Upload folder using huggingface_hub
Browse files- README.md +202 -3
- adapter_config.json +31 -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 +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +187 -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: ibm-granite/granite-3b-code-base-2k
|
| 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 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3b-code-base-2k",
|
| 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 |
+
"q_proj",
|
| 23 |
+
"up_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"gate_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM"
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c8da5146914187a9c7aab1a04d41f0857180254b4abed40e20d4c80dba2c2fd
|
| 3 |
+
size 120646088
|
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 sha256:62b34568320ba3bc92d143898e12d119ab2c10364be2e47ece8dbe24e4b8232b
|
| 3 |
+
size 60929044
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a00094faa25436b9e8484315c37a7bc16af2a97506f1a85a0599d8afadc3c474
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7583583053cbb38a8e1efa830c23b8ba5155109f21f76543e83dab7ca2732924
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"pad_token": {
|
| 38 |
+
"content": "<|endoftext|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<|endoftext|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<filename>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<gh_stars>",
|
| 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": "<empty_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<commit_before>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<commit_msg>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<commit_after>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<reponame>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
}
|
| 156 |
+
},
|
| 157 |
+
"additional_special_tokens": [
|
| 158 |
+
"<|endoftext|>",
|
| 159 |
+
"<fim_prefix>",
|
| 160 |
+
"<fim_middle>",
|
| 161 |
+
"<fim_suffix>",
|
| 162 |
+
"<fim_pad>",
|
| 163 |
+
"<filename>",
|
| 164 |
+
"<gh_stars>",
|
| 165 |
+
"<issue_start>",
|
| 166 |
+
"<issue_comment>",
|
| 167 |
+
"<issue_closed>",
|
| 168 |
+
"<jupyter_start>",
|
| 169 |
+
"<jupyter_text>",
|
| 170 |
+
"<jupyter_code>",
|
| 171 |
+
"<jupyter_output>",
|
| 172 |
+
"<empty_output>",
|
| 173 |
+
"<commit_before>",
|
| 174 |
+
"<commit_msg>",
|
| 175 |
+
"<commit_after>",
|
| 176 |
+
"<reponame>"
|
| 177 |
+
],
|
| 178 |
+
"bos_token": "<|endoftext|>",
|
| 179 |
+
"clean_up_tokenization_spaces": true,
|
| 180 |
+
"eos_token": "<|endoftext|>",
|
| 181 |
+
"model_max_length": 9223372036854775807,
|
| 182 |
+
"pad_token": "<|endoftext|>",
|
| 183 |
+
"padding_side": "left",
|
| 184 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 185 |
+
"unk_token": "<|endoftext|>",
|
| 186 |
+
"vocab_size": 49152
|
| 187 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.961363636363636,
|
| 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": 0.022727272727272728,
|
| 13 |
+
"grad_norm": 0.026781119406223297,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 0.922,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.045454545454545456,
|
| 20 |
+
"grad_norm": 0.024741673842072487,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 0.8923,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06818181818181818,
|
| 27 |
+
"grad_norm": 0.02995569072663784,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 0.9527,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09090909090909091,
|
| 34 |
+
"grad_norm": 0.029402069747447968,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 0.9525,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11363636363636363,
|
| 41 |
+
"grad_norm": 0.030222086235880852,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 0.868,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13636363636363635,
|
| 48 |
+
"grad_norm": 0.026196401566267014,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 0.8827,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1590909090909091,
|
| 55 |
+
"grad_norm": 0.029812786728143692,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 0.9446,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.18181818181818182,
|
| 62 |
+
"grad_norm": 0.02471482940018177,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 0.9012,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.20454545454545456,
|
| 69 |
+
"grad_norm": 0.032019663602113724,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 0.9249,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.22727272727272727,
|
| 76 |
+
"grad_norm": 0.03502049297094345,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 0.9458,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.25,
|
| 83 |
+
"grad_norm": 0.03877561166882515,
|
| 84 |
+
"learning_rate": 4.4e-06,
|
| 85 |
+
"loss": 0.9368,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2727272727272727,
|
| 90 |
+
"grad_norm": 0.03687964007258415,
|
| 91 |
+
"learning_rate": 4.800000000000001e-06,
|
| 92 |
+
"loss": 0.9022,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.29545454545454547,
|
| 97 |
+
"grad_norm": 0.03736700490117073,
|
| 98 |
+
"learning_rate": 5.2e-06,
|
| 99 |
+
"loss": 0.9155,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3181818181818182,
|
| 104 |
+
"grad_norm": 0.04338955879211426,
|
| 105 |
+
"learning_rate": 5.600000000000001e-06,
|
| 106 |
+
"loss": 0.8981,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3409090909090909,
|
| 111 |
+
"grad_norm": 0.03441348299384117,
|
| 112 |
+
"learning_rate": 6e-06,
|
| 113 |
+
"loss": 0.8779,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.36363636363636365,
|
| 118 |
+
"grad_norm": 0.04274949058890343,
|
| 119 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 120 |
+
"loss": 0.9095,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.38636363636363635,
|
| 125 |
+
"grad_norm": 0.04366679862141609,
|
| 126 |
+
"learning_rate": 6.800000000000001e-06,
|
| 127 |
+
"loss": 0.8781,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.4090909090909091,
|
| 132 |
+
"grad_norm": 0.041996780782938004,
|
| 133 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 134 |
+
"loss": 0.9327,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4318181818181818,
|
| 139 |
+
"grad_norm": 0.050978969782590866,
|
| 140 |
+
"learning_rate": 7.600000000000001e-06,
|
| 141 |
+
"loss": 0.864,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.45454545454545453,
|
| 146 |
+
"grad_norm": 0.04162677377462387,
|
| 147 |
+
"learning_rate": 8.000000000000001e-06,
|
| 148 |
+
"loss": 0.9109,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.4772727272727273,
|
| 153 |
+
"grad_norm": 0.041858162730932236,
|
| 154 |
+
"learning_rate": 8.400000000000001e-06,
|
| 155 |
+
"loss": 0.8516,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5,
|
| 160 |
+
"grad_norm": 0.04480082169175148,
|
| 161 |
+
"learning_rate": 8.8e-06,
|
| 162 |
+
"loss": 0.8642,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5227272727272727,
|
| 167 |
+
"grad_norm": 0.035324063152074814,
|
| 168 |
+
"learning_rate": 9.200000000000002e-06,
|
| 169 |
+
"loss": 0.8552,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5454545454545454,
|
| 174 |
+
"grad_norm": 0.04161485657095909,
|
| 175 |
+
"learning_rate": 9.600000000000001e-06,
|
| 176 |
+
"loss": 0.8037,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5681818181818182,
|
| 181 |
+
"grad_norm": 0.04798528924584389,
|
| 182 |
+
"learning_rate": 1e-05,
|
| 183 |
+
"loss": 0.8653,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5909090909090909,
|
| 188 |
+
"grad_norm": 0.03867500275373459,
|
| 189 |
+
"learning_rate": 9.999688185881378e-06,
|
| 190 |
+
"loss": 0.8552,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6136363636363636,
|
| 195 |
+
"grad_norm": 0.04236117750406265,
|
| 196 |
+
"learning_rate": 9.998752782416726e-06,
|
