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 +2413 -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 |
+
"gate_proj",
|
| 23 |
+
"v_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"up_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 sha256:36915da2aa9cf0b1bcf28089f95276bb26b6ce2b0a13aa5f394478f16fa6b106
|
| 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:f3f78ece1cbb9072c104b2accf6b1e90a456398d5c34b61e31c1e4cf67ec850d
|
| 3 |
+
size 60929044
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fece3d40ce7c05479c2710a8cb6b035e5b63dbf31866931faf6d3f173f5584f
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bec65b9b93138f1ead159ea90f2e281469faeef5662b208c752bbd45d8e84a1c
|
| 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 +1,2413 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.438194280311983,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3405,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.018908059560387616,
|
| 13 |
+
"grad_norm": 0.025965163484215736,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 0.8123,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03781611912077523,
|
| 20 |
+
"grad_norm": 0.027516305446624756,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 0.8007,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05672417868116285,
|
| 27 |
+
"grad_norm": 0.02769283391535282,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 0.8213,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07563223824155046,
|
| 34 |
+
"grad_norm": 0.025368299335241318,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 0.7853,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.09454029780193808,
|
| 41 |
+
"grad_norm": 0.026271438226103783,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 0.8131,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1134483573623257,
|
| 48 |
+
"grad_norm": 0.027166498824954033,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 0.7867,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1323564169227133,
|
| 55 |
+
"grad_norm": 0.028786830604076385,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 0.8183,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.15126447648310093,
|
| 62 |
+
"grad_norm": 0.026403894647955894,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 0.8384,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.17017253604348853,
|
| 69 |
+
"grad_norm": 0.028935490176081657,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 0.8062,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.18908059560387616,
|
| 76 |
+
"grad_norm": 0.031438667327165604,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 0.8085,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.20798865516426376,
|
| 83 |
+
"grad_norm": 0.031011823564767838,
|
| 84 |
+
"learning_rate": 4.4e-06,
|
| 85 |
+
"loss": 0.8057,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2268967147246514,
|
| 90 |
+
"grad_norm": 0.03556632995605469,
|
| 91 |
+
"learning_rate": 4.800000000000001e-06,
|
| 92 |
+
"loss": 0.7454,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.245804774285039,
|
| 97 |
+
"grad_norm": 0.0362481027841568,
|
| 98 |
+
"learning_rate": 5.2e-06,
|
| 99 |
+
"loss": 0.8343,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2647128338454266,
|
| 104 |
+
"grad_norm": 0.032787468284368515,
|
| 105 |
+
"learning_rate": 5.600000000000001e-06,
|
| 106 |
+
"loss": 0.7836,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2836208934058142,
|
| 111 |
+
"grad_norm": 0.04355374351143837,
|
| 112 |
+
"learning_rate": 6e-06,
|
| 113 |
+
"loss": 0.7873,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.30252895296620186,
|
| 118 |
+
"grad_norm": 0.035903844982385635,
|
| 119 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 120 |
+
"loss": 0.7888,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.32143701252658946,
|
| 125 |
+
"grad_norm": 0.04153973609209061,
|
| 126 |
+
"learning_rate": 6.800000000000001e-06,
|
| 127 |
+
"loss": 0.7646,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.34034507208697706,
|
| 132 |
+
"grad_norm": 0.04311086982488632,
|
| 133 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 134 |
+
"loss": 0.7963,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.35925313164736467,
|
| 139 |
+
"grad_norm": 0.047484926879405975,
|
| 140 |
+
"learning_rate": 7.600000000000001e-06,
|
| 141 |
+
"loss": 0.7631,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3781611912077523,
|
| 146 |
+
"grad_norm": 0.05766135826706886,
|
| 147 |
+
"learning_rate": 8.000000000000001e-06,
|
| 148 |
+
"loss": 0.7649,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3970692507681399,
|
| 153 |
+
"grad_norm": 0.044645749032497406,
|
| 154 |
+
"learning_rate": 8.400000000000001e-06,
|
| 155 |
+
"loss": 0.7443,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4159773103285275,
|
| 160 |
+
"grad_norm": 0.05479070544242859,
|
| 161 |
+
"learning_rate": 8.8e-06,
|
| 162 |
+
"loss": 0.7184,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.43488536988891513,
|
| 167 |
+
"grad_norm": 0.045226652175188065,
|
| 168 |
+
"learning_rate": 9.200000000000002e-06,
|
| 169 |
+
"loss": 0.7487,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4537934294493028,
|
| 174 |
+
"grad_norm": 0.041623398661613464,
|
| 175 |
+
"learning_rate": 9.600000000000001e-06,
|
| 176 |
+
"loss": 0.6997,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4727014890096904,
|
| 181 |
+
"grad_norm": 0.03361015394330025,
|
| 182 |
+
"learning_rate": 1e-05,
|
| 183 |
+
"loss": 0.712,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.491609548570078,
|
| 188 |
+
"grad_norm": 0.03581312671303749,
|
| 189 |
+
"learning_rate": 9.999752122311021e-06,
|
| 190 |
+
"loss": 0.7277,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5105176081304656,
|
| 195 |
+
"grad_norm": 0.040930092334747314,
|
| 196 |
+
"learning_rate": 9.99900851382142e-06,
|
| 197 |
+
"loss": 0.7027,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5294256676908532,
|
| 202 |
+
"grad_norm": 0.033486612141132355,
|
| 203 |
+
"learning_rate": 9.99776924826078e-06,
|
| 204 |
+
"loss": 0.7078,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5483337272512409,
|
| 209 |
+
"grad_norm": 0.04255792871117592,
|
| 210 |
+
"learning_rate": 9.996034448503617e-06,
|
| 211 |
+
"loss": 0.7065,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5672417868116284,
|
| 216 |
+
"grad_norm": 0.03878919407725334,
|
| 217 |
+
"learning_rate": 9.993804286557189e-06,
|
| 218 |
+
"loss": 0.7006,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5861498463720161,
|
| 223 |
+
"grad_norm": 0.03808160126209259,
|
| 224 |
+
"learning_rate": 9.991078983544453e-06,
|
| 225 |
+
"loss": 0.6788,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6050579059324037,
|
| 230 |
+
"grad_norm": 0.03979503735899925,
|
| 231 |
+
"learning_rate": 9.987858809682133e-06,
|
| 232 |
+
"loss": 0.7208,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6239659654927913,
|
| 237 |
+
"grad_norm": 0.035877715796232224,
|
| 238 |
+
"learning_rate": 9.984144084253932e-06,
|
| 239 |
+
"loss": 0.6906,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6428740250531789,
|
| 244 |
+
"grad_norm": 0.03366890922188759,
|
| 245 |
+
"learning_rate": 9.979935175578873e-06,
|
| 246 |
+
"loss": 0.7089,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6617820846135666,
|
| 251 |
+
"grad_norm": 0.03546404838562012,
|
| 252 |
+
"learning_rate": 9.975232500974777e-06,
|
| 253 |
+
"loss": 0.6748,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6806901441739541,
|
| 258 |
+
"grad_norm": 0.037561580538749695,
|
| 259 |
+
"learning_rate": 9.970036526716889e-06,
|
| 260 |
+
"loss": 0.6739,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6995982037343418,
|
| 265 |
+
"grad_norm": 0.034097544848918915,
|
| 266 |
+
"learning_rate": 9.964347767991645e-06,
|
| 267 |
+
"loss": 0.6683,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7185062632947293,
|
| 272 |
+
"grad_norm": 0.034007199108600616,
|
| 273 |
+
"learning_rate": 9.958166788845593e-06,
|
| 274 |
+
"loss": 0.7276,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.737414322855117,
|
| 279 |
+
"grad_norm": 0.0377151183784008,
|
| 280 |
+
"learning_rate": 9.95149420212946e-06,
|
| 281 |
+
"loss": 0.6728,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7563223824155046,
|
| 286 |
+
"grad_norm": 0.03274886682629585,
|
| 287 |
+
"learning_rate": 9.944330669437402e-06,
|
| 288 |
+
"loss": 0.7146,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7752304419758922,
|
| 293 |
+
"grad_norm": 0.035580553114414215,
|
| 294 |
+
