upload all model files
Browse filesExtracted all the model files and uploaded.
- README.md +202 -3
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +40 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +326 -0
- trainer_state.json +1993 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,202 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/phi-2
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.14.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/phi-2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 32,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 16,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"q_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"dense"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:763c81136d99820ca248ef4597c67d6d78c449007aea88b62cfe8f16135dcc5d
|
| 3 |
+
size 41977360
|
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
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 sha256:646d4f487a71c50f3db1aa3bd8e5a736341897f5adeb09a078de540ef56ab17c
|
| 3 |
+
size 84037562
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afc09d9fb1f403f1b24fee3d70d6cfe9af0fd6cd9ff28cb259765762c8823e53
|
| 3 |
+
size 14244
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:488341b84be4d141b80ff7a3c415a5379e4f119b97bd41cb6c25814f1435efa8
|
| 3 |
+
size 988
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2392011c84b4f34c297237910f29d1ca5210b6cae19a9f6405857d131d112c9a
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"clean_up_tokenization_spaces": true,
|
| 319 |
+
"eos_token": "<|endoftext|>",
|
| 320 |
+
"extra_special_tokens": {},
|
| 321 |
+
"model_max_length": 2048,
|
| 322 |
+
"pad_token": "<|endoftext|>",
|
| 323 |
+
"return_token_type_ids": false,
|
| 324 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 325 |
+
"unk_token": "<|endoftext|>"
|
| 326 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1993 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9998981773750127,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2455,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004072904999490887,
|
| 13 |
+
"grad_norm": 0.7094523906707764,
|
| 14 |
+
"learning_rate": 2.702702702702703e-05,
|
| 15 |
+
"loss": 1.8961,
|
| 16 |
+
"mean_token_accuracy": 0.5438283555209636,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.008145809998981774,
|
| 21 |
+
"grad_norm": 0.4965726137161255,
|
| 22 |
+
"learning_rate": 5.405405405405406e-05,
|
| 23 |
+
"loss": 2.0135,
|
| 24 |
+
"mean_token_accuracy": 0.5206024497747421,
|
| 25 |
+
"step": 20
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.01221871499847266,
|
| 29 |
+
"grad_norm": 0.5204955339431763,
|
| 30 |
+
"learning_rate": 8.108108108108109e-05,
|
| 31 |
+
"loss": 1.7338,
|
| 32 |
+
"mean_token_accuracy": 0.5830004885792732,
|
| 33 |
+
"step": 30
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01629161999796355,
|
| 37 |
+
"grad_norm": 0.4678299129009247,
|
| 38 |
+
"learning_rate": 0.00010810810810810812,
|
| 39 |
+
"loss": 1.7561,
|
| 40 |
+
"mean_token_accuracy": 0.5730855345726014,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.020364524997454433,
|
| 45 |
+
"grad_norm": 0.439376562833786,
|
| 46 |
+
"learning_rate": 0.00013513513513513514,
|
| 47 |
+
"loss": 1.7277,
|
| 48 |
+
"mean_token_accuracy": 0.5785414174199104,
|
| 49 |
+
"step": 50
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.02443742999694532,
|
| 53 |
+
"grad_norm": 0.5652154684066772,
|
| 54 |
+
"learning_rate": 0.00016216216216216218,
|
| 55 |
+
"loss": 1.5663,
|
| 56 |
+
"mean_token_accuracy": 0.6036677993834019,
|
| 57 |
+
"step": 60
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.02851033499643621,
|
| 61 |
+
"grad_norm": 0.5163070559501648,
|
| 62 |
+
"learning_rate": 0.0001891891891891892,
|
| 63 |
+
"loss": 1.8259,
|
| 64 |
+
"mean_token_accuracy": 0.5530456639826298,
|
| 65 |
+
"step": 70
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0325832399959271,
|
| 69 |
+
"grad_norm": 0.41974571347236633,
|
| 70 |
+
"learning_rate": 0.00019999686634492516,
|
| 71 |
+
"loss": 1.6554,
|
| 72 |
+
"mean_token_accuracy": 0.6073097884654999,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.03665614499541798,
|
| 77 |
+
"grad_norm": 0.5097134709358215,
|
| 78 |
+
"learning_rate": 0.00019997771694180204,
|
| 79 |
+
"loss": 1.7208,
|
| 80 |
+
"mean_token_accuracy": 0.5835812106728554,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04072904999490887,
|
| 85 |
+
"grad_norm": 0.3469955623149872,
|
| 86 |
+
"learning_rate": 0.00019994116238472668,
|
| 87 |
+
"loss": 1.7954,
|
| 88 |
+
"mean_token_accuracy": 0.5794057920575142,
|
| 89 |
+
"step": 100
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.044801954994399755,
|
| 93 |
+
"grad_norm": 0.5898286700248718,
|
| 94 |
+
"learning_rate": 0.0001998872090374941,
|
| 95 |
+
"loss": 1.8089,
|
| 96 |
+
"mean_token_accuracy": 0.5614037178456783,
|
| 97 |
+
"step": 110
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.04887485999389064,
|
| 101 |
+
"grad_norm": 0.3150334656238556,
|
| 102 |
+
"learning_rate": 0.0001998158662928604,
|
| 103 |
+
"loss": 1.5827,
|
| 104 |
+
"mean_token_accuracy": 0.5801003761589527,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05294776499338153,
|
| 109 |
+
"grad_norm": 0.3100312352180481,
|
| 110 |
+
"learning_rate": 0.00019972714657090772,
|
| 111 |
+
"loss": 1.6712,
|
| 112 |
+
"mean_token_accuracy": 0.5900266923010349,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.05702066999287242,
|
| 117 |
+
"grad_norm": 0.30420345067977905,
|
| 118 |
+
"learning_rate": 0.0001996210653168819,
|
| 119 |
+
"loss": 1.646,
|
| 120 |
+
"mean_token_accuracy": 0.5839473098516464,
|
| 121 |
+
"step": 140
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0610935749923633,
|
| 125 |
+
"grad_norm": 0.454593688249588,
|
| 126 |
+
"learning_rate": 0.0001994976409985037,
|
| 127 |
+
"loss": 1.7184,
|
| 128 |
+
"mean_token_accuracy": 0.566600239276886,
|
| 129 |
+
"step": 150
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0651664799918542,
|
| 133 |
+
"grad_norm": 0.35688647627830505,
|
| 134 |
+
"learning_rate": 0.0001993568951027537,
|
| 135 |
+
"loss": 1.6766,
|
| 136 |
+
"mean_token_accuracy": 0.5824202686548233,
|
| 137 |
+
"step": 160
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.06923938499134508,
|
| 141 |
+
"grad_norm": 0.3199939727783203,
|
| 142 |
+
"learning_rate": 0.0001991988521321317,
|
| 143 |
+
"loss": 1.542,
|
| 144 |
+
"mean_token_accuracy": 0.6095141984522343,
|
| 145 |
+
"step": 170
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.07331228999083596,
|
| 149 |
+
"grad_norm": 0.5523242950439453,
|
| 150 |
+
"learning_rate": 0.00019902353960039087,
|
| 151 |
+
"loss": 1.7218,
|
| 152 |
+
"mean_token_accuracy": 0.5745485998690129,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.07738519499032685,
|
| 157 |
+
"grad_norm": 0.3872721493244171,
|
| 158 |
+
"learning_rate": 0.00019883098802774812,
|
| 159 |
+
"loss": 1.7306,
|
| 160 |
+
"mean_token_accuracy": 0.5514535710215569,
|
| 161 |
+
"step": 190
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.08145809998981773,
|
| 165 |
+
"grad_norm": 0.2679811120033264,
|
| 166 |
+
"learning_rate": 0.0001986212309355707,
|
| 167 |
+
"loss": 1.6524,
|
| 168 |
+
"mean_token_accuracy": 0.5822832569479942,
|
| 169 |
+
"step": 200
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.08553100498930863,
|
| 173 |
+
"grad_norm": 0.5167363882064819,
|
| 174 |
+
"learning_rate": 0.00019839430484054046,
|
| 175 |
+
"loss": 1.6964,
|
| 176 |
+
"mean_token_accuracy": 0.573430598527193,
|
| 177 |
+
"step": 210
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08960390998879951,
|
| 181 |
+
"grad_norm": 0.4363399147987366,
|
| 182 |
+
"learning_rate": 0.0001981502492482967,
|
| 183 |
+
"loss": 1.7296,
|
| 184 |
+
"mean_token_accuracy": 0.5835007324814796,
|
| 185 |
+
"step": 220
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.0936768149882904,
|
| 189 |
+
"grad_norm": 0.4052150845527649,
|
| 190 |
+
"learning_rate": 0.00019788910664655848,
|
| 191 |
+
"loss": 1.5772,
|
| 192 |
+
"mean_token_accuracy": 0.5771500714123249,
|
| 193 |
+
"step": 230
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.09774971998778129,
|
| 197 |
+
"grad_norm": 0.34224212169647217,
|
| 198 |
+
"learning_rate": 0.0001976109224977281,
|
| 199 |
+
"loss": 1.6263,
|
| 200 |
+
"mean_token_accuracy": 0.5942870646715164,
|
| 201 |
+
"step": 240
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.10182262498727217,
|
| 205 |
+
"grad_norm": 0.4852873980998993,
|
| 206 |
+
"learning_rate": 0.00019731574523097647,
|
| 207 |
+
"loss": 1.5731,
|
| 208 |
+
"mean_token_accuracy": 0.5886094763875007,
|
| 209 |
+
"step": 250
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.10589552998676306,
|
| 213 |
+
"grad_norm": 0.30241233110427856,
|
| 214 |
+
"learning_rate": 0.00019700362623381197,
