Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- trainer_state.json +1468 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: lmsys/vicuna-7b-v1.5
|
| 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 0.11.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e2e6a2789e9910bc7306ec936cf6ea5f97e098f344624da3420e3f6fbcd18ab
|
| 3 |
+
size 16794200
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3696c497953fa36401c0bff4bd0fe020bf4cf61c17017d6cd628465b6978c059
|
| 3 |
+
size 33630266
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fe354f5312bbd2c7dc8639aa5ff5fa20bc413c5d4ea3bcf01260704c51bb809
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b039f92d290406fa39c48a5063b170148ec8923f915f3b1a16f012662252f4c
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 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.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 4096,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"padding_side": "right",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1468 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2050,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04878048780487805,
|
| 13 |
+
"grad_norm": 0.4036892056465149,
|
| 14 |
+
"learning_rate": 0.00019999478113897612,
|
| 15 |
+
"loss": 1.0282,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0975609756097561,
|
| 20 |
+
"grad_norm": 0.3629762828350067,
|
| 21 |
+
"learning_rate": 0.0001999791251006346,
|
| 22 |
+
"loss": 0.7875,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.14634146341463414,
|
| 27 |
+
"grad_norm": 0.4877622425556183,
|
| 28 |
+
"learning_rate": 0.0001999530335191093,
|
| 29 |
+
"loss": 0.5942,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1951219512195122,
|
| 34 |
+
"grad_norm": 0.4466260075569153,
|
| 35 |
+
"learning_rate": 0.00019991650911776695,
|
| 36 |
+
"loss": 0.3866,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.24390243902439024,
|
| 41 |
+
"grad_norm": 0.649118959903717,
|
| 42 |
+
"learning_rate": 0.000199869555708923,
|
| 43 |
+
"loss": 0.3928,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2926829268292683,
|
| 48 |
+
"grad_norm": 0.8762800097465515,
|
| 49 |
+
"learning_rate": 0.0001998121781934438,
|
| 50 |
+
"loss": 0.3258,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.34146341463414637,
|
| 55 |
+
"grad_norm": 0.9195622801780701,
|
| 56 |
+
"learning_rate": 0.0001997443825602349,
|
| 57 |
+
"loss": 0.2885,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3902439024390244,
|
| 62 |
+
"grad_norm": 0.5856262445449829,
|
| 63 |
+
"learning_rate": 0.00019966617588561609,
|
| 64 |
+
"loss": 0.2888,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.43902439024390244,
|
| 69 |
+
"grad_norm": 0.5520443320274353,
|
| 70 |
+
"learning_rate": 0.00019957756633258265,
|
| 71 |
+
"loss": 0.2242,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4878048780487805,
|
| 76 |
+
"grad_norm": 0.9435800909996033,
|
| 77 |
+
"learning_rate": 0.00019947856314995349,
|
| 78 |
+
"loss": 0.1629,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5365853658536586,
|
| 83 |
+
"grad_norm": 0.9416623115539551,
|
| 84 |
+
"learning_rate": 0.00019936917667140555,
|
| 85 |
+
"loss": 0.1555,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5853658536585366,
|
| 90 |
+
"grad_norm": 0.802065372467041,
|
| 91 |
+
"learning_rate": 0.0001992494183143955,
|
| 92 |
+
"loss": 0.1339,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6341463414634146,
|
| 97 |
+
"grad_norm": 0.7007794380187988,
|
| 98 |
+
"learning_rate": 0.00019911930057896774,
|
| 99 |
+
"loss": 0.1191,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6829268292682927,
|
| 104 |
+
"grad_norm": 0.6755990386009216,
|
| 105 |
+
"learning_rate": 0.00019897883704644983,