"learning_rate": 9.936676901041386e-06,
|
| 295 |
+
"loss": 0.7084,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7941385015362799,
|
| 300 |
+
"grad_norm": 0.03300866112112999,
|
| 301 |
+
"learning_rate": 9.92853365582078e-06,
|
| 302 |
+
"loss": 0.7168,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8130465610966675,
|
| 307 |
+
"grad_norm": 0.03483871743083,
|
| 308 |
+
"learning_rate": 9.91990174118711e-06,
|
| 309 |
+
"loss": 0.7041,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.831954620657055,
|
| 314 |
+
"grad_norm": 0.02913292683660984,
|
| 315 |
+
"learning_rate": 9.910782013003995e-06,
|
| 316 |
+
"loss": 0.6911,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8508626802174427,
|
| 321 |
+
"grad_norm": 0.03175769001245499,
|
| 322 |
+
"learning_rate": 9.90117537550229e-06,
|
| 323 |
+
"loss": 0.6849,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8697707397778303,
|
| 328 |
+
"grad_norm": 0.031419094651937485,
|
| 329 |
+
"learning_rate": 9.89108278119044e-06,
|
| 330 |
+
"loss": 0.7276,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8886787993382179,
|
| 335 |
+
"grad_norm": 0.03397994861006737,
|
| 336 |
+
"learning_rate": 9.880505230760027e-06,
|
| 337 |
+
"loss": 0.7295,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.9075868588986056,
|
| 342 |
+
"grad_norm": 0.03156342729926109,
|
| 343 |
+
"learning_rate": 9.869443772986552e-06,
|
| 344 |
+
"loss": 0.6624,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.9264949184589931,
|
| 349 |
+
"grad_norm": 0.03708454221487045,
|
| 350 |
+
"learning_rate": 9.85789950462545e-06,
|
| 351 |
+
"loss": 0.7073,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9454029780193808,
|
| 356 |
+
"grad_norm": 0.035610634833574295,
|
| 357 |
+
"learning_rate": 9.845873570303346e-06,
|
| 358 |
+
"loss": 0.7135,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9643110375797683,
|
| 363 |
+
"grad_norm": 0.03249524533748627,
|
| 364 |
+
"learning_rate": 9.833367162404564e-06,
|
| 365 |
+
"loss": 0.6935,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.983219097140156,
|
| 370 |
+
"grad_norm": 0.03497915342450142,
|
| 371 |
+
"learning_rate": 9.8203815209529e-06,
|
| 372 |
+
"loss": 0.7198,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.0021271567005436,
|
| 377 |
+
"grad_norm": 0.03658578172326088,
|
| 378 |
+
"learning_rate": 9.806917933488668e-06,
|
| 379 |
+
"loss": 0.7324,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.0210352162609313,
|
| 384 |
+
"grad_norm": 0.03637828305363655,
|
| 385 |
+
"learning_rate": 9.792977734941049e-06,
|
| 386 |
+
"loss": 0.7391,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.0399432758213187,
|
| 391 |
+
"grad_norm": 0.030937302857637405,
|
| 392 |
+
"learning_rate": 9.778562307495722e-06,
|
| 393 |
+
"loss": 0.6518,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.0588513353817064,
|
| 398 |
+
"grad_norm": 0.034040458500385284,
|
| 399 |
+
"learning_rate": 9.763673080457822e-06,
|
| 400 |
+
"loss": 0.6846,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.077759394942094,
|
| 405 |
+
"grad_norm": 0.034276511520147324,
|
| 406 |
+
"learning_rate": 9.74831153011023e-06,
|
| 407 |
+
"loss": 0.6396,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.0966674545024817,
|
| 412 |
+
"grad_norm": 0.036644868552684784,
|
| 413 |
+
"learning_rate": 9.732479179567178e-06,
|
| 414 |
+
"loss": 0.6882,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.1155755140628694,
|
| 419 |
+
"grad_norm": 0.03399999067187309,
|
| 420 |
+
"learning_rate": 9.716177598623258e-06,
|
| 421 |
+
"loss": 0.6809,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.1344835736232568,
|
| 426 |
+
"grad_norm": 0.03530950844287872,
|
| 427 |
+
"learning_rate": 9.69940840359775e-06,
|
| 428 |
+
"loss": 0.7231,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.1533916331836445,
|
| 433 |
+
"grad_norm": 0.03427257388830185,
|
| 434 |
+
"learning_rate": 9.68217325717438e-06,
|
| 435 |
+
"loss": 0.6532,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.1722996927440321,
|
| 440 |
+
"grad_norm": 0.03930140659213066,
|
| 441 |
+
"learning_rate": 9.664473868236452e-06,
|
| 442 |
+
"loss": 0.6725,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.1912077523044198,
|
| 447 |
+
"grad_norm": 0.033676933497190475,
|
| 448 |
+
"learning_rate": 9.646311991697421e-06,
|
| 449 |
+
"loss": 0.6813,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.2101158118648074,
|
| 454 |
+
"grad_norm": 0.03723222389817238,
|
| 455 |
+
"learning_rate": 9.627689428326875e-06,
|
| 456 |
+
"loss": 0.7048,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.2290238714251949,
|
| 461 |
+
"grad_norm": 0.04367990419268608,
|
| 462 |
+
"learning_rate": 9.608608024572004e-06,
|
| 463 |
+
"loss": 0.6879,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.2479319309855825,
|
| 468 |
+
"grad_norm": 0.03997201845049858,
|
| 469 |
+
"learning_rate": 9.589069672374516e-06,
|
| 470 |
+
"loss": 0.7123,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.2668399905459702,
|
| 475 |
+
"grad_norm": 0.03593291714787483,
|
| 476 |
+
"learning_rate": 9.569076308983046e-06,
|
| 477 |
+
"loss": 0.7099,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.2857480501063578,
|
| 482 |
+
"grad_norm": 0.03724157065153122,
|
| 483 |
+
"learning_rate": 9.548629916761077e-06,
|
| 484 |
+
"loss": 0.6893,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.3046561096667455,
|
| 489 |
+
"grad_norm": 0.038895316421985626,
|
| 490 |
+
"learning_rate": 9.527732522990391e-06,
|
| 491 |
+
"loss": 0.7025,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.323564169227133,
|
| 496 |
+
"grad_norm": 0.034872233867645264,
|
| 497 |
+
"learning_rate": 9.50638619967006e-06,
|
| 498 |
+
"loss": 0.7254,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.3424722287875208,
|
| 503 |
+
"grad_norm": 0.040150392800569534,
|
| 504 |
+
"learning_rate": 9.484593063310998e-06,
|
| 505 |
+
"loss": 0.7077,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.3613802883479083,
|
| 510 |
+
"grad_norm": 0.03619126230478287,
|
| 511 |
+
"learning_rate": 9.462355274726117e-06,
|
| 512 |
+
"loss": 0.6835,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.380288347908296,
|
| 517 |
+
"grad_norm": 0.03600538149476051,
|
| 518 |
+
"learning_rate": 9.439675038816071e-06,
|
| 519 |
+
"loss": 0.6701,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.3991964074686836,
|
| 524 |
+
"grad_norm": 0.03670930117368698,
|
| 525 |
+
"learning_rate": 9.41655460435065e-06,
|
| 526 |
+
"loss": 0.6516,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.418104467029071,
|
| 531 |
+
"grad_norm": 0.04134395346045494,
|
| 532 |
+
"learning_rate": 9.392996263745796e-06,
|
| 533 |
+
"loss": 0.6648,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.4370125265894589,
|
| 538 |
+
"grad_norm": 0.036546383053064346,
|
| 539 |
+
"learning_rate": 9.36900235283632e-06,
|
| 540 |
+
"loss": 0.6653,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.4559205861498463,
|
| 545 |
+
"grad_norm": 0.039511166512966156,
|
| 546 |
+
"learning_rate": 9.344575250644297e-06,
|
| 547 |
+
"loss": 0.7179,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.474828645710234,
|
| 552 |
+
"grad_norm": 0.04085073992609978,
|
| 553 |
+
"learning_rate": 9.31971737914318e-06,
|
| 554 |
+
"loss": 0.6504,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.4937367052706216,
|
| 559 |
+
"grad_norm": 0.03965315595269203,
|
| 560 |
+
"learning_rate": 9.29443120301767e-06,
|
| 561 |
+
"loss": 0.6915,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.512644764831009,
|
| 566 |
+
"grad_norm": 0.04195081442594528,
|
| 567 |
+
"learning_rate": 9.268719229419325e-06,
|
| 568 |
+
"loss": 0.6647,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.531552824391397,
|
| 573 |
+
"grad_norm": 0.040395915508270264,
|
| 574 |
+
"learning_rate": 9.242584007717983e-06,
|
| 575 |
+
"loss": 0.6891,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.5504608839517844,
|
| 580 |
+
"grad_norm": 0.040031347423791885,
|
| 581 |
+
"learning_rate": 9.216028129248986e-06,
|
| 582 |
+
"loss": 0.683,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.569368943512172,
|
| 587 |
+
"grad_norm": 0.042245492339134216,
|
| 588 |
+
"learning_rate": 9.189054227056247e-06,
|
| 589 |
+
"loss": 0.6932,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.5882770030725597,
|
| 594 |
+
"grad_norm": 0.041085727512836456,
|
| 595 |
+
"learning_rate": 9.161664975631184e-06,
|
| 596 |
+
"loss": 0.662,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.6071850626329471,
|
| 601 |
+
"grad_norm": 0.04155590385198593,
|
| 602 |
+
"learning_rate": 9.133863090647533e-06,