| 197 |
+
"loss": 0.8153,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6363636363636364,
|
| 202 |
+
"grad_norm": 0.036168813705444336,
|
| 203 |
+
"learning_rate": 9.997193906274847e-06,
|
| 204 |
+
"loss": 0.8214,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6590909090909091,
|
| 209 |
+
"grad_norm": 0.042327072471380234,
|
| 210 |
+
"learning_rate": 9.995011751887578e-06,
|
| 211 |
+
"loss": 0.8484,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6818181818181818,
|
| 216 |
+
"grad_norm": 0.03896569833159447,
|
| 217 |
+
"learning_rate": 9.992206591425538e-06,
|
| 218 |
+
"loss": 0.8249,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7045454545454546,
|
| 223 |
+
"grad_norm": 0.042347826063632965,
|
| 224 |
+
"learning_rate": 9.988778774764182e-06,
|
| 225 |
+
"loss": 0.8279,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7272727272727273,
|
| 230 |
+
"grad_norm": 0.037002451717853546,
|
| 231 |
+
"learning_rate": 9.984728729440162e-06,
|
| 232 |
+
"loss": 0.8321,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.75,
|
| 237 |
+
"grad_norm": 0.03902013972401619,
|
| 238 |
+
"learning_rate": 9.980056960598003e-06,
|
| 239 |
+
"loss": 0.8043,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7727272727272727,
|
| 244 |
+
"grad_norm": 0.03872638940811157,
|
| 245 |
+
"learning_rate": 9.974764050927098e-06,
|
| 246 |
+
"loss": 0.8564,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7954545454545454,
|
| 251 |
+
"grad_norm": 0.03531708940863609,
|
| 252 |
+
"learning_rate": 9.968850660589034e-06,
|
| 253 |
+
"loss": 0.7862,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8181818181818182,
|
| 258 |
+
"grad_norm": 0.03553822636604309,
|
| 259 |
+
"learning_rate": 9.962317527135248e-06,
|
| 260 |
+
"loss": 0.8055,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8409090909090909,
|
| 265 |
+
"grad_norm": 0.034433577209711075,
|
| 266 |
+
"learning_rate": 9.955165465415041e-06,
|
| 267 |
+
"loss": 0.8178,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8636363636363636,
|
| 272 |
+
"grad_norm": 0.03880152851343155,
|
| 273 |
+
"learning_rate": 9.947395367473945e-06,
|
| 274 |
+
"loss": 0.7978,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8863636363636364,
|
| 279 |
+
"grad_norm": 0.035060495138168335,
|
| 280 |
+
"learning_rate": 9.939008202442448e-06,
|
| 281 |
+
"loss": 0.8052,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9090909090909091,
|
| 286 |
+
"grad_norm": 0.029547426849603653,
|
| 287 |
+
"learning_rate": 9.930005016415148e-06,
|
| 288 |
+
"loss": 0.8159,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9318181818181818,
|
| 293 |
+
"grad_norm": 0.03689836710691452,
|
| 294 |
+
"learning_rate": 9.920386932320243e-06,
|
| 295 |
+
"loss": 0.8229,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.9545454545454546,
|
| 300 |
+
"grad_norm": 0.035304516553878784,
|
| 301 |
+
"learning_rate": 9.910155149779505e-06,
|
| 302 |
+
"loss": 0.8144,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.9772727272727273,
|
| 307 |
+
"grad_norm": 0.03637601435184479,
|
| 308 |
+
"learning_rate": 9.899310944958634e-06,
|
| 309 |
+
"loss": 0.8451,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.0,
|
| 314 |
+
"grad_norm": 0.032583512365818024,
|
| 315 |
+
"learning_rate": 9.887855670408098e-06,
|
| 316 |
+
"loss": 0.8083,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.0227272727272727,
|
| 321 |
+
"grad_norm": 0.037623800337314606,
|
| 322 |
+
"learning_rate": 9.87579075489443e-06,
|
| 323 |
+
"loss": 0.8463,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.0454545454545454,
|
| 328 |
+
"grad_norm": 0.0319579653441906,
|
| 329 |
+
"learning_rate": 9.863117703222032e-06,
|
| 330 |
+
"loss": 0.8575,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0681818181818181,
|
| 335 |
+
"grad_norm": 0.03368237987160683,
|
| 336 |
+
"learning_rate": 9.849838096045475e-06,
|
| 337 |
+
"loss": 0.8193,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.0909090909090908,
|
| 342 |
+
"grad_norm": 0.03865516185760498,
|
| 343 |
+
"learning_rate": 9.835953589672364e-06,
|
| 344 |
+
"loss": 0.7893,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.1136363636363635,
|
| 349 |
+
"grad_norm": 0.0340314581990242,
|
| 350 |
+
"learning_rate": 9.82146591585675e-06,
|
| 351 |
+
"loss": 0.8193,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.1363636363636362,
|
| 356 |
+
"grad_norm": 0.03837134689092636,
|
| 357 |
+
"learning_rate": 9.806376881583122e-06,
|
| 358 |
+
"loss": 0.7955,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.1590909090909092,
|
| 363 |
+
"grad_norm": 0.03679390251636505,
|
| 364 |
+
"learning_rate": 9.790688368841054e-06,
|
| 365 |
+
"loss": 0.8371,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.1818181818181819,
|
| 370 |
+
"grad_norm": 0.03493216633796692,
|
| 371 |
+
"learning_rate": 9.774402334390454e-06,
|
| 372 |
+
"loss": 0.8137,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.2045454545454546,
|
| 377 |
+
"grad_norm": 0.0344357043504715,
|
| 378 |
+
"learning_rate": 9.757520809517515e-06,
|
| 379 |
+
"loss": 0.8007,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.2272727272727273,
|
| 384 |
+
"grad_norm": 0.036025360226631165,
|
| 385 |
+
"learning_rate": 9.740045899781353e-06,
|
| 386 |
+
"loss": 0.8015,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.25,
|
| 391 |
+
"grad_norm": 0.03330492600798607,
|
| 392 |
+
"learning_rate": 9.721979784751403e-06,
|
| 393 |
+
"loss": 0.8023,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.2727272727272727,
|
| 398 |
+
"grad_norm": 0.03598447144031525,
|
| 399 |
+
"learning_rate": 9.703324717735556e-06,
|
| 400 |
+
"loss": 0.8281,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.2954545454545454,
|
| 405 |
+
"grad_norm": 0.03607608377933502,
|
| 406 |
+
"learning_rate": 9.684083025499125e-06,
|
| 407 |
+
"loss": 0.8004,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.3181818181818181,
|
| 412 |
+
"grad_norm": 0.03628605976700783,
|
| 413 |
+
"learning_rate": 9.664257107974633e-06,
|
| 414 |
+
"loss": 0.7802,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.3409090909090908,
|
| 419 |
+
"grad_norm": 0.036778271198272705,
|
| 420 |
+
"learning_rate": 9.643849437962476e-06,
|
| 421 |
+
"loss": 0.8156,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.3636363636363638,
|
| 426 |
+
"grad_norm": 0.03817847743630409,
|
| 427 |
+
"learning_rate": 9.622862560822515e-06,
|
| 428 |
+
"loss": 0.8253,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.3863636363636362,
|
| 433 |
+
"grad_norm": 0.039363328367471695,
|
| 434 |
+
"learning_rate": 9.601299094156584e-06,
|
| 435 |
+
"loss": 0.8231,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.4090909090909092,
|
| 440 |
+
"grad_norm": 0.04012521356344223,
|
| 441 |
+
"learning_rate": 9.579161727482027e-06,
|
| 442 |
+
"loss": 0.7971,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.4318181818181819,
|
| 447 |
+
"grad_norm": 0.03911637142300606,
|
| 448 |
+
"learning_rate": 9.556453221896234e-06,
|
| 449 |
+
"loss": 0.7919,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.4545454545454546,
|
| 454 |
+
"grad_norm": 0.037754397839307785,
|
| 455 |
+
"learning_rate": 9.53317640973227e-06,
|
| 456 |
+
"loss": 0.8145,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.4772727272727273,
|
| 461 |
+
"grad_norm": 0.03671397641301155,
|
| 462 |
+
"learning_rate": 9.509334194205597e-06,
|
| 463 |
+
"loss": 0.7797,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.5,
|
| 468 |
+
"grad_norm": 0.03528128191828728,
|
| 469 |
+
"learning_rate": 9.484929549051987e-06,
|
| 470 |
+
"loss": 0.8019,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.5227272727272727,
|
| 475 |
+
"grad_norm": 0.038603346794843674,
|
| 476 |
+
"learning_rate": 9.459965518156607e-06,
|
| 477 |
+
"loss": 0.8291,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.5454545454545454,
|
| 482 |
+
"grad_norm": 0.03947769105434418,