|
| 215 |
+
"loss": 1.8311,
|
| 216 |
+
"mean_token_accuracy": 0.5616028495132923,
|
| 217 |
+
"step": 260
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.10996843498625394,
|
| 221 |
+
"grad_norm": 0.38147303462028503,
|
| 222 |
+
"learning_rate": 0.00019667461984313448,
|
| 223 |
+
"loss": 1.652,
|
| 224 |
+
"mean_token_accuracy": 0.5836799181997776,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.11404133998574484,
|
| 229 |
+
"grad_norm": 0.3174324333667755,
|
| 230 |
+
"learning_rate": 0.00019632878333577592,
|
| 231 |
+
"loss": 1.6831,
|
| 232 |
+
"mean_token_accuracy": 0.5850063987076283,
|
| 233 |
+
"step": 280
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.11811424498523572,
|
| 237 |
+
"grad_norm": 0.350323349237442,
|
| 238 |
+
"learning_rate": 0.00019596617691852863,
|
| 239 |
+
"loss": 1.6644,
|
| 240 |
+
"mean_token_accuracy": 0.5841067053377629,
|
| 241 |
+
"step": 290
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.1221871499847266,
|
| 245 |
+
"grad_norm": 0.30346542596817017,
|
| 246 |
+
"learning_rate": 0.0001955868637176643,
|
| 247 |
+
"loss": 1.656,
|
| 248 |
+
"mean_token_accuracy": 0.584677055478096,
|
| 249 |
+
"step": 300
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.1262600549842175,
|
| 253 |
+
"grad_norm": 0.2639765739440918,
|
| 254 |
+
"learning_rate": 0.00019519090976794406,
|
| 255 |
+
"loss": 1.7454,
|
| 256 |
+
"mean_token_accuracy": 0.5678185373544693,
|
| 257 |
+
"step": 310
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.1303329599837084,
|
| 261 |
+
"grad_norm": 0.3039887547492981,
|
| 262 |
+
"learning_rate": 0.00019477838400112254,
|
| 263 |
+
"loss": 1.754,
|
| 264 |
+
"mean_token_accuracy": 0.5744720883667469,
|
| 265 |
+
"step": 320
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.13440586498319926,
|
| 269 |
+
"grad_norm": 0.35102295875549316,
|
| 270 |
+
"learning_rate": 0.00019434935823394746,
|
| 271 |
+
"loss": 1.6665,
|
| 272 |
+
"mean_token_accuracy": 0.5876846723258495,
|
| 273 |
+
"step": 330
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.13847876998269015,
|
| 277 |
+
"grad_norm": 0.3325759470462799,
|
| 278 |
+
"learning_rate": 0.00019390390715565725,
|
| 279 |
+
"loss": 1.6773,
|
| 280 |
+
"mean_token_accuracy": 0.5869172632694244,
|
| 281 |
+
"step": 340
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.14255167498218105,
|
| 285 |
+
"grad_norm": 0.37209993600845337,
|
| 286 |
+
"learning_rate": 0.000193442108314978,
|
| 287 |
+
"loss": 1.6328,
|
| 288 |
+
"mean_token_accuracy": 0.5927142709493637,
|
| 289 |
+
"step": 350
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.14662457998167192,
|
| 293 |
+
"grad_norm": 0.2964717149734497,
|
| 294 |
+
"learning_rate": 0.00019296404210662331,
|
| 295 |
+
"loss": 1.5659,
|
| 296 |
+
"mean_token_accuracy": 0.60322862342,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.1506974849811628,
|
| 301 |
+
"grad_norm": 0.29879456758499146,
|
| 302 |
+
"learning_rate": 0.00019246979175729822,
|
| 303 |
+
"loss": 1.7083,
|
| 304 |
+
"mean_token_accuracy": 0.5893984287977219,
|
| 305 |
+
"step": 370
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.1547703899806537,
|
| 309 |
+
"grad_norm": 0.3726056218147278,
|
| 310 |
+
"learning_rate": 0.00019195944331121015,
|
| 311 |
+
"loss": 1.6854,
|
| 312 |
+
"mean_token_accuracy": 0.5761750474572181,
|
| 313 |
+
"step": 380
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.1588432949801446,
|
| 317 |
+
"grad_norm": 0.517816424369812,
|
| 318 |
+
"learning_rate": 0.0001914330856150897,
|
| 319 |
+
"loss": 1.7282,
|
| 320 |
+
"mean_token_accuracy": 0.5854727104306221,
|
| 321 |
+
"step": 390
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.16291619997963547,
|
| 325 |
+
"grad_norm": 0.25848233699798584,
|
| 326 |
+
"learning_rate": 0.00019089081030272296,
|
| 327 |
+
"loss": 1.5562,
|
| 328 |
+
"mean_token_accuracy": 0.6038706839084625,
|
| 329 |
+
"step": 400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.16698910497912636,
|
| 333 |
+
"grad_norm": 0.3191607892513275,
|
| 334 |
+
"learning_rate": 0.00019033271177899922,
|
| 335 |
+
"loss": 1.6452,
|
| 336 |
+
"mean_token_accuracy": 0.5812859788537026,
|
| 337 |
+
"step": 410
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.17106200997861726,
|
| 341 |
+
"grad_norm": 0.3990655243396759,
|
| 342 |
+
"learning_rate": 0.0001897588872034758,
|
| 343 |
+
"loss": 1.626,
|
| 344 |
+
"mean_token_accuracy": 0.569889971613884,
|
| 345 |
+
"step": 420
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.17513491497810812,
|
| 349 |
+
"grad_norm": 0.346086323261261,
|
| 350 |
+
"learning_rate": 0.00018916943647346375,
|
| 351 |
+
"loss": 1.7451,
|
| 352 |
+
"mean_token_accuracy": 0.578500047326088,
|
| 353 |
+
"step": 430
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.17920781997759902,
|
| 357 |
+
"grad_norm": 0.36437422037124634,
|
| 358 |
+
"learning_rate": 0.0001885644622066364,
|
| 359 |
+
"loss": 1.846,
|
| 360 |
+
"mean_token_accuracy": 0.5627885892987251,
|
| 361 |
+
"step": 440
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.18328072497708991,
|
| 365 |
+
"grad_norm": 0.2968160808086395,
|
| 366 |
+
"learning_rate": 0.00018794406972316482,
|
| 367 |
+
"loss": 1.671,
|
| 368 |
+
"mean_token_accuracy": 0.5769762165844441,
|
| 369 |
+
"step": 450
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.1873536299765808,
|
| 373 |
+
"grad_norm": 0.2781198024749756,
|
| 374 |
+
"learning_rate": 0.00018730836702738257,
|
| 375 |
+
"loss": 1.4983,
|
| 376 |
+
"mean_token_accuracy": 0.613883113116026,
|
| 377 |
+
"step": 460
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.19142653497607168,
|
| 381 |
+
"grad_norm": 0.4645621180534363,
|
| 382 |
+
"learning_rate": 0.0001866574647889831,
|
| 383 |
+
"loss": 1.6776,
|
| 384 |
+
"mean_token_accuracy": 0.5890260674059391,
|
| 385 |
+
"step": 470
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.19549943997556257,
|
| 389 |
+
"grad_norm": 0.3920878767967224,
|
| 390 |
+
"learning_rate": 0.00018599147632375332,
|
| 391 |
+
"loss": 1.802,
|
| 392 |
+
"mean_token_accuracy": 0.568213502317667,
|
| 393 |
+
"step": 480
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.19957234497505347,
|
| 397 |
+
"grad_norm": 0.3473225235939026,
|
| 398 |
+
"learning_rate": 0.00018531051757384633,
|
| 399 |
+
"loss": 1.7161,
|
| 400 |
+
"mean_token_accuracy": 0.5727271348237991,
|
| 401 |
+
"step": 490
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.20364524997454433,
|
| 405 |
+
"grad_norm": 0.30091673135757446,
|
| 406 |
+
"learning_rate": 0.00018461470708759712,
|
| 407 |
+
"loss": 1.7042,
|
| 408 |
+
"mean_token_accuracy": 0.5763454169034958,
|
| 409 |
+
"step": 500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.20771815497403523,
|
| 413 |
+
"grad_norm": 0.31175661087036133,
|
| 414 |
+
"learning_rate": 0.00018390416599888435,
|
| 415 |
+
"loss": 1.689,
|
| 416 |
+
"mean_token_accuracy": 0.5796464458107948,
|
| 417 |
+
"step": 510
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.21179105997352612,
|
| 421 |
+
"grad_norm": 0.3624255955219269,
|
| 422 |
+
"learning_rate": 0.0001831790180060422,
|
| 423 |
+
"loss": 1.5619,
|
| 424 |
+
"mean_token_accuracy": 0.6015763126313687,
|
| 425 |
+
"step": 520
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.215863964973017,
|
| 429 |
+
"grad_norm": 0.2667541205883026,
|
| 430 |
+
"learning_rate": 0.00018243938935032561,
|
| 431 |
+
"loss": 1.6877,
|
| 432 |
+
"mean_token_accuracy": 0.5839527539908886,
|
| 433 |
+
"step": 530
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.2199368699725079,
|
| 437 |
+
"grad_norm": 0.31019967794418335,
|
| 438 |
+
"learning_rate": 0.00018168540879393296,
|
| 439 |
+
"loss": 1.7831,
|
| 440 |
+
"mean_token_accuracy": 0.5688935197889805,
|
| 441 |
+
"step": 540
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.22400977497199878,
|
| 445 |
+
"grad_norm": 0.2726418673992157,
|
| 446 |
+
"learning_rate": 0.0001809172075975897,
|
| 447 |
+
"loss": 1.7288,
|
| 448 |
+
"mean_token_accuracy": 0.5798229008913041,
|
| 449 |
+
"step": 550
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.22808267997148968,
|
| 453 |
+
"grad_norm": 0.29514381289482117,
|
| 454 |
+
"learning_rate": 0.00018013491949769734,
|
| 455 |
+
"loss": 1.7188,
|
| 456 |
+
"mean_token_accuracy": 0.5756009854376316,
|
| 457 |
+
"step": 560
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.23215558497098054,
|
| 461 |
+
"grad_norm": 0.37964069843292236,
|
| 462 |
+
"learning_rate": 0.00017933868068305104,
|
| 463 |
+
"loss": 1.6244,
|
| 464 |
+
"mean_token_accuracy": 0.5932842157781124,
|
| 465 |
+
"step": 570
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.23622848997047144,
|
| 469 |
+
"grad_norm": 0.300620436668396,
|
| 470 |
+
"learning_rate": 0.0001785286297711305,
|
| 471 |
+
"loss": 1.5565,
|
| 472 |
+
"mean_token_accuracy": 0.5965760670602321,
|
| 473 |
+