|
| 106 |
+
"loss": 0.1571,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7317073170731707,
|
| 111 |
+
"grad_norm": 1.6951078176498413,
|
| 112 |
+
"learning_rate": 0.00019882804237803488,
|
| 113 |
+
"loss": 0.1309,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7804878048780488,
|
| 118 |
+
"grad_norm": 0.567158579826355,
|
| 119 |
+
"learning_rate": 0.0001986669323132512,
|
| 120 |
+
"loss": 0.0766,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8292682926829268,
|
| 125 |
+
"grad_norm": 0.8820038437843323,
|
| 126 |
+
"learning_rate": 0.0001984955236683196,
|
| 127 |
+
"loss": 0.0839,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8780487804878049,
|
| 132 |
+
"grad_norm": 0.6520794034004211,
|
| 133 |
+
"learning_rate": 0.00019831383433439797,
|
| 134 |
+
"loss": 0.0863,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.926829268292683,
|
| 139 |
+
"grad_norm": 0.45519864559173584,
|
| 140 |
+
"learning_rate": 0.00019812188327571399,
|
| 141 |
+
"loss": 0.0889,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.975609756097561,
|
| 146 |
+
"grad_norm": 0.614235520362854,
|
| 147 |
+
"learning_rate": 0.00019791969052758562,
|
| 148 |
+
"loss": 0.0725,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.024390243902439,
|
| 153 |
+
"grad_norm": 0.2764686644077301,
|
| 154 |
+
"learning_rate": 0.00019770727719432994,
|
| 155 |
+
"loss": 0.0407,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.0731707317073171,
|
| 160 |
+
"grad_norm": 0.6082726716995239,
|
| 161 |
+
"learning_rate": 0.00019748466544706022,
|
| 162 |
+
"loss": 0.044,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.1219512195121952,
|
| 167 |
+
"grad_norm": 0.9295619130134583,
|
| 168 |
+
"learning_rate": 0.00019725187852137195,
|
| 169 |
+
"loss": 0.0675,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.170731707317073,
|
| 174 |
+
"grad_norm": 0.3758924603462219,
|
| 175 |
+
"learning_rate": 0.00019700894071491732,
|
| 176 |
+
"loss": 0.0439,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.2195121951219512,
|
| 181 |
+
"grad_norm": 0.46514585614204407,
|
| 182 |
+
"learning_rate": 0.00019675587738486936,
|
| 183 |
+
"loss": 0.0398,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.2682926829268293,
|
| 188 |
+
"grad_norm": 0.5870018005371094,
|
| 189 |
+
"learning_rate": 0.0001964927149452751,
|
| 190 |
+
"loss": 0.0406,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.3170731707317074,
|
| 195 |
+
"grad_norm": 0.30292996764183044,
|
| 196 |
+
"learning_rate": 0.00019621948086429844,
|
| 197 |
+
"loss": 0.028,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.3658536585365852,
|
| 202 |
+
"grad_norm": 0.47037121653556824,
|
| 203 |
+
"learning_rate": 0.00019593620366135337,
|
| 204 |
+
"loss": 0.0239,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.4146341463414633,
|
| 209 |
+
"grad_norm": 0.4176475405693054,
|
| 210 |
+
"learning_rate": 0.00019564291290412688,
|
| 211 |
+
"loss": 0.0281,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.4634146341463414,
|
| 216 |
+
"grad_norm": 0.3179157078266144,
|
| 217 |
+
"learning_rate": 0.00019533963920549306,
|
| 218 |
+
"loss": 0.0281,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.5121951219512195,
|
| 223 |
+
"grad_norm": 0.5817562937736511,
|
| 224 |
+
"learning_rate": 0.00019502641422031763,
|
| 225 |
+
"loss": 0.0296,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.5609756097560976,
|
| 230 |
+
"grad_norm": 0.7409655451774597,
|
| 231 |
+
"learning_rate": 0.00019470327064215383,
|
| 232 |
+
"loss": 0.029,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.6097560975609757,
|
| 237 |
+
"grad_norm": 0.4418310225009918,
|
| 238 |
+
"learning_rate": 0.00019437024219983028,
|
| 239 |
+
