
|
| 364 |
+
"learning_rate": 1.8747503660044127e-05,
|
| 365 |
+
"loss": 1.1008,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.0970464135021096,
|
| 370 |
+
"grad_norm": 0.5666527152061462,
|
| 371 |
+
"learning_rate": 1.869701098324633e-05,
|
| 372 |
+
"loss": 1.071,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.1181434599156117,
|
| 377 |
+
"grad_norm": 0.507770836353302,
|
| 378 |
+
"learning_rate": 1.864559134429745e-05,
|
| 379 |
+
"loss": 1.0876,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.139240506329114,
|
| 384 |
+
"grad_norm": 0.5918306112289429,
|
| 385 |
+
"learning_rate": 1.85932502237079e-05,
|
| 386 |
+
"loss": 1.0926,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.160337552742616,
|
| 391 |
+
"grad_norm": 0.5296492576599121,
|
| 392 |
+
"learning_rate": 1.853999320020326e-05,
|
| 393 |
+
"loss": 1.0804,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.1814345991561181,
|
| 398 |
+
"grad_norm": 0.583659827709198,
|
| 399 |
+
"learning_rate": 1.8485825950129715e-05,
|
| 400 |
+
"loss": 1.1073,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.2025316455696202,
|
| 405 |
+
"grad_norm": 0.46049240231513977,
|
| 406 |
+
"learning_rate": 1.8430754246849024e-05,
|
| 407 |
+
"loss": 1.0384,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.2236286919831223,
|
| 412 |
+
"grad_norm": 0.49372121691703796,
|
| 413 |
+
"learning_rate": 1.8374783960123178e-05,
|
| 414 |
+
"loss": 1.0382,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.2447257383966246,
|
| 419 |
+
"grad_norm": 1.3448891639709473,
|
| 420 |
+
"learning_rate": 1.831792105548879e-05,
|
| 421 |
+
"loss": 1.0804,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.2658227848101267,
|
| 426 |
+
"grad_norm": 0.4508301019668579,
|
| 427 |
+
"learning_rate": 1.826017159362124e-05,
|
| 428 |
+
"loss": 1.0698,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.2869198312236287,
|
| 433 |
+
"grad_norm": 0.6035999655723572,
|
| 434 |
+
"learning_rate": 1.8201541729688727e-05,
|
| 435 |
+
"loss": 1.0308,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.3080168776371308,
|
| 440 |
+
"grad_norm": 0.6147104501724243,
|
| 441 |
+
"learning_rate": 1.8142037712696213e-05,
|
| 442 |
+
"loss": 1.0251,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.3291139240506329,
|
| 447 |
+
"grad_norm": 0.6955983638763428,
|
| 448 |
+
"learning_rate": 1.8081665884819376e-05,
|
| 449 |
+
"loss": 1.0428,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.350210970464135,
|
| 454 |
+
"grad_norm": 0.7107847929000854,
|
| 455 |
+
"learning_rate": 1.8020432680728655e-05,
|
| 456 |
+
"loss": 1.0337,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.371308016877637,
|
| 461 |
+
"grad_norm": 0.6034618020057678,
|
| 462 |
+
"learning_rate": 1.79583446269034e-05,
|
| 463 |
+
"loss": 1.0401,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.3924050632911391,
|
| 468 |
+
"grad_norm": 0.49049898982048035,
|
| 469 |
+
"learning_rate": 1.789540834093626e-05,
|
| 470 |
+
"loss": 1.0474,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.4135021097046414,
|
| 475 |
+
"grad_norm": 1.1223995685577393,
|
| 476 |
+
"learning_rate": 1.7831630530827843e-05,
|
| 477 |
+
"loss": 1.0551,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.4345991561181435,
|
| 482 |
+
"grad_norm": 0.9353031516075134,
|
| 483 |
+
"learning_rate": 1.7767017994271764e-05,
|
| 484 |
+
"loss": 1.0567,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.4556962025316456,
|
| 489 |
+
"grad_norm": 0.4723357856273651,
|
| 490 |
+
"learning_rate": 1.7701577617930126e-05,
|
| 491 |
+
"loss": 1.0528,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.4767932489451476,
|
| 496 |
+
"grad_norm": 0.5055142641067505,
|
| 497 |
+
"learning_rate": 1.763531637669949e-05,
|
| 498 |
+
"loss": 1.0344,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.49789029535865,
|
| 503 |
+
"grad_norm": 0.49486976861953735,
|
| 504 |
+
"learning_rate": 1.7568241332967474e-05,
|
| 505 |
+
"loss": 1.0346,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.518987341772152,
|
| 510 |
+
"grad_norm": 0.7445654273033142,
|
| 511 |
+
"learning_rate": 1.7500359635860018e-05,
|
| 512 |
+
"loss": 0.9996,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.540084388185654,
|
| 517 |
+
"grad_norm": 0.5551081299781799,
|
| 518 |
+
"learning_rate": 1.7431678520479402e-05,
|
| 519 |
+
"loss": 1.0206,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.5611814345991561,
|
| 524 |
+
"grad_norm": 0.6225650310516357,
|
| 525 |
+
"learning_rate": 1.7362205307133095e-05,
|
| 526 |
+
"loss": 1.0851,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.5822784810126582,
|
| 531 |
+
"grad_norm": 0.4787660539150238,
|
| 532 |
+
"learning_rate": 1.729194740055352e-05,
|
| 533 |
+
"loss": 1.0411,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.6033755274261603,
|
| 538 |
+
"grad_norm": 0.5873054265975952,
|
| 539 |
+
"learning_rate": 1.7220912289108858e-05,
|
| 540 |
+
"loss": 1.0371,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.6244725738396624,
|
| 545 |
+
"grad_norm": 0.6177183389663696,
|
| 546 |
+
"learning_rate": 1.7149107544004868e-05,
|
| 547 |
+
"loss": 1.0862,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.6455696202531644,
|
| 552 |
+
"grad_norm": 0.6516501903533936,
|
| 553 |
+
"learning_rate": 1.7076540818477946e-05,
|
| 554 |
+
"loss": 1.0608,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.6666666666666665,
|
| 559 |
+
"grad_norm": 0.7590875625610352,
|
| 560 |
+
"learning_rate": 1.7003219846979403e-05,
|
| 561 |
+
"loss": 1.0223,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.6877637130801688,
|
| 566 |
+
"grad_norm": 0.5621942281723022,
|
| 567 |
+
"learning_rate": 1.6929152444351095e-05,
|
| 568 |
+
"loss": 1.0259,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.7088607594936709,
|
| 573 |
+
"grad_norm": 0.6706472635269165,
|
| 574 |
+
"learning_rate": 1.6854346504992486e-05,
|
| 575 |
+
"loss": 1.0054,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.729957805907173,
|
| 580 |
+
"grad_norm": 0.7586253881454468,
|
| 581 |
+
"learning_rate": 1.677881000201924e-05,
|
| 582 |
+
"loss": 1.0763,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.7510548523206753,
|
| 587 |
+
"grad_norm": 0.6050952076911926,
|
| 588 |
+
"learning_rate": 1.6702550986413396e-05,
|
| 589 |
+
"loss": 0.9916,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.7721518987341773,
|
| 594 |
+