|
| 483 |
+
"learning_rate": 9.434445215174372e-06,
|
| 484 |
+
"loss": 0.8228,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.5681818181818183,
|
| 489 |
+
"grad_norm": 0.037381611764431,
|
| 490 |
+
"learning_rate": 9.408371823141597e-06,
|
| 491 |
+
"loss": 0.8238,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.5909090909090908,
|
| 496 |
+
"grad_norm": 0.03954509273171425,
|
| 497 |
+
"learning_rate": 9.381748594078983e-06,
|
| 498 |
+
"loss": 0.8188,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.6136363636363638,
|
| 503 |
+
"grad_norm": 0.038289956748485565,
|
| 504 |
+
"learning_rate": 9.354578848586011e-06,
|
| 505 |
+
"loss": 0.7787,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.6363636363636362,
|
| 510 |
+
"grad_norm": 0.038311704993247986,
|
| 511 |
+
"learning_rate": 9.326865975426782e-06,
|
| 512 |
+
"loss": 0.786,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.6590909090909092,
|
| 517 |
+
"grad_norm": 0.03961798921227455,
|
| 518 |
+
"learning_rate": 9.298613431107339e-06,
|
| 519 |
+
"loss": 0.7887,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.6818181818181817,
|
| 524 |
+
"grad_norm": 0.038849055767059326,
|
| 525 |
+
"learning_rate": 9.269824739444568e-06,
|
| 526 |
+
"loss": 0.8028,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.7045454545454546,
|
| 531 |
+
"grad_norm": 0.04103654995560646,
|
| 532 |
+
"learning_rate": 9.240503491126676e-06,
|
| 533 |
+
"loss": 0.8409,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.7272727272727273,
|
| 538 |
+
"grad_norm": 0.03809870034456253,
|
| 539 |
+
"learning_rate": 9.210653343265341e-06,
|
| 540 |
+
"loss": 0.809,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.75,
|
| 545 |
+
"grad_norm": 0.037855364382267,
|
| 546 |
+
"learning_rate": 9.180278018939581e-06,
|
| 547 |
+
"loss": 0.8192,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.7727272727272727,
|
| 552 |
+
"grad_norm": 0.04093025252223015,
|
| 553 |
+
"learning_rate": 9.149381306731392e-06,
|
| 554 |
+
"loss": 0.8421,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.7954545454545454,
|
| 559 |
+
"grad_norm": 0.036524541676044464,
|
| 560 |
+
"learning_rate": 9.117967060253205e-06,
|
| 561 |
+
"loss": 0.7747,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.8181818181818183,
|
| 566 |
+
"grad_norm": 0.04049857705831528,
|
| 567 |
+
"learning_rate": 9.086039197667255e-06,
|
| 568 |
+
"loss": 0.8201,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.8409090909090908,
|
| 573 |
+
"grad_norm": 0.0417928546667099,
|
| 574 |
+
"learning_rate": 9.053601701196871e-06,
|
| 575 |
+
"loss": 0.7924,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.8636363636363638,
|
| 580 |
+
"grad_norm": 0.04128099977970123,
|
| 581 |
+
"learning_rate": 9.020658616629804e-06,
|
| 582 |
+
"loss": 0.8143,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.8863636363636362,
|
| 587 |
+
"grad_norm": 0.040873561054468155,
|
| 588 |
+
"learning_rate": 8.987214052813605e-06,
|
| 589 |
+
"loss": 0.8141,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.9090909090909092,
|
| 594 |
+
"grad_norm": 0.04162426292896271,
|
| 595 |
+
"learning_rate": 8.953272181143149e-06,
|
| 596 |
+
"loss": 0.7927,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.9318181818181817,
|
| 601 |
+
"grad_norm": 0.039612602442502975,
|
| 602 |
+
"learning_rate": 8.918837235040357e-06,
|
| 603 |
+
"loss": 0.8134,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.9545454545454546,
|
| 608 |
+
"grad_norm": 0.039780184626579285,
|
| 609 |
+
"learning_rate": 8.883913509426176e-06,
|
| 610 |
+
"loss": 0.7678,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.9772727272727273,
|
| 615 |
+
"grad_norm": 0.0440000519156456,
|
| 616 |
+
"learning_rate": 8.848505360184895e-06,
|
| 617 |
+
"loss": 0.79,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.0,
|
| 622 |
+
"grad_norm": 0.04121037945151329,
|
| 623 |
+
"learning_rate": 8.812617203620853e-06,
|
| 624 |
+
"loss": 0.7499,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.022727272727273,
|
| 629 |
+
"grad_norm": 0.04250968620181084,
|
| 630 |
+
"learning_rate": 8.776253515907611e-06,
|
| 631 |
+
"loss": 0.8203,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.0454545454545454,
|
| 636 |
+
"grad_norm": 0.04543096572160721,
|
| 637 |
+
"learning_rate": 8.739418832529665e-06,
|
| 638 |
+
"loss": 0.8114,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.0681818181818183,
|
| 643 |
+
"grad_norm": 0.0420922227203846,
|
| 644 |
+
"learning_rate": 8.70211774771675e-06,
|
| 645 |
+
"loss": 0.8247,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.090909090909091,
|
| 650 |
+
"grad_norm": 0.04692165553569794,
|
| 651 |
+
"learning_rate": 8.664354913870813e-06,
|
| 652 |
+
"loss": 0.8278,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.1136363636363638,
|
| 657 |
+
"grad_norm": 0.040763940662145615,
|
| 658 |
+
"learning_rate": 8.626135040985762e-06,
|
| 659 |
+
"loss": 0.7801,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.1363636363636362,
|
| 664 |
+
"grad_norm": 0.046543512493371964,
|
| 665 |
+
"learning_rate": 8.587462896059986e-06,
|
| 666 |
+
"loss": 0.8104,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.159090909090909,
|
| 671 |
+
"grad_norm": 0.04344585910439491,
|
| 672 |
+
"learning_rate": 8.548343302501796e-06,
|
| 673 |
+
"loss": 0.8122,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.1818181818181817,
|
| 678 |
+
"grad_norm": 0.046868693083524704,
|
| 679 |
+
"learning_rate": 8.508781139527831e-06,
|
| 680 |
+
"loss": 0.8149,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.2045454545454546,
|
| 685 |
+
"grad_norm": 0.04557256028056145,
|
| 686 |
+
"learning_rate": 8.46878134155448e-06,
|
| 687 |
+
"loss": 0.7924,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.227272727272727,
|
| 692 |
+
"grad_norm": 0.04453985020518303,
|
| 693 |
+
"learning_rate": 8.428348897582442e-06,
|
| 694 |
+
"loss": 0.7918,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.25,
|
| 699 |
+
"grad_norm": 0.04629656299948692,
|
| 700 |
+
"learning_rate": 8.387488850574473e-06,
|
| 701 |
+
"loss": 0.7705,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.2727272727272725,
|
| 706 |
+
"grad_norm": 0.0446246862411499,
|
| 707 |
+
"learning_rate": 8.346206296826387e-06,
|
| 708 |
+
"loss": 0.7967,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.2954545454545454,
|
| 713 |
+
"grad_norm": 0.044356152415275574,
|
| 714 |
+
"learning_rate": 8.30450638533143e-06,
|
| 715 |
+
"loss": 0.7817,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.3181818181818183,
|
| 720 |
+
"grad_norm": 0.043874483555555344,
|
| 721 |
+
"learning_rate": 8.262394317138062e-06,
|
| 722 |
+
"loss": 0.784,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.340909090909091,
|
| 727 |
+
"grad_norm": 0.044783398509025574,
|
| 728 |
+
"learning_rate": 8.219875344701255e-06,
|
| 729 |
+
"loss": 0.787,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.3636363636363638,
|
| 734 |
+
"grad_norm": 0.04361894354224205,
|
| 735 |
+
"learning_rate": 8.176954771227372e-06,
|
| 736 |
+
"loss": 0.7436,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.3863636363636362,
|
| 741 |
+
"grad_norm": 0.04469903185963631,
|
| 742 |
+
"learning_rate": 8.133637950012732e-06,
|
| 743 |
+
"loss": 0.817,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.409090909090909,
|
| 748 |
+
"grad_norm": 0.04548465088009834,
|
| 749 |
+
"learning_rate": 8.089930283775906e-06,
|
| 750 |
+
"loss": 0.7791,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.4318181818181817,
|
| 755 |
+
"grad_norm": 0.04449579119682312,
|
| 756 |
+
"learning_rate": 8.04583722398386e-06,
|
| 757 |
+
"loss": 0.8076,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.4545454545454546,
|
| 762 |
+
"grad_norm": 0.05069056153297424,
|
| 763 |
+
"learning_rate": 8.001364270172029e-06,
|
| 764 |
+
"loss": 0.7932,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.4772727272727275,