"loss": 0.0583,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.6585365853658538,
|
| 244 |
+
"grad_norm": 0.31637728214263916,
|
| 245 |
+
"learning_rate": 0.0001940273636539301,
|
| 246 |
+
"loss": 0.0354,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.7073170731707317,
|
| 251 |
+
"grad_norm": 0.22175493836402893,
|
| 252 |
+
"learning_rate": 0.00019367467079316279,
|
| 253 |
+
"loss": 0.0514,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.7560975609756098,
|
| 258 |
+
"grad_norm": 0.6636152267456055,
|
| 259 |
+
"learning_rate": 0.00019331220043062894,
|
| 260 |
+
"loss": 0.034,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.8048780487804879,
|
| 265 |
+
"grad_norm": 0.8424332141876221,
|
| 266 |
+
"learning_rate": 0.00019293999039997746,
|
| 267 |
+
"loss": 0.0299,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.8536585365853657,
|
| 272 |
+
"grad_norm": 0.6435155272483826,
|
| 273 |
+
"learning_rate": 0.00019255807955145677,
|
| 274 |
+
"loss": 0.0508,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.9024390243902438,
|
| 279 |
+
"grad_norm": 0.7734220027923584,
|
| 280 |
+
"learning_rate": 0.00019216650774785972,
|
| 281 |
+
"loss": 0.035,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.951219512195122,
|
| 286 |
+
"grad_norm": 0.2854250967502594,
|
| 287 |
+
"learning_rate": 0.0001917653158603628,
|
| 288 |
+
"loss": 0.0339,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.0,
|
| 293 |
+
"grad_norm": 0.6165639758110046,
|
| 294 |
+
"learning_rate": 0.0001913545457642601,
|
| 295 |
+
"loss": 0.0323,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.048780487804878,
|
| 300 |
+
"grad_norm": 0.2167205959558487,
|
| 301 |
+
"learning_rate": 0.00019093424033459248,
|
| 302 |
+
"loss": 0.026,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.097560975609756,
|
| 307 |
+
"grad_norm": 0.2723434269428253,
|
| 308 |
+
"learning_rate": 0.0001905044434416725,
|
| 309 |
+
"loss": 0.0176,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.1463414634146343,
|
| 314 |
+
"grad_norm": 0.4085879325866699,
|
| 315 |
+
"learning_rate": 0.00019006519994650513,
|
| 316 |
+
"loss": 0.0138,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.1951219512195124,
|
| 321 |
+
"grad_norm": 0.17931397259235382,
|
| 322 |
+
"learning_rate": 0.00018961655569610557,
|
| 323 |
+
"loss": 0.0358,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.2439024390243905,
|
| 328 |
+
"grad_norm": 0.3886450231075287,
|
| 329 |
+
"learning_rate": 0.00018915855751871363,
|
| 330 |
+
"loss": 0.0209,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.292682926829268,
|
| 335 |
+
"grad_norm": 0.11022531986236572,
|
| 336 |
+
"learning_rate": 0.0001886912532189061,
|
| 337 |
+
"loss": 0.0101,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.341463414634146,
|
| 342 |
+
"grad_norm": 0.14626094698905945,
|
| 343 |
+
"learning_rate": 0.00018821469157260685,
|
| 344 |
+
"loss": 0.0156,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.3902439024390243,
|
| 349 |
+
"grad_norm": 0.18015721440315247,
|
| 350 |
+
"learning_rate": 0.00018772892232199592,
|
| 351 |
+
"loss": 0.0156,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.4390243902439024,
|
| 356 |
+
"grad_norm": 0.3262254595756531,
|
| 357 |
+
"learning_rate": 0.00018723399617031751,
|
| 358 |
+
"loss": 0.0295,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.4878048780487805,
|
| 363 |
+
"grad_norm": 0.10063759982585907,
|
| 364 |
+
"learning_rate": 0.00018672996477658767,
|
| 365 |
+
"loss": 0.0164,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.5365853658536586,
|
| 370 |
+
"grad_norm": 0.11382050812244415,
|
| 371 |
+
"learning_rate": 0.00018621688075020227,
|
| 372 |
+
"loss": 0.0207,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.5853658536585367,