"step": 580
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.24030139496996233,
|
| 477 |
+
"grad_norm": 0.5466737151145935,
|
| 478 |
+
"learning_rate": 0.00017770490778396808,
|
| 479 |
+
"loss": 1.6532,
|
| 480 |
+
"mean_token_accuracy": 0.5821332208812237,
|
| 481 |
+
"step": 590
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.2443742999694532,
|
| 485 |
+
"grad_norm": 0.3445660173892975,
|
| 486 |
+
"learning_rate": 0.00017686765812359808,
|
| 487 |
+
"loss": 1.7585,
|
| 488 |
+
"mean_token_accuracy": 0.5790032669901848,
|
| 489 |
+
"step": 600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.2484472049689441,
|
| 493 |
+
"grad_norm": 0.3492606282234192,
|
| 494 |
+
"learning_rate": 0.0001760170265470921,
|
| 495 |
+
"loss": 1.6401,
|
| 496 |
+
"mean_token_accuracy": 0.6002471588551999,
|
| 497 |
+
"step": 610
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.252520109968435,
|
| 501 |
+
"grad_norm": 0.31294527649879456,
|
| 502 |
+
"learning_rate": 0.00017515316114118375,
|
| 503 |
+
"loss": 1.6915,
|
| 504 |
+
"mean_token_accuracy": 0.5570432722568512,
|
| 505 |
+
"step": 620
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.25659301496792586,
|
| 509 |
+
"grad_norm": 0.27257561683654785,
|
| 510 |
+
"learning_rate": 0.00017427621229648853,
|
| 511 |
+
"loss": 1.5666,
|
| 512 |
+
"mean_token_accuracy": 0.6028999522328377,
|
| 513 |
+
"step": 630
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.2606659199674168,
|
| 517 |
+
"grad_norm": 0.29818692803382874,
|
| 518 |
+
"learning_rate": 0.00017338633268132212,
|
| 519 |
+
"loss": 1.5926,
|
| 520 |
+
"mean_token_accuracy": 0.5965964362025261,
|
| 521 |
+
"step": 640
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.26473882496690765,
|
| 525 |
+
"grad_norm": 0.49210649728775024,
|
| 526 |
+
"learning_rate": 0.0001724836772151223,
|
| 527 |
+
"loss": 1.5925,
|
| 528 |
+
"mean_token_accuracy": 0.5952631443738937,
|
| 529 |
+
"step": 650
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.2688117299663985,
|
| 533 |
+
"grad_norm": 0.3807302713394165,
|
| 534 |
+
"learning_rate": 0.00017156840304147902,
|
| 535 |
+
"loss": 1.6237,
|
| 536 |
+
"mean_token_accuracy": 0.5884141281247139,
|
| 537 |
+
"step": 660
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.27288463496588944,
|
| 541 |
+
"grad_norm": 0.2621661126613617,
|
| 542 |
+
"learning_rate": 0.00017064066950077722,
|
| 543 |
+
"loss": 1.7356,
|
| 544 |
+
"mean_token_accuracy": 0.5827617473900318,
|
| 545 |
+
"step": 670
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.2769575399653803,
|
| 549 |
+
"grad_norm": 0.30957838892936707,
|
| 550 |
+
"learning_rate": 0.00016970063810245716,
|
| 551 |
+
"loss": 1.5585,
|
| 552 |
+
"mean_token_accuracy": 0.5888052701950073,
|
| 553 |
+
"step": 680
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.2810304449648712,
|
| 557 |
+
"grad_norm": 0.2501460611820221,
|
| 558 |
+
"learning_rate": 0.00016874847249689722,
|
| 559 |
+
"loss": 1.5913,
|
| 560 |
+
"mean_token_accuracy": 0.5886548452079297,
|
| 561 |
+
"step": 690
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.2851033499643621,
|
| 565 |
+
"grad_norm": 0.3207811415195465,
|
| 566 |
+
"learning_rate": 0.00016778433844692397,
|
| 567 |
+
"loss": 1.6791,
|
| 568 |
+
"mean_token_accuracy": 0.5861249402165413,
|
| 569 |
+
"step": 700
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.28917625496385296,
|
| 573 |
+
"grad_norm": 0.45466601848602295,
|
| 574 |
+
"learning_rate": 0.0001668084037989544,
|
| 575 |
+
"loss": 1.5153,
|
| 576 |
+
"mean_token_accuracy": 0.5999807387590408,
|
| 577 |
+
"step": 710
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.29324915996334383,
|
| 581 |
+
"grad_norm": 0.34910282492637634,
|
| 582 |
+
"learning_rate": 0.00016582083845377552,
|
| 583 |
+
"loss": 1.6821,
|
| 584 |
+
"mean_token_accuracy": 0.5889992110431195,
|
| 585 |
+
"step": 720
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.29732206496283475,
|
| 589 |
+
"grad_norm": 0.4916020929813385,
|
| 590 |
+
"learning_rate": 0.00016482181433696643,
|
| 591 |
+
"loss": 1.8462,
|
| 592 |
+
"mean_token_accuracy": 0.5748938458040357,
|
| 593 |
+
"step": 730
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.3013949699623256,
|
| 597 |
+
"grad_norm": 0.2545833885669708,
|
| 598 |
+
"learning_rate": 0.00016381150536896736,
|
| 599 |
+
"loss": 1.5756,
|
| 600 |
+
"mean_token_accuracy": 0.6056667067110538,
|
| 601 |
+
"step": 740
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.3054678749618165,
|
| 605 |
+
"grad_norm": 0.30347147583961487,
|
| 606 |
+
"learning_rate": 0.0001627900874348022,
|
| 607 |
+
"loss": 1.6003,
|
| 608 |
+
"mean_token_accuracy": 0.5873342089354991,
|
| 609 |
+
"step": 750
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.3095407799613074,
|
| 613 |
+
"grad_norm": 0.37371426820755005,
|
| 614 |
+
"learning_rate": 0.0001617577383534584,
|
| 615 |
+
"loss": 1.6576,
|
| 616 |
+
"mean_token_accuracy": 0.5790071420371532,
|
| 617 |
+
"step": 760
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.3136136849607983,
|
| 621 |
+
"grad_norm": 0.41969504952430725,
|
| 622 |
+
"learning_rate": 0.00016071463784693045,
|
| 623 |
+
"loss": 1.6181,
|
| 624 |
+
"mean_token_accuracy": 0.5854876518249512,
|
| 625 |
+
"step": 770
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.3176865899602892,
|
| 629 |
+
"grad_norm": 0.17495319247245789,
|
| 630 |
+
"learning_rate": 0.00015966096750893197,
|
| 631 |
+
"loss": 1.5142,
|
| 632 |
+
"mean_token_accuracy": 0.6079291738569736,
|
| 633 |
+
"step": 780
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.32175949495978007,
|
| 637 |
+
"grad_norm": 0.30013784766197205,
|
| 638 |
+
"learning_rate": 0.00015859691077328215,
|
| 639 |
+
"loss": 1.6583,
|
| 640 |
+
"mean_token_accuracy": 0.581703095138073,
|
| 641 |
+
"step": 790
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.32583239995927094,
|
| 645 |
+
"grad_norm": 0.3358050584793091,
|
| 646 |
+
"learning_rate": 0.00015752265288197155,
|
| 647 |
+
"loss": 1.6468,
|
| 648 |
+
"mean_token_accuracy": 0.6049091577529907,
|
| 649 |
+
"step": 800
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.32990530495876186,
|
| 653 |
+
"grad_norm": 0.3690403699874878,
|
| 654 |
+
"learning_rate": 0.00015643838085291323,
|
| 655 |
+
"loss": 1.8431,
|
| 656 |
+
"mean_token_accuracy": 0.5602408707141876,
|
| 657 |
+
"step": 810
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.3339782099582527,
|
| 661 |
+
"grad_norm": 0.34296655654907227,
|
| 662 |
+
"learning_rate": 0.00015534428344738505,
|
| 663 |
+
"loss": 1.7042,
|
| 664 |
+
"mean_token_accuracy": 0.5799131192266941,
|
| 665 |
+
"step": 820
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.3380511149577436,
|
| 669 |
+
"grad_norm": 0.2764555513858795,
|
| 670 |
+
"learning_rate": 0.00015424055113716763,
|
| 671 |
+
"loss": 1.5479,
|
| 672 |
+
"mean_token_accuracy": 0.5909703068435193,
|
| 673 |
+
"step": 830
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.3421240199572345,
|
| 677 |
+
"grad_norm": 0.26227012276649475,
|
| 678 |
+
"learning_rate": 0.0001531273760713855,
|
| 679 |
+
"loss": 1.5303,
|
| 680 |
+
"mean_token_accuracy": 0.5910052061080933,
|
| 681 |
+
"step": 840
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.3461969249567254,
|
| 685 |
+
"grad_norm": 0.3656936585903168,
|
| 686 |
+
"learning_rate": 0.00015200495204305574,
|
| 687 |
+
"loss": 1.5586,
|
| 688 |
+
"mean_token_accuracy": 0.5943005800247192,
|
| 689 |
+
"step": 850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.35026982995621625,
|
| 693 |
+
"grad_norm": 0.29997819662094116,
|
| 694 |
+
"learning_rate": 0.00015087347445535013,
|
| 695 |
+
"loss": 1.8219,
|
| 696 |
+
"mean_token_accuracy": 0.5533552631735802,
|
| 697 |
+
"step": 860
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.3543427349557072,
|
| 701 |
+
"grad_norm": 0.290685772895813,
|
| 702 |
+
"learning_rate": 0.00014973314028757787,
|
| 703 |
+
"loss": 1.7261,
|
| 704 |
+
"mean_token_accuracy": 0.5844682581722737,
|
| 705 |
+
"step": 870
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.35841563995519804,
|
| 709 |
+
"grad_norm": 0.34553012251853943,
|
| 710 |
+
"learning_rate": 0.00014858414806089295,
|
| 711 |
+
"loss": 1.6982,
|
| 712 |
+
"mean_token_accuracy": 0.5762835793197155,
|
| 713 |
+
"step": 880
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.3624885449546889,
|
| 717 |
+
"grad_norm": 0.2141156941652298,
|
| 718 |
+
"learning_rate": 0.0001474266978037338,
|
| 719 |
+
"loss": 1.5318,
|
| 720 |
+
"mean_token_accuracy": 0.6048024773597718,
|
| 721 |
+
"step": 890
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.36656144995417983,
|
| 725 |
+
"grad_norm": 0.30456602573394775,
|
| 726 |
+
"learning_rate": 0.00014626099101700018,
|
| 727 |
+
"loss": 1.7901,
|
| 728 |
+
"mean_token_accuracy": 0.5763920709490776,
|
| 729 |
+
"step": 900