|
| 769 |
+
"grad_norm": 0.04452840983867645,
|
| 770 |
+
"learning_rate": 7.95651696925837e-06,
|
| 771 |
+
"loss": 0.7752,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.5,
|
| 776 |
+
"grad_norm": 0.044558193534612656,
|
| 777 |
+
"learning_rate": 7.911300914851523e-06,
|
| 778 |
+
"loss": 0.7854,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.5227272727272725,
|
| 783 |
+
"grad_norm": 0.044422492384910583,
|
| 784 |
+
"learning_rate": 7.865721746553151e-06,
|
| 785 |
+
"loss": 0.7784,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.5454545454545454,
|
| 790 |
+
"grad_norm": 0.04627745598554611,
|
| 791 |
+
"learning_rate": 7.819785149254534e-06,
|
| 792 |
+
"loss": 0.7476,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.5681818181818183,
|
| 797 |
+
"grad_norm": 0.04218703508377075,
|
| 798 |
+
"learning_rate": 7.773496852427504e-06,
|
| 799 |
+
"loss": 0.8409,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.590909090909091,
|
| 804 |
+
"grad_norm": 0.050779055804014206,
|
| 805 |
+
"learning_rate": 7.72686262940986e-06,
|
| 806 |
+
"loss": 0.8242,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.6136363636363638,
|
| 811 |
+
"grad_norm": 0.04828439652919769,
|
| 812 |
+
"learning_rate": 7.679888296685256e-06,
|
| 813 |
+
"loss": 0.7958,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.6363636363636362,
|
| 818 |
+
"grad_norm": 0.05190173536539078,
|
| 819 |
+
"learning_rate": 7.632579713157755e-06,
|
| 820 |
+
"loss": 0.8086,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.659090909090909,
|
| 825 |
+
"grad_norm": 0.046120744198560715,
|
| 826 |
+
"learning_rate": 7.58494277942107e-06,
|
| 827 |
+
"loss": 0.83,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.6818181818181817,
|
| 832 |
+
"grad_norm": 0.051556602120399475,
|
| 833 |
+
"learning_rate": 7.5369834370226005e-06,
|
| 834 |
+
"loss": 0.8245,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.7045454545454546,
|
| 839 |
+
"grad_norm": 0.045309435576200485,
|
| 840 |
+
"learning_rate": 7.488707667722381e-06,
|
| 841 |
+
"loss": 0.7797,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.7272727272727275,
|
| 846 |
+
"grad_norm": 0.046404462307691574,
|
| 847 |
+
"learning_rate": 7.440121492746992e-06,
|
| 848 |
+
"loss": 0.7935,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.75,
|
| 853 |
+
"grad_norm": 0.04626648873090744,
|
| 854 |
+
"learning_rate": 7.391230972038567e-06,
|
| 855 |
+
"loss": 0.8127,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.7727272727272725,
|
| 860 |
+
"grad_norm": 0.049298033118247986,
|
| 861 |
+
"learning_rate": 7.342042203498952e-06,
|
| 862 |
+
"loss": 0.8366,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.7954545454545454,
|
| 867 |
+
"grad_norm": 0.047652631998062134,
|
| 868 |
+
"learning_rate": 7.292561322229152e-06,
|
| 869 |
+
"loss": 0.7797,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.8181818181818183,
|
| 874 |
+
"grad_norm": 0.05071092024445534,
|
| 875 |
+
"learning_rate": 7.2427944997641186e-06,
|
| 876 |
+
"loss": 0.7936,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.840909090909091,
|
| 881 |
+
"grad_norm": 0.04736604541540146,
|
| 882 |
+
"learning_rate": 7.192747943303008e-06,
|
| 883 |
+
"loss": 0.8147,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.8636363636363638,
|
| 888 |
+
"grad_norm": 0.044138215482234955,
|
| 889 |
+
"learning_rate": 7.142427894934975e-06,
|
| 890 |
+
"loss": 0.7978,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.8863636363636362,
|
| 895 |
+
"grad_norm": 0.04737458750605583,
|
| 896 |
+
"learning_rate": 7.0918406308606336e-06,
|
| 897 |
+
"loss": 0.8327,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.909090909090909,
|
| 902 |
+
"grad_norm": 0.05238456651568413,
|
| 903 |
+
"learning_rate": 7.040992460609246e-06,
|
| 904 |
+
"loss": 0.816,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.9318181818181817,
|
| 909 |
+
"grad_norm": 0.04763491824269295,
|
| 910 |
+
"learning_rate": 6.98988972625177e-06,
|
| 911 |
+
"loss": 0.8347,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.9545454545454546,
|
| 916 |
+
"grad_norm": 0.045320168137550354,
|
| 917 |
+
"learning_rate": 6.938538801609834e-06,
|
| 918 |
+
"loss": 0.79,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.9772727272727275,
|
| 923 |
+
"grad_norm": 0.04802026227116585,
|
| 924 |
+
"learning_rate": 6.886946091460762e-06,
|
| 925 |
+
"loss": 0.8046,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.0,
|
| 930 |
+
"grad_norm": 0.047994792461395264,
|
| 931 |
+
"learning_rate": 6.835118030738731e-06,
|
| 932 |
+
"loss": 0.8179,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 3.022727272727273,
|
| 937 |
+
"grad_norm": 0.04660705476999283,
|
| 938 |
+
"learning_rate": 6.78306108373217e-06,
|
| 939 |
+
"loss": 0.7756,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 3.0454545454545454,
|
| 944 |
+
"grad_norm": 0.04617464914917946,
|
| 945 |
+
"learning_rate": 6.730781743277498e-06,
|
| 946 |
+
"loss": 0.79,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 3.0681818181818183,
|
| 951 |
+
"grad_norm": 0.0491408072412014,
|
| 952 |
+
"learning_rate": 6.678286529949303e-06,
|
| 953 |
+
"loss": 0.819,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 3.090909090909091,
|
| 958 |
+
"grad_norm": 0.046425145119428635,
|
| 959 |
+
"learning_rate": 6.625581991247054e-06,
|
| 960 |
+
"loss": 0.7697,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 3.1136363636363638,
|
| 965 |
+
"grad_norm": 0.046251095831394196,
|
| 966 |
+
"learning_rate": 6.5726747007784655e-06,
|
| 967 |
+
"loss": 0.7601,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.1363636363636362,
|
| 972 |
+
"grad_norm": 0.04971086233854294,
|
| 973 |
+
"learning_rate": 6.5195712574395945e-06,
|
| 974 |
+
"loss": 0.784,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 3.159090909090909,
|
| 979 |
+
"grad_norm": 0.05220796912908554,
|
| 980 |
+
"learning_rate": 6.466278284591793e-06,
|
| 981 |
+
"loss": 0.7537,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.1818181818181817,
|
| 986 |
+
"grad_norm": 0.04714221879839897,
|
| 987 |
+
"learning_rate": 6.4128024292356065e-06,
|
| 988 |
+
"loss": 0.8391,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.2045454545454546,
|
| 993 |
+
"grad_norm": 0.051231637597084045,
|
| 994 |
+
"learning_rate": 6.3591503611817155e-06,
|
| 995 |
+
"loss": 0.8392,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 3.227272727272727,
|
| 1000 |
+
"grad_norm": 0.0514928475022316,
|
| 1001 |
+
"learning_rate": 6.305328772219044e-06,
|
| 1002 |
+
"loss": 0.7629,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.25,
|
| 1007 |
+
"grad_norm": 0.05148511752486229,
|
| 1008 |
+
"learning_rate": 6.251344375280124e-06,
|
| 1009 |
+
"loss": 0.8342,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.2727272727272725,
|
| 1014 |
+
"grad_norm": 0.050781212747097015,
|
| 1015 |
+
"learning_rate": 6.197203903603814e-06,
|
| 1016 |
+
"loss": 0.7909,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.2954545454545454,
|
| 1021 |
+
"grad_norm": 0.05220821499824524,
|
| 1022 |
+
"learning_rate": 6.142914109895499e-06,
|
| 1023 |
+
"loss": 0.8147,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.3181818181818183,
|
| 1028 |
+
"grad_norm": 0.055957481265068054,
|
| 1029 |
+
"learning_rate": 6.088481765484849e-06,
|
| 1030 |
+
"loss": 0.8109,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.340909090909091,
|
| 1035 |
+
"grad_norm": 0.047921840101480484,
|
| 1036 |
+
"learning_rate": 6.033913659481261e-06,
|
| 1037 |
+
"loss": 0.7386,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.3636363636363638,
|
| 1042 |
+
"grad_norm": 0.05010027065873146,
|
| 1043 |
+
"learning_rate": 5.979216597927088e-06,
|
| 1044 |
+
"loss": 0.7778,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 3.3863636363636362,
|
| 1049 |
+
"grad_norm": 0.05108246952295303,
|
| 1050 |
+