|
| 377 |
+
"grad_norm": 0.12307539582252502,
|
| 378 |
+
"learning_rate": 0.0001856947976454459,
|
| 379 |
+
"loss": 0.0326,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.6341463414634148,
|
| 384 |
+
"grad_norm": 0.18902955949306488,
|
| 385 |
+
"learning_rate": 0.00018516376995590187,
|
| 386 |
+
"loss": 0.0144,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.682926829268293,
|
| 391 |
+
"grad_norm": 0.18087974190711975,
|
| 392 |
+
"learning_rate": 0.00018462385310876443,
|
| 393 |
+
"loss": 0.0111,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.7317073170731705,
|
| 398 |
+
"grad_norm": 0.2894444465637207,
|
| 399 |
+
"learning_rate": 0.00018407510345905332,
|
| 400 |
+
"loss": 0.0081,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.7804878048780486,
|
| 405 |
+
"grad_norm": 0.24273361265659332,
|
| 406 |
+
"learning_rate": 0.0001835175782837318,
|
| 407 |
+
"loss": 0.0301,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.8292682926829267,
|
| 412 |
+
"grad_norm": 0.069428451359272,
|
| 413 |
+
"learning_rate": 0.00018295133577572799,
|
| 414 |
+
"loss": 0.0234,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.8780487804878048,
|
| 419 |
+
"grad_norm": 0.1845165342092514,
|
| 420 |
+
"learning_rate": 0.00018237643503786095,
|
| 421 |
+
"loss": 0.0112,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.926829268292683,
|
| 426 |
+
"grad_norm": 0.06373828649520874,
|
| 427 |
+
"learning_rate": 0.00018179293607667178,
|
| 428 |
+
"loss": 0.0241,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.975609756097561,
|
| 433 |
+
"grad_norm": 0.09466666728258133,
|
| 434 |
+
"learning_rate": 0.0001812008997961602,
|
| 435 |
+
"loss": 0.0151,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 3.024390243902439,
|
| 440 |
+
"grad_norm": 0.5068451762199402,
|
| 441 |
+
"learning_rate": 0.00018060038799142759,
|
| 442 |
+
"loss": 0.02,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.073170731707317,
|
| 447 |
+
"grad_norm": 0.17547158896923065,
|
| 448 |
+
"learning_rate": 0.00017999146334222695,
|
| 449 |
+
"loss": 0.0111,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.1219512195121952,
|
| 454 |
+
"grad_norm": 0.24108292162418365,
|
| 455 |
+
"learning_rate": 0.00017937418940642074,
|
| 456 |
+
"loss": 0.0095,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 3.1707317073170733,
|
| 461 |
+
"grad_norm": 0.24457822740077972,
|
| 462 |
+
"learning_rate": 0.00017874863061334657,
|
| 463 |
+
"loss": 0.0134,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.2195121951219514,
|
| 468 |
+
"grad_norm": 0.2185467779636383,
|
| 469 |
+
"learning_rate": 0.00017811485225709256,
|
| 470 |
+
"loss": 0.0135,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.2682926829268295,
|
| 475 |
+
"grad_norm": 0.12849357724189758,
|
| 476 |
+
"learning_rate": 0.00017747292048968187,
|
| 477 |
+
"loss": 0.0154,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 3.317073170731707,
|
| 482 |
+
"grad_norm": 0.09158976376056671,
|
| 483 |
+
"learning_rate": 0.0001768229023141682,
|
| 484 |
+
"loss": 0.0137,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.3658536585365852,
|
| 489 |
+
"grad_norm": 0.09520118683576584,
|
| 490 |
+
"learning_rate": 0.00017616486557764187,
|
| 491 |
+
"loss": 0.0147,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 3.4146341463414633,
|
| 496 |
+
"grad_norm": 0.11151307821273804,
|
| 497 |
+
"learning_rate": 0.00017549887896414851,
|
| 498 |
+
"loss": 0.0168,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 3.4634146341463414,
|
| 503 |
+
"grad_norm": 0.1175757572054863,
|
| 504 |
+
"learning_rate": 0.00017482501198751965,
|
| 505 |
+
"loss": 0.015,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.5121951219512195,
|
| 510 |
+