"grad_norm": 0.5705825686454773,
|
| 595 |
+
"learning_rate": 1.6625577586165288e-05,
|
| 596 |
+
"loss": 1.0412,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.7932489451476794,
|
| 601 |
+
"grad_norm": 0.4899527132511139,
|
| 602 |
+
"learning_rate": 1.6547898005407207e-05,
|
| 603 |
+
"loss": 1.0354,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.8143459915611815,
|
| 608 |
+
"grad_norm": 0.6274574995040894,
|
| 609 |
+
"learning_rate": 1.6469520523538986e-05,
|
| 610 |
+
"loss": 0.9917,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.8354430379746836,
|
| 615 |
+
"grad_norm": 0.490570992231369,
|
| 616 |
+
"learning_rate": 1.639045349434554e-05,
|
| 617 |
+
"loss": 1.0623,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.8565400843881856,
|
| 622 |
+
"grad_norm": 0.49156588315963745,
|
| 623 |
+
"learning_rate": 1.6310705345106505e-05,
|
| 624 |
+
"loss": 1.0722,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.8776371308016877,
|
| 629 |
+
"grad_norm": 0.5059338212013245,
|
| 630 |
+
"learning_rate": 1.6230284575697986e-05,
|
| 631 |
+
"loss": 1.0307,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.8987341772151898,
|
| 636 |
+
"grad_norm": 0.5933522582054138,
|
| 637 |
+
"learning_rate": 1.614919975768665e-05,
|
| 638 |
+
"loss": 1.0517,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.9198312236286919,
|
| 643 |
+
"grad_norm": 0.5222599506378174,
|
| 644 |
+
"learning_rate": 1.6067459533416118e-05,
|
| 645 |
+
"loss": 0.987,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.9409282700421941,
|
| 650 |
+
"grad_norm": 0.6938186883926392,
|
| 651 |
+
"learning_rate": 1.5985072615085806e-05,
|
| 652 |
+
"loss": 1.0169,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.9620253164556962,
|
| 657 |
+
"grad_norm": 0.5320377945899963,
|
| 658 |
+
"learning_rate": 1.5902047783822385e-05,
|
| 659 |
+
"loss": 1.0421,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.9831223628691983,
|
| 664 |
+
"grad_norm": 0.5304467678070068,
|
| 665 |
+
"learning_rate": 1.5818393888743823e-05,
|
| 666 |
+
"loss": 1.0214,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.0042194092827006,
|
| 671 |
+
"grad_norm": 0.5151244401931763,
|
| 672 |
+
"learning_rate": 1.5734119846016224e-05,
|
| 673 |
+
"loss": 1.0074,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.0253164556962027,
|
| 678 |
+
"grad_norm": 0.5229523777961731,
|
| 679 |
+
"learning_rate": 1.5649234637903503e-05,
|
| 680 |
+
"loss": 0.9872,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.0464135021097047,
|
| 685 |
+
"grad_norm": 0.5985708832740784,
|
| 686 |
+
"learning_rate": 1.5563747311810023e-05,
|
| 687 |
+
"loss": 0.9669,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.067510548523207,
|
| 692 |
+
"grad_norm": 0.522693395614624,
|
| 693 |
+
"learning_rate": 1.547766697931628e-05,
|
| 694 |
+
"loss": 0.9778,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.088607594936709,
|
| 699 |
+
"grad_norm": 0.5560949444770813,
|
| 700 |
+
"learning_rate": 1.5391002815207772e-05,
|
| 701 |
+
"loss": 1.0171,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.109704641350211,
|
| 706 |
+
"grad_norm": 0.6248462200164795,
|
| 707 |
+
"learning_rate": 1.5303764056497086e-05,
|
| 708 |
+
"loss": 0.9818,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.130801687763713,
|
| 713 |
+
"grad_norm": 0.4498722553253174,
|
| 714 |
+
"learning_rate": 1.5215960001439402e-05,
|
| 715 |
+
"loss": 1.0226,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.151898734177215,
|
| 720 |
+
"grad_norm": 1.4349712133407593,
|
| 721 |
+
"learning_rate": 1.512760000854145e-05,
|
| 722 |
+
"loss": 1.0547,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.172995780590717,
|
| 727 |
+
"grad_norm": 0.5725253224372864,
|
| 728 |
+
"learning_rate": 1.503869349556402e-05,
|
| 729 |
+
"loss": 1.0465,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.1940928270042193,
|
| 734 |
+
"grad_norm": 0.706743597984314,
|
| 735 |
+
"learning_rate": 1.4949249938518203e-05,
|
| 736 |
+
"loss": 0.9972,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.2151898734177213,
|
| 741 |
+
"grad_norm": 0.5506371259689331,
|
| 742 |
+
"learning_rate": 1.4859278870655387e-05,
|
| 743 |
+
"loss": 0.9572,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.2362869198312234,
|
| 748 |
+
"grad_norm": 0.5830360054969788,
|
| 749 |
+
"learning_rate": 1.476878988145117e-05,
|
| 750 |
+
"loss": 0.9966,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.257383966244726,
|
| 755 |
+
"grad_norm": 0.564736008644104,
|
| 756 |
+
"learning_rate": 1.4677792615583277e-05,
|
| 757 |
+
"loss": 0.9768,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.278481012658228,
|
| 762 |
+
"grad_norm": 0.5060303807258606,
|
| 763 |
+
"learning_rate": 1.4586296771903582e-05,
|
| 764 |
+
"loss": 0.9935,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.29957805907173,
|
| 769 |
+
"grad_norm": 0.499325692653656,
|
| 770 |
+
"learning_rate": 1.4494312102404382e-05,
|
| 771 |
+
"loss": 0.9918,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.320675105485232,
|
| 776 |
+
"grad_norm": 0.5975970029830933,
|
| 777 |
+
"learning_rate": 1.440184841117897e-05,
|
| 778 |
+
"loss": 0.9811,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.3417721518987342,
|
| 783 |
+
"grad_norm": 0.6109151244163513,
|
| 784 |
+
"learning_rate": 1.43089155533767e-05,
|
| 785 |
+
"loss": 1.0358,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.3628691983122363,
|
| 790 |
+
"grad_norm": 0.5909796953201294,
|
| 791 |
+
"learning_rate": 1.4215523434152562e-05,
|
| 792 |
+
"loss": 1.0327,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.3839662447257384,
|
| 797 |
+
"grad_norm": 0.5238848924636841,
|
| 798 |
+
"learning_rate": 1.4121682007611467e-05,
|
| 799 |
+
"loss": 1.003,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.4050632911392404,
|
| 804 |
+
"grad_norm": 0.6874323487281799,
|
| 805 |
+
"learning_rate": 1.4027401275747292e-05,
|
| 806 |
+
"loss": 0.9948,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.4261603375527425,
|
| 811 |
+
"grad_norm": 0.5528364181518555,
|
| 812 |
+
"learning_rate": 1.3932691287376829e-05,
|
| 813 |
+
"loss": 1.0084,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.4472573839662446,
|
| 818 |
+
"grad_norm": 0.5873010754585266,
|
| 819 |
+
"learning_rate": 1.3837562137068746e-05,
|
| 820 |
+
"loss": 0.9936,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.4683544303797467,
|
| 825 |