"learning_rate": 5.924397402948745e-06,
|
| 1051 |
+
"loss": 0.7815,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.409090909090909,
|
| 1056 |
+
"grad_norm": 0.05210183188319206,
|
| 1057 |
+
"learning_rate": 5.86946291190582e-06,
|
| 1058 |
+
"loss": 0.8016,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.4318181818181817,
|
| 1063 |
+
"grad_norm": 0.052292466163635254,
|
| 1064 |
+
"learning_rate": 5.8144199765382736e-06,
|
| 1065 |
+
"loss": 0.7615,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.4545454545454546,
|
| 1070 |
+
"grad_norm": 0.05555827170610428,
|
| 1071 |
+
"learning_rate": 5.759275462111858e-06,
|
| 1072 |
+
"loss": 0.773,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.4772727272727275,
|
| 1077 |
+
"grad_norm": 0.05111211910843849,
|
| 1078 |
+
"learning_rate": 5.704036246561836e-06,
|
| 1079 |
+
"loss": 0.8308,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.5,
|
| 1084 |
+
"grad_norm": 0.05257695913314819,
|
| 1085 |
+
"learning_rate": 5.648709219635134e-06,
|
| 1086 |
+
"loss": 0.8092,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 3.5227272727272725,
|
| 1091 |
+
"grad_norm": 0.056300047785043716,
|
| 1092 |
+
"learning_rate": 5.5933012820310095e-06,
|
| 1093 |
+
"loss": 0.8009,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.5454545454545454,
|
| 1098 |
+
"grad_norm": 0.05202391743659973,
|
| 1099 |
+
"learning_rate": 5.537819344540349e-06,
|
| 1100 |
+
"loss": 0.8005,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.5681818181818183,
|
| 1105 |
+
"grad_norm": 0.0530916303396225,
|
| 1106 |
+
"learning_rate": 5.482270327183732e-06,
|
| 1107 |
+
"loss": 0.8038,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 3.590909090909091,
|
| 1112 |
+
"grad_norm": 0.05197259411215782,
|
| 1113 |
+
"learning_rate": 5.42666115834831e-06,
|
| 1114 |
+
"loss": 0.7946,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.6136363636363638,
|
| 1119 |
+
"grad_norm": 0.052419282495975494,
|
| 1120 |
+
"learning_rate": 5.37099877392367e-06,
|
| 1121 |
+
"loss": 0.8152,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 3.6363636363636362,
|
| 1126 |
+
"grad_norm": 0.06443214416503906,
|
| 1127 |
+
"learning_rate": 5.315290116436752e-06,
|
| 1128 |
+
"loss": 0.8069,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.659090909090909,
|
| 1133 |
+
"grad_norm": 0.05957184359431267,
|
| 1134 |
+
"learning_rate": 5.259542134185925e-06,
|
| 1135 |
+
"loss": 0.8128,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.6818181818181817,
|
| 1140 |
+
"grad_norm": 0.0548897311091423,
|
| 1141 |
+
"learning_rate": 5.203761780374372e-06,
|
| 1142 |
+
"loss": 0.7734,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.7045454545454546,
|
| 1147 |
+
"grad_norm": 0.05778632313013077,
|
| 1148 |
+
"learning_rate": 5.147956012242837e-06,
|
| 1149 |
+
"loss": 0.8028,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.7272727272727275,
|
| 1154 |
+
"grad_norm": 0.057780634611845016,
|
| 1155 |
+
"learning_rate": 5.092131790201882e-06,
|
| 1156 |
+
"loss": 0.7897,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.75,
|
| 1161 |
+
"grad_norm": 0.05503814294934273,
|
| 1162 |
+
"learning_rate": 5.0362960769637415e-06,
|
| 1163 |
+
"loss": 0.7838,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.7727272727272725,
|
| 1168 |
+
"grad_norm": 0.05687331035733223,
|
| 1169 |
+
"learning_rate": 4.980455836673902e-06,
|
| 1170 |
+
"loss": 0.7852,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.7954545454545454,
|
| 1175 |
+
"grad_norm": 0.059677232056856155,
|
| 1176 |
+
"learning_rate": 4.924618034042488e-06,
|
| 1177 |
+
"loss": 0.8021,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.8181818181818183,
|
| 1182 |
+
"grad_norm": 0.056579746305942535,
|
| 1183 |
+
"learning_rate": 4.868789633475583e-06,
|
| 1184 |
+
"loss": 0.8155,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.840909090909091,
|
| 1189 |
+
"grad_norm": 0.055581267923116684,
|
| 1190 |
+
"learning_rate": 4.812977598206595e-06,
|
| 1191 |
+
"loss": 0.8065,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 3.8636363636363638,
|
| 1196 |
+
"grad_norm": 0.047986991703510284,
|
| 1197 |
+
"learning_rate": 4.757188889427761e-06,
|
| 1198 |
+
"loss": 0.8285,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.8863636363636362,
|
| 1203 |
+
"grad_norm": 0.059346918016672134,
|
| 1204 |
+
"learning_rate": 4.701430465421897e-06,
|
| 1205 |
+
"loss": 0.7768,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.909090909090909,
|
| 1210 |
+
"grad_norm": 0.059216298162937164,
|
| 1211 |
+
"learning_rate": 4.645709280694545e-06,
|
| 1212 |
+
"loss": 0.8109,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.9318181818181817,
|
| 1217 |
+
"grad_norm": 0.05952894687652588,
|
| 1218 |
+
"learning_rate": 4.590032285106541e-06,
|
| 1219 |
+
"loss": 0.8026,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.9545454545454546,
|
| 1224 |
+
"grad_norm": 0.057186175137758255,
|
| 1225 |
+
"learning_rate": 4.534406423007212e-06,
|
| 1226 |
+
"loss": 0.8187,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.9772727272727275,
|
| 1231 |
+
"grad_norm": 0.059881679713726044,
|
| 1232 |
+
"learning_rate": 4.478838632368221e-06,
|
| 1233 |
+
"loss": 0.8422,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 4.0,
|
| 1238 |
+
"grad_norm": 0.057068806141614914,
|
| 1239 |
+
"learning_rate": 4.423335843918233e-06,
|
| 1240 |
+
"loss": 0.804,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 4.0227272727272725,
|
| 1245 |
+
"grad_norm": 0.05267658457159996,
|
| 1246 |
+
"learning_rate": 4.367904980278475e-06,
|
| 1247 |
+
"loss": 0.7534,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 4.045454545454546,
|
| 1252 |
+
"grad_norm": 0.06152062863111496,
|
| 1253 |
+
"learning_rate": 4.312552955099299e-06,
|
| 1254 |
+
"loss": 0.8301,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 4.068181818181818,
|
| 1259 |
+
"grad_norm": 0.05504327639937401,
|
| 1260 |
+
"learning_rate": 4.257286672197888e-06,
|
| 1261 |
+
"loss": 0.8144,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 4.090909090909091,
|
| 1266 |
+
"grad_norm": 0.05590361729264259,
|
| 1267 |
+
"learning_rate": 4.202113024697156e-06,
|
| 1268 |
+
"loss": 0.7977,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 4.113636363636363,
|
| 1273 |
+
"grad_norm": 0.06019588187336922,
|
| 1274 |
+
"learning_rate": 4.1470388941660076e-06,
|
| 1275 |
+
"loss": 0.8213,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 4.136363636363637,
|
| 1280 |
+
"grad_norm": 0.05402204021811485,
|
| 1281 |
+
"learning_rate": 4.092071149761035e-06,
|
| 1282 |
+
"loss": 0.7839,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 4.159090909090909,
|
| 1287 |
+
"grad_norm": 0.05966588109731674,
|
| 1288 |
+
"learning_rate": 4.037216647369745e-06,
|
| 1289 |
+
"loss": 0.7739,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 4.181818181818182,
|
| 1294 |
+
"grad_norm": 0.06286252290010452,
|
| 1295 |
+
"learning_rate": 3.982482228755468e-06,
|
| 1296 |
+
"loss": 0.8067,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 4.204545454545454,
|
| 1301 |
+
"grad_norm": 0.05303211137652397,
|
| 1302 |
+
"learning_rate": 3.9278747207039995e-06,
|
| 1303 |
+
"loss": 0.7935,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.2272727272727275,
|
| 1308 |
+
"grad_norm": 0.06371833384037018,
|
| 1309 |
+
"learning_rate": 3.873400934172137e-06,
|
| 1310 |
+
"loss": 0.7752,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 4.25,
|
| 1315 |
+
"grad_norm": 0.06287337839603424,
|
| 1316 |
+
"learning_rate": 3.8190676634381775e-06,
|
| 1317 |
+
"loss": 0.8394,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 4.2727272727272725,
|
| 1322 |
+
"grad_norm": 0.059799861162900925,
|
| 1323 |
+
"learning_rate": 3.7648816852544873e-06,
|
| 1324 |
+
"loss": 0.7587,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 4.295454545454546,
|
| 1329 |
+
"grad_norm": 0.05993163585662842,