|
| 603 |
+
"loss": 0.7057,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.626093122193335,
|
| 608 |
+
"grad_norm": 0.03857599198818207,
|
| 609 |
+
"learning_rate": 9.105651328692093e-06,
|
| 610 |
+
"loss": 0.7096,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.6450011817537225,
|
| 615 |
+
"grad_norm": 0.04026035964488983,
|
| 616 |
+
"learning_rate": 9.077032486991409e-06,
|
| 617 |
+
"loss": 0.7072,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.66390924131411,
|
| 622 |
+
"grad_norm": 0.04304495453834534,
|
| 623 |
+
"learning_rate": 9.048009403134416e-06,
|
| 624 |
+
"loss": 0.6984,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.6828173008744978,
|
| 629 |
+
"grad_norm": 0.04076143354177475,
|
| 630 |
+
"learning_rate": 9.018584954791096e-06,
|
| 631 |
+
"loss": 0.6906,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.7017253604348852,
|
| 636 |
+
"grad_norm": 0.04462475702166557,
|
| 637 |
+
"learning_rate": 8.988762059427151e-06,
|
| 638 |
+
"loss": 0.6823,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.720633419995273,
|
| 643 |
+
"grad_norm": 0.0413421094417572,
|
| 644 |
+
"learning_rate": 8.958543674014733e-06,
|
| 645 |
+
"loss": 0.6567,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.7395414795556605,
|
| 650 |
+
"grad_norm": 0.043752122670412064,
|
| 651 |
+
"learning_rate": 8.927932794739258e-06,
|
| 652 |
+
"loss": 0.7111,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.7584495391160482,
|
| 657 |
+
"grad_norm": 0.04320874437689781,
|
| 658 |
+
"learning_rate": 8.896932456702332e-06,
|
| 659 |
+
"loss": 0.6818,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.7773575986764358,
|
| 664 |
+
"grad_norm": 0.04405179247260094,
|
| 665 |
+
"learning_rate": 8.865545733620816e-06,
|
| 666 |
+
"loss": 0.6954,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.7962656582368235,
|
| 671 |
+
"grad_norm": 0.04215887188911438,
|
| 672 |
+
"learning_rate": 8.83377573752206e-06,
|
| 673 |
+
"loss": 0.6932,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.8151737177972112,
|
| 678 |
+
"grad_norm": 0.041994575411081314,
|
| 679 |
+
"learning_rate": 8.80162561843535e-06,
|
| 680 |
+
"loss": 0.7062,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.8340817773575986,
|
| 685 |
+
"grad_norm": 0.044879619032144547,
|
| 686 |
+
"learning_rate": 8.769098564079575e-06,
|
| 687 |
+
"loss": 0.6746,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.8529898369179862,
|
| 692 |
+
"grad_norm": 0.044902119785547256,
|
| 693 |
+
"learning_rate": 8.736197799547158e-06,
|
| 694 |
+
"loss": 0.6808,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.871897896478374,
|
| 699 |
+
"grad_norm": 0.041419774293899536,
|
| 700 |
+
"learning_rate": 8.702926586984295e-06,
|
| 701 |
+
"loss": 0.6933,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.8908059560387616,
|
| 706 |
+
"grad_norm": 0.044605787843465805,
|
| 707 |
+
"learning_rate": 8.669288225267491e-06,
|
| 708 |
+
"loss": 0.7086,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.9097140155991492,
|
| 713 |
+
"grad_norm": 0.046282704919576645,
|
| 714 |
+
"learning_rate": 8.635286049676497e-06,
|
| 715 |
+
"loss": 0.6531,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.9286220751595367,
|
| 720 |
+
"grad_norm": 0.043578825891017914,
|
| 721 |
+
"learning_rate": 8.60092343156359e-06,
|
| 722 |
+
"loss": 0.7319,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.9475301347199245,
|
| 727 |
+
"grad_norm": 0.04184921458363533,
|
| 728 |
+
"learning_rate": 8.566203778019323e-06,
|
| 729 |
+
"loss": 0.6714,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.966438194280312,
|
| 734 |
+
"grad_norm": 0.044262003153562546,
|
| 735 |
+
"learning_rate": 8.531130531534683e-06,
|
| 736 |
+
"loss": 0.6804,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.9853462538406996,
|
| 741 |
+
"grad_norm": 0.04731186479330063,
|
| 742 |
+
"learning_rate": 8.495707169659786e-06,
|
| 743 |
+
"loss": 0.7039,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.0042543134010873,
|
| 748 |
+
"grad_norm": 0.04587468504905701,
|
| 749 |
+
"learning_rate": 8.459937204659064e-06,
|
| 750 |
+
"loss": 0.7089,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.0231623729614747,
|
| 755 |
+
"grad_norm": 0.0443338043987751,
|
| 756 |
+
"learning_rate": 8.423824183163016e-06,
|
| 757 |
+
"loss": 0.7337,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.0420704325218626,
|
| 762 |
+
"grad_norm": 0.0441860668361187,
|
| 763 |
+
"learning_rate": 8.387371685816573e-06,
|
| 764 |
+
"loss": 0.6772,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.06097849208225,
|
| 769 |
+
"grad_norm": 0.0456668958067894,
|
| 770 |
+
"learning_rate": 8.35058332692405e-06,
|
| 771 |
+
"loss": 0.7313,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.0798865516426375,
|
| 776 |
+
"grad_norm": 0.04839623346924782,
|
| 777 |
+
"learning_rate": 8.3134627540908e-06,
|
| 778 |
+
"loss": 0.7097,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.0987946112030254,
|
| 783 |
+
"grad_norm": 0.04605531319975853,
|
| 784 |
+
"learning_rate": 8.276013647861551e-06,
|
| 785 |
+
"loss": 0.6692,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.117702670763413,
|
| 790 |
+
"grad_norm": 0.04938478022813797,
|
| 791 |
+
"learning_rate": 8.23823972135546e-06,
|
| 792 |
+
"loss": 0.7164,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.1366107303238007,
|
| 797 |
+
"grad_norm": 0.04710887372493744,
|
| 798 |
+
"learning_rate": 8.200144719897974e-06,
|
| 799 |
+
"loss": 0.6791,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.155518789884188,
|
| 804 |
+
"grad_norm": 0.04783915355801582,
|
| 805 |
+
"learning_rate": 8.16173242064946e-06,
|
| 806 |
+
"loss": 0.6915,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.1744268494445755,
|
| 811 |
+
"grad_norm": 0.04555421695113182,
|
| 812 |
+
"learning_rate": 8.123006632230702e-06,
|
| 813 |
+
"loss": 0.679,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.1933349090049634,
|
| 818 |
+
"grad_norm": 0.05009933188557625,
|
| 819 |
+
"learning_rate": 8.08397119434528e-06,
|
| 820 |
+
"loss": 0.6971,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.212242968565351,
|
| 825 |
+
"grad_norm": 0.05265818163752556,
|
| 826 |
+
"learning_rate": 8.044629977398846e-06,
|
| 827 |
+
"loss": 0.6619,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.2311510281257387,
|
| 832 |
+
"grad_norm": 0.049943771213293076,
|
| 833 |
+
"learning_rate": 8.00498688211537e-06,
|
| 834 |
+
"loss": 0.6774,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.250059087686126,
|
| 839 |
+
"grad_norm": 0.046229682862758636,
|
| 840 |
+
"learning_rate": 7.965045839150393e-06,
|
| 841 |
+
"loss": 0.6598,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.2689671472465136,
|
| 846 |
+
"grad_norm": 0.04708926007151604,
|
| 847 |
+
"learning_rate": 7.924810808701286e-06,
|
| 848 |
+
"loss": 0.6866,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.2878752068069015,
|
| 853 |
+
"grad_norm": 0.04711465537548065,
|
| 854 |
+
"learning_rate": 7.884285780114592e-06,
|
| 855 |
+
"loss": 0.6921,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.306783266367289,
|
| 860 |
+
"grad_norm": 0.04712436720728874,
|
| 861 |
+
"learning_rate": 7.843474771490486e-06,
|
| 862 |
+
"loss": 0.678,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.325691325927677,
|
| 867 |
+
"grad_norm": 0.05399713292717934,
|
| 868 |
+
"learning_rate": 7.802381829284366e-06,
|
| 869 |
+
"loss": 0.6913,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.3445993854880642,
|
| 874 |
+
"grad_norm": 0.05280677229166031,
|
| 875 |
+
"learning_rate": 7.761011027905655e-06,
|
| 876 |
+
"loss": 0.6885,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.3635074450484517,
|
| 881 |
+
"grad_norm": 0.050864093005657196,
|
| 882 |
+
"learning_rate": 7.719366469313807e-06,
|
| 883 |
+
"loss": 0.669,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.3824155046088396,
|
| 888 |
+
"grad_norm": 0.049628086388111115,
|
| 889 |
+
"learning_rate": 7.677452282611595e-06,
|
| 890 |
+
"loss": 0.672,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.401323564169227,
|
| 895 |
+
"grad_norm": 0.04994028061628342,
|
| 896 |
+
"learning_rate": 7.635272623635717e-06,
|
| 897 |
+
"loss": 0.6958,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.420231623729615,
|
| 902 |
+
"grad_norm": 0.0501830168068409,
|
| 903 |
+
"learning_rate": 7.592831674544728e-06,
|
| 904 |
+
"loss": 0.685,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.4391396832900023,
|
| 909 |
+
"grad_norm": 0.0533694364130497,
|
| 910 |
+
"learning_rate": 7.550133643404377e-06,
|
| 911 |
+