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.3706343549536707,
|
| 733 |
+
"grad_norm": 0.26921945810317993,
|
| 734 |
+
"learning_rate": 0.00014508723063897376,
|
| 735 |
+
"loss": 1.4936,
|
| 736 |
+
"mean_token_accuracy": 0.6303243085741996,
|
| 737 |
+
"step": 910
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.3747072599531616,
|
| 741 |
+
"grad_norm": 0.28455570340156555,
|
| 742 |
+
"learning_rate": 0.00014390562100998868,
|
| 743 |
+
"loss": 1.5804,
|
| 744 |
+
"mean_token_accuracy": 0.6074232332408428,
|
| 745 |
+
"step": 920
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.3787801649526525,
|
| 749 |
+
"grad_norm": 0.3388415575027466,
|
| 750 |
+
"learning_rate": 0.00014271636783685777,
|
| 751 |
+
"loss": 1.6731,
|
| 752 |
+
"mean_token_accuracy": 0.5768752813339233,
|
| 753 |
+
"step": 930
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.38285306995214335,
|
| 757 |
+
"grad_norm": 0.4311608076095581,
|
| 758 |
+
"learning_rate": 0.00014151967815706091,
|
| 759 |
+
"loss": 1.7237,
|
| 760 |
+
"mean_token_accuracy": 0.5706497602164745,
|
| 761 |
+
"step": 940
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.3869259749516343,
|
| 765 |
+
"grad_norm": 0.35940027236938477,
|
| 766 |
+
"learning_rate": 0.00014031576030270202,
|
| 767 |
+
"loss": 1.5355,
|
| 768 |
+
"mean_token_accuracy": 0.5908183179795742,
|
| 769 |
+
"step": 950
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.39099887995112514,
|
| 773 |
+
"grad_norm": 0.34071287512779236,
|
| 774 |
+
"learning_rate": 0.00013910482386424023,
|
| 775 |
+
"loss": 1.7247,
|
| 776 |
+
"mean_token_accuracy": 0.5757749699056148,
|
| 777 |
+
"step": 960
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.395071784950616,
|
| 781 |
+
"grad_norm": 0.413870245218277,
|
| 782 |
+
"learning_rate": 0.00013788707965400236,
|
| 783 |
+
"loss": 1.6796,
|
| 784 |
+
"mean_token_accuracy": 0.592286454886198,
|
| 785 |
+
"step": 970
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.39914468995010693,
|
| 789 |
+
"grad_norm": 0.2649496793746948,
|
| 790 |
+
"learning_rate": 0.00013666273966948252,
|
| 791 |
+
"loss": 1.5955,
|
| 792 |
+
"mean_token_accuracy": 0.5936679825186729,
|
| 793 |
+
"step": 980
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.4032175949495978,
|
| 797 |
+
"grad_norm": 0.3525199294090271,
|
| 798 |
+
"learning_rate": 0.00013543201705643526,
|
| 799 |
+
"loss": 1.647,
|
| 800 |
+
"mean_token_accuracy": 0.5950982637703419,
|
| 801 |
+
"step": 990
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.40729049994908867,
|
| 805 |
+
"grad_norm": 0.33436283469200134,
|
| 806 |
+
"learning_rate": 0.00013419512607176914,
|
| 807 |
+
"loss": 1.7161,
|
| 808 |
+
"mean_token_accuracy": 0.574284989386797,
|
| 809 |
+
"step": 1000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.4113634049485796,
|
| 813 |
+
"grad_norm": 0.46867313981056213,
|
| 814 |
+
"learning_rate": 0.00013295228204624648,
|
| 815 |
+
"loss": 1.544,
|
| 816 |
+
"mean_token_accuracy": 0.6102774910628795,
|
| 817 |
+
"step": 1010
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.41543630994807046,
|
| 821 |
+
"grad_norm": 0.30373555421829224,
|
| 822 |
+
"learning_rate": 0.00013170370134699653,
|
| 823 |
+
"loss": 1.6287,
|
| 824 |
+
"mean_token_accuracy": 0.5843084178864956,
|
| 825 |
+
"step": 1020
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.4195092149475613,
|
| 829 |
+
"grad_norm": 0.2981624901294708,
|
| 830 |
+
"learning_rate": 0.00013044960133984804,
|
| 831 |
+
"loss": 1.6858,
|
| 832 |
+
"mean_token_accuracy": 0.5856122255325318,
|
| 833 |
+
"step": 1030
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.42358211994705225,
|
| 837 |
+
"grad_norm": 0.3545626997947693,
|
| 838 |
+
"learning_rate": 0.00012919020035148776,
|
| 839 |
+
"loss": 1.7392,
|
| 840 |
+
"mean_token_accuracy": 0.5841099888086319,
|
| 841 |
+
"step": 1040
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.4276550249465431,
|
| 845 |
+
"grad_norm": 0.2896677553653717,
|
| 846 |
+
"learning_rate": 0.0001279257176314521,
|
| 847 |
+
"loss": 1.5007,
|
| 848 |
+
"mean_token_accuracy": 0.573243772238493,
|
| 849 |
+
"step": 1050
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.431727929946034,
|
| 853 |
+
"grad_norm": 0.36384209990501404,
|
| 854 |
+
"learning_rate": 0.00012665637331395785,
|
| 855 |
+
"loss": 1.487,
|
| 856 |
+
"mean_token_accuracy": 0.6025885075330735,
|
| 857 |
+
"step": 1060
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.4358008349455249,
|
| 861 |
+
"grad_norm": 0.3681187033653259,
|
| 862 |
+
"learning_rate": 0.00012538238837957882,
|
| 863 |
+
"loss": 1.4913,
|
| 864 |
+
"mean_token_accuracy": 0.5982382036745548,
|
| 865 |
+
"step": 1070
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.4398737399450158,
|
| 869 |
+
"grad_norm": 0.2680988311767578,
|
| 870 |
+
"learning_rate": 0.00012410398461677554,
|
| 871 |
+
"loss": 1.6263,
|
| 872 |
+
"mean_token_accuracy": 0.5956345148384571,
|
| 873 |
+
"step": 1080
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.4439466449445067,
|
| 877 |
+
"grad_norm": 0.23174384236335754,
|
| 878 |
+
"learning_rate": 0.00012282138458328358,
|
| 879 |
+
"loss": 1.7378,
|
| 880 |
+
"mean_token_accuracy": 0.590882021188736,
|
| 881 |
+
"step": 1090
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.44801954994399756,
|
| 885 |
+
"grad_norm": 0.34088292717933655,
|
| 886 |
+
"learning_rate": 0.00012153481156736892,
|
| 887 |
+
"loss": 1.7385,
|
| 888 |
+
"mean_token_accuracy": 0.5994494572281838,
|
| 889 |
+
"step": 1100
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.45209245494348843,
|
| 893 |
+
"grad_norm": 0.24563632905483246,
|
| 894 |
+
"learning_rate": 0.00012024448954895522,
|
| 895 |
+
"loss": 1.5212,
|
| 896 |
+
"mean_token_accuracy": 0.6165470741689205,
|
| 897 |
+
"step": 1110
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.45616535994297935,
|
| 901 |
+
"grad_norm": 0.26980966329574585,
|
| 902 |
+
"learning_rate": 0.00011895064316063127,
|
| 903 |
+
"loss": 1.5254,
|
| 904 |
+
"mean_token_accuracy": 0.5898841544985771,
|
| 905 |
+
"step": 1120
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.4602382649424702,
|
| 909 |
+
"grad_norm": 0.32573202252388,
|
| 910 |
+
"learning_rate": 0.00011765349764854461,
|
| 911 |
+
"loss": 1.5704,
|
| 912 |
+
"mean_token_accuracy": 0.6047514051198959,
|
| 913 |
+
"step": 1130
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.4643111699419611,
|
| 917 |
+
"grad_norm": 0.3137454390525818,
|
| 918 |
+
"learning_rate": 0.00011635327883318831,
|
| 919 |
+
"loss": 1.5893,
|
| 920 |
+
"mean_token_accuracy": 0.5792985640466213,
|
| 921 |
+
"step": 1140
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.468384074941452,
|
| 925 |
+
"grad_norm": 0.368747353553772,
|
| 926 |
+
"learning_rate": 0.00011505021307008785,
|
| 927 |
+
"loss": 1.6388,
|
| 928 |
+
"mean_token_accuracy": 0.5851111486554146,
|
| 929 |
+
"step": 1150
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.4724569799409429,
|
| 933 |
+
"grad_norm": 0.325250506401062,
|
| 934 |
+
"learning_rate": 0.00011374452721039477,
|
| 935 |
+
"loss": 1.7192,
|
| 936 |
+
"mean_token_accuracy": 0.5636343933641911,
|
| 937 |
+
"step": 1160
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.47652988494043375,
|
| 941 |
+
"grad_norm": 0.32918378710746765,
|
| 942 |
+
"learning_rate": 0.00011243644856139403,
|
| 943 |
+
"loss": 1.6048,
|
| 944 |
+
"mean_token_accuracy": 0.6072004094719887,
|
| 945 |
+
"step": 1170
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.48060278993992467,
|
| 949 |
+
"grad_norm": 0.2892746031284332,
|
| 950 |
+
"learning_rate": 0.00011112620484693223,
|
| 951 |
+
"loss": 1.6785,
|
| 952 |
+
"mean_token_accuracy": 0.5872686378657818,
|
| 953 |
+
"step": 1180
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.48467569493941554,
|
| 957 |
+
"grad_norm": 0.2459000200033188,
|
| 958 |
+
"learning_rate": 0.0001098140241677728,
|
| 959 |
+
"loss": 1.5799,
|
| 960 |
+
"mean_token_accuracy": 0.6077749952673912,
|
| 961 |
+
"step": 1190
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.4887485999389064,
|
| 965 |
+
"grad_norm": 0.3696756660938263,
|
| 966 |
+
"learning_rate": 0.00010850013496188606,
|
| 967 |
+
"loss": 1.5966,
|
| 968 |
+
"mean_token_accuracy": 0.5970290452241898,
|
| 969 |
+
"step": 1200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.4928215049383973,
|
| 973 |
+
"grad_norm": 0.27681517601013184,
|
| 974 |
+
"learning_rate": 0.00010718476596468028,
|
| 975 |
+
"loss": 1.7161,
|
| 976 |
+
"mean_token_accuracy": 0.5730410292744637,
|
| 977 |
+
"step": 1210
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.4968944099378882,
|
| 981 |
+
"grad_norm": 0.2720302641391754,
|
| 982 |
+
"learning_rate": 0.00010586814616918113,
|
| 983 |
+
"loss": 1.6991,
|
| 984 |
+
"mean_token_accuracy": 0.5764113113284111,
|
| 985 |
+
"step": 1220