"grad_norm": 0.12314116209745407,
|
| 511 |
+
"learning_rate": 0.00017414333498411733,
|
| 512 |
+
"loss": 0.0179,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 3.5609756097560976,
|
| 517 |
+
"grad_norm": 0.08803991228342056,
|
| 518 |
+
"learning_rate": 0.00017345391910549238,
|
| 519 |
+
"loss": 0.0105,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 3.6097560975609757,
|
| 524 |
+
"grad_norm": 0.06382381916046143,
|
| 525 |
+
"learning_rate": 0.000172756836310958,
|
| 526 |
+
"loss": 0.0106,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 3.658536585365854,
|
| 531 |
+
"grad_norm": 0.47523975372314453,
|
| 532 |
+
"learning_rate": 0.0001720521593600787,
|
| 533 |
+
"loss": 0.0085,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.7073170731707314,
|
| 538 |
+
"grad_norm": 0.1268441379070282,
|
| 539 |
+
"learning_rate": 0.000171339961805076,
|
| 540 |
+
"loss": 0.0155,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 3.7560975609756095,
|
| 545 |
+
"grad_norm": 0.23719309270381927,
|
| 546 |
+
"learning_rate": 0.000170620317983151,
|
| 547 |
+
"loss": 0.015,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.8048780487804876,
|
| 552 |
+
"grad_norm": 0.0664207935333252,
|
| 553 |
+
"learning_rate": 0.00016989330300872576,
|
| 554 |
+
"loss": 0.0179,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.8536585365853657,
|
| 559 |
+
"grad_norm": 0.3121427893638611,
|
| 560 |
+
"learning_rate": 0.00016915899276560237,
|
| 561 |
+
"loss": 0.0138,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.902439024390244,
|
| 566 |
+
"grad_norm": 0.0784049853682518,
|
| 567 |
+
"learning_rate": 0.00016841746389904304,
|
| 568 |
+
"loss": 0.0114,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.951219512195122,
|
| 573 |
+
"grad_norm": 0.7239044904708862,
|
| 574 |
+
"learning_rate": 0.0001676687938077698,
|
| 575 |
+
"loss": 0.0251,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.0,
|
| 580 |
+
"grad_norm": 0.2333860546350479,
|
| 581 |
+
"learning_rate": 0.00016691306063588583,
|
| 582 |
+
"loss": 0.0135,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 4.048780487804878,
|
| 587 |
+
"grad_norm": 0.7087911367416382,
|
| 588 |
+
"learning_rate": 0.00016615034326471898,
|
| 589 |
+
"loss": 0.0195,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 4.097560975609756,
|
| 594 |
+
"grad_norm": 0.07190815359354019,
|
| 595 |
+
"learning_rate": 0.00016538072130458853,
|
| 596 |
+
"loss": 0.0095,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.146341463414634,
|
| 601 |
+
"grad_norm": 0.33951500058174133,
|
| 602 |
+
"learning_rate": 0.00016460427508649546,
|
| 603 |
+
"loss": 0.0131,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 4.195121951219512,
|
| 608 |
+
"grad_norm": 0.06381627917289734,
|
| 609 |
+
"learning_rate": 0.00016382108565373785,
|
| 610 |
+
"loss": 0.0119,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.2439024390243905,
|
| 615 |
+
"grad_norm": 0.44717633724212646,
|
| 616 |
+
"learning_rate": 0.00016303123475345182,
|
| 617 |
+
"loss": 0.0127,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 4.2926829268292686,
|
| 622 |
+
"grad_norm": 0.6674973368644714,
|
| 623 |
+
"learning_rate": 0.00016223480482807894,
|
| 624 |
+
"loss": 0.0111,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 4.341463414634147,
|
| 629 |
+
"grad_norm": 0.3303108215332031,
|
| 630 |
+
"learning_rate": 0.00016143187900676112,
|
| 631 |
+
"loss": 0.0159,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 4.390243902439025,
|
| 636 |
+
"grad_norm": 0.2972947359085083,
|
| 637 |
+
"learning_rate": 0.0001606225410966638,
|
| 638 |
+
"loss": 0.0086,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 4.439024390243903,
|
| 643 |
+
"grad_norm": 0.059205561876297,
|
| 644 |
+