"loss": 0.662,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.4580477428503897,
|
| 916 |
+
"grad_norm": 0.05292650684714317,
|
| 917 |
+
"learning_rate": 7.507182763770382e-06,
|
| 918 |
+
"loss": 0.6927,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.4769558024107776,
|
| 923 |
+
"grad_norm": 0.05379761382937431,
|
| 924 |
+
"learning_rate": 7.463983294268651e-06,
|
| 925 |
+
"loss": 0.6999,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.495863861971165,
|
| 930 |
+
"grad_norm": 0.05280940234661102,
|
| 931 |
+
"learning_rate": 7.420539518173053e-06,
|
| 932 |
+
"loss": 0.6753,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.514771921531553,
|
| 937 |
+
"grad_norm": 0.05738574638962746,
|
| 938 |
+
"learning_rate": 7.376855742980718e-06,
|
| 939 |
+
"loss": 0.6765,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.5336799810919404,
|
| 944 |
+
"grad_norm": 0.0549960657954216,
|
| 945 |
+
"learning_rate": 7.332936299984936e-06,
|
| 946 |
+
"loss": 0.6672,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.552588040652328,
|
| 951 |
+
"grad_norm": 0.05606316402554512,
|
| 952 |
+
"learning_rate": 7.2887855438457245e-06,
|
| 953 |
+
"loss": 0.7149,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.5714961002127157,
|
| 958 |
+
"grad_norm": 0.05418732389807701,
|
| 959 |
+
"learning_rate": 7.244407852158042e-06,
|
| 960 |
+
"loss": 0.6798,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.590404159773103,
|
| 965 |
+
"grad_norm": 0.056678082793951035,
|
| 966 |
+
"learning_rate": 7.19980762501775e-06,
|
| 967 |
+
"loss": 0.6821,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.609312219333491,
|
| 972 |
+
"grad_norm": 0.06135575473308563,
|
| 973 |
+
"learning_rate": 7.154989284585342e-06,
|
| 974 |
+
"loss": 0.6999,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.6282202788938784,
|
| 979 |
+
"grad_norm": 0.053315985947847366,
|
| 980 |
+
"learning_rate": 7.109957274647477e-06,
|
| 981 |
+
"loss": 0.6951,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.647128338454266,
|
| 986 |
+
"grad_norm": 0.057439010590314865,
|
| 987 |
+
"learning_rate": 7.06471606017638e-06,
|
| 988 |
+
"loss": 0.7058,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.6660363980146538,
|
| 993 |
+
"grad_norm": 0.05061256140470505,
|
| 994 |
+
"learning_rate": 7.019270126887123e-06,
|
| 995 |
+
"loss": 0.6472,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.6849444575750416,
|
| 1000 |
+
"grad_norm": 0.05650395527482033,
|
| 1001 |
+
"learning_rate": 6.973623980792875e-06,
|
| 1002 |
+
"loss": 0.7099,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.703852517135429,
|
| 1007 |
+
"grad_norm": 0.05364992842078209,
|
| 1008 |
+
"learning_rate": 6.927782147758118e-06,
|
| 1009 |
+
"loss": 0.6958,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.7227605766958165,
|
| 1014 |
+
"grad_norm": 0.05512566491961479,
|
| 1015 |
+
"learning_rate": 6.881749173049902e-06,
|
| 1016 |
+
"loss": 0.6266,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.741668636256204,
|
| 1021 |
+
"grad_norm": 0.054573893547058105,
|
| 1022 |
+
"learning_rate": 6.835529620887184e-06,
|
| 1023 |
+
"loss": 0.6358,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.760576695816592,
|
| 1028 |
+
"grad_norm": 0.05702576786279678,
|
| 1029 |
+
"learning_rate": 6.789128073988276e-06,
|
| 1030 |
+
"loss": 0.6709,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.7794847553769797,
|
| 1035 |
+
"grad_norm": 0.06671806424856186,
|
| 1036 |
+
"learning_rate": 6.742549133116459e-06,
|
| 1037 |
+
"loss": 0.6921,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.798392814937367,
|
| 1042 |
+
"grad_norm": 0.05824644863605499,
|
| 1043 |
+
"learning_rate": 6.695797416623821e-06,
|
| 1044 |
+
"loss": 0.6382,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.8173008744977546,
|
| 1049 |
+
"grad_norm": 0.05811014026403427,
|
| 1050 |
+
"learning_rate": 6.64887755999334e-06,
|
| 1051 |
+
"loss": 0.6728,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.836208934058142,
|
| 1056 |
+
"grad_norm": 0.05731780454516411,
|
| 1057 |
+
"learning_rate": 6.601794215379266e-06,
|
| 1058 |
+
"loss": 0.6531,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.85511699361853,
|
| 1063 |
+
"grad_norm": 0.05633535236120224,
|
| 1064 |
+
"learning_rate": 6.5545520511458605e-06,
|
| 1065 |
+
"loss": 0.7032,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.8740250531789178,
|
| 1070 |
+
"grad_norm": 0.06355008482933044,
|
| 1071 |
+
"learning_rate": 6.507155751404518e-06,
|
| 1072 |
+
"loss": 0.6529,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.892933112739305,
|
| 1077 |
+
"grad_norm": 0.06318964809179306,
|
| 1078 |
+
"learning_rate": 6.45961001554934e-06,
|
| 1079 |
+
"loss": 0.678,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.9118411722996926,
|
| 1084 |
+
"grad_norm": 0.0571432039141655,
|
| 1085 |
+
"learning_rate": 6.411919557791176e-06,
|
| 1086 |
+
"loss": 0.6691,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.9307492318600805,
|
| 1091 |
+
"grad_norm": 0.0572994127869606,
|
| 1092 |
+
"learning_rate": 6.364089106690209e-06,
|
| 1093 |
+
"loss": 0.6973,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.949657291420468,
|
| 1098 |
+
"grad_norm": 0.060109131038188934,
|
| 1099 |
+
"learning_rate": 6.316123404687108e-06,
|
| 1100 |
+
"loss": 0.6711,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.968565350980856,
|
| 1105 |
+
"grad_norm": 0.0652967318892479,
|
| 1106 |
+
"learning_rate": 6.268027207632822e-06,
|
| 1107 |
+
"loss": 0.6829,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.9874734105412433,
|
| 1112 |
+
"grad_norm": 0.06120815873146057,
|
| 1113 |
+
"learning_rate": 6.2198052843170184e-06,
|
| 1114 |
+
"loss": 0.6615,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.0063814701016307,
|
| 1119 |
+
"grad_norm": 0.05858151242136955,
|
| 1120 |
+
"learning_rate": 6.171462415995263e-06,
|
| 1121 |
+
"loss": 0.6505,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 3.0252895296620186,
|
| 1126 |
+
"grad_norm": 0.06770987808704376,
|
| 1127 |
+
"learning_rate": 6.123003395914946e-06,
|
| 1128 |
+
"loss": 0.6791,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.044197589222406,
|
| 1133 |
+
"grad_norm": 0.07135272771120071,
|
| 1134 |
+
"learning_rate": 6.074433028840029e-06,
|
| 1135 |
+
"loss": 0.6923,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.0631056487827935,
|
| 1140 |
+
"grad_norm": 0.062477704137563705,
|
| 1141 |
+
"learning_rate": 6.0257561305746524e-06,
|
| 1142 |
+
"loss": 0.6795,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.0820137083431813,
|
| 1147 |
+
"grad_norm": 0.06046826392412186,
|
| 1148 |
+
"learning_rate": 5.976977527485634e-06,
|
| 1149 |
+
"loss": 0.6415,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.1009217679035688,
|
| 1154 |
+
"grad_norm": 0.06548671424388885,
|
| 1155 |
+
"learning_rate": 5.928102056023935e-06,
|
| 1156 |
+
"loss": 0.6811,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.1198298274639567,
|
| 1161 |
+
"grad_norm": 0.06585259735584259,
|
| 1162 |
+
"learning_rate": 5.879134562245124e-06,
|
| 1163 |
+
"loss": 0.7001,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.138737887024344,
|
| 1168 |
+
"grad_norm": 0.060643814504146576,
|
| 1169 |
+
"learning_rate": 5.830079901328876e-06,
|
| 1170 |
+
"loss": 0.6876,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.157645946584732,
|
| 1175 |
+
"grad_norm": 0.06475692987442017,
|
| 1176 |
+
"learning_rate": 5.780942937097584e-06,
|
| 1177 |
+
"loss": 0.6451,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.1765540061451194,
|
| 1182 |
+
"grad_norm": 0.06038076803088188,
|
| 1183 |
+
"learning_rate": 5.7317285415341015e-06,
|
| 1184 |
+
"loss": 0.7299,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.195462065705507,
|
| 1189 |
+
"grad_norm": 0.0708499401807785,
|
| 1190 |
+
"learning_rate": 5.682441594298684e-06,
|
| 1191 |
+
"loss": 0.6758,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 3.2143701252658947,
|
| 1196 |
+
"grad_norm": 0.059092409908771515,
|
| 1197 |
+
"learning_rate": 5.633086982245166e-06,
|
| 1198 |
+
"loss": 0.6753,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.233278184826282,
|
| 1203 |
+
"grad_norm": 0.07227720320224762,
|
| 1204 |
+
"learning_rate": 5.583669598936414e-06,
|
| 1205 |
+
"loss": 0.7004,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.25218624438667,
|
| 1210 |
+
"grad_norm": 0.06542421877384186,
|
| 1211 |
+
"learning_rate": 5.5341943441591364e-06,
|
| 1212 |
+
"loss": 0.6322,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.2710943039470575,
|
| 1217 |
+