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.5009673149373791,
|
| 989 |
+
"grad_norm": 0.34990179538726807,
|
| 990 |
+
"learning_rate": 0.00010455050478616617,
|
| 991 |
+
"loss": 1.7114,
|
| 992 |
+
"mean_token_accuracy": 0.5776129819452762,
|
| 993 |
+
"step": 1230
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.50504021993687,
|
| 997 |
+
"grad_norm": 0.33753877878189087,
|
| 998 |
+
"learning_rate": 0.00010323207120426142,
|
| 999 |
+
"loss": 1.8174,
|
| 1000 |
+
"mean_token_accuracy": 0.5551487416028976,
|
| 1001 |
+
"step": 1240
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.5091131249363609,
|
| 1005 |
+
"grad_norm": 0.41568267345428467,
|
| 1006 |
+
"learning_rate": 0.00010191307495000712,
|
| 1007 |
+
"loss": 1.799,
|
| 1008 |
+
"mean_token_accuracy": 0.5767477229237556,
|
| 1009 |
+
"step": 1250
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.5131860299358517,
|
| 1013 |
+
"grad_norm": 0.2747114300727844,
|
| 1014 |
+
"learning_rate": 0.00010059374564789932,
|
| 1015 |
+
"loss": 1.4763,
|
| 1016 |
+
"mean_token_accuracy": 0.6238099962472916,
|
| 1017 |
+
"step": 1260
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.5172589349353426,
|
| 1021 |
+
"grad_norm": 0.2458280771970749,
|
| 1022 |
+
"learning_rate": 9.927431298041441e-05,
|
| 1023 |
+
"loss": 1.5262,
|
| 1024 |
+
"mean_token_accuracy": 0.6056429393589496,
|
| 1025 |
+
"step": 1270
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5213318399348336,
|
| 1029 |
+
"grad_norm": 0.2757134437561035,
|
| 1030 |
+
"learning_rate": 9.795500664802385e-05,
|
| 1031 |
+
"loss": 1.621,
|
| 1032 |
+
"mean_token_accuracy": 0.5842474676668644,
|
| 1033 |
+
"step": 1280
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.5254047449343244,
|
| 1037 |
+
"grad_norm": 0.21551673114299774,
|
| 1038 |
+
"learning_rate": 9.663605632920518e-05,
|
| 1039 |
+
"loss": 1.659,
|
| 1040 |
+
"mean_token_accuracy": 0.5935076788067818,
|
| 1041 |
+
"step": 1290
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.5294776499338153,
|
| 1045 |
+
"grad_norm": 0.5034237504005432,
|
| 1046 |
+
"learning_rate": 9.53176916404576e-05,
|
| 1047 |
+
"loss": 1.7666,
|
| 1048 |
+
"mean_token_accuracy": 0.5699214018881321,
|
| 1049 |
+
"step": 1300
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.5335505549333062,
|
| 1053 |
+
"grad_norm": 0.26525890827178955,
|
| 1054 |
+
"learning_rate": 9.400014209632763e-05,
|
| 1055 |
+
"loss": 1.6026,
|
| 1056 |
+
"mean_token_accuracy": 0.5935329027473927,
|
| 1057 |
+
"step": 1310
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.537623459932797,
|
| 1061 |
+
"grad_norm": 0.28077974915504456,
|
| 1062 |
+
"learning_rate": 9.268363706945312e-05,
|
| 1063 |
+
"loss": 1.7769,
|
| 1064 |
+
"mean_token_accuracy": 0.5664741955697536,
|
| 1065 |
+
"step": 1320
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.5416963649322879,
|
| 1069 |
+
"grad_norm": 0.514976978302002,
|
| 1070 |
+
"learning_rate": 9.136840575063147e-05,
|
| 1071 |
+
"loss": 1.5157,
|
| 1072 |
+
"mean_token_accuracy": 0.6034789860248566,
|
| 1073 |
+
"step": 1330
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.5457692699317789,
|
| 1077 |
+
"grad_norm": 0.318249374628067,
|
| 1078 |
+
"learning_rate": 9.005467710891987e-05,
|
| 1079 |
+
"loss": 1.8756,
|
| 1080 |
+
"mean_token_accuracy": 0.5630597174167633,
|
| 1081 |
+
"step": 1340
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5498421749312697,
|
| 1085 |
+
"grad_norm": 0.24940232932567596,
|
| 1086 |
+
"learning_rate": 8.874267985177394e-05,
|
| 1087 |
+
"loss": 1.5708,
|
| 1088 |
+
"mean_token_accuracy": 0.5888857699930667,
|
| 1089 |
+
"step": 1350
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.5539150799307606,
|
| 1093 |
+
"grad_norm": 0.26299914717674255,
|
| 1094 |
+
"learning_rate": 8.743264238523199e-05,
|
| 1095 |
+
"loss": 1.6876,
|
| 1096 |
+
"mean_token_accuracy": 0.5782084472477436,
|
| 1097 |
+
"step": 1360
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.5579879849302515,
|
| 1101 |
+
"grad_norm": 0.2588869333267212,
|
| 1102 |
+
"learning_rate": 8.612479277415174e-05,
|
| 1103 |
+
"loss": 1.6694,
|
| 1104 |
+
"mean_token_accuracy": 0.585976778715849,
|
| 1105 |
+
"step": 1370
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.5620608899297423,
|
| 1109 |
+
"grad_norm": 0.2464841604232788,
|
| 1110 |
+
"learning_rate": 8.481935870250637e-05,
|
| 1111 |
+
"loss": 1.5838,
|
| 1112 |
+
"mean_token_accuracy": 0.605075704306364,
|
| 1113 |
+
"step": 1380
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.5661337949292333,
|
| 1117 |
+
"grad_norm": 0.3231446146965027,
|
| 1118 |
+
"learning_rate": 8.351656743374709e-05,
|
| 1119 |
+
"loss": 1.6321,
|
| 1120 |
+
"mean_token_accuracy": 0.5716924026608468,
|
| 1121 |
+
"step": 1390
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.5702066999287242,
|
| 1125 |
+
"grad_norm": 0.23010632395744324,
|
| 1126 |
+
"learning_rate": 8.22166457712386e-05,
|
| 1127 |
+
"loss": 1.5016,
|
| 1128 |
+
"mean_token_accuracy": 0.6048496462404728,
|
| 1129 |
+
"step": 1400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.5742796049282151,
|
| 1133 |
+
"grad_norm": 0.3723667860031128,
|
| 1134 |
+
"learning_rate": 8.091982001877493e-05,
|
| 1135 |
+
"loss": 1.5412,
|
| 1136 |
+
"mean_token_accuracy": 0.6111127749085427,
|
| 1137 |
+
"step": 1410
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.5783525099277059,
|
| 1141 |
+
"grad_norm": 0.24990710616111755,
|
| 1142 |
+
"learning_rate": 7.962631594118208e-05,
|
| 1143 |
+
"loss": 1.7629,
|
| 1144 |
+
"mean_token_accuracy": 0.5585654892027379,
|
| 1145 |
+
"step": 1420
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.5824254149271968,
|
| 1149 |
+
"grad_norm": 0.3681967556476593,
|
| 1150 |
+
"learning_rate": 7.833635872501462e-05,
|
| 1151 |
+
"loss": 1.6342,
|
| 1152 |
+
"mean_token_accuracy": 0.5907308183610439,
|
| 1153 |
+
"step": 1430
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.5864983199266877,
|
| 1157 |
+
"grad_norm": 0.3382493555545807,
|
| 1158 |
+
"learning_rate": 7.705017293935281e-05,
|
| 1159 |
+
"loss": 1.5803,
|
| 1160 |
+
"mean_token_accuracy": 0.6061145611107349,
|
| 1161 |
+
"step": 1440
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.5905712249261786,
|
| 1165 |
+
"grad_norm": 0.28145501017570496,
|
| 1166 |
+
"learning_rate": 7.576798249670725e-05,
|
| 1167 |
+
"loss": 1.8459,
|
| 1168 |
+
"mean_token_accuracy": 0.5457224696874619,
|
| 1169 |
+
"step": 1450
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.5946441299256695,
|
| 1173 |
+
"grad_norm": 0.3189752697944641,
|
| 1174 |
+
"learning_rate": 7.449001061403809e-05,
|
| 1175 |
+
"loss": 1.5263,
|
| 1176 |
+
"mean_token_accuracy": 0.5937092356383801,
|
| 1177 |
+
"step": 1460
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.5987170349251604,
|
| 1181 |
+
"grad_norm": 0.2588890492916107,
|
| 1182 |
+
"learning_rate": 7.321647977389479e-05,
|
| 1183 |
+
"loss": 1.5965,
|
| 1184 |
+
"mean_token_accuracy": 0.5941358201205731,
|
| 1185 |
+
"step": 1470
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.6027899399246512,
|
| 1189 |
+
"grad_norm": 0.2777283191680908,
|
| 1190 |
+
"learning_rate": 7.194761168568445e-05,
|
| 1191 |
+
"loss": 1.5667,
|
| 1192 |
+
"mean_token_accuracy": 0.6003799811005592,
|
| 1193 |
+
"step": 1480
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6068628449241421,
|
| 1197 |
+
"grad_norm": 0.23376941680908203,
|
| 1198 |
+
"learning_rate": 7.068362724707392e-05,
|
| 1199 |
+
"loss": 1.4813,
|
| 1200 |
+
"mean_token_accuracy": 0.6078310683369637,
|
| 1201 |
+
"step": 1490
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.610935749923633,
|
| 1205 |
+
"grad_norm": 0.2295948565006256,
|
| 1206 |
+
"learning_rate": 6.942474650553408e-05,
|
| 1207 |
+
"loss": 1.6786,
|
| 1208 |
+
"mean_token_accuracy": 0.5886344678699971,
|
| 1209 |
+
"step": 1500
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.615008654923124,
|
| 1213 |
+
"grad_norm": 0.3243666887283325,
|
| 1214 |
+
"learning_rate": 6.817118862003132e-05,
|
| 1215 |
+
"loss": 1.6343,
|
| 1216 |
+
"mean_token_accuracy": 0.5855603873729706,
|
| 1217 |
+
"step": 1510
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.6190815599226148,
|
| 1221 |
+
"grad_norm": 0.7187057733535767,
|
| 1222 |
+
"learning_rate": 6.692317182287432e-05,
|
| 1223 |
+
"loss": 1.8144,
|
| 1224 |
+
"mean_token_accuracy": 0.5671629451215268,
|
| 1225 |
+
"step": 1520
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.6231544649221057,
|
| 1229 |
+
"grad_norm": 0.35659492015838623,
|
| 1230 |
+
"learning_rate": 6.568091338172195e-05,
|
| 1231 |
+
"loss": 1.6117,
|
| 1232 |
+
"mean_token_accuracy": 0.601442601531744,
|
| 1233 |
+
"step": 1530
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.6272273699215966,
|
| 1237 |
+
"grad_norm": 0.3395217955112457,
|
| 1238 |
+
"learning_rate": 6.444462956175876e-05,
|
| 1239 |
+
"loss": 1.6222,
|
| 1240 |