+
"grad_norm": 0.5948253273963928,
|
| 826 |
+
"learning_rate": 1.3742023964067657e-05,
|
| 827 |
+
"loss": 1.0179,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.489451476793249,
|
| 832 |
+
"grad_norm": 2.4981517791748047,
|
| 833 |
+
"learning_rate": 1.3646086951213451e-05,
|
| 834 |
+
"loss": 0.9609,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.510548523206751,
|
| 839 |
+
"grad_norm": 0.8416944146156311,
|
| 840 |
+
"learning_rate": 1.3549761323855963e-05,
|
| 841 |
+
"loss": 0.9583,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.5316455696202533,
|
| 846 |
+
"grad_norm": 0.5092337131500244,
|
| 847 |
+
"learning_rate": 1.3453057348765109e-05,
|
| 848 |
+
"loss": 0.9639,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.5527426160337554,
|
| 853 |
+
"grad_norm": 0.6320915222167969,
|
| 854 |
+
"learning_rate": 1.335598533303662e-05,
|
| 855 |
+
"loss": 1.0155,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.5738396624472575,
|
| 860 |
+
"grad_norm": 0.5696821808815002,
|
| 861 |
+
"learning_rate": 1.3258555622993465e-05,
|
| 862 |
+
"loss": 0.9251,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.5949367088607596,
|
| 867 |
+
"grad_norm": 0.5761372447013855,
|
| 868 |
+
"learning_rate": 1.3160778603083104e-05,
|
| 869 |
+
"loss": 1.0202,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.6160337552742616,
|
| 874 |
+
"grad_norm": 0.5222246050834656,
|
| 875 |
+
"learning_rate": 1.3062664694770668e-05,
|
| 876 |
+
"loss": 0.9805,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.6371308016877637,
|
| 881 |
+
"grad_norm": 0.7842735052108765,
|
| 882 |
+
"learning_rate": 1.2964224355428194e-05,
|
| 883 |
+
"loss": 1.0286,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.6582278481012658,
|
| 888 |
+
"grad_norm": 0.5675404667854309,
|
| 889 |
+
"learning_rate": 1.2865468077220052e-05,
|
| 890 |
+
"loss": 1.0586,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.679324894514768,
|
| 895 |
+
"grad_norm": 0.5645381212234497,
|
| 896 |
+
"learning_rate": 1.2766406385984625e-05,
|
| 897 |
+
"loss": 0.9967,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.70042194092827,
|
| 902 |
+
"grad_norm": 0.5045151114463806,
|
| 903 |
+
"learning_rate": 1.2667049840112446e-05,
|
| 904 |
+
"loss": 1.0062,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.721518987341772,
|
| 909 |
+
"grad_norm": 0.615481972694397,
|
| 910 |
+
"learning_rate": 1.2567409029420828e-05,
|
| 911 |
+
"loss": 1.0349,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.742616033755274,
|
| 916 |
+
"grad_norm": 0.5723300576210022,
|
| 917 |
+
"learning_rate": 1.2467494574025166e-05,
|
| 918 |
+
"loss": 0.9948,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.7637130801687766,
|
| 923 |
+
"grad_norm": 0.5182732939720154,
|
| 924 |
+
"learning_rate": 1.2367317123206989e-05,
|
| 925 |
+
"loss": 0.9959,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.7848101265822782,
|
| 930 |
+
"grad_norm": 0.5043283104896545,
|
| 931 |
+
"learning_rate": 1.2266887354278949e-05,
|
| 932 |
+
"loss": 0.9774,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.8059071729957807,
|
| 937 |
+
"grad_norm": 0.609108030796051,
|
| 938 |
+
"learning_rate": 1.2166215971446749e-05,
|
| 939 |
+
"loss": 0.9801,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.827004219409283,
|
| 944 |
+
"grad_norm": 0.6657718420028687,
|
| 945 |
+
"learning_rate": 1.2065313704668276e-05,
|
| 946 |
+
"loss": 0.9891,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.848101265822785,
|
| 951 |
+
"grad_norm": 0.49846649169921875,
|
| 952 |
+
"learning_rate": 1.1964191308509949e-05,
|
| 953 |
+
"loss": 0.9791,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.869198312236287,
|
| 958 |
+
"grad_norm": 0.7247899174690247,
|
| 959 |
+
"learning_rate": 1.1862859561000452e-05,
|
| 960 |
+
"loss": 0.969,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.890295358649789,
|
| 965 |
+
"grad_norm": 0.542321503162384,
|
| 966 |
+
"learning_rate": 1.1761329262481981e-05,
|
| 967 |
+
"loss": 0.9655,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.911392405063291,
|
| 972 |
+
"grad_norm": 0.5614388585090637,
|
| 973 |
+
"learning_rate": 1.165961123445908e-05,
|
| 974 |
+
"loss": 0.9902,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.932489451476793,
|
| 979 |
+
"grad_norm": 0.5627961754798889,
|
| 980 |
+
"learning_rate": 1.1557716318445259e-05,
|
| 981 |
+
"loss": 0.9746,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.9535864978902953,
|
| 986 |
+
"grad_norm": 0.6578301787376404,
|
| 987 |
+
"learning_rate": 1.1455655374807452e-05,
|
| 988 |
+
"loss": 0.9727,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.9746835443037973,
|
| 993 |
+
"grad_norm": 0.6406633257865906,
|
| 994 |
+
"learning_rate": 1.1353439281608486e-05,
|
| 995 |
+
"loss": 0.9755,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.9957805907173,
|
| 1000 |
+
"grad_norm": 0.5521556735038757,
|
| 1001 |
+
"learning_rate": 1.1251078933447643e-05,
|
| 1002 |
+
"loss": 0.9525,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.0168776371308015,
|
| 1007 |
+
"grad_norm": 0.5983248353004456,
|
| 1008 |
+
"learning_rate": 1.1148585240299477e-05,
|
| 1009 |
+
"loss": 0.9821,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.037974683544304,
|
| 1014 |
+
"grad_norm": 0.7607985734939575,
|
| 1015 |
+
"learning_rate": 1.1045969126350982e-05,
|
| 1016 |
+
"loss": 0.9958,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.059071729957806,
|
| 1021 |
+
"grad_norm": 0.5998318791389465,
|
| 1022 |
+
"learning_rate": 1.094324152883725e-05,
|
| 1023 |
+
"loss": 1.0006,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.080168776371308,
|
| 1028 |
+
"grad_norm": 0.5375860929489136,
|
| 1029 |
+
"learning_rate": 1.0840413396875733e-05,
|
| 1030 |
+
"loss": 0.9893,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.1012658227848102,
|
| 1035 |
+
"grad_norm": 0.5799211263656616,
|
| 1036 |
+
"learning_rate": 1.0737495690299256e-05,
|
| 1037 |
+
"loss": 0.9625,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.1223628691983123,
|
| 1042 |
+
"grad_norm": 0.5588505864143372,
|
| 1043 |
+
"learning_rate": 1.063449937848785e-05,
|
| 1044 |
+
"loss": 0.9497,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 3.1434599156118144,
|
| 1049 |
+
"grad_norm": 0.6329061388969421,
|
| 1050 |
+
"learning_rate": 1.053143543919962e-05,
|
| 1051 |
+
"loss": 0.9664,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.1645569620253164,