"grad_norm": 0.06533703953027725,
|
| 1218 |
+
"learning_rate": 5.48466612343806e-06,
|
| 1219 |
+
"loss": 0.6379,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.290002363507445,
|
| 1224 |
+
"grad_norm": 0.0733456239104271,
|
| 1225 |
+
"learning_rate": 5.435089847549541e-06,
|
| 1226 |
+
"loss": 0.6609,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.308910423067833,
|
| 1231 |
+
"grad_norm": 0.06628765165805817,
|
| 1232 |
+
"learning_rate": 5.38547043203466e-06,
|
| 1233 |
+
"loss": 0.6694,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 3.32781848262822,
|
| 1238 |
+
"grad_norm": 0.07368200272321701,
|
| 1239 |
+
"learning_rate": 5.3358127967118355e-06,
|
| 1240 |
+
"loss": 0.6572,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 3.346726542188608,
|
| 1245 |
+
"grad_norm": 0.06234520301222801,
|
| 1246 |
+
"learning_rate": 5.286121865189016e-06,
|
| 1247 |
+
"loss": 0.7065,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.3656346017489955,
|
| 1252 |
+
"grad_norm": 0.06914972513914108,
|
| 1253 |
+
"learning_rate": 5.236402564375514e-06,
|
| 1254 |
+
"loss": 0.7108,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 3.384542661309383,
|
| 1259 |
+
"grad_norm": 0.06980318576097488,
|
| 1260 |
+
"learning_rate": 5.186659823993482e-06,
|
| 1261 |
+
"loss": 0.7008,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 3.403450720869771,
|
| 1266 |
+
"grad_norm": 0.06499587744474411,
|
| 1267 |
+
"learning_rate": 5.136898576089131e-06,
|
| 1268 |
+
"loss": 0.6951,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.4223587804301583,
|
| 1273 |
+
"grad_norm": 0.0658080130815506,
|
| 1274 |
+
"learning_rate": 5.087123754543715e-06,
|
| 1275 |
+
"loss": 0.6703,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 3.441266839990546,
|
| 1280 |
+
"grad_norm": 0.06298273801803589,
|
| 1281 |
+
"learning_rate": 5.037340294584323e-06,
|
| 1282 |
+
"loss": 0.6709,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 3.4601748995509336,
|
| 1287 |
+
"grad_norm": 0.07536780089139938,
|
| 1288 |
+
"learning_rate": 4.9875531322945635e-06,
|
| 1289 |
+
"loss": 0.6573,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 3.479082959111321,
|
| 1294 |
+
"grad_norm": 0.07163431495428085,
|
| 1295 |
+
"learning_rate": 4.937767204125122e-06,
|
| 1296 |
+
"loss": 0.6739,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 3.497991018671709,
|
| 1301 |
+
"grad_norm": 0.06597751379013062,
|
| 1302 |
+
"learning_rate": 4.88798744640433e-06,
|
| 1303 |
+
"loss": 0.648,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 3.5168990782320964,
|
| 1308 |
+
"grad_norm": 0.061648089438676834,
|
| 1309 |
+
"learning_rate": 4.838218794848706e-06,
|
| 1310 |
+
"loss": 0.6848,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.5358071377924842,
|
| 1315 |
+
"grad_norm": 0.06730767339468002,
|
| 1316 |
+
"learning_rate": 4.788466184073586e-06,
|
| 1317 |
+
"loss": 0.6555,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 3.5547151973528717,
|
| 1322 |
+
"grad_norm": 0.070393867790699,
|
| 1323 |
+
"learning_rate": 4.738734547103836e-06,
|
| 1324 |
+
"loss": 0.6613,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 3.573623256913259,
|
| 1329 |
+
"grad_norm": 0.07426159828901291,
|
| 1330 |
+
"learning_rate": 4.6890288148847564e-06,
|
| 1331 |
+
"loss": 0.6941,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 3.592531316473647,
|
| 1336 |
+
"grad_norm": 0.0717974454164505,
|
| 1337 |
+
"learning_rate": 4.639353915793159e-06,
|
| 1338 |
+
"loss": 0.733,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 3.6114393760340344,
|
| 1343 |
+
"grad_norm": 0.07027947902679443,
|
| 1344 |
+
"learning_rate": 4.589714775148719e-06,
|
| 1345 |
+
"loss": 0.6731,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 3.6303474355944223,
|
| 1350 |
+
"grad_norm": 0.06726668030023575,
|
| 1351 |
+
"learning_rate": 4.540116314725622e-06,
|
| 1352 |
+
"loss": 0.6837,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 3.6492554951548097,
|
| 1357 |
+
"grad_norm": 0.062310460954904556,
|
| 1358 |
+
"learning_rate": 4.49056345226457e-06,
|
| 1359 |
+
"loss": 0.7209,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 3.668163554715197,
|
| 1364 |
+
"grad_norm": 0.07572998106479645,
|
| 1365 |
+
"learning_rate": 4.441061100985169e-06,
|
| 1366 |
+
"loss": 0.6864,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 3.687071614275585,
|
| 1371 |
+
"grad_norm": 0.07206368446350098,
|
| 1372 |
+
"learning_rate": 4.391614169098795e-06,
|
| 1373 |
+
"loss": 0.6827,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.7059796738359725,
|
| 1378 |
+
"grad_norm": 0.07162526249885559,
|
| 1379 |
+
"learning_rate": 4.342227559321932e-06,
|
| 1380 |
+
"loss": 0.6844,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 3.7248877333963604,
|
| 1385 |
+
"grad_norm": 0.07335004955530167,
|
| 1386 |
+
"learning_rate": 4.292906168390056e-06,
|
| 1387 |
+
"loss": 0.7004,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 3.743795792956748,
|
| 1392 |
+
"grad_norm": 0.07719966024160385,
|
| 1393 |
+
"learning_rate": 4.24365488657213e-06,
|
| 1394 |
+
"loss": 0.6674,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.7627038525171352,
|
| 1399 |
+
"grad_norm": 0.06994116306304932,
|
| 1400 |
+
"learning_rate": 4.194478597185716e-06,
|
| 1401 |
+
"loss": 0.6682,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 3.781611912077523,
|
| 1406 |
+
"grad_norm": 0.071551114320755,
|
| 1407 |
+
"learning_rate": 4.145382176112804e-06,
|
| 1408 |
+
"loss": 0.6676,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 3.8005199716379106,
|
| 1413 |
+
"grad_norm": 0.07608342170715332,
|
| 1414 |
+
"learning_rate": 4.0963704913163525e-06,
|
| 1415 |
+
"loss": 0.6799,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 3.8194280311982984,
|
| 1420 |
+
"grad_norm": 0.06601590663194656,
|
| 1421 |
+
"learning_rate": 4.047448402357622e-06,
|
| 1422 |
+
"loss": 0.675,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 3.838336090758686,
|
| 1427 |
+
"grad_norm": 0.07468881458044052,
|
| 1428 |
+
"learning_rate": 3.9986207599143566e-06,
|
| 1429 |
+
"loss": 0.6544,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 3.8572441503190733,
|
| 1434 |
+
"grad_norm": 0.06805694103240967,
|
| 1435 |
+
"learning_rate": 3.9498924052998195e-06,
|
| 1436 |
+
"loss": 0.6856,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 3.876152209879461,
|
| 1441 |
+
"grad_norm": 0.08336406946182251,
|
| 1442 |
+
"learning_rate": 3.901268169982784e-06,
|
| 1443 |
+
"loss": 0.6535,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 3.8950602694398486,
|
| 1448 |
+
"grad_norm": 0.06868647038936615,
|
| 1449 |
+
"learning_rate": 3.852752875108483e-06,
|
| 1450 |
+
"loss": 0.6657,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 3.9139683290002365,
|
| 1455 |
+
"grad_norm": 0.07650279253721237,
|
| 1456 |
+
"learning_rate": 3.804351331020584e-06,
|
| 1457 |
+
"loss": 0.6587,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 3.932876388560624,
|
| 1462 |
+
"grad_norm": 0.07571345567703247,
|
| 1463 |
+
"learning_rate": 3.7560683367842456e-06,
|
| 1464 |
+
"loss": 0.6694,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 3.9517844481210114,
|
| 1469 |
+
"grad_norm": 0.06946905702352524,
|
| 1470 |
+
"learning_rate": 3.707908679710276e-06,
|
| 1471 |
+
"loss": 0.6646,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 3.9706925076813993,
|
| 1476 |
+
"grad_norm": 0.07537796348333359,
|
| 1477 |
+
"learning_rate": 3.659877134880477e-06,
|
| 1478 |
+
"loss": 0.6716,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 3.9896005672417867,
|
| 1483 |
+
"grad_norm": 0.07623406499624252,
|
| 1484 |
+
"learning_rate": 3.6119784646741807e-06,
|
| 1485 |
+
"loss": 0.6503,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 4.008508626802175,
|
| 1490 |
+
"grad_norm": 0.07248073071241379,
|
| 1491 |
+
"learning_rate": 3.5642174182960554e-06,
|
| 1492 |
+
"loss": 0.6953,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 4.027416686362562,
|
| 1497 |
+
"grad_norm": 0.07673463970422745,
|
| 1498 |
+
"learning_rate": 3.5165987313052225e-06,
|
| 1499 |
+
"loss": 0.7001,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 4.046324745922949,
|
| 1504 |
+
"grad_norm": 0.06918472051620483,
|
| 1505 |
+
"learning_rate": 3.469127125145717e-06,
|
| 1506 |
+
"loss": 0.6945,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 4.065232805483337,
|
| 1511 |
+
"grad_norm": 0.06996827572584152,
|
| 1512 |
+
"learning_rate": 3.4218073066783464e-06,
|
| 1513 |
+
"loss": 0.6454,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 4.084140865043725,
|
| 1518 |
+
"grad_norm": 0.08209812641143799,