+
"mean_token_accuracy": 0.5970501154661179,
|
| 1241 |
+
"step": 1540
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.6313002749210874,
|
| 1245 |
+
"grad_norm": 0.26399192214012146,
|
| 1246 |
+
"learning_rate": 6.321453558804571e-05,
|
| 1247 |
+
"loss": 1.6048,
|
| 1248 |
+
"mean_token_accuracy": 0.5844796732068062,
|
| 1249 |
+
"step": 1550
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6353731799205784,
|
| 1253 |
+
"grad_norm": 0.2993052899837494,
|
| 1254 |
+
"learning_rate": 6.199084560805121e-05,
|
| 1255 |
+
"loss": 1.7073,
|
| 1256 |
+
"mean_token_accuracy": 0.5789771333336831,
|
| 1257 |
+
"step": 1560
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.6394460849200693,
|
| 1261 |
+
"grad_norm": 0.2676873505115509,
|
| 1262 |
+
"learning_rate": 6.077377265437043e-05,
|
| 1263 |
+
"loss": 1.8152,
|
| 1264 |
+
"mean_token_accuracy": 0.5734024614095687,
|
| 1265 |
+
"step": 1570
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.6435189899195601,
|
| 1269 |
+
"grad_norm": 0.293557733297348,
|
| 1270 |
+
"learning_rate": 5.956352860763809e-05,
|
| 1271 |
+
"loss": 1.7108,
|
| 1272 |
+
"mean_token_accuracy": 0.5808110930025577,
|
| 1273 |
+
"step": 1580
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.647591894919051,
|
| 1277 |
+
"grad_norm": 0.23729322850704193,
|
| 1278 |
+
"learning_rate": 5.83603241596423e-05,
|
| 1279 |
+
"loss": 1.4793,
|
| 1280 |
+
"mean_token_accuracy": 0.6202867470681668,
|
| 1281 |
+
"step": 1590
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.6516647999185419,
|
| 1285 |
+
"grad_norm": 0.30609002709388733,
|
| 1286 |
+
"learning_rate": 5.716436877664517e-05,
|
| 1287 |
+
"loss": 1.752,
|
| 1288 |
+
"mean_token_accuracy": 0.5730870619416237,
|
| 1289 |
+
"step": 1600
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 0.6557377049180327,
|
| 1293 |
+
"grad_norm": 0.30717799067497253,
|
| 1294 |
+
"learning_rate": 5.5975870662916484e-05,
|
| 1295 |
+
"loss": 1.7172,
|
| 1296 |
+
"mean_token_accuracy": 0.5701417997479439,
|
| 1297 |
+
"step": 1610
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.6598106099175237,
|
| 1301 |
+
"grad_norm": 0.44037064909935,
|
| 1302 |
+
"learning_rate": 5.4795036724487735e-05,
|
| 1303 |
+
"loss": 1.5377,
|
| 1304 |
+
"mean_token_accuracy": 0.6102925211191177,
|
| 1305 |
+
"step": 1620
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.6638835149170146,
|
| 1309 |
+
"grad_norm": 0.24488377571105957,
|
| 1310 |
+
"learning_rate": 5.362207253313136e-05,
|
| 1311 |
+
"loss": 1.4547,
|
| 1312 |
+
"mean_token_accuracy": 0.6181615687906742,
|
| 1313 |
+
"step": 1630
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.6679564199165055,
|
| 1317 |
+
"grad_norm": 0.2750435769557953,
|
| 1318 |
+
"learning_rate": 5.245718229057326e-05,
|
| 1319 |
+
"loss": 1.6086,
|
| 1320 |
+
"mean_token_accuracy": 0.5703060247004033,
|
| 1321 |
+
"step": 1640
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.6720293249159963,
|
| 1325 |
+
"grad_norm": 0.2821342647075653,
|
| 1326 |
+
"learning_rate": 5.1300568792942535e-05,
|
| 1327 |
+
"loss": 1.6018,
|
| 1328 |
+
"mean_token_accuracy": 0.5989562854170799,
|
| 1329 |
+
"step": 1650
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.6761022299154872,
|
| 1333 |
+
"grad_norm": 0.22521165013313293,
|
| 1334 |
+
"learning_rate": 5.015243339546731e-05,
|
| 1335 |
+
"loss": 1.7574,
|
| 1336 |
+
"mean_token_accuracy": 0.5801547184586525,
|
| 1337 |
+
"step": 1660
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 0.6801751349149782,
|
| 1341 |
+
"grad_norm": 0.29259297251701355,
|
| 1342 |
+
"learning_rate": 4.90129759774202e-05,
|
| 1343 |
+
"loss": 1.7425,
|
| 1344 |
+
"mean_token_accuracy": 0.5723637498915195,
|
| 1345 |
+
"step": 1670
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 0.684248039914469,
|
| 1349 |
+
"grad_norm": 0.2705146074295044,
|
| 1350 |
+
"learning_rate": 4.7882394907321674e-05,
|
| 1351 |
+
"loss": 1.6121,
|
| 1352 |
+
"mean_token_accuracy": 0.6098110035061837,
|
| 1353 |
+
"step": 1680
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.6883209449139599,
|
| 1357 |
+
"grad_norm": 0.2677505910396576,
|
| 1358 |
+
"learning_rate": 4.676088700840575e-05,
|
| 1359 |
+
"loss": 1.6416,
|
| 1360 |
+
"mean_token_accuracy": 0.5757282719016075,
|
| 1361 |
+
"step": 1690
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.6923938499134508,
|
| 1365 |
+
"grad_norm": 0.2644527554512024,
|
| 1366 |
+
"learning_rate": 4.564864752435509e-05,
|
| 1367 |
+
"loss": 1.6675,
|
| 1368 |
+
"mean_token_accuracy": 0.6154301188886165,
|
| 1369 |
+
"step": 1700
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.6964667549129416,
|
| 1373 |
+
"grad_norm": 0.23048701882362366,
|
| 1374 |
+
"learning_rate": 4.454587008531097e-05,
|
| 1375 |
+
"loss": 1.6641,
|
| 1376 |
+
"mean_token_accuracy": 0.5855869121849537,
|
| 1377 |
+
"step": 1710
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.7005396599124325,
|
| 1381 |
+
"grad_norm": 0.2789078652858734,
|
| 1382 |
+
"learning_rate": 4.345274667416399e-05,
|
| 1383 |
+
"loss": 1.6978,
|
| 1384 |
+
"mean_token_accuracy": 0.5762215368449688,
|
| 1385 |
+
"step": 1720
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.7046125649119235,
|
| 1389 |
+
"grad_norm": 0.271881103515625,
|
| 1390 |
+
"learning_rate": 4.2369467593131926e-05,
|
| 1391 |
+
"loss": 1.681,
|
| 1392 |
+
"mean_token_accuracy": 0.5667479492723941,
|
| 1393 |
+
"step": 1730
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 0.7086854699114143,
|
| 1397 |
+
"grad_norm": 0.24953240156173706,
|
| 1398 |
+
"learning_rate": 4.129622143062985e-05,
|
| 1399 |
+
"loss": 1.5405,
|
| 1400 |
+
"mean_token_accuracy": 0.6005463972687721,
|
| 1401 |
+
"step": 1740
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.7127583749109052,
|
| 1405 |
+
"grad_norm": 0.3925758898258209,
|
| 1406 |
+
"learning_rate": 4.02331950284387e-05,
|
| 1407 |
+
"loss": 1.7217,
|
| 1408 |
+
"mean_token_accuracy": 0.5689709268510341,
|
| 1409 |
+
"step": 1750
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.7168312799103961,
|
| 1413 |
+
"grad_norm": 0.2544846832752228,
|
| 1414 |
+
"learning_rate": 3.918057344917795e-05,
|
| 1415 |
+
"loss": 1.5948,
|
| 1416 |
+
"mean_token_accuracy": 0.5933421194553375,
|
| 1417 |
+
"step": 1760
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.720904184909887,
|
| 1421 |
+
"grad_norm": 0.32760509848594666,
|
| 1422 |
+
"learning_rate": 3.813853994408793e-05,
|
| 1423 |
+
"loss": 1.6678,
|
| 1424 |
+
"mean_token_accuracy": 0.5856216661632061,
|
| 1425 |
+
"step": 1770
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.7249770899093778,
|
| 1429 |
+
"grad_norm": 0.2847062647342682,
|
| 1430 |
+
"learning_rate": 3.7107275921127704e-05,
|
| 1431 |
+
"loss": 1.682,
|
| 1432 |
+
"mean_token_accuracy": 0.5889982558786869,
|
| 1433 |
+
"step": 1780
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.7290499949088688,
|
| 1437 |
+
"grad_norm": 0.22774401307106018,
|
| 1438 |
+
"learning_rate": 3.60869609133936e-05,
|
| 1439 |
+
"loss": 1.7135,
|
| 1440 |
+
"mean_token_accuracy": 0.5773006275296211,
|
| 1441 |
+
"step": 1790
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.7331228999083597,
|
| 1445 |
+
"grad_norm": 0.2606080174446106,
|
| 1446 |
+
"learning_rate": 3.507777254786425e-05,
|
| 1447 |
+
"loss": 1.4999,
|
| 1448 |
+
"mean_token_accuracy": 0.6269011601805687,
|
| 1449 |
+
"step": 1800
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.7371958049078505,
|
| 1453 |
+
"grad_norm": 0.2962757647037506,
|
| 1454 |
+
"learning_rate": 3.407988651447738e-05,
|
| 1455 |
+
"loss": 1.6202,
|
| 1456 |
+
"mean_token_accuracy": 0.5973276488482953,
|
| 1457 |
+
"step": 1810
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.7412687099073414,
|
| 1461 |
+
"grad_norm": 0.29107147455215454,
|
| 1462 |
+
"learning_rate": 3.3093476535544074e-05,
|
| 1463 |
+
"loss": 1.5502,
|
| 1464 |
+
"mean_token_accuracy": 0.6133273020386696,
|
| 1465 |
+
"step": 1820
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.7453416149068323,
|
| 1469 |
+
"grad_norm": 0.20980948209762573,
|
| 1470 |
+
"learning_rate": 3.211871433550513e-05,
|
| 1471 |
+
"loss": 1.6333,
|
| 1472 |
+
"mean_token_accuracy": 0.6155988665297627,
|
| 1473 |
+
"step": 1830
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.7494145199063232,
|
| 1477 |
+
"grad_norm": 0.24882718920707703,
|
| 1478 |
+
"learning_rate": 3.1155769611035825e-05,
|
| 1479 |
+
"loss": 1.4907,
|
| 1480 |
+
"mean_token_accuracy": 0.6201219961047173,
|
| 1481 |
+
"step": 1840
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.7534874249058141,
|
| 1485 |
+
"grad_norm": 0.23715901374816895,
|
| 1486 |
+
"learning_rate": 3.0204810001503124e-05,
|
| 1487 |
+
"loss": 1.8018,
|
| 1488 |
+
"mean_token_accuracy": 0.5756942637264728,
|
| 1489 |
+
"step": 1850
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 0.757560329905305,
|