|
| 1056 |
+
"grad_norm": 0.6371050477027893,
|
| 1057 |
+
"learning_rate": 1.0428314857400666e-05,
|
| 1058 |
+
"loss": 0.9833,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.1856540084388185,
|
| 1063 |
+
"grad_norm": 0.7161750197410583,
|
| 1064 |
+
"learning_rate": 1.0325148624094274e-05,
|
| 1065 |
+
"loss": 0.9926,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.2067510548523206,
|
| 1070 |
+
"grad_norm": 0.7472956776618958,
|
| 1071 |
+
"learning_rate": 1.0221947735149463e-05,
|
| 1072 |
+
"loss": 0.963,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.2278481012658227,
|
| 1077 |
+
"grad_norm": 0.5231541395187378,
|
| 1078 |
+
"learning_rate": 1.0118723190128969e-05,
|
| 1079 |
+
"loss": 1.0121,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.2489451476793247,
|
| 1084 |
+
"grad_norm": 0.5988788604736328,
|
| 1085 |
+
"learning_rate": 1.0015485991116904e-05,
|
| 1086 |
+
"loss": 0.9946,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 3.270042194092827,
|
| 1091 |
+
"grad_norm": 0.5369338393211365,
|
| 1092 |
+
"learning_rate": 9.91224714154608e-06,
|
| 1093 |
+
"loss": 0.9719,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.291139240506329,
|
| 1098 |
+
"grad_norm": 0.7602208852767944,
|
| 1099 |
+
"learning_rate": 9.809017645025242e-06,
|
| 1100 |
+
"loss": 1.0155,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.3122362869198314,
|
| 1105 |
+
"grad_norm": 1.0432655811309814,
|
| 1106 |
+
"learning_rate": 9.705808504166241e-06,
|
| 1107 |
+
"loss": 0.9271,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 3.3333333333333335,
|
| 1112 |
+
"grad_norm": 0.6576730608940125,
|
| 1113 |
+
"learning_rate": 9.602630719411347e-06,
|
| 1114 |
+
"loss": 0.9607,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.3544303797468356,
|
| 1119 |
+
"grad_norm": 0.6119015216827393,
|
| 1120 |
+
"learning_rate": 9.499495287860767e-06,
|
| 1121 |
+
"loss": 0.9346,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 3.3755274261603376,
|
| 1126 |
+
"grad_norm": 0.5240073800086975,
|
| 1127 |
+
"learning_rate": 9.39641320210054e-06,
|
| 1128 |
+
"loss": 0.9865,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.3966244725738397,
|
| 1133 |
+
"grad_norm": 0.5481302738189697,
|
| 1134 |
+
"learning_rate": 9.29339544903089e-06,
|
| 1135 |
+
"loss": 0.9459,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.4177215189873418,
|
| 1140 |
+
"grad_norm": 0.5367913246154785,
|
| 1141 |
+
"learning_rate": 9.190453008695211e-06,
|
| 1142 |
+
"loss": 0.9328,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.438818565400844,
|
| 1147 |
+
"grad_norm": 0.5393932461738586,
|
| 1148 |
+
"learning_rate": 9.087596853109763e-06,
|
| 1149 |
+
"loss": 0.9799,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.459915611814346,
|
| 1154 |
+
"grad_norm": 0.5419475436210632,
|
| 1155 |
+
"learning_rate": 8.984837945094236e-06,
|
| 1156 |
+
"loss": 0.946,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.481012658227848,
|
| 1161 |
+
"grad_norm": 0.4995289742946625,
|
| 1162 |
+
"learning_rate": 8.882187237103283e-06,
|
| 1163 |
+
"loss": 0.9512,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.50210970464135,
|
| 1168 |
+
"grad_norm": 0.6618465781211853,
|
| 1169 |
+
"learning_rate": 8.779655670059167e-06,
|
| 1170 |
+
"loss": 0.9976,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.523206751054852,
|
| 1175 |
+
"grad_norm": 0.5813521146774292,
|
| 1176 |
+
"learning_rate": 8.677254172185632e-06,
|
| 1177 |
+
"loss": 0.9626,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.5443037974683547,
|
| 1182 |
+
"grad_norm": 0.49877235293388367,
|
| 1183 |
+
"learning_rate": 8.574993657843135e-06,
|
| 1184 |
+
"loss": 0.9186,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.5654008438818563,
|
| 1189 |
+
"grad_norm": 0.6298680305480957,
|
| 1190 |
+
"learning_rate": 8.472885026365537e-06,
|
| 1191 |
+
"loss": 0.9909,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 3.586497890295359,
|
| 1196 |
+
"grad_norm": 0.8999304175376892,
|
| 1197 |
+
"learning_rate": 8.37093916089843e-06,
|
| 1198 |
+
"loss": 0.9434,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.607594936708861,
|
| 1203 |
+
"grad_norm": 0.6086742281913757,
|
| 1204 |
+
"learning_rate": 8.269166927239136e-06,
|
| 1205 |
+
"loss": 1.0081,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.628691983122363,
|
| 1210 |
+
"grad_norm": 0.5396959185600281,
|
| 1211 |
+
"learning_rate": 8.16757917267863e-06,
|
| 1212 |
+
"loss": 1.0028,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.649789029535865,
|
| 1217 |
+
"grad_norm": 0.48324915766716003,
|
| 1218 |
+
"learning_rate": 8.066186724845344e-06,
|
| 1219 |
+
"loss": 0.9769,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.670886075949367,
|
| 1224 |
+
"grad_norm": 0.5358965396881104,
|
| 1225 |
+
"learning_rate": 7.965000390551155e-06,
|
| 1226 |
+
"loss": 0.9697,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.691983122362869,
|
| 1231 |
+
"grad_norm": 0.6094380021095276,
|
| 1232 |
+
"learning_rate": 7.86403095463953e-06,
|
| 1233 |
+
"loss": 1.0159,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 3.7130801687763713,
|
| 1238 |
+
"grad_norm": 1.5224417448043823,
|
| 1239 |
+
"learning_rate": 7.763289178836044e-06,
|
| 1240 |
+
"loss": 0.9389,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 3.7341772151898733,
|
| 1245 |
+
"grad_norm": 0.5542327761650085,
|
| 1246 |
+
"learning_rate": 7.662785800601342e-06,
|
| 1247 |
+
"loss": 0.8919,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.7552742616033754,
|
| 1252 |
+
"grad_norm": 0.5416964888572693,
|
| 1253 |
+
"learning_rate": 7.562531531986713e-06,
|
| 1254 |
+
"loss": 0.9842,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 3.7763713080168775,
|
| 1259 |
+
"grad_norm": 0.5305083394050598,
|
| 1260 |
+
"learning_rate": 7.462537058492343e-06,
|
| 1261 |
+
"loss": 0.95,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 3.7974683544303796,
|
| 1266 |
+
"grad_norm": 0.7290380001068115,
|
| 1267 |
+
"learning_rate": 7.362813037928419e-06,
|
| 1268 |
+
"loss": 0.9207,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.818565400843882,
|
| 1273 |
+
"grad_norm": 0.6322868466377258,
|
| 1274 |
+
"learning_rate": 7.263370099279173e-06,
|
| 1275 |
+
"loss": 0.9681,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 3.8396624472573837,
|
| 1280 |
+
"grad_norm": 0.5915969014167786,
|
| 1281 |
+