|
| 1330 |
+
"learning_rate": 3.710849758002282e-06,
|
| 1331 |
+
"loss": 0.7891,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 4.318181818181818,
|
| 1336 |
+
"grad_norm": 0.05344055965542793,
|
| 1337 |
+
"learning_rate": 3.6569786208486692e-06,
|
| 1338 |
+
"loss": 0.8,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 4.340909090909091,
|
| 1343 |
+
"grad_norm": 0.05599065497517586,
|
| 1344 |
+
"learning_rate": 3.6032749929061078e-06,
|
| 1345 |
+
"loss": 0.8135,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.363636363636363,
|
| 1350 |
+
"grad_norm": 0.0619407594203949,
|
| 1351 |
+
"learning_rate": 3.5497455723943673e-06,
|
| 1352 |
+
"loss": 0.785,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 4.386363636363637,
|
| 1357 |
+
"grad_norm": 0.06416480988264084,
|
| 1358 |
+
"learning_rate": 3.4963970358050756e-06,
|
| 1359 |
+
"loss": 0.8161,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 4.409090909090909,
|
| 1364 |
+
"grad_norm": 0.05641242861747742,
|
| 1365 |
+
"learning_rate": 3.443236037068999e-06,
|
| 1366 |
+
"loss": 0.8188,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 4.431818181818182,
|
| 1371 |
+
"grad_norm": 0.05751458555459976,
|
| 1372 |
+
"learning_rate": 3.3902692067261256e-06,
|
| 1373 |
+
"loss": 0.801,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 4.454545454545454,
|
| 1378 |
+
"grad_norm": 0.05939492955803871,
|
| 1379 |
+
"learning_rate": 3.3375031510986606e-06,
|
| 1380 |
+
"loss": 0.775,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 4.4772727272727275,
|
| 1385 |
+
"grad_norm": 0.059105709195137024,
|
| 1386 |
+
"learning_rate": 3.2849444514670587e-06,
|
| 1387 |
+
"loss": 0.7853,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 4.5,
|
| 1392 |
+
"grad_norm": 0.06332360953092575,
|
| 1393 |
+
"learning_rate": 3.2325996632491597e-06,
|
| 1394 |
+
"loss": 0.7645,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 4.5227272727272725,
|
| 1399 |
+
"grad_norm": 0.05962349474430084,
|
| 1400 |
+
"learning_rate": 3.180475315182563e-06,
|
| 1401 |
+
"loss": 0.8033,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 4.545454545454545,
|
| 1406 |
+
"grad_norm": 0.05617254227399826,
|
| 1407 |
+
"learning_rate": 3.1285779085103313e-06,
|
| 1408 |
+
"loss": 0.7815,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 4.568181818181818,
|
| 1413 |
+
"grad_norm": 0.06171968951821327,
|
| 1414 |
+
"learning_rate": 3.07691391617011e-06,
|
| 1415 |
+
"loss": 0.7809,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 4.590909090909091,
|
| 1420 |
+
"grad_norm": 0.060661982744932175,
|
| 1421 |
+
"learning_rate": 3.0254897819867974e-06,
|
| 1422 |
+
"loss": 0.8506,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 4.613636363636363,
|
| 1427 |
+
"grad_norm": 0.05857427418231964,
|
| 1428 |
+
"learning_rate": 2.974311919868821e-06,
|
| 1429 |
+
"loss": 0.7433,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 4.636363636363637,
|
| 1434 |
+
"grad_norm": 0.06344863772392273,
|
| 1435 |
+
"learning_rate": 2.9233867130081677e-06,
|
| 1436 |
+
"loss": 0.8371,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 4.659090909090909,
|
| 1441 |
+
"grad_norm": 0.056676462292671204,
|
| 1442 |
+
"learning_rate": 2.87272051308424e-06,
|
| 1443 |
+
"loss": 0.8027,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 4.681818181818182,
|
| 1448 |
+
"grad_norm": 0.06252826750278473,
|
| 1449 |
+
"learning_rate": 2.822319639471619e-06,
|
| 1450 |
+
"loss": 0.8059,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 4.704545454545455,
|
| 1455 |
+
"grad_norm": 0.06604735553264618,
|
| 1456 |
+
"learning_rate": 2.7721903784519056e-06,
|
| 1457 |
+
"loss": 0.7642,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 4.7272727272727275,
|
| 1462 |
+
"grad_norm": 0.06098971143364906,
|
| 1463 |
+
"learning_rate": 2.7223389824296354e-06,
|
| 1464 |
+
"loss": 0.7714,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 4.75,
|
| 1469 |
+
"grad_norm": 0.05798983573913574,
|
| 1470 |
+
"learning_rate": 2.6727716691524474e-06,
|
| 1471 |
+
"loss": 0.8064,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 4.7727272727272725,
|
| 1476 |
+
"grad_norm": 0.05816567689180374,
|
| 1477 |
+
"learning_rate": 2.6234946209355906e-06,
|
| 1478 |
+
"loss": 0.7697,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 4.795454545454545,
|
| 1483 |
+
"grad_norm": 0.058813825249671936,
|
| 1484 |
+
"learning_rate": 2.574513983890803e-06,
|
| 1485 |
+
"loss": 0.8058,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 4.818181818181818,
|
| 1490 |
+
"grad_norm": 0.07025865465402603,
|
| 1491 |
+
"learning_rate": 2.525835867159754e-06,
|
| 1492 |
+
"loss": 0.8349,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 4.840909090909091,
|
| 1497 |
+
"grad_norm": 0.056820739060640335,
|
| 1498 |
+
"learning_rate": 2.4774663421520688e-06,
|
| 1499 |
+
"loss": 0.768,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 4.863636363636363,
|
| 1504 |
+
"grad_norm": 0.06224190443754196,
|
| 1505 |
+
"learning_rate": 2.429411441788072e-06,
|
| 1506 |
+
"loss": 0.7897,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 4.886363636363637,
|
| 1511 |
+
"grad_norm": 0.05832672491669655,
|
| 1512 |
+
"learning_rate": 2.381677159746324e-06,
|
| 1513 |
+
"loss": 0.8114,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 4.909090909090909,
|
| 1518 |
+
"grad_norm": 0.059900589287281036,
|
| 1519 |
+
"learning_rate": 2.334269449716058e-06,
|
| 1520 |
+
"loss": 0.7891,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 4.931818181818182,
|
| 1525 |
+
"grad_norm": 0.0635821595788002,
|
| 1526 |
+
"learning_rate": 2.287194224654602e-06,
|
| 1527 |
+
"loss": 0.8026,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 4.954545454545455,
|
| 1532 |
+
"grad_norm": 0.05612201988697052,
|
| 1533 |
+
"learning_rate": 2.24045735604988e-06,
|
| 1534 |
+
"loss": 0.7916,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 4.9772727272727275,
|
| 1539 |
+
"grad_norm": 0.05763179436326027,
|
| 1540 |
+
"learning_rate": 2.1940646731880887e-06,
|
| 1541 |
+
"loss": 0.7679,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 5.0,
|
| 1546 |
+
"grad_norm": 0.05941809341311455,
|
| 1547 |
+
"learning_rate": 2.148021962426635e-06,
|
| 1548 |
+
"loss": 0.8058,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 5.0227272727272725,
|
| 1553 |
+
"grad_norm": 0.07011684030294418,
|
| 1554 |
+
"learning_rate": 2.102334966472429e-06,
|
| 1555 |
+
"loss": 0.8188,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 5.045454545454546,
|
| 1560 |
+
"grad_norm": 0.056112293154001236,
|
| 1561 |
+
"learning_rate": 2.057009383665621e-06,
|
| 1562 |
+
"loss": 0.7685,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 5.068181818181818,
|
| 1567 |
+
"grad_norm": 0.05940523371100426,
|
| 1568 |
+
"learning_rate": 2.012050867268873e-06,
|
| 1569 |
+
"loss": 0.7676,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 5.090909090909091,
|
| 1574 |
+
"grad_norm": 0.06017325818538666,
|
| 1575 |
+
"learning_rate": 1.967465024762251e-06,
|
| 1576 |
+
"loss": 0.7589,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 5.113636363636363,
|
| 1581 |
+
"grad_norm": 0.05958075076341629,
|
| 1582 |
+
"learning_rate": 1.9232574171438273e-06,
|
| 1583 |
+
"loss": 0.8143,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 5.136363636363637,
|
| 1588 |
+
"grad_norm": 0.059776924550533295,
|
| 1589 |
+
"learning_rate": 1.8794335582360873e-06,
|
| 1590 |
+
"loss": 0.8186,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 5.159090909090909,
|
| 1595 |
+
"grad_norm": 0.061050403863191605,
|
| 1596 |
+
"learning_rate": 1.8359989139982021e-06,
|
| 1597 |
+
"loss": 0.7815,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 5.181818181818182,
|
| 1602 |
+
"grad_norm": 0.05887814611196518,
|
| 1603 |
+
"learning_rate": 1.7929589018443016e-06,
|
| 1604 |
+
"loss": 0.8223,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 5.204545454545454,