"learning_rate": 0.00015980687557422854,
|
| 645 |
+
"loss": 0.0104,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 4.487804878048781,
|
| 650 |
+
"grad_norm": 0.08515360206365585,
|
| 651 |
+
"learning_rate": 0.00015898496757635536,
|
| 652 |
+
"loss": 0.0079,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 4.536585365853659,
|
| 657 |
+
"grad_norm": 0.14600469172000885,
|
| 658 |
+
"learning_rate": 0.00015815690289151658,
|
| 659 |
+
"loss": 0.0101,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 4.585365853658536,
|
| 664 |
+
"grad_norm": 0.05901546776294708,
|
| 665 |
+
"learning_rate": 0.0001573227679508024,
|
| 666 |
+
"loss": 0.0075,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 4.634146341463414,
|
| 671 |
+
"grad_norm": 0.3404502868652344,
|
| 672 |
+
"learning_rate": 0.00015648264981889934,
|
| 673 |
+
"loss": 0.0158,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 4.682926829268292,
|
| 678 |
+
"grad_norm": 0.0968211218714714,
|
| 679 |
+
"learning_rate": 0.00015563663618500302,
|
| 680 |
+
"loss": 0.0092,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 4.7317073170731705,
|
| 685 |
+
"grad_norm": 0.08040373027324677,
|
| 686 |
+
"learning_rate": 0.00015478481535366494,
|
| 687 |
+
"loss": 0.0088,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 4.780487804878049,
|
| 692 |
+
"grad_norm": 0.7208348512649536,
|
| 693 |
+
"learning_rate": 0.00015392727623557585,
|
| 694 |
+
"loss": 0.0132,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 4.829268292682927,
|
| 699 |
+
"grad_norm": 0.26821044087409973,
|
| 700 |
+
"learning_rate": 0.00015306410833828535,
|
| 701 |
+
"loss": 0.0113,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 4.878048780487805,
|
| 706 |
+
"grad_norm": 0.09240720421075821,
|
| 707 |
+
"learning_rate": 0.00015219540175685938,
|
| 708 |
+
"loss": 0.0096,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 4.926829268292683,
|
| 713 |
+
"grad_norm": 0.3397311270236969,
|
| 714 |
+
"learning_rate": 0.00015132124716447627,
|
| 715 |
+
"loss": 0.0072,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 4.975609756097561,
|
| 720 |
+
"grad_norm": 0.07910922169685364,
|
| 721 |
+
"learning_rate": 0.00015044173580296266,
|
| 722 |
+
"loss": 0.0115,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 5.024390243902439,
|
| 727 |
+
"grad_norm": 0.05629584938287735,
|
| 728 |
+
"learning_rate": 0.00014955695947326987,
|
| 729 |
+
"loss": 0.0066,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 5.073170731707317,
|
| 734 |
+
"grad_norm": 0.7522541880607605,
|
| 735 |
+
"learning_rate": 0.00014866701052589193,
|
| 736 |
+
"loss": 0.0159,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 5.121951219512195,
|
| 741 |
+
"grad_norm": 0.09192178398370743,
|
| 742 |
+
"learning_rate": 0.0001477719818512263,
|
| 743 |
+
"loss": 0.0085,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 5.170731707317073,
|
| 748 |
+
"grad_norm": 0.3984428346157074,
|
| 749 |
+
"learning_rate": 0.00014687196686987832,
|
| 750 |
+
"loss": 0.0091,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 5.219512195121951,
|
| 755 |
+
"grad_norm": 0.4188997149467468,
|
| 756 |
+
"learning_rate": 0.00014596705952291017,
|
| 757 |
+
"loss": 0.0083,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 5.2682926829268295,
|
| 762 |
+
"grad_norm": 0.07686212658882141,
|
| 763 |
+
"learning_rate": 0.00014505735426203543,
|
| 764 |
+
"loss": 0.0064,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 5.317073170731708,
|
| 769 |
+
"grad_norm": 0.38933801651000977,
|
| 770 |
+
"learning_rate": 0.00014414294603976076,
|
| 771 |
+
"loss": 0.0086,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 5.365853658536586,
|
| 776 |
+
"grad_norm": 0.0843789279460907,
|
| 777 |
+