"learning_rate": 7.1642188415700074e-06,
|
| 1282 |
+
"loss": 0.9749,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 3.8607594936708862,
|
| 1287 |
+
"grad_norm": 0.5843455195426941,
|
| 1288 |
+
"learning_rate": 7.065369832737796e-06,
|
| 1289 |
+
"loss": 0.972,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 3.8818565400843883,
|
| 1294 |
+
"grad_norm": 0.5843347907066345,
|
| 1295 |
+
"learning_rate": 6.966833608504542e-06,
|
| 1296 |
+
"loss": 1.0092,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 3.9029535864978904,
|
| 1301 |
+
"grad_norm": 0.5809078216552734,
|
| 1302 |
+
"learning_rate": 6.868620671254389e-06,
|
| 1303 |
+
"loss": 0.9749,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 3.9240506329113924,
|
| 1308 |
+
"grad_norm": 0.6204249262809753,
|
| 1309 |
+
"learning_rate": 6.770741488914291e-06,
|
| 1310 |
+
"loss": 0.9546,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.9451476793248945,
|
| 1315 |
+
"grad_norm": 0.6413384675979614,
|
| 1316 |
+
"learning_rate": 6.673206493838247e-06,
|
| 1317 |
+
"loss": 0.9374,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 3.9662447257383966,
|
| 1322 |
+
"grad_norm": 0.5627954006195068,
|
| 1323 |
+
"learning_rate": 6.576026081695421e-06,
|
| 1324 |
+
"loss": 0.9751,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 3.9873417721518987,
|
| 1329 |
+
"grad_norm": 0.5923116207122803,
|
| 1330 |
+
"learning_rate": 6.479210610362103e-06,
|
| 1331 |
+
"loss": 0.9937,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 4.008438818565401,
|
| 1336 |
+
"grad_norm": 0.5560117363929749,
|
| 1337 |
+
"learning_rate": 6.382770398817741e-06,
|
| 1338 |
+
"loss": 0.9403,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 4.029535864978903,
|
| 1343 |
+
"grad_norm": 0.6586416363716125,
|
| 1344 |
+
"learning_rate": 6.286715726045089e-06,
|
| 1345 |
+
"loss": 0.9965,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.050632911392405,
|
| 1350 |
+
"grad_norm": 0.4938979148864746,
|
| 1351 |
+
"learning_rate": 6.191056829934647e-06,
|
| 1352 |
+
"loss": 0.9334,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 4.071729957805907,
|
| 1357 |
+
"grad_norm": 0.5240390300750732,
|
| 1358 |
+
"learning_rate": 6.095803906193452e-06,
|
| 1359 |
+
"loss": 0.9452,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 4.0928270042194095,
|
| 1364 |
+
"grad_norm": 0.8655621409416199,
|
| 1365 |
+
"learning_rate": 6.000967107258388e-06,
|
| 1366 |
+
"loss": 0.9959,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 4.113924050632911,
|
| 1371 |
+
"grad_norm": 0.6976946592330933,
|
| 1372 |
+
"learning_rate": 5.906556541214099e-06,
|
| 1373 |
+
"loss": 0.9801,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 4.135021097046414,
|
| 1378 |
+
"grad_norm": 0.5815954804420471,
|
| 1379 |
+
"learning_rate": 5.812582270715621e-06,
|
| 1380 |
+
"loss": 0.9402,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 4.156118143459915,
|
| 1385 |
+
"grad_norm": 0.5947538614273071,
|
| 1386 |
+
"learning_rate": 5.7190543119158704e-06,
|
| 1387 |
+
"loss": 0.9987,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 4.177215189873418,
|
| 1392 |
+
"grad_norm": 0.6958327889442444,
|
| 1393 |
+
"learning_rate": 5.6259826333980835e-06,
|
| 1394 |
+
"loss": 0.9857,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 4.198312236286919,
|
| 1399 |
+
"grad_norm": 0.9180216193199158,
|
| 1400 |
+
"learning_rate": 5.533377155113313e-06,
|
| 1401 |
+
"loss": 1.007,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 4.219409282700422,
|
| 1406 |
+
"grad_norm": 0.5390021204948425,
|
| 1407 |
+
"learning_rate": 5.441247747323148e-06,
|
| 1408 |
+
"loss": 0.9497,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 4.2405063291139244,
|
| 1413 |
+
"grad_norm": 0.9804661273956299,
|
| 1414 |
+
"learning_rate": 5.3496042295476665e-06,
|
| 1415 |
+
"loss": 0.9817,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 4.261603375527426,
|
| 1420 |
+
"grad_norm": 0.5353003144264221,
|
| 1421 |
+
"learning_rate": 5.258456369518856e-06,
|
| 1422 |
+
"loss": 0.9536,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 4.282700421940929,
|
| 1427 |
+
"grad_norm": 0.7157588005065918,
|
| 1428 |
+
"learning_rate": 5.167813882139518e-06,
|
| 1429 |
+
"loss": 0.9536,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 4.30379746835443,
|
| 1434 |
+
"grad_norm": 0.6708821058273315,
|
| 1435 |
+
"learning_rate": 5.077686428447835e-06,
|
| 1436 |
+
"loss": 0.9559,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 4.324894514767933,
|
| 1441 |
+
"grad_norm": 0.6380380392074585,
|
| 1442 |
+
"learning_rate": 4.9880836145876145e-06,
|
| 1443 |
+
"loss": 0.9588,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 4.345991561181434,
|
| 1448 |
+
"grad_norm": 0.6591257452964783,
|
| 1449 |
+
"learning_rate": 4.899014990784485e-06,
|
| 1450 |
+
"loss": 1.0262,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 4.367088607594937,
|
| 1455 |
+
"grad_norm": 0.5861677527427673,
|
| 1456 |
+
"learning_rate": 4.810490050327952e-06,
|
| 1457 |
+
"loss": 0.9388,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 4.3881856540084385,
|
| 1462 |
+
"grad_norm": 0.9419888257980347,
|
| 1463 |
+
"learning_rate": 4.7225182285595785e-06,
|
| 1464 |
+
"loss": 0.9411,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 4.409282700421941,
|
| 1469 |
+
"grad_norm": 0.5278356075286865,
|
| 1470 |
+
"learning_rate": 4.63510890186733e-06,
|
| 1471 |
+
"loss": 0.9645,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 4.430379746835443,
|
| 1476 |
+
"grad_norm": 0.7032003998756409,
|
| 1477 |
+
"learning_rate": 4.548271386686211e-06,
|
| 1478 |
+
"loss": 0.9719,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 4.451476793248945,
|
| 1483 |
+
"grad_norm": 0.6221036314964294,
|
| 1484 |
+
"learning_rate": 4.4620149385052615e-06,
|
| 1485 |
+
"loss": 0.9467,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 4.472573839662447,
|
| 1490 |
+
"grad_norm": 0.5741263031959534,
|
| 1491 |
+
"learning_rate": 4.3763487508810845e-06,
|
| 1492 |
+
"loss": 0.9745,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 4.493670886075949,
|
| 1497 |
+
"grad_norm": 0.5083219408988953,
|
| 1498 |
+
"learning_rate": 4.291281954457952e-06,
|
| 1499 |
+
"loss": 0.917,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 4.514767932489452,
|
| 1504 |
+
"grad_norm": 0.6289077401161194,
|
| 1505 |
+
"learning_rate": 4.206823615994641e-06,
|
| 1506 |
+