|
| 1519 |
+
"learning_rate": 3.374643967714011e-06,
|
| 1520 |
+
"loss": 0.6974,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 4.103048924604113,
|
| 1525 |
+
"grad_norm": 0.07365689426660538,
|
| 1526 |
+
"learning_rate": 3.327641784548495e-06,
|
| 1527 |
+
"loss": 0.6876,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 4.1219569841645,
|
| 1532 |
+
"grad_norm": 0.07676127552986145,
|
| 1533 |
+
"learning_rate": 3.2808054174988165e-06,
|
| 1534 |
+
"loss": 0.6322,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 4.1408650437248875,
|
| 1539 |
+
"grad_norm": 0.08051763474941254,
|
| 1540 |
+
"learning_rate": 3.2341395104411467e-06,
|
| 1541 |
+
"loss": 0.6707,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 4.159773103285275,
|
| 1546 |
+
"grad_norm": 0.08313941955566406,
|
| 1547 |
+
"learning_rate": 3.18764869035036e-06,
|
| 1548 |
+
"loss": 0.661,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 4.178681162845663,
|
| 1553 |
+
"grad_norm": 0.0765809416770935,
|
| 1554 |
+
"learning_rate": 3.141337566841277e-06,
|
| 1555 |
+
"loss": 0.6962,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 4.197589222406051,
|
| 1560 |
+
"grad_norm": 0.10051856189966202,
|
| 1561 |
+
"learning_rate": 3.095210731711603e-06,
|
| 1562 |
+
"loss": 0.6339,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 4.216497281966438,
|
| 1567 |
+
"grad_norm": 0.07644385099411011,
|
| 1568 |
+
"learning_rate": 3.0492727584866554e-06,
|
| 1569 |
+
"loss": 0.707,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 4.235405341526826,
|
| 1574 |
+
"grad_norm": 0.07614172250032425,
|
| 1575 |
+
"learning_rate": 3.003528201965893e-06,
|
| 1576 |
+
"loss": 0.6511,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 4.254313401087213,
|
| 1581 |
+
"grad_norm": 0.07704110443592072,
|
| 1582 |
+
"learning_rate": 2.957981597771292e-06,
|
| 1583 |
+
"loss": 0.7068,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 4.273221460647601,
|
| 1588 |
+
"grad_norm": 0.07838738709688187,
|
| 1589 |
+
"learning_rate": 2.9126374618976526e-06,
|
| 1590 |
+
"loss": 0.6293,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 4.292129520207989,
|
| 1595 |
+
"grad_norm": 0.07882346957921982,
|
| 1596 |
+
"learning_rate": 2.8675002902648148e-06,
|
| 1597 |
+
"loss": 0.6677,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 4.311037579768376,
|
| 1602 |
+
"grad_norm": 0.07263699918985367,
|
| 1603 |
+
"learning_rate": 2.8225745582718964e-06,
|
| 1604 |
+
"loss": 0.6794,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 4.329945639328764,
|
| 1609 |
+
"grad_norm": 0.0822502002120018,
|
| 1610 |
+
"learning_rate": 2.7778647203535474e-06,
|
| 1611 |
+
"loss": 0.665,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 4.348853698889151,
|
| 1616 |
+
"grad_norm": 0.07821501791477203,
|
| 1617 |
+
"learning_rate": 2.7333752095382883e-06,
|
| 1618 |
+
"loss": 0.6642,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 4.367761758449539,
|
| 1623 |
+
"grad_norm": 0.08269735425710678,
|
| 1624 |
+
"learning_rate": 2.6891104370089644e-06,
|
| 1625 |
+
"loss": 0.7082,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 4.386669818009927,
|
| 1630 |
+
"grad_norm": 0.07760092616081238,
|
| 1631 |
+
"learning_rate": 2.645074791665386e-06,
|
| 1632 |
+
"loss": 0.6985,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 4.405577877570314,
|
| 1637 |
+
"grad_norm": 0.09205616265535355,
|
| 1638 |
+
"learning_rate": 2.601272639689152e-06,
|
| 1639 |
+
"loss": 0.6436,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 4.424485937130702,
|
| 1644 |
+
"grad_norm": 0.07168934494256973,
|
| 1645 |
+
"learning_rate": 2.557708324110747e-06,
|
| 1646 |
+
"loss": 0.6426,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 4.443393996691089,
|
| 1651 |
+
"grad_norm": 0.07921484857797623,
|
| 1652 |
+
"learning_rate": 2.5143861643789153e-06,
|
| 1653 |
+
"loss": 0.6513,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 4.4623020562514775,
|
| 1658 |
+
"grad_norm": 0.07425461709499359,
|
| 1659 |
+
"learning_rate": 2.4713104559323896e-06,
|
| 1660 |
+
"loss": 0.6513,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 4.481210115811865,
|
| 1665 |
+
"grad_norm": 0.08021389693021774,
|
| 1666 |
+
"learning_rate": 2.4284854697739974e-06,
|
| 1667 |
+
"loss": 0.6922,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 4.500118175372252,
|
| 1672 |
+
"grad_norm": 0.08110744506120682,
|
| 1673 |
+
"learning_rate": 2.385915452047177e-06,
|
| 1674 |
+
"loss": 0.6894,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 4.51902623493264,
|
| 1679 |
+
"grad_norm": 0.08530419319868088,
|
| 1680 |
+
"learning_rate": 2.343604623614974e-06,
|
| 1681 |
+
"loss": 0.6671,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 4.537934294493027,
|
| 1686 |
+
"grad_norm": 0.07330188900232315,
|
| 1687 |
+
"learning_rate": 2.3015571796415397e-06,
|
| 1688 |
+
"loss": 0.6694,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 4.5568423540534155,
|
| 1693 |
+
"grad_norm": 0.07557007670402527,
|
| 1694 |
+
"learning_rate": 2.2597772891761655e-06,
|
| 1695 |
+
"loss": 0.6843,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 4.575750413613803,
|
| 1700 |
+
"grad_norm": 0.07595443725585938,
|
| 1701 |
+
"learning_rate": 2.2182690947399306e-06,
|
| 1702 |
+
"loss": 0.6942,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 4.59465847317419,
|
| 1707 |
+
"grad_norm": 0.09174559265375137,
|
| 1708 |
+
"learning_rate": 2.17703671191496e-06,
|
| 1709 |
+
"loss": 0.7176,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 4.613566532734578,
|
| 1714 |
+
"grad_norm": 0.077406145632267,
|
| 1715 |
+
"learning_rate": 2.1360842289363616e-06,
|
| 1716 |
+
"loss": 0.7041,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 4.632474592294965,
|
| 1721 |
+
"grad_norm": 0.07479016482830048,
|
| 1722 |
+
"learning_rate": 2.0954157062868667e-06,
|
| 1723 |
+
"loss": 0.6791,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 4.651382651855354,
|
| 1728 |
+
"grad_norm": 0.08275721967220306,
|
| 1729 |
+
"learning_rate": 2.0550351762942427e-06,
|
| 1730 |
+
"loss": 0.6529,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 4.670290711415741,
|
| 1735 |
+
"grad_norm": 0.08451598882675171,
|
| 1736 |
+
"learning_rate": 2.0149466427314684e-06,
|
| 1737 |
+
"loss": 0.6607,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 4.6891987709761285,
|
| 1742 |
+
"grad_norm": 0.07672012597322464,
|
| 1743 |
+
"learning_rate": 1.9751540804197667e-06,
|
| 1744 |
+
"loss": 0.6645,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 4.708106830536516,
|
| 1749 |
+
"grad_norm": 0.07269056886434555,
|
| 1750 |
+
"learning_rate": 1.935661434834491e-06,
|
| 1751 |
+
"loss": 0.6861,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 4.727014890096903,
|
| 1756 |
+
"grad_norm": 0.07922536134719849,
|
| 1757 |
+
"learning_rate": 1.89647262171393e-06,
|
| 1758 |
+
"loss": 0.6497,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 4.745922949657292,
|
| 1763 |
+
"grad_norm": 0.07756451517343521,
|
| 1764 |
+
"learning_rate": 1.8575915266710565e-06,
|
| 1765 |
+
"loss": 0.6736,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 4.764831009217679,
|
| 1770 |
+
"grad_norm": 0.08501828461885452,
|
| 1771 |
+
"learning_rate": 1.8190220048082613e-06,
|
| 1772 |
+
"loss": 0.6626,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 4.7837390687780665,
|
| 1777 |
+
"grad_norm": 0.07419081032276154,
|
| 1778 |
+
"learning_rate": 1.7807678803351236e-06,
|
| 1779 |
+
"loss": 0.6612,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 4.802647128338454,
|
| 1784 |
+
"grad_norm": 0.08240891993045807,
|
| 1785 |
+
"learning_rate": 1.742832946189233e-06,
|
| 1786 |
+
"loss": 0.6822,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 4.821555187898841,
|
| 1791 |
+
"grad_norm": 0.08003178238868713,
|
| 1792 |
+
"learning_rate": 1.7052209636601086e-06,
|
| 1793 |
+
"loss": 0.6583,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 4.84046324745923,
|
| 1798 |
+
"grad_norm": 0.08147577196359634,
|
| 1799 |
+
"learning_rate": 1.6679356620162767e-06,
|
| 1800 |
+
"loss": 0.6486,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 4.859371307019617,
|
| 1805 |
+
"grad_norm": 0.08541478961706161,
|
| 1806 |
+
"learning_rate": 1.6309807381354958e-06,
|
| 1807 |
+
"loss": 0.6622,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 4.878279366580005,
|
| 1812 |
+
"grad_norm": 0.0798458531498909,
|
| 1813 |
+
"learning_rate": 1.594359856138219e-06,
|
| 1814 |
+
"loss": 0.636,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 4.897187426140392,
|
| 1819 |
+
"grad_norm": 0.07943376153707504,
|
| 1820 |