| 1493 |
+
"grad_norm": 0.35216882824897766,
|
| 1494 |
+
"learning_rate": 2.9266001059781258e-05,
|
| 1495 |
+
"loss": 1.7305,
|
| 1496 |
+
"mean_token_accuracy": 0.5722471877932549,
|
| 1497 |
+
"step": 1860
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.7616332349047958,
|
| 1501 |
+
"grad_norm": 0.2924104332923889,
|
| 1502 |
+
"learning_rate": 2.83395062234308e-05,
|
| 1503 |
+
"loss": 1.6642,
|
| 1504 |
+
"mean_token_accuracy": 0.58627370595932,
|
| 1505 |
+
"step": 1870
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.7657061399042867,
|
| 1509 |
+
"grad_norm": 0.27772393822669983,
|
| 1510 |
+
"learning_rate": 2.742548678624548e-05,
|
| 1511 |
+
"loss": 1.8349,
|
| 1512 |
+
"mean_token_accuracy": 0.5614061944186688,
|
| 1513 |
+
"step": 1880
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.7697790449037776,
|
| 1517 |
+
"grad_norm": 0.31574469804763794,
|
| 1518 |
+
"learning_rate": 2.6524101870172846e-05,
|
| 1519 |
+
"loss": 1.7883,
|
| 1520 |
+
"mean_token_accuracy": 0.561104378849268,
|
| 1521 |
+
"step": 1890
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.7738519499032686,
|
| 1525 |
+
"grad_norm": 0.253779798746109,
|
| 1526 |
+
"learning_rate": 2.5635508397612262e-05,
|
| 1527 |
+
"loss": 1.6654,
|
| 1528 |
+
"mean_token_accuracy": 0.5888113439083099,
|
| 1529 |
+
"step": 1900
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.7779248549027594,
|
| 1533 |
+
"grad_norm": 0.2504970133304596,
|
| 1534 |
+
"learning_rate": 2.4759861064096603e-05,
|
| 1535 |
+
"loss": 1.6478,
|
| 1536 |
+
"mean_token_accuracy": 0.5726306334137916,
|
| 1537 |
+
"step": 1910
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 0.7819977599022503,
|
| 1541 |
+
"grad_norm": 0.23571030795574188,
|
| 1542 |
+
"learning_rate": 2.3897312311360955e-05,
|
| 1543 |
+
"loss": 1.5355,
|
| 1544 |
+
"mean_token_accuracy": 0.6026113323867321,
|
| 1545 |
+
"step": 1920
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.7860706649017412,
|
| 1549 |
+
"grad_norm": 0.2395690232515335,
|
| 1550 |
+
"learning_rate": 2.3048012300804222e-05,
|
| 1551 |
+
"loss": 1.5565,
|
| 1552 |
+
"mean_token_accuracy": 0.5976604223251343,
|
| 1553 |
+
"step": 1930
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 0.790143569901232,
|
| 1557 |
+
"grad_norm": 0.5269713997840881,
|
| 1558 |
+
"learning_rate": 2.221210888734736e-05,
|
| 1559 |
+
"loss": 1.636,
|
| 1560 |
+
"mean_token_accuracy": 0.5818449839949608,
|
| 1561 |
+
"step": 1940
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.7942164749007229,
|
| 1565 |
+
"grad_norm": 0.4233987033367157,
|
| 1566 |
+
"learning_rate": 2.13897475936933e-05,
|
| 1567 |
+
"loss": 1.7844,
|
| 1568 |
+
"mean_token_accuracy": 0.5720866233110428,
|
| 1569 |
+
"step": 1950
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.7982893799002139,
|
| 1573 |
+
"grad_norm": 0.2641923427581787,
|
| 1574 |
+
"learning_rate": 2.0581071584992818e-05,
|
| 1575 |
+
"loss": 1.5874,
|
| 1576 |
+
"mean_token_accuracy": 0.5966846913099288,
|
| 1577 |
+
"step": 1960
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.8023622848997047,
|
| 1581 |
+
"grad_norm": 0.27280351519584656,
|
| 1582 |
+
"learning_rate": 1.9786221643920844e-05,
|
| 1583 |
+
"loss": 1.6279,
|
| 1584 |
+
"mean_token_accuracy": 0.5751761384308338,
|
| 1585 |
+
"step": 1970
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.8064351898991956,
|
| 1589 |
+
"grad_norm": 0.3823714256286621,
|
| 1590 |
+
"learning_rate": 1.9005336146167686e-05,
|
| 1591 |
+
"loss": 1.6269,
|
| 1592 |
+
"mean_token_accuracy": 0.5963201723992825,
|
| 1593 |
+
"step": 1980
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.8105080948986865,
|
| 1597 |
+
"grad_norm": 0.25173816084861755,
|
| 1598 |
+
"learning_rate": 1.8238551036349028e-05,
|
| 1599 |
+
"loss": 1.5308,
|
| 1600 |
+
"mean_token_accuracy": 0.6112879984080791,
|
| 1601 |
+
"step": 1990
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 0.8145809998981773,
|
| 1605 |
+
"grad_norm": 0.21256780624389648,
|
| 1606 |
+
"learning_rate": 1.7485999804339348e-05,
|
| 1607 |
+
"loss": 1.5568,
|
| 1608 |
+
"mean_token_accuracy": 0.5963364981114865,
|
| 1609 |
+
"step": 2000
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 0.8186539048976683,
|
| 1613 |
+
"grad_norm": 0.2510949969291687,
|
| 1614 |
+
"learning_rate": 1.6747813462032615e-05,
|
| 1615 |
+
"loss": 1.6787,
|
| 1616 |
+
"mean_token_accuracy": 0.58960345312953,
|
| 1617 |
+
"step": 2010
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.8227268098971592,
|
| 1621 |
+
"grad_norm": 0.255790650844574,
|
| 1622 |
+
"learning_rate": 1.6024120520534326e-05,
|
| 1623 |
+
"loss": 1.6416,
|
| 1624 |
+
"mean_token_accuracy": 0.5875880800187587,
|
| 1625 |
+
"step": 2020
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 0.82679971489665,
|
| 1629 |
+
"grad_norm": 0.307492196559906,
|
| 1630 |
+
"learning_rate": 1.5315046967789082e-05,
|
| 1631 |
+
"loss": 1.69,
|
| 1632 |
+
"mean_token_accuracy": 0.5625761769711971,
|
| 1633 |
+
"step": 2030
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.8308726198961409,
|
| 1637 |
+
"grad_norm": 0.2648999094963074,
|
| 1638 |
+
"learning_rate": 1.4620716246647203e-05,
|
| 1639 |
+
"loss": 1.6092,
|
| 1640 |
+
"mean_token_accuracy": 0.6106476083397865,
|
| 1641 |
+
"step": 2040
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.8349455248956318,
|
| 1645 |
+
"grad_norm": 0.2488166093826294,
|
| 1646 |
+
"learning_rate": 1.394124923337462e-05,
|
| 1647 |
+
"loss": 1.6848,
|
| 1648 |
+
"mean_token_accuracy": 0.5697021905332804,
|
| 1649 |
+
"step": 2050
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 0.8390184298951227,
|
| 1653 |
+
"grad_norm": 0.2427694946527481,
|
| 1654 |
+
"learning_rate": 1.3276764216609294e-05,
|
| 1655 |
+
"loss": 1.5843,
|
| 1656 |
+
"mean_token_accuracy": 0.6084981314837933,
|
| 1657 |
+
"step": 2060
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.8430913348946136,
|
| 1661 |
+
"grad_norm": 0.2833966910839081,
|
| 1662 |
+
"learning_rate": 1.2627376876768593e-05,
|
| 1663 |
+
"loss": 1.5443,
|
| 1664 |
+
"mean_token_accuracy": 0.6015144042670727,
|
| 1665 |
+
"step": 2070
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.8471642398941045,
|
| 1669 |
+
"grad_norm": 0.4057978689670563,
|
| 1670 |
+
"learning_rate": 1.1993200265910131e-05,
|
| 1671 |
+
"loss": 1.6073,
|
| 1672 |
+
"mean_token_accuracy": 0.5917512811720371,
|
| 1673 |
+
"step": 2080
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.8512371448935954,
|
| 1677 |
+
"grad_norm": 0.25613030791282654,
|
| 1678 |
+
"learning_rate": 1.1374344788050829e-05,
|
| 1679 |
+
"loss": 1.8038,
|
| 1680 |
+
"mean_token_accuracy": 0.5568435616791249,
|
| 1681 |
+
"step": 2090
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.8553100498930862,
|
| 1685 |
+
"grad_norm": 0.30181950330734253,
|
| 1686 |
+
"learning_rate": 1.0770918179946388e-05,
|
| 1687 |
+
"loss": 1.5022,
|
| 1688 |
+
"mean_token_accuracy": 0.6081097513437271,
|
| 1689 |
+
"step": 2100
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.8593829548925771,
|
| 1693 |
+
"grad_norm": 0.23373402655124664,
|
| 1694 |
+
"learning_rate": 1.0183025492335408e-05,
|
| 1695 |
+
"loss": 1.7432,
|
| 1696 |
+
"mean_token_accuracy": 0.5653887689113617,
|
| 1697 |
+
"step": 2110
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.863455859892068,
|
| 1701 |
+
"grad_norm": 0.2826649248600006,
|
| 1702 |
+
"learning_rate": 9.610769071651193e-06,
|
| 1703 |
+
"loss": 1.6706,
|
| 1704 |
+
"mean_token_accuracy": 0.5875243842601776,
|
| 1705 |
+
"step": 2120
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.867528764891559,
|
| 1709 |
+
"grad_norm": 0.3047688603401184,
|
| 1710 |
+
"learning_rate": 9.05424854220408e-06,
|
| 1711 |
+
"loss": 1.5901,
|
| 1712 |
+
"mean_token_accuracy": 0.6013362683355808,
|
| 1713 |
+
"step": 2130
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.8716016698910498,
|
| 1717 |
+
"grad_norm": 0.3211512863636017,
|
| 1718 |
+
"learning_rate": 8.513560788837916e-06,
|
| 1719 |
+
"loss": 1.6414,
|
| 1720 |
+
"mean_token_accuracy": 0.5845984369516373,
|
| 1721 |
+
"step": 2140
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.8756745748905407,
|
| 1725 |
+
"grad_norm": 0.22475050389766693,
|
| 1726 |
+
"learning_rate": 7.988799940063297e-06,
|
| 1727 |
+
"loss": 1.6038,
|
| 1728 |
+
"mean_token_accuracy": 0.5835995152592659,
|
| 1729 |
+
"step": 2150
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.8797474798900315,
|
| 1733 |
+
"grad_norm": 0.2239948809146881,
|
| 1734 |
+
"learning_rate": 7.480057351670688e-06,
|
| 1735 |
+
"loss": 1.6661,
|
| 1736 |
+
"mean_token_accuracy": 0.5898953646421432,
|
| 1737 |
+
"step": 2160
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.8838203848895224,
|
| 1741 |
+
"grad_norm": 0.3669275641441345,
|
| 1742 |
+
"learning_rate": 6.987421590826282e-06,
|
| 1743 |
+
"loss": 1.6066,
|
| 1744 |
+