|
| 1609 |
+
"grad_norm": 0.0575253888964653,
|
| 1610 |
+
"learning_rate": 1.7503188899677642e-06,
|
| 1611 |
+
"loss": 0.8012,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 5.2272727272727275,
|
| 1616 |
+
"grad_norm": 0.06290145218372345,
|
| 1617 |
+
"learning_rate": 1.7080841966716777e-06,
|
| 1618 |
+
"loss": 0.7403,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 5.25,
|
| 1623 |
+
"grad_norm": 0.06359874457120895,
|
| 1624 |
+
"learning_rate": 1.6662600897055132e-06,
|
| 1625 |
+
"loss": 0.8377,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 5.2727272727272725,
|
| 1630 |
+
"grad_norm": 0.06408390402793884,
|
| 1631 |
+
"learning_rate": 1.6248517856080848e-06,
|
| 1632 |
+
"loss": 0.7776,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 5.295454545454546,
|
| 1637 |
+
"grad_norm": 0.0607023611664772,
|
| 1638 |
+
"learning_rate": 1.5838644490569372e-06,
|
| 1639 |
+
"loss": 0.8408,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 5.318181818181818,
|
| 1644 |
+
"grad_norm": 0.06409065425395966,
|
| 1645 |
+
"learning_rate": 1.5433031922241538e-06,
|
| 1646 |
+
"loss": 0.8198,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 5.340909090909091,
|
| 1651 |
+
"grad_norm": 0.06282657384872437,
|
| 1652 |
+
"learning_rate": 1.5031730741387567e-06,
|
| 1653 |
+
"loss": 0.7881,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 5.363636363636363,
|
| 1658 |
+
"grad_norm": 0.06287471950054169,
|
| 1659 |
+
"learning_rate": 1.4634791000557058e-06,
|
| 1660 |
+
"loss": 0.7462,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 5.386363636363637,
|
| 1665 |
+
"grad_norm": 0.06724315136671066,
|
| 1666 |
+
"learning_rate": 1.4242262208316187e-06,
|
| 1667 |
+
"loss": 0.8024,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 5.409090909090909,
|
| 1672 |
+
"grad_norm": 0.061781395226716995,
|
| 1673 |
+
"learning_rate": 1.3854193323072707e-06,
|
| 1674 |
+
"loss": 0.7826,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 5.431818181818182,
|
| 1679 |
+
"grad_norm": 0.06064334139227867,
|
| 1680 |
+
"learning_rate": 1.3470632746969586e-06,
|
| 1681 |
+
"loss": 0.7883,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 5.454545454545454,
|
| 1686 |
+
"grad_norm": 0.05812542885541916,
|
| 1687 |
+
"learning_rate": 1.3091628319848016e-06,
|
| 1688 |
+
"loss": 0.7925,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 5.4772727272727275,
|
| 1693 |
+
"grad_norm": 0.059440333396196365,
|
| 1694 |
+
"learning_rate": 1.271722731328055e-06,
|
| 1695 |
+
"loss": 0.7692,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 5.5,
|
| 1700 |
+
"grad_norm": 0.06575117260217667,
|
| 1701 |
+
"learning_rate": 1.2347476424675142e-06,
|
| 1702 |
+
"loss": 0.7772,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 5.5227272727272725,
|
| 1707 |
+
"grad_norm": 0.06302516162395477,
|
| 1708 |
+
"learning_rate": 1.1982421771450775e-06,
|
| 1709 |
+
"loss": 0.7927,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 5.545454545454545,
|
| 1714 |
+
"grad_norm": 0.06540846079587936,
|
| 1715 |
+
"learning_rate": 1.1622108885285415e-06,
|
| 1716 |
+
"loss": 0.7724,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 5.568181818181818,
|
| 1721 |
+
"grad_norm": 0.06591441482305527,
|
| 1722 |
+
"learning_rate": 1.126658270643708e-06,
|
| 1723 |
+
"loss": 0.779,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 5.590909090909091,
|
| 1728 |
+
"grad_norm": 0.06068432703614235,
|
| 1729 |
+
"learning_rate": 1.0915887578138606e-06,
|
| 1730 |
+
"loss": 0.7768,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 5.613636363636363,
|
| 1735 |
+
"grad_norm": 0.0614112988114357,
|
| 1736 |
+
"learning_rate": 1.057006724106695e-06,
|
| 1737 |
+
"loss": 0.8061,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 5.636363636363637,
|
| 1742 |
+
"grad_norm": 0.06147473677992821,
|
| 1743 |
+
"learning_rate": 1.0229164827887512e-06,
|
| 1744 |
+
"loss": 0.805,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 5.659090909090909,
|
| 1749 |
+
"grad_norm": 0.06091708317399025,
|
| 1750 |
+
"learning_rate": 9.89322285787454e-07,
|
| 1751 |
+
"loss": 0.7883,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 5.681818181818182,
|
| 1756 |
+
"grad_norm": 0.05688236653804779,
|
| 1757 |
+
"learning_rate": 9.5622832316077e-07,
|
| 1758 |
+
"loss": 0.7763,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 5.704545454545455,
|
| 1763 |
+
"grad_norm": 0.06602354347705841,
|
| 1764 |
+
"learning_rate": 9.236387225746185e-07,
|
| 1765 |
+
"loss": 0.809,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 5.7272727272727275,
|
| 1770 |
+
"grad_norm": 0.06536935269832611,
|
| 1771 |
+
"learning_rate": 8.915575487880324e-07,
|
| 1772 |
+
"loss": 0.779,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 5.75,
|
| 1777 |
+
"grad_norm": 0.06449291855096817,
|
| 1778 |
+
"learning_rate": 8.599888031461801e-07,
|
| 1779 |
+
"loss": 0.7984,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 5.7727272727272725,
|
| 1784 |
+
"grad_norm": 0.06858620792627335,
|
| 1785 |
+
"learning_rate": 8.289364230813052e-07,
|
| 1786 |
+
"loss": 0.8298,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 5.795454545454545,
|
| 1791 |
+
"grad_norm": 0.05864429101347923,
|
| 1792 |
+
"learning_rate": 7.984042816216109e-07,
|
| 1793 |
+
"loss": 0.7846,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 5.818181818181818,
|
| 1798 |
+
"grad_norm": 0.059347003698349,
|
| 1799 |
+
"learning_rate": 7.683961869082146e-07,
|
| 1800 |
+
"loss": 0.8246,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 5.840909090909091,
|
| 1805 |
+
"grad_norm": 0.06505056470632553,
|
| 1806 |
+
"learning_rate": 7.389158817201541e-07,
|
| 1807 |
+
"loss": 0.811,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 5.863636363636363,
|
| 1812 |
+
"grad_norm": 0.06296805292367935,
|
| 1813 |
+
"learning_rate": 7.099670430075828e-07,
|
| 1814 |
+
"loss": 0.8004,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 5.886363636363637,
|
| 1819 |
+
"grad_norm": 0.06585711985826492,
|
| 1820 |
+
"learning_rate": 6.815532814331505e-07,
|
| 1821 |
+
"loss": 0.7814,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 5.909090909090909,
|
| 1826 |
+
"grad_norm": 0.06298382580280304,
|
| 1827 |
+
"learning_rate": 6.536781409216664e-07,
|
| 1828 |
+
"loss": 0.8115,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 5.931818181818182,
|
| 1833 |
+
"grad_norm": 0.06103487312793732,
|
| 1834 |
+
"learning_rate": 6.263450982180813e-07,
|
| 1835 |
+
"loss": 0.8036,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 5.954545454545455,
|
| 1840 |
+
"grad_norm": 0.06315191090106964,
|
| 1841 |
+
"learning_rate": 5.995575624538397e-07,
|
| 1842 |
+
"loss": 0.7637,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 5.9772727272727275,
|
| 1847 |
+
"grad_norm": 0.06248250976204872,
|
| 1848 |
+
"learning_rate": 5.733188747216845e-07,
|
| 1849 |
+
"loss": 0.7912,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 6.0,
|
| 1854 |
+
"grad_norm": 0.06412005424499512,
|
| 1855 |
+
"learning_rate": 5.476323076589319e-07,
|
| 1856 |
+
"loss": 0.815,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 6.0227272727272725,
|
| 1861 |
+
"grad_norm": 0.060897987335920334,
|
| 1862 |
+
"learning_rate": 5.225010650392887e-07,
|
| 1863 |
+
"loss": 0.8012,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 6.045454545454546,
|
| 1868 |
+
"grad_norm": 0.06144240126013756,
|
| 1869 |
+
"learning_rate": 4.979282813732622e-07,
|
| 1870 |
+
"loss": 0.798,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 6.068181818181818,
|
| 1875 |
+
"grad_norm": 0.05944688990712166,
|
| 1876 |
+
"learning_rate": 4.739170215172051e-07,
|
| 1877 |
+
"loss": 0.7948,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 6.090909090909091,
|
| 1882 |
+
"grad_norm": 0.06139964610338211,
|
| 1883 |
+
"learning_rate": 4.5047028029104877e-07,
|
| 1884 |
+