"loss": 0.9575,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 4.5358649789029535,
|
| 1511 |
+
"grad_norm": 0.5753020644187927,
|
| 1512 |
+
"learning_rate": 4.1229827373980366e-06,
|
| 1513 |
+
"loss": 0.9767,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 4.556962025316456,
|
| 1518 |
+
"grad_norm": 0.6226878762245178,
|
| 1519 |
+
"learning_rate": 4.039768254763695e-06,
|
| 1520 |
+
"loss": 0.9485,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 4.578059071729958,
|
| 1525 |
+
"grad_norm": 0.6323665380477905,
|
| 1526 |
+
"learning_rate": 3.957189037423381e-06,
|
| 1527 |
+
"loss": 1.0249,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 4.59915611814346,
|
| 1532 |
+
"grad_norm": 0.5639895796775818,
|
| 1533 |
+
"learning_rate": 3.8752538869997655e-06,
|
| 1534 |
+
"loss": 0.9755,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 4.620253164556962,
|
| 1539 |
+
"grad_norm": 0.5681629180908203,
|
| 1540 |
+
"learning_rate": 3.7939715364682704e-06,
|
| 1541 |
+
"loss": 0.9597,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 4.641350210970464,
|
| 1546 |
+
"grad_norm": 1.1015621423721313,
|
| 1547 |
+
"learning_rate": 3.7133506492263237e-06,
|
| 1548 |
+
"loss": 0.9353,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 4.662447257383966,
|
| 1553 |
+
"grad_norm": 0.5930614471435547,
|
| 1554 |
+
"learning_rate": 3.633399818169939e-06,
|
| 1555 |
+
"loss": 0.9802,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 4.6835443037974684,
|
| 1560 |
+
"grad_norm": 0.7959696650505066,
|
| 1561 |
+
"learning_rate": 3.5541275647778804e-06,
|
| 1562 |
+
"loss": 0.9717,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 4.70464135021097,
|
| 1567 |
+
"grad_norm": 0.5339838266372681,
|
| 1568 |
+
"learning_rate": 3.475542338203377e-06,
|
| 1569 |
+
"loss": 0.9193,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 4.725738396624473,
|
| 1574 |
+
"grad_norm": 0.5793105959892273,
|
| 1575 |
+
"learning_rate": 3.397652514373616e-06,
|
| 1576 |
+
"loss": 0.9267,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 4.746835443037975,
|
| 1581 |
+
"grad_norm": 0.5588264465332031,
|
| 1582 |
+
"learning_rate": 3.3204663950969717e-06,
|
| 1583 |
+
"loss": 0.9833,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 4.767932489451477,
|
| 1588 |
+
"grad_norm": 0.5399629473686218,
|
| 1589 |
+
"learning_rate": 3.2439922071781814e-06,
|
| 1590 |
+
"loss": 0.92,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 4.789029535864979,
|
| 1595 |
+
"grad_norm": 0.599014163017273,
|
| 1596 |
+
"learning_rate": 3.1682381015414942e-06,
|
| 1597 |
+
"loss": 0.93,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 4.810126582278481,
|
| 1602 |
+
"grad_norm": 0.5534657835960388,
|
| 1603 |
+
"learning_rate": 3.093212152361923e-06,
|
| 1604 |
+
"loss": 0.9384,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 4.831223628691983,
|
| 1609 |
+
"grad_norm": 0.4902456998825073,
|
| 1610 |
+
"learning_rate": 3.0189223562046476e-06,
|
| 1611 |
+
"loss": 0.965,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 4.852320675105485,
|
| 1616 |
+
"grad_norm": 0.525508463382721,
|
| 1617 |
+
"learning_rate": 2.945376631172726e-06,
|
| 1618 |
+
"loss": 0.9382,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 4.8734177215189876,
|
| 1623 |
+
"grad_norm": 0.5271111130714417,
|
| 1624 |
+
"learning_rate": 2.872582816063141e-06,
|
| 1625 |
+
"loss": 0.8921,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 4.894514767932489,
|
| 1630 |
+
"grad_norm": 0.5723162889480591,
|
| 1631 |
+
"learning_rate": 2.8005486695313234e-06,
|
| 1632 |
+
"loss": 0.9736,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 4.915611814345992,
|
| 1637 |
+
"grad_norm": 0.6840436458587646,
|
| 1638 |
+
"learning_rate": 2.7292818692641778e-06,
|
| 1639 |
+
"loss": 0.9456,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 4.936708860759493,
|
| 1644 |
+
"grad_norm": 0.5373286604881287,
|
| 1645 |
+
"learning_rate": 2.6587900111617983e-06,
|
| 1646 |
+
"loss": 0.9295,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 4.957805907172996,
|
| 1651 |
+
"grad_norm": 0.6412104964256287,
|
| 1652 |
+
"learning_rate": 2.5890806085278352e-06,
|
| 1653 |
+
"loss": 0.8981,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 4.978902953586498,
|
| 1658 |
+
"grad_norm": 0.8979920148849487,
|
| 1659 |
+
"learning_rate": 2.5201610912687267e-06,
|
| 1660 |
+
"loss": 0.9915,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 5.0,
|
| 1665 |
+
"grad_norm": 1.023783802986145,
|
| 1666 |
+
"learning_rate": 2.452038805101753e-06,
|
| 1667 |
+
"loss": 0.9515,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 5.0210970464135025,
|
| 1672 |
+
"grad_norm": 0.526311993598938,
|
| 1673 |
+
"learning_rate": 2.384721010772143e-06,
|
| 1674 |
+
"loss": 0.985,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 5.042194092827004,
|
| 1679 |
+
"grad_norm": 0.6119584441184998,
|
| 1680 |
+
"learning_rate": 2.3182148832791596e-06,
|
| 1681 |
+
"loss": 0.963,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 5.063291139240507,
|
| 1686 |
+
"grad_norm": 0.5512840747833252,
|
| 1687 |
+
"learning_rate": 2.252527511111381e-06,
|
| 1688 |
+
"loss": 0.995,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 5.084388185654008,
|
| 1693 |
+
"grad_norm": 0.655735194683075,
|
| 1694 |
+
"learning_rate": 2.187665895491169e-06,
|
| 1695 |
+
"loss": 0.977,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 5.105485232067511,
|
| 1700 |
+
"grad_norm": 0.4825851619243622,
|
| 1701 |
+
"learning_rate": 2.1236369496284637e-06,
|
| 1702 |
+
"loss": 0.9355,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 5.1265822784810124,
|
| 1707 |
+
"grad_norm": 0.5352940559387207,
|
| 1708 |
+
"learning_rate": 2.0604474979839304e-06,
|
| 1709 |
+
"loss": 0.96,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 5.147679324894515,
|
| 1714 |
+
"grad_norm": 0.50180584192276,
|
| 1715 |
+
"learning_rate": 1.998104275541595e-06,
|
| 1716 |
+
"loss": 0.9304,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 5.168776371308017,
|
| 1721 |
+
"grad_norm": 0.6091214418411255,
|
| 1722 |
+
"learning_rate": 1.936613927090988e-06,
|
| 1723 |
+
"loss": 0.9572,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 5.189873417721519,
|
| 1728 |
+
"grad_norm": 0.5810332298278809,
|
| 1729 |
+
"learning_rate": 1.87598300651894e-06,
|
| 1730 |
+
"loss": 0.9476,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 5.210970464135021,