+
"learning_rate": 1.5580766470242853e-06,
|
| 1821 |
+
"loss": 0.6839,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 4.9160954857007795,
|
| 1826 |
+
"grad_norm": 0.07922222465276718,
|
| 1827 |
+
"learning_rate": 1.5221347083129045e-06,
|
| 1828 |
+
"loss": 0.6999,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 4.935003545261168,
|
| 1833 |
+
"grad_norm": 0.07585081458091736,
|
| 1834 |
+
"learning_rate": 1.4865376036859597e-06,
|
| 1835 |
+
"loss": 0.6508,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 4.953911604821555,
|
| 1840 |
+
"grad_norm": 0.09331846982240677,
|
| 1841 |
+
"learning_rate": 1.45128886263466e-06,
|
| 1842 |
+
"loss": 0.6792,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 4.972819664381943,
|
| 1847 |
+
"grad_norm": 0.08158135414123535,
|
| 1848 |
+
"learning_rate": 1.4163919801095955e-06,
|
| 1849 |
+
"loss": 0.6796,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 4.99172772394233,
|
| 1854 |
+
"grad_norm": 0.07948708534240723,
|
| 1855 |
+
"learning_rate": 1.381850416174203e-06,
|
| 1856 |
+
"loss": 0.6901,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 5.010635783502718,
|
| 1861 |
+
"grad_norm": 0.08439305424690247,
|
| 1862 |
+
"learning_rate": 1.3476675956617008e-06,
|
| 1863 |
+
"loss": 0.6418,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 5.029543843063106,
|
| 1868 |
+
"grad_norm": 0.07965263724327087,
|
| 1869 |
+
"learning_rate": 1.313846907835507e-06,
|
| 1870 |
+
"loss": 0.6565,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 5.048451902623493,
|
| 1875 |
+
"grad_norm": 0.08111811429262161,
|
| 1876 |
+
"learning_rate": 1.2803917060531994e-06,
|
| 1877 |
+
"loss": 0.6952,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 5.067359962183881,
|
| 1882 |
+
"grad_norm": 0.08763491362333298,
|
| 1883 |
+
"learning_rate": 1.2473053074340159e-06,
|
| 1884 |
+
"loss": 0.7075,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 5.086268021744268,
|
| 1889 |
+
"grad_norm": 0.07912111282348633,
|
| 1890 |
+
"learning_rate": 1.2145909925299687e-06,
|
| 1891 |
+
"loss": 0.6754,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 5.1051760813046565,
|
| 1896 |
+
"grad_norm": 0.08513174206018448,
|
| 1897 |
+
"learning_rate": 1.1822520050005677e-06,
|
| 1898 |
+
"loss": 0.6667,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 5.124084140865044,
|
| 1903 |
+
"grad_norm": 0.07933773100376129,
|
| 1904 |
+
"learning_rate": 1.1502915512912095e-06,
|
| 1905 |
+
"loss": 0.6672,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 5.142992200425431,
|
| 1910 |
+
"grad_norm": 0.08284608274698257,
|
| 1911 |
+
"learning_rate": 1.118712800315258e-06,
|
| 1912 |
+
"loss": 0.6442,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 5.161900259985819,
|
| 1917 |
+
"grad_norm": 0.0854770690202713,
|
| 1918 |
+
"learning_rate": 1.0875188831398354e-06,
|
| 1919 |
+
"loss": 0.6357,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 5.180808319546206,
|
| 1924 |
+
"grad_norm": 0.07782963663339615,
|
| 1925 |
+
"learning_rate": 1.0567128926753827e-06,
|
| 1926 |
+
"loss": 0.6778,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 5.199716379106595,
|
| 1931 |
+
"grad_norm": 0.07680613547563553,
|
| 1932 |
+
"learning_rate": 1.0262978833689907e-06,
|
| 1933 |
+
"loss": 0.6519,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 5.218624438666982,
|
| 1938 |
+
"grad_norm": 0.07989546656608582,
|
| 1939 |
+
"learning_rate": 9.962768709015436e-07,
|
| 1940 |
+
"loss": 0.6956,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 5.237532498227369,
|
| 1945 |
+
"grad_norm": 0.08639136701822281,
|
| 1946 |
+
"learning_rate": 9.666528318887198e-07,
|
| 1947 |
+
"loss": 0.6724,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 5.256440557787757,
|
| 1952 |
+
"grad_norm": 0.08070726692676544,
|
| 1953 |
+
"learning_rate": 9.374287035858492e-07,
|
| 1954 |
+
"loss": 0.6969,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 5.275348617348144,
|
| 1959 |
+
"grad_norm": 0.08380179107189178,
|
| 1960 |
+
"learning_rate": 9.086073835966869e-07,
|
| 1961 |
+
"loss": 0.6846,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 5.294256676908533,
|
| 1966 |
+
"grad_norm": 0.07772370427846909,
|
| 1967 |
+
"learning_rate": 8.801917295861101e-07,
|
| 1968 |
+
"loss": 0.7061,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 5.31316473646892,
|
| 1973 |
+
"grad_norm": 0.07815873622894287,
|
| 1974 |
+
"learning_rate": 8.521845589967775e-07,
|
| 1975 |
+
"loss": 0.6832,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 5.3320727960293075,
|
| 1980 |
+
"grad_norm": 0.08794362843036652,
|
| 1981 |
+
"learning_rate": 8.24588648769778e-07,
|
| 1982 |
+
"loss": 0.6796,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 5.350980855589695,
|
| 1987 |
+
"grad_norm": 0.08358251303434372,
|
| 1988 |
+
"learning_rate": 7.974067350692921e-07,
|
| 1989 |
+
"loss": 0.6958,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 5.369888915150082,
|
| 1994 |
+
"grad_norm": 0.08284702897071838,
|
| 1995 |
+
"learning_rate": 7.706415130112993e-07,
|
| 1996 |
+
"loss": 0.6696,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 5.388796974710471,
|
| 2001 |
+
"grad_norm": 0.08031268417835236,
|
| 2002 |
+
"learning_rate": 7.44295636396356e-07,
|
| 2003 |
+
"loss": 0.6463,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 5.407705034270858,
|
| 2008 |
+
"grad_norm": 0.0891246348619461,
|
| 2009 |
+
"learning_rate": 7.183717174464649e-07,
|
| 2010 |
+
"loss": 0.6802,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 5.426613093831246,
|
| 2015 |
+
"grad_norm": 0.08383399248123169,
|
| 2016 |
+
"learning_rate": 6.928723265460735e-07,
|
| 2017 |
+
"loss": 0.6742,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 5.445521153391633,
|
| 2022 |
+
"grad_norm": 0.08535037934780121,
|
| 2023 |
+
"learning_rate": 6.677999919872185e-07,
|
| 2024 |
+
"loss": 0.6898,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 5.46442921295202,
|
| 2029 |
+
"grad_norm": 0.08179079741239548,
|
| 2030 |
+
"learning_rate": 6.431571997188363e-07,
|
| 2031 |
+
"loss": 0.6393,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 5.483337272512409,
|
| 2036 |
+
"grad_norm": 0.0862477719783783,
|
| 2037 |
+
"learning_rate": 6.189463931002871e-07,
|
| 2038 |
+
"loss": 0.6808,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 5.502245332072796,
|
| 2043 |
+
"grad_norm": 0.08993732929229736,
|
| 2044 |
+
"learning_rate": 5.951699726590881e-07,
|
| 2045 |
+
"loss": 0.6702,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 5.521153391633184,
|
| 2050 |
+
"grad_norm": 0.08879116177558899,
|
| 2051 |
+
"learning_rate": 5.718302958528999e-07,
|
| 2052 |
+
"loss": 0.6776,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 5.540061451193571,
|
| 2057 |
+
"grad_norm": 0.08478083461523056,
|
| 2058 |
+
"learning_rate": 5.489296768357827e-07,
|
| 2059 |
+
"loss": 0.666,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 5.5589695107539585,
|
| 2064 |
+
"grad_norm": 0.09191175550222397,
|
| 2065 |
+
"learning_rate": 5.264703862287418e-07,
|
| 2066 |
+
"loss": 0.6819,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 5.577877570314347,
|
| 2071 |
+
"grad_norm": 0.09217491000890732,
|
| 2072 |
+
"learning_rate": 5.044546508945997e-07,
|
| 2073 |
+
"loss": 0.6555,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 5.596785629874734,
|
| 2078 |
+
"grad_norm": 0.08284752815961838,
|
| 2079 |
+
"learning_rate": 4.828846537171933e-07,
|
| 2080 |
+
"loss": 0.6863,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 5.615693689435122,
|
| 2085 |
+
"grad_norm": 0.09084407240152359,
|
| 2086 |
+
"learning_rate": 4.617625333849435e-07,
|
| 2087 |
+
"loss": 0.6511,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 5.634601748995509,
|
| 2092 |
+
"grad_norm": 0.08455785363912582,
|
| 2093 |
+
"learning_rate": 4.4109038417880003e-07,
|
| 2094 |
+
"loss": 0.6841,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 5.653509808555897,
|
| 2099 |
+
"grad_norm": 0.086379773914814,
|
| 2100 |
+
"learning_rate": 4.208702557645933e-07,
|
| 2101 |
+
"loss": 0.6792,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 5.672417868116285,
|
| 2106 |
+
"grad_norm": 0.08563714474439621,
|
| 2107 |
+
"learning_rate": 4.0110415298980187e-07,
|
| 2108 |
+
"loss": 0.6813,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 5.691325927676672,
|
| 2113 |
+
"grad_norm": 0.08284977078437805,
|
| 2114 |
+
"learning_rate": 3.817940356847766e-07,
|
| 2115 |
+
"loss": 0.6625,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 5.71023398723706,
|
| 2120 |
+
"grad_norm": 0.08987167477607727,
|
| 2121 |
+