"mean_token_accuracy": 0.5877827815711498,
|
| 1745 |
+
"step": 2170
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.8878932898890134,
|
| 1749 |
+
"grad_norm": 0.30003634095191956,
|
| 1750 |
+
"learning_rate": 6.510978420653335e-06,
|
| 1751 |
+
"loss": 1.6816,
|
| 1752 |
+
"mean_token_accuracy": 0.5926426865160466,
|
| 1753 |
+
"step": 2180
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.8919661948885043,
|
| 1757 |
+
"grad_norm": 0.2707299590110779,
|
| 1758 |
+
"learning_rate": 6.050810785301597e-06,
|
| 1759 |
+
"loss": 1.7702,
|
| 1760 |
+
"mean_token_accuracy": 0.561020129173994,
|
| 1761 |
+
"step": 2190
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.8960390998879951,
|
| 1765 |
+
"grad_norm": 0.3029952347278595,
|
| 1766 |
+
"learning_rate": 5.606998795507578e-06,
|
| 1767 |
+
"loss": 1.5417,
|
| 1768 |
+
"mean_token_accuracy": 0.598423033952713,
|
| 1769 |
+
"step": 2200
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 0.900112004887486,
|
| 1773 |
+
"grad_norm": 0.27840766310691833,
|
| 1774 |
+
"learning_rate": 5.1796197146479985e-06,
|
| 1775 |
+
"loss": 1.5119,
|
| 1776 |
+
"mean_token_accuracy": 0.6152562454342843,
|
| 1777 |
+
"step": 2210
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 0.9041849098869769,
|
| 1781 |
+
"grad_norm": 0.28235796093940735,
|
| 1782 |
+
"learning_rate": 4.768747945288987e-06,
|
| 1783 |
+
"loss": 1.5287,
|
| 1784 |
+
"mean_token_accuracy": 0.61318289488554,
|
| 1785 |
+
"step": 2220
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.9082578148864677,
|
| 1789 |
+
"grad_norm": 0.21450947225093842,
|
| 1790 |
+
"learning_rate": 4.37445501623337e-06,
|
| 1791 |
+
"loss": 1.5842,
|
| 1792 |
+
"mean_token_accuracy": 0.6025399126112461,
|
| 1793 |
+
"step": 2230
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 0.9123307198859587,
|
| 1797 |
+
"grad_norm": 0.29954469203948975,
|
| 1798 |
+
"learning_rate": 3.996809570068127e-06,
|
| 1799 |
+
"loss": 1.5514,
|
| 1800 |
+
"mean_token_accuracy": 0.6040661752223968,
|
| 1801 |
+
"step": 2240
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.9164036248854496,
|
| 1805 |
+
"grad_norm": 0.34261876344680786,
|
| 1806 |
+
"learning_rate": 3.635877351214445e-06,
|
| 1807 |
+
"loss": 1.5493,
|
| 1808 |
+
"mean_token_accuracy": 0.5996488876640796,
|
| 1809 |
+
"step": 2250
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.9204765298849404,
|
| 1813 |
+
"grad_norm": 0.24511079490184784,
|
| 1814 |
+
"learning_rate": 3.291721194482189e-06,
|
| 1815 |
+
"loss": 1.5494,
|
| 1816 |
+
"mean_token_accuracy": 0.6054005287587643,
|
| 1817 |
+
"step": 2260
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 0.9245494348844313,
|
| 1821 |
+
"grad_norm": 0.21510252356529236,
|
| 1822 |
+
"learning_rate": 2.9644010141310017e-06,
|
| 1823 |
+
"loss": 1.6294,
|
| 1824 |
+
"mean_token_accuracy": 0.5961603626608849,
|
| 1825 |
+
"step": 2270
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 0.9286223398839222,
|
| 1829 |
+
"grad_norm": 0.23636655509471893,
|
| 1830 |
+
"learning_rate": 2.65397379343979e-06,
|
| 1831 |
+
"loss": 1.7332,
|
| 1832 |
+
"mean_token_accuracy": 0.5859133303165436,
|
| 1833 |
+
"step": 2280
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.932695244883413,
|
| 1837 |
+
"grad_norm": 0.25582408905029297,
|
| 1838 |
+
"learning_rate": 2.3604935747865377e-06,
|
| 1839 |
+
"loss": 1.6691,
|
| 1840 |
+
"mean_token_accuracy": 0.5889919593930244,
|
| 1841 |
+
"step": 2290
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 0.936768149882904,
|
| 1845 |
+
"grad_norm": 0.3853449523448944,
|
| 1846 |
+
"learning_rate": 2.0840114502400086e-06,
|
| 1847 |
+
"loss": 1.5358,
|
| 1848 |
+
"mean_token_accuracy": 0.5844359740614891,
|
| 1849 |
+
"step": 2300
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.9408410548823949,
|
| 1853 |
+
"grad_norm": 0.2177136093378067,
|
| 1854 |
+
"learning_rate": 1.8245755526650753e-06,
|
| 1855 |
+
"loss": 1.6318,
|
| 1856 |
+
"mean_token_accuracy": 0.5915890723466873,
|
| 1857 |
+
"step": 2310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.9449139598818858,
|
| 1861 |
+
"grad_norm": 0.23138591647148132,
|
| 1862 |
+
"learning_rate": 1.5822310473433411e-06,
|
| 1863 |
+
"loss": 1.5595,
|
| 1864 |
+
"mean_token_accuracy": 0.5974130786955356,
|
| 1865 |
+
"step": 2320
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.9489868648813766,
|
| 1869 |
+
"grad_norm": 0.2235519289970398,
|
| 1870 |
+
"learning_rate": 1.357020124110231e-06,
|
| 1871 |
+
"loss": 1.7522,
|
| 1872 |
+
"mean_token_accuracy": 0.5713608346879482,
|
| 1873 |
+
"step": 2330
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 0.9530597698808675,
|
| 1877 |
+
"grad_norm": 0.37900933623313904,
|
| 1878 |
+
"learning_rate": 1.1489819900101784e-06,
|
| 1879 |
+
"loss": 1.5307,
|
| 1880 |
+
"mean_token_accuracy": 0.6045880667865277,
|
| 1881 |
+
"step": 2340
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 0.9571326748803585,
|
| 1885 |
+
"grad_norm": 0.2911360561847687,
|
| 1886 |
+
"learning_rate": 9.581528624710734e-07,
|
| 1887 |
+
"loss": 1.5633,
|
| 1888 |
+
"mean_token_accuracy": 0.5826431967318058,
|
| 1889 |
+
"step": 2350
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.9612055798798493,
|
| 1893 |
+
"grad_norm": 0.25369352102279663,
|
| 1894 |
+
"learning_rate": 7.845659629990842e-07,
|
| 1895 |
+
"loss": 1.6927,
|
| 1896 |
+
"mean_token_accuracy": 0.5901580177247524,
|
| 1897 |
+
"step": 2360
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 0.9652784848793402,
|
| 1901 |
+
"grad_norm": 0.32107028365135193,
|
| 1902 |
+
"learning_rate": 6.282515113952281e-07,
|
| 1903 |
+
"loss": 1.815,
|
| 1904 |
+
"mean_token_accuracy": 0.56534923017025,
|
| 1905 |
+
"step": 2370
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.9693513898788311,
|
| 1909 |
+
"grad_norm": 0.3105465769767761,
|
| 1910 |
+
"learning_rate": 4.892367204943016e-07,
|
| 1911 |
+
"loss": 1.5694,
|
| 1912 |
+
"mean_token_accuracy": 0.5809950686991214,
|
| 1913 |
+
"step": 2380
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.9734242948783219,
|
| 1917 |
+
"grad_norm": 0.2689298689365387,
|
| 1918 |
+
"learning_rate": 3.6754579142741495e-07,
|
| 1919 |
+
"loss": 1.6555,
|
| 1920 |
+
"mean_token_accuracy": 0.591179046779871,
|
| 1921 |
+
"step": 2390
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.9774971998778128,
|
| 1925 |
+
"grad_norm": 0.44850870966911316,
|
| 1926 |
+
"learning_rate": 2.6319990940885107e-07,
|
| 1927 |
+
"loss": 1.7315,
|
| 1928 |
+
"mean_token_accuracy": 0.5772897489368916,
|
| 1929 |
+
"step": 2400
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.9815701048773038,
|
| 1933 |
+
"grad_norm": 0.25496381521224976,
|
| 1934 |
+
"learning_rate": 1.762172400478601e-07,
|
| 1935 |
+
"loss": 1.5847,
|
| 1936 |
+
"mean_token_accuracy": 0.5798953503370285,
|
| 1937 |
+
"step": 2410
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 0.9856430098767947,
|
| 1941 |
+
"grad_norm": 0.2383822500705719,
|
| 1942 |
+
"learning_rate": 1.0661292618624474e-07,
|
| 1943 |
+
"loss": 1.54,
|
| 1944 |
+
"mean_token_accuracy": 0.6138455606997013,
|
| 1945 |
+
"step": 2420
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.9897159148762855,
|
| 1949 |
+
"grad_norm": 0.2854715585708618,
|
| 1950 |
+
"learning_rate": 5.439908526212456e-08,
|
| 1951 |
+
"loss": 1.4109,
|
| 1952 |
+
"mean_token_accuracy": 0.6151122771203518,
|
| 1953 |
+
"step": 2430
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 0.9937888198757764,
|
| 1957 |
+
"grad_norm": 0.297370046377182,
|
| 1958 |
+
"learning_rate": 1.9584807200423438e-08,
|
| 1959 |
+
"loss": 1.5128,
|
| 1960 |
+
"mean_token_accuracy": 0.6013165354728699,
|
| 1961 |
+
"step": 2440
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.9978617248752673,
|
| 1965 |
+
"grad_norm": 0.2563394010066986,
|
| 1966 |
+
"learning_rate": 2.176152830357658e-09,
|
| 1967 |
+
"loss": 1.6287,
|
| 1968 |
+
"mean_token_accuracy": 0.5945099242031574,
|
| 1969 |
+
"step": 2450
|
| 1970 |
+
}
|
| 1971 |
+
],
|
| 1972 |
+
"logging_steps": 10,
|
| 1973 |
+
"max_steps": 2455,
|
| 1974 |
+
"num_input_tokens_seen": 0,
|
| 1975 |
+
"num_train_epochs": 1,
|
| 1976 |
+
"save_steps": 100,
|
| 1977 |
+
"stateful_callbacks": {
|
| 1978 |
+
"TrainerControl": {
|
| 1979 |
+
"args": {
|
| 1980 |
+
"should_epoch_stop": false,
|
| 1981 |
+
"should_evaluate": false,
|
| 1982 |
+
"should_log": false,
|
| 1983 |
+
"should_save": true,
|
| 1984 |
+
"should_training_stop": true
|
| 1985 |
+
},
|
| 1986 |
+
"attributes": {}
|
| 1987 |
+
}
|
| 1988 |
+
},
|
| 1989 |
+
"total_flos": 1.283473658609664e+18,
|
| 1990 |
+
"train_batch_size": 4,
|
| 1991 |
+
"trial_name": null,
|
| 1992 |
+
"trial_params": null
|
| 1993 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:233dc34c1c2e16959d732eacbcbe4b0891d07771508d857bd458fe07662db28c
|
| 3 |
+
size 5624
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|