|
| 1735 |
+
"grad_norm": 0.8323220014572144,
|
| 1736 |
+
"learning_rate": 1.8162179761110078e-06,
|
| 1737 |
+
"loss": 0.942,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 5.232067510548523,
|
| 1742 |
+
"grad_norm": 0.47791892290115356,
|
| 1743 |
+
"learning_rate": 1.7573252058627367e-06,
|
| 1744 |
+
"loss": 0.9274,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 5.253164556962025,
|
| 1749 |
+
"grad_norm": 0.549113392829895,
|
| 1750 |
+
"learning_rate": 1.6993109728006873e-06,
|
| 1751 |
+
"loss": 0.9421,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 5.274261603375527,
|
| 1756 |
+
"grad_norm": 0.5429459810256958,
|
| 1757 |
+
"learning_rate": 1.6421814603134346e-06,
|
| 1758 |
+
"loss": 0.9327,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 5.29535864978903,
|
| 1763 |
+
"grad_norm": 0.5613409876823425,
|
| 1764 |
+
"learning_rate": 1.5859427574924812e-06,
|
| 1765 |
+
"loss": 0.9333,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 5.3164556962025316,
|
| 1770 |
+
"grad_norm": 0.5223398208618164,
|
| 1771 |
+
"learning_rate": 1.530600858483301e-06,
|
| 1772 |
+
"loss": 0.9675,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 5.337552742616034,
|
| 1777 |
+
"grad_norm": 0.9334096908569336,
|
| 1778 |
+
"learning_rate": 1.4761616618464247e-06,
|
| 1779 |
+
"loss": 0.9793,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 5.358649789029536,
|
| 1784 |
+
"grad_norm": 0.7707008123397827,
|
| 1785 |
+
"learning_rate": 1.4226309699287644e-06,
|
| 1786 |
+
"loss": 0.9329,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 5.379746835443038,
|
| 1791 |
+
"grad_norm": 0.7877485752105713,
|
| 1792 |
+
"learning_rate": 1.3700144882451693e-06,
|
| 1793 |
+
"loss": 0.9336,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 5.40084388185654,
|
| 1798 |
+
"grad_norm": 0.6202056407928467,
|
| 1799 |
+
"learning_rate": 1.3183178248703187e-06,
|
| 1800 |
+
"loss": 0.9396,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 5.421940928270042,
|
| 1805 |
+
"grad_norm": 0.6117923259735107,
|
| 1806 |
+
"learning_rate": 1.2675464898409772e-06,
|
| 1807 |
+
"loss": 0.9758,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 5.443037974683544,
|
| 1812 |
+
"grad_norm": 0.6278054714202881,
|
| 1813 |
+
"learning_rate": 1.2177058945687248e-06,
|
| 1814 |
+
"loss": 0.9744,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 5.4641350210970465,
|
| 1819 |
+
"grad_norm": 0.6328499913215637,
|
| 1820 |
+
"learning_rate": 1.1688013512631768e-06,
|
| 1821 |
+
"loss": 1.0033,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 5.485232067510548,
|
| 1826 |
+
"grad_norm": 0.6842343211174011,
|
| 1827 |
+
"learning_rate": 1.120838072365803e-06,
|
| 1828 |
+
"loss": 0.9515,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 5.506329113924051,
|
| 1833 |
+
"grad_norm": 0.7078588008880615,
|
| 1834 |
+
"learning_rate": 1.0738211699943458e-06,
|
| 1835 |
+
"loss": 0.9005,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 5.527426160337553,
|
| 1840 |
+
"grad_norm": 0.6245320439338684,
|
| 1841 |
+
"learning_rate": 1.0277556553979605e-06,
|
| 1842 |
+
"loss": 0.9987,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 5.548523206751055,
|
| 1847 |
+
"grad_norm": 0.6007537245750427,
|
| 1848 |
+
"learning_rate": 9.826464384230983e-07,
|
| 1849 |
+
"loss": 0.95,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 5.569620253164557,
|
| 1854 |
+
"grad_norm": 0.5233466625213623,
|
| 1855 |
+
"learning_rate": 9.38498326990196e-07,
|
| 1856 |
+
"loss": 0.9524,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 5.590717299578059,
|
| 1861 |
+
"grad_norm": 0.9564990401268005,
|
| 1862 |
+
"learning_rate": 8.953160265812088e-07,
|
| 1863 |
+
"loss": 0.9375,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 5.6118143459915615,
|
| 1868 |
+
"grad_norm": 0.5528080463409424,
|
| 1869 |
+
"learning_rate": 8.531041397381179e-07,
|
| 1870 |
+
"loss": 0.9601,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 5.632911392405063,
|
| 1875 |
+
"grad_norm": 0.5790895223617554,
|
| 1876 |
+
"learning_rate": 8.118671655723375e-07,
|
| 1877 |
+
"loss": 0.9187,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 5.654008438818566,
|
| 1882 |
+
"grad_norm": 0.609240710735321,
|
| 1883 |
+
"learning_rate": 7.716094992852041e-07,
|
| 1884 |
+
"loss": 0.9405,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 5.675105485232067,
|
| 1889 |
+
"grad_norm": 0.6695911288261414,
|
| 1890 |
+
"learning_rate": 7.323354316995057e-07,
|
| 1891 |
+
"loss": 0.942,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 5.69620253164557,
|
| 1896 |
+
"grad_norm": 0.6779336333274841,
|
| 1897 |
+
"learning_rate": 6.940491488021595e-07,
|
| 1898 |
+
"loss": 0.9464,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 5.717299578059071,
|
| 1903 |
+
"grad_norm": 0.5404800176620483,
|
| 1904 |
+
"learning_rate": 6.567547312980438e-07,
|
| 1905 |
+
"loss": 0.9421,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 5.738396624472574,
|
| 1910 |
+
"grad_norm": 0.6370323896408081,
|
| 1911 |
+
"learning_rate": 6.204561541750643e-07,
|
| 1912 |
+
"loss": 0.9601,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 5.759493670886076,
|
| 1917 |
+
"grad_norm": 0.5309698581695557,
|
| 1918 |
+
"learning_rate": 5.851572862804811e-07,
|
| 1919 |
+
"loss": 0.9586,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 5.780590717299578,
|
| 1924 |
+
"grad_norm": 0.5793449878692627,
|
| 1925 |
+
"learning_rate": 5.508618899085583e-07,
|
| 1926 |
+
"loss": 0.9522,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 5.80168776371308,
|
| 1931 |
+
"grad_norm": 0.6610496640205383,
|
| 1932 |
+
"learning_rate": 5.175736203995541e-07,
|
| 1933 |
+
"loss": 0.9673,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 5.822784810126582,
|
| 1938 |
+
"grad_norm": 0.707855224609375,
|
| 1939 |
+
"learning_rate": 4.852960257501293e-07,
|
| 1940 |
+
"loss": 0.9816,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 5.843881856540085,
|
| 1945 |
+
"grad_norm": 0.5480538606643677,
|
| 1946 |
+
"learning_rate": 4.5403254623517914e-07,
|
| 1947 |
+
"loss": 0.9561,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 5.864978902953586,
|
| 1952 |
+
"grad_norm": 0.6886956095695496,
|
| 1953 |
+
"learning_rate": 4.2378651404116566e-07,
|
| 1954 |
+
"loss": 0.9979,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 5.886075949367089,
|
| 1959 |
+
"grad_norm": 0.5038341879844666,