"learning_rate": 0.00014322393029947468,
|
| 778 |
+
"loss": 0.0074,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 5.414634146341464,
|
| 783 |
+
"grad_norm": 0.19899946451187134,
|
| 784 |
+
"learning_rate": 0.0001423004029654859,
|
| 785 |
+
"loss": 0.0102,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 5.463414634146342,
|
| 790 |
+
"grad_norm": 0.06790963560342789,
|
| 791 |
+
"learning_rate": 0.00014137246043301042,
|
| 792 |
+
"loss": 0.0102,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 5.512195121951219,
|
| 797 |
+
"grad_norm": 0.08267515152692795,
|
| 798 |
+
"learning_rate": 0.00014044019955811065,
|
| 799 |
+
"loss": 0.009,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 5.560975609756097,
|
| 804 |
+
"grad_norm": 0.3616844713687897,
|
| 805 |
+
"learning_rate": 0.00013950371764758542,
|
| 806 |
+
"loss": 0.0119,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 5.609756097560975,
|
| 811 |
+
"grad_norm": 0.052261725068092346,
|
| 812 |
+
"learning_rate": 0.0001385631124488136,
|
| 813 |
+
"loss": 0.0078,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 5.658536585365853,
|
| 818 |
+
"grad_norm": 0.07086987048387527,
|
| 819 |
+
"learning_rate": 0.00013761848213955134,
|
| 820 |
+
"loss": 0.0112,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 5.7073170731707314,
|
| 825 |
+
"grad_norm": 0.05841855704784393,
|
| 826 |
+
"learning_rate": 0.00013666992531768482,
|
| 827 |
+
"loss": 0.0095,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 5.7560975609756095,
|
| 832 |
+
"grad_norm": 0.2936477065086365,
|
| 833 |
+
"learning_rate": 0.00013571754099093848,
|
| 834 |
+
"loss": 0.0082,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 5.804878048780488,
|
| 839 |
+
"grad_norm": 0.7195134162902832,
|
| 840 |
+
"learning_rate": 0.0001347614285665412,
|
| 841 |
+
"loss": 0.0093,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 5.853658536585366,
|
| 846 |
+
"grad_norm": 0.09665755927562714,
|
| 847 |
+
"learning_rate": 0.00013380168784085027,
|
| 848 |
+
"loss": 0.0125,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 5.902439024390244,
|
| 853 |
+
"grad_norm": 0.08146821707487106,
|
| 854 |
+
"learning_rate": 0.0001328384189889351,
|
| 855 |
+
"loss": 0.0094,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 5.951219512195122,
|
| 860 |
+
"grad_norm": 1.6456434726715088,
|
| 861 |
+
"learning_rate": 0.00013187172255412096,
|
| 862 |
+
"loss": 0.0104,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 6.0,
|
| 867 |
+
"grad_norm": 0.46437689661979675,
|
| 868 |
+
"learning_rate": 0.00013090169943749476,
|
| 869 |
+
"loss": 0.0103,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 6.048780487804878,
|
| 874 |
+
"grad_norm": 0.40744251012802124,
|
| 875 |
+
"learning_rate": 0.00012992845088737322,
|
| 876 |
+
"loss": 0.0105,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 6.097560975609756,
|
| 881 |
+
"grad_norm": 0.09202691912651062,
|
| 882 |
+
"learning_rate": 0.00012895207848873487,
|
| 883 |
+
"loss": 0.0088,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 6.146341463414634,
|
| 888 |
+
"grad_norm": 0.41562455892562866,
|
| 889 |
+
"learning_rate": 0.00012797268415261682,
|
| 890 |
+
"loss": 0.0105,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 6.195121951219512,
|
| 895 |
+
"grad_norm": 0.061398524791002274,
|
| 896 |
+
"learning_rate": 0.0001269903701054776,
|
| 897 |
+
"loss": 0.0084,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 6.2439024390243905,
|
| 902 |
+
"grad_norm": 0.0851488932967186,
|
| 903 |
+
"learning_rate": 0.00012600523887852706,
|
| 904 |
+
"loss": 0.0081,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 6.2926829268292686,
|
| 909 |
+
"grad_norm": 0.4565141201019287,
|
| 910 |
+