"learning_rate": 3.6294181846841856e-07,
|
| 2122 |
+
"loss": 0.6621,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 5.729142046797447,
|
| 2127 |
+
"grad_norm": 0.08199549466371536,
|
| 2128 |
+
"learning_rate": 3.445493705583419e-07,
|
| 2129 |
+
"loss": 0.6684,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 5.748050106357835,
|
| 2134 |
+
"grad_norm": 0.08346036076545715,
|
| 2135 |
+
"learning_rate": 3.266185155855406e-07,
|
| 2136 |
+
"loss": 0.6584,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 5.766958165918223,
|
| 2141 |
+
"grad_norm": 0.08736700564622879,
|
| 2142 |
+
"learning_rate": 3.0915103141356984e-07,
|
| 2143 |
+
"loss": 0.653,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 5.78586622547861,
|
| 2148 |
+
"grad_norm": 0.09791529923677444,
|
| 2149 |
+
"learning_rate": 2.92148649962275e-07,
|
| 2150 |
+
"loss": 0.6633,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 5.804774285038998,
|
| 2155 |
+
"grad_norm": 0.07101596146821976,
|
| 2156 |
+
"learning_rate": 2.756130570360621e-07,
|
| 2157 |
+
"loss": 0.6742,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 5.823682344599385,
|
| 2162 |
+
"grad_norm": 0.08588287234306335,
|
| 2163 |
+
"learning_rate": 2.595458921567573e-07,
|
| 2164 |
+
"loss": 0.6596,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 5.842590404159774,
|
| 2169 |
+
"grad_norm": 0.08986763656139374,
|
| 2170 |
+
"learning_rate": 2.4394874840104e-07,
|
| 2171 |
+
"loss": 0.6637,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 5.861498463720161,
|
| 2176 |
+
"grad_norm": 0.08732476830482483,
|
| 2177 |
+
"learning_rate": 2.2882317224248886e-07,
|
| 2178 |
+
"loss": 0.6658,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 5.8804065232805485,
|
| 2183 |
+
"grad_norm": 0.0841900184750557,
|
| 2184 |
+
"learning_rate": 2.1417066339824934e-07,
|
| 2185 |
+
"loss": 0.643,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 5.899314582840936,
|
| 2190 |
+
"grad_norm": 0.08480223268270493,
|
| 2191 |
+
"learning_rate": 1.9999267468033323e-07,
|
| 2192 |
+
"loss": 0.6721,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 5.918222642401323,
|
| 2197 |
+
"grad_norm": 0.08658278733491898,
|
| 2198 |
+
"learning_rate": 1.8629061185157228e-07,
|
| 2199 |
+
"loss": 0.6757,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 5.937130701961712,
|
| 2204 |
+
"grad_norm": 0.08789494633674622,
|
| 2205 |
+
"learning_rate": 1.730658334862334e-07,
|
| 2206 |
+
"loss": 0.668,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 5.956038761522099,
|
| 2211 |
+
"grad_norm": 0.08130628615617752,
|
| 2212 |
+
"learning_rate": 1.603196508353161e-07,
|
| 2213 |
+
"loss": 0.6859,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 5.9749468210824865,
|
| 2218 |
+
"grad_norm": 0.08904296159744263,
|
| 2219 |
+
"learning_rate": 1.4805332769654013e-07,
|
| 2220 |
+
"loss": 0.6657,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 5.993854880642874,
|
| 2225 |
+
"grad_norm": 0.0906049981713295,
|
| 2226 |
+
"learning_rate": 1.362680802890376e-07,
|
| 2227 |
+
"loss": 0.6263,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 6.012762940203261,
|
| 2232 |
+
"grad_norm": 0.07836922258138657,
|
| 2233 |
+
"learning_rate": 1.2496507713276484e-07,
|
| 2234 |
+
"loss": 0.6531,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 6.031670999763649,
|
| 2239 |
+
"grad_norm": 0.0807194784283638,
|
| 2240 |
+
"learning_rate": 1.1414543893264351e-07,
|
| 2241 |
+
"loss": 0.6953,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 6.050579059324037,
|
| 2246 |
+
"grad_norm": 0.08561025559902191,
|
| 2247 |
+
"learning_rate": 1.0381023846743831e-07,
|
| 2248 |
+
"loss": 0.6435,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 6.069487118884425,
|
| 2253 |
+
"grad_norm": 0.07596372067928314,
|
| 2254 |
+
"learning_rate": 9.3960500483391e-08,
|
| 2255 |
+
"loss": 0.6553,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 6.088395178444812,
|
| 2260 |
+
"grad_norm": 0.08634670078754425,
|
| 2261 |
+
"learning_rate": 8.459720159261719e-08,
|
| 2262 |
+
"loss": 0.6475,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 6.1073032380051995,
|
| 2267 |
+
"grad_norm": 0.10798340290784836,
|
| 2268 |
+
"learning_rate": 7.572127017627328e-08,
|
| 2269 |
+
"loss": 0.6866,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 6.126211297565587,
|
| 2274 |
+
"grad_norm": 0.0855603814125061,
|
| 2275 |
+
"learning_rate": 6.73335862925062e-08,
|
| 2276 |
+
"loss": 0.7054,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 6.145119357125975,
|
| 2281 |
+
"grad_norm": 0.08026163280010223,
|
| 2282 |
+
"learning_rate": 5.9434981589195363e-08,
|
| 2283 |
+
"loss": 0.6163,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 6.164027416686363,
|
| 2288 |
+
"grad_norm": 0.09041197597980499,
|
| 2289 |
+
"learning_rate": 5.2026239221491524e-08,
|
| 2290 |
+
"loss": 0.6661,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 6.18293547624675,
|
| 2295 |
+
"grad_norm": 0.07854273915290833,
|
| 2296 |
+
"learning_rate": 4.510809377416936e-08,
|
| 2297 |
+
"loss": 0.7043,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 6.2018435358071375,
|
| 2302 |
+
"grad_norm": 0.08152135461568832,
|
| 2303 |
+
"learning_rate": 3.8681231188791857e-08,
|
| 2304 |
+
"loss": 0.6621,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 6.220751595367525,
|
| 2309 |
+
"grad_norm": 0.08624988794326782,
|
| 2310 |
+
"learning_rate": 3.27462886956964e-08,
|
| 2311 |
+
"loss": 0.7024,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 6.239659654927913,
|
| 2316 |
+
"grad_norm": 0.08582387864589691,
|
| 2317 |
+
"learning_rate": 2.730385475081532e-08,
|
| 2318 |
+
"loss": 0.6288,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 6.258567714488301,
|
| 2323 |
+
"grad_norm": 0.09809162467718124,
|
| 2324 |
+
"learning_rate": 2.2354468977327516e-08,
|
| 2325 |
+
"loss": 0.6968,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 6.277475774048688,
|
| 2330 |
+
"grad_norm": 0.08818063884973526,
|
| 2331 |
+
"learning_rate": 1.7898622112156316e-08,
|
| 2332 |
+
"loss": 0.666,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 6.296383833609076,
|
| 2337 |
+
"grad_norm": 0.08366916328668594,
|
| 2338 |
+
"learning_rate": 1.3936755957311143e-08,
|
| 2339 |
+
"loss": 0.6828,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 6.315291893169464,
|
| 2344 |
+
"grad_norm": 0.08646037429571152,
|
| 2345 |
+
"learning_rate": 1.0469263336082003e-08,
|
| 2346 |
+
"loss": 0.6642,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 6.334199952729851,
|
| 2351 |
+
"grad_norm": 0.08840810507535934,
|
| 2352 |
+
"learning_rate": 7.496488054092866e-09,
|
| 2353 |
+
"loss": 0.6554,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 6.353108012290239,
|
| 2358 |
+
"grad_norm": 0.08178407698869705,
|
| 2359 |
+
"learning_rate": 5.01872486520949e-09,
|
| 2360 |
+
"loss": 0.6952,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 6.372016071850626,
|
| 2365 |
+
"grad_norm": 0.08657605946063995,
|
| 2366 |
+
"learning_rate": 3.0362194423172452e-09,
|
| 2367 |
+
"loss": 0.6672,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 6.390924131411014,
|
| 2372 |
+
"grad_norm": 0.08829477429389954,
|
| 2373 |
+
"learning_rate": 1.5491683529617051e-09,
|
| 2374 |
+
"loss": 0.6847,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 6.409832190971402,
|
| 2379 |
+
"grad_norm": 0.07726303488016129,
|
| 2380 |
+
"learning_rate": 5.577190398575738e-10,
|
| 2381 |
+
"loss": 0.6313,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 6.428740250531789,
|
| 2386 |
+
"grad_norm": 0.10468406975269318,
|
| 2387 |
+
"learning_rate": 6.196980627093396e-11,
|
| 2388 |
+
"loss": 0.6979,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
}
|
| 2391 |
+
],
|
| 2392 |
+
"logging_steps": 10,
|
| 2393 |
+
"max_steps": 3405,
|
| 2394 |
+
"num_input_tokens_seen": 0,
|
| 2395 |
+
"num_train_epochs": 7,
|
| 2396 |
+
"save_steps": 500,
|
| 2397 |
+
"stateful_callbacks": {
|
| 2398 |
+
"TrainerControl": {
|
| 2399 |
+
"args": {
|
| 2400 |
+
"should_epoch_stop": false,
|
| 2401 |
+
"should_evaluate": false,
|
| 2402 |
+
"should_log": false,
|
| 2403 |
+
"should_save": true,
|
| 2404 |
+
"should_training_stop": true
|
| 2405 |
+
},
|
| 2406 |
+
"attributes": {}
|
| 2407 |
+
}
|
| 2408 |
+
},
|
| 2409 |
+
"total_flos": 5.668270529052672e+17,
|
| 2410 |
+
"train_batch_size": 1,
|
| 2411 |
+
"trial_name": null,
|
| 2412 |
+
"trial_params": null
|
| 2413 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80bf421f25a46b6b892ed43fa185599ba90b0e33df4370005e2f5b9b6c13ae01
|
| 3 |
+
size 5496
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|