|
| 1960 |
+
"learning_rate": 3.9456115291094275e-07,
|
| 1961 |
+
"loss": 0.9212,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 5.9071729957805905,
|
| 1966 |
+
"grad_norm": 0.6231849789619446,
|
| 1967 |
+
"learning_rate": 3.6635957780017716e-07,
|
| 1968 |
+
"loss": 0.9102,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 5.928270042194093,
|
| 1973 |
+
"grad_norm": 0.9208401441574097,
|
| 1974 |
+
"learning_rate": 3.3918479454533524e-07,
|
| 1975 |
+
"loss": 0.9473,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 5.949367088607595,
|
| 1980 |
+
"grad_norm": 0.5422254800796509,
|
| 1981 |
+
"learning_rate": 3.130396995432983e-07,
|
| 1982 |
+
"loss": 0.903,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 5.970464135021097,
|
| 1987 |
+
"grad_norm": 0.7246553301811218,
|
| 1988 |
+
"learning_rate": 2.879270794426714e-07,
|
| 1989 |
+
"loss": 0.9435,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 5.991561181434599,
|
| 1994 |
+
"grad_norm": 0.5847915410995483,
|
| 1995 |
+
"learning_rate": 2.638496108467614e-07,
|
| 1996 |
+
"loss": 0.9915,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 6.012658227848101,
|
| 2001 |
+
"grad_norm": 0.5698049068450928,
|
| 2002 |
+
"learning_rate": 2.4080986002829267e-07,
|
| 2003 |
+
"loss": 1.0059,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 6.033755274261603,
|
| 2008 |
+
"grad_norm": 0.5052976608276367,
|
| 2009 |
+
"learning_rate": 2.188102826558869e-07,
|
| 2010 |
+
"loss": 0.9318,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 6.0548523206751055,
|
| 2015 |
+
"grad_norm": 0.6817172765731812,
|
| 2016 |
+
"learning_rate": 1.9785322353232938e-07,
|
| 2017 |
+
"loss": 0.9258,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 6.075949367088608,
|
| 2022 |
+
"grad_norm": 0.53616863489151,
|
| 2023 |
+
"learning_rate": 1.779409163446455e-07,
|
| 2024 |
+
"loss": 0.9498,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 6.09704641350211,
|
| 2029 |
+
"grad_norm": 0.5920806527137756,
|
| 2030 |
+
"learning_rate": 1.5907548342603107e-07,
|
| 2031 |
+
"loss": 0.9657,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 6.118143459915612,
|
| 2036 |
+
"grad_norm": 0.8010777235031128,
|
| 2037 |
+
"learning_rate": 1.4125893552964122e-07,
|
| 2038 |
+
"loss": 0.9843,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 6.139240506329114,
|
| 2043 |
+
"grad_norm": 0.5737888813018799,
|
| 2044 |
+
"learning_rate": 1.2449317161427942e-07,
|
| 2045 |
+
"loss": 0.9208,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 6.160337552742616,
|
| 2050 |
+
"grad_norm": 0.5839754343032837,
|
| 2051 |
+
"learning_rate": 1.0877997864199519e-07,
|
| 2052 |
+
"loss": 0.9246,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 6.181434599156118,
|
| 2057 |
+
"grad_norm": 0.6490985751152039,
|
| 2058 |
+
"learning_rate": 9.412103138762618e-08,
|
| 2059 |
+
"loss": 0.9679,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 6.2025316455696204,
|
| 2064 |
+
"grad_norm": 0.5477576851844788,
|
| 2065 |
+
"learning_rate": 8.051789226029338e-08,
|
| 2066 |
+
"loss": 0.9961,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 6.223628691983122,
|
| 2071 |
+
"grad_norm": 0.6516560912132263,
|
| 2072 |
+
"learning_rate": 6.797201113687313e-08,
|
| 2073 |
+
"loss": 0.9696,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 6.244725738396625,
|
| 2078 |
+
"grad_norm": 0.5474268794059753,
|
| 2079 |
+
"learning_rate": 5.648472520745851e-08,
|
| 2080 |
+
"loss": 0.9495,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 6.265822784810126,
|
| 2085 |
+
"grad_norm": 0.49119266867637634,
|
| 2086 |
+
"learning_rate": 4.605725883284562e-08,
|
| 2087 |
+
"loss": 0.9818,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 6.286919831223629,
|
| 2092 |
+
"grad_norm": 0.711467444896698,
|
| 2093 |
+
"learning_rate": 3.669072341403013e-08,
|
| 2094 |
+
"loss": 0.96,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 6.308016877637131,
|
| 2099 |
+
"grad_norm": 0.6409249305725098,
|
| 2100 |
+
"learning_rate": 2.8386117273749846e-08,
|
| 2101 |
+
"loss": 0.9632,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 6.329113924050633,
|
| 2106 |
+
"grad_norm": 0.7857047915458679,
|
| 2107 |
+
"learning_rate": 2.1144325550079837e-08,
|
| 2108 |
+
"loss": 0.9326,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 6.350210970464135,
|
| 2113 |
+
"grad_norm": 0.6604498028755188,
|
| 2114 |
+
"learning_rate": 1.4966120102094527e-08,
|
| 2115 |
+
"loss": 0.9718,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 6.371308016877637,
|
| 2120 |
+
"grad_norm": 0.5844841003417969,
|
| 2121 |
+
"learning_rate": 9.852159427594655e-09,
|
| 2122 |
+
"loss": 0.9742,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 6.3924050632911396,
|
| 2127 |
+
"grad_norm": 0.6354609727859497,
|
| 2128 |
+
"learning_rate": 5.802988592925607e-09,
|
| 2129 |
+
"loss": 0.9509,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 6.413502109704641,
|
| 2134 |
+
"grad_norm": 0.6316894888877869,
|
| 2135 |
+
"learning_rate": 2.8190391748794678e-09,
|
| 2136 |
+
"loss": 0.9592,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 6.434599156118144,
|
| 2141 |
+
"grad_norm": 0.5979645848274231,
|
| 2142 |
+
"learning_rate": 9.006292146984674e-10,
|
| 2143 |
+
"loss": 0.9484,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 6.455696202531645,
|
| 2148 |
+
"grad_norm": 0.6670655608177185,
|
| 2149 |
+
"learning_rate": 4.796318417432666e-11,
|
| 2150 |
+
"loss": 0.9456,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
}
|
| 2153 |
+
],
|
| 2154 |
+
"logging_steps": 10,
|
| 2155 |
+
"max_steps": 3063,
|
| 2156 |
+
"num_input_tokens_seen": 0,
|
| 2157 |
+
"num_train_epochs": 7,
|
| 2158 |
+
"save_steps": 500,
|
| 2159 |
+
"stateful_callbacks": {
|
| 2160 |
+
"TrainerControl": {
|
| 2161 |
+
"args": {
|
| 2162 |
+
"should_epoch_stop": false,
|
| 2163 |
+
"should_evaluate": false,
|
| 2164 |
+
"should_log": false,
|
| 2165 |
+
"should_save": true,
|
| 2166 |
+
"should_training_stop": true
|
| 2167 |
+
},
|
| 2168 |
+
"attributes": {}
|
| 2169 |
+
}
|
| 2170 |
+
},
|
| 2171 |
+
"total_flos": 4.3676544022452634e+17,
|
| 2172 |
+
"train_batch_size": 4,
|
| 2173 |
+
"trial_name": null,
|
| 2174 |
+
"trial_params": null
|
| 2175 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28c12cce4f72f2bd64ab74a87a422d0b87d8849ad69e053be6927c24ebe821c3
|
| 3 |
+
size 5496
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|