"loss": 0.8287,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 6.113636363636363,
|
| 1889 |
+
"grad_norm": 0.06420081108808517,
|
| 1890 |
+
"learning_rate": 4.27590982104773e-07,
|
| 1891 |
+
"loss": 0.7973,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 6.136363636363637,
|
| 1896 |
+
"grad_norm": 0.06291543692350388,
|
| 1897 |
+
"learning_rate": 4.0528198059365863e-07,
|
| 1898 |
+
"loss": 0.7956,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 6.159090909090909,
|
| 1903 |
+
"grad_norm": 0.05762983486056328,
|
| 1904 |
+
"learning_rate": 3.8354605826235957e-07,
|
| 1905 |
+
"loss": 0.8054,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 6.181818181818182,
|
| 1910 |
+
"grad_norm": 0.05916955694556236,
|
| 1911 |
+
"learning_rate": 3.623859261378654e-07,
|
| 1912 |
+
"loss": 0.7634,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 6.204545454545454,
|
| 1917 |
+
"grad_norm": 0.064091257750988,
|
| 1918 |
+
"learning_rate": 3.4180422343135346e-07,
|
| 1919 |
+
"loss": 0.8345,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 6.2272727272727275,
|
| 1924 |
+
"grad_norm": 0.061927612870931625,
|
| 1925 |
+
"learning_rate": 3.2180351720902003e-07,
|
| 1926 |
+
"loss": 0.8129,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 6.25,
|
| 1931 |
+
"grad_norm": 0.06499668955802917,
|
| 1932 |
+
"learning_rate": 3.0238630207189867e-07,
|
| 1933 |
+
"loss": 0.8057,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 6.2727272727272725,
|
| 1938 |
+
"grad_norm": 0.06719426810741425,
|
| 1939 |
+
"learning_rate": 2.8355499984471737e-07,
|
| 1940 |
+
"loss": 0.7677,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 6.295454545454546,
|
| 1945 |
+
"grad_norm": 0.07048514485359192,
|
| 1946 |
+
"learning_rate": 2.6531195927384067e-07,
|
| 1947 |
+
"loss": 0.8099,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 6.318181818181818,
|
| 1952 |
+
"grad_norm": 0.06214950233697891,
|
| 1953 |
+
"learning_rate": 2.476594557343126e-07,
|
| 1954 |
+
"loss": 0.7769,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 6.340909090909091,
|
| 1959 |
+
"grad_norm": 0.06586616486310959,
|
| 1960 |
+
"learning_rate": 2.305996909460695e-07,
|
| 1961 |
+
"loss": 0.8022,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 6.363636363636363,
|
| 1966 |
+
"grad_norm": 0.06200889125466347,
|
| 1967 |
+
"learning_rate": 2.141347926993176e-07,
|
| 1968 |
+
"loss": 0.771,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 6.386363636363637,
|
| 1973 |
+
"grad_norm": 0.058896422386169434,
|
| 1974 |
+
"learning_rate": 1.9826681458915088e-07,
|
| 1975 |
+
"loss": 0.7611,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 6.409090909090909,
|
| 1980 |
+
"grad_norm": 0.06591584533452988,
|
| 1981 |
+
"learning_rate": 1.8299773575941483e-07,
|
| 1982 |
+
"loss": 0.8151,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 6.431818181818182,
|
| 1987 |
+
"grad_norm": 0.05796649307012558,
|
| 1988 |
+
"learning_rate": 1.6832946065585e-07,
|
| 1989 |
+
"loss": 0.8017,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 6.454545454545454,
|
| 1994 |
+
"grad_norm": 0.059807244688272476,
|
| 1995 |
+
"learning_rate": 1.542638187885681e-07,
|
| 1996 |
+
"loss": 0.812,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 6.4772727272727275,
|
| 2001 |
+
"grad_norm": 0.06900903582572937,
|
| 2002 |
+
"learning_rate": 1.4080256450385578e-07,
|
| 2003 |
+
"loss": 0.8105,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 6.5,
|
| 2008 |
+
"grad_norm": 0.06508809328079224,
|
| 2009 |
+
"learning_rate": 1.2794737676536993e-07,
|
| 2010 |
+
"loss": 0.7147,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 6.5227272727272725,
|
| 2015 |
+
"grad_norm": 0.06716930121183395,
|
| 2016 |
+
"learning_rate": 1.1569985894472446e-07,
|
| 2017 |
+
"loss": 0.7677,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 6.545454545454545,
|
| 2022 |
+
"grad_norm": 0.06471340358257294,
|
| 2023 |
+
"learning_rate": 1.0406153862150881e-07,
|
| 2024 |
+
"loss": 0.82,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 6.568181818181818,
|
| 2029 |
+
"grad_norm": 0.05981110781431198,
|
| 2030 |
+
"learning_rate": 9.30338673927611e-08,
|
| 2031 |
+
"loss": 0.7904,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 6.590909090909091,
|
| 2036 |
+
"grad_norm": 0.06340961158275604,
|
| 2037 |
+
"learning_rate": 8.261822069191461e-08,
|
| 2038 |
+
"loss": 0.8186,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 6.613636363636363,
|
| 2043 |
+
"grad_norm": 0.06290656328201294,
|
| 2044 |
+
"learning_rate": 7.281589761724828e-08,
|
| 2045 |
+
"loss": 0.7665,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 6.636363636363637,
|
| 2050 |
+
"grad_norm": 0.07086827605962753,
|
| 2051 |
+
"learning_rate": 6.362812076985359e-08,
|
| 2052 |
+
"loss": 0.7613,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 6.659090909090909,
|
| 2057 |
+
"grad_norm": 0.06620458513498306,
|
| 2058 |
+
"learning_rate": 5.505603610114651e-08,
|
| 2059 |
+
"loss": 0.7762,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 6.681818181818182,
|
| 2064 |
+
"grad_norm": 0.06518013775348663,
|
| 2065 |
+
"learning_rate": 4.7100712769937994e-08,
|
| 2066 |
+
"loss": 0.7707,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 6.704545454545455,
|
| 2071 |
+
"grad_norm": 0.06568311899900436,
|
| 2072 |
+
"learning_rate": 3.976314300908002e-08,
|
| 2073 |
+
"loss": 0.8052,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 6.7272727272727275,
|
| 2078 |
+
"grad_norm": 0.06033078953623772,
|
| 2079 |
+
"learning_rate": 3.3044242001712415e-08,
|
| 2080 |
+
"loss": 0.7725,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 6.75,
|
| 2085 |
+
"grad_norm": 0.060128528624773026,
|
| 2086 |
+
"learning_rate": 2.6944847767114146e-08,
|
| 2087 |
+
"loss": 0.7712,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 6.7727272727272725,
|
| 2092 |
+
"grad_norm": 0.06406668573617935,
|
| 2093 |
+
"learning_rate": 2.1465721056179168e-08,
|
| 2094 |
+
"loss": 0.8116,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 6.795454545454545,
|
| 2099 |
+
"grad_norm": 0.05837489292025566,
|
| 2100 |
+
"learning_rate": 1.6607545256533407e-08,
|
| 2101 |
+
"loss": 0.8084,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 6.818181818181818,
|
| 2106 |
+
"grad_norm": 0.06511975079774857,
|
| 2107 |
+
"learning_rate": 1.2370926307300746e-08,
|
| 2108 |
+
"loss": 0.8018,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 6.840909090909091,
|
| 2113 |
+
"grad_norm": 0.0646391287446022,
|
| 2114 |
+
"learning_rate": 8.756392623521237e-09,
|
| 2115 |
+
"loss": 0.7921,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 6.863636363636363,
|
| 2120 |
+
"grad_norm": 0.06122921034693718,
|
| 2121 |
+
"learning_rate": 5.7643950302488375e-09,
|
| 2122 |
+
"loss": 0.7981,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 6.886363636363637,
|
| 2127 |
+
"grad_norm": 0.06278009712696075,
|
| 2128 |
+
"learning_rate": 3.3953067063213772e-09,
|
| 2129 |
+
"loss": 0.7755,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 6.909090909090909,
|
| 2134 |
+
"grad_norm": 0.06424996256828308,
|
| 2135 |
+
"learning_rate": 1.649423137813355e-09,
|
| 2136 |
+
"loss": 0.7825,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 6.931818181818182,
|
| 2141 |
+
"grad_norm": 0.07108237594366074,
|
| 2142 |
+
"learning_rate": 5.26962081183191e-10,
|
| 2143 |
+
"loss": 0.8121,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 6.954545454545455,
|
| 2148 |
+
"grad_norm": 0.06434624642133713,
|
| 2149 |
+
"learning_rate": 2.806353611273238e-11,
|
| 2150 |
+
"loss": 0.8185,
|
| 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": 5.098946440672051e+17,
|
| 2172 |
+
"train_batch_size": 1,
|
| 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 sha256:6550d5398c59d524b3d9cfa0df4e144a89005babaa7a1bf8a47a40f154133b18
|
| 3 |
+
size 5496
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|