"learning_rate": 0.00012501739329702453,
|
| 911 |
+
"loss": 0.0122,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 6.341463414634147,
|
| 916 |
+
"grad_norm": 0.06614430993795395,
|
| 917 |
+
"learning_rate": 0.00012402693646954607,
|
| 918 |
+
"loss": 0.0079,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 6.390243902439025,
|
| 923 |
+
"grad_norm": 0.3719758987426758,
|
| 924 |
+
"learning_rate": 0.00012303397177722234,
|
| 925 |
+
"loss": 0.0096,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 6.439024390243903,
|
| 930 |
+
"grad_norm": 0.06896215677261353,
|
| 931 |
+
"learning_rate": 0.0001220386028629479,
|
| 932 |
+
"loss": 0.0059,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 6.487804878048781,
|
| 937 |
+
"grad_norm": 0.05981654301285744,
|
| 938 |
+
"learning_rate": 0.00012104093362056341,
|
| 939 |
+
"loss": 0.007,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 6.536585365853659,
|
| 944 |
+
"grad_norm": 0.0625968649983406,
|
| 945 |
+
"learning_rate": 0.00012004106818401135,
|
| 946 |
+
"loss": 0.0104,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 6.585365853658536,
|
| 951 |
+
"grad_norm": 0.04070024937391281,
|
| 952 |
+
"learning_rate": 0.00011903911091646684,
|
| 953 |
+
"loss": 0.0082,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 6.634146341463414,
|
| 958 |
+
"grad_norm": 0.05095053091645241,
|
| 959 |
+
"learning_rate": 0.00011803516639944452,
|
| 960 |
+
"loss": 0.008,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 6.682926829268292,
|
| 965 |
+
"grad_norm": 0.058545567095279694,
|
| 966 |
+
"learning_rate": 0.00011702933942188252,
|
| 967 |
+
"loss": 0.0079,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 6.7317073170731705,
|
| 972 |
+
"grad_norm": 0.06065903976559639,
|
| 973 |
+
"learning_rate": 0.0001160217349692051,
|
| 974 |
+
"loss": 0.0075,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 6.780487804878049,
|
| 979 |
+
"grad_norm": 0.13544753193855286,
|
| 980 |
+
"learning_rate": 0.00011501245821236439,
|
| 981 |
+
"loss": 0.0075,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 6.829268292682927,
|
| 986 |
+
"grad_norm": 0.06476018577814102,
|
| 987 |
+
"learning_rate": 0.00011400161449686293,
|
| 988 |
+
"loss": 0.0086,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 6.878048780487805,
|
| 993 |
+
"grad_norm": 0.0454210601747036,
|
| 994 |
+
"learning_rate": 0.00011298930933175804,
|
| 995 |
+
"loss": 0.0074,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 6.926829268292683,
|
| 1000 |
+
"grad_norm": 0.05906907469034195,
|
| 1001 |
+
"learning_rate": 0.00011197564837864922,
|
| 1002 |
+
"loss": 0.007,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 6.975609756097561,
|
| 1007 |
+
"grad_norm": 0.2888021171092987,
|
| 1008 |
+
"learning_rate": 0.00011096073744064919,
|
| 1009 |
+
"loss": 0.0076,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 7.024390243902439,
|
| 1014 |
+
"grad_norm": 0.05438758432865143,
|
| 1015 |
+
"learning_rate": 0.00010994468245134071,
|
| 1016 |
+
"loss": 0.008,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 7.073170731707317,
|
| 1021 |
+
"grad_norm": 0.04347096383571625,
|
| 1022 |
+
"learning_rate": 0.00010892758946371944,
|
| 1023 |
+
"loss": 0.006,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 7.121951219512195,
|
| 1028 |
+
"grad_norm": 0.06834473460912704,
|
| 1029 |
+
"learning_rate": 0.00010790956463912438,
|
| 1030 |
+
"loss": 0.0079,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 7.170731707317073,
|
| 1035 |
+
"grad_norm": 0.04391489177942276,
|
| 1036 |
+
"learning_rate": 0.00010689071423615709,
|
| 1037 |
+
"loss": 0.0061,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 7.219512195121951,
|
| 1042 |
+
"grad_norm": 0.0990622267127037,
|
| 1043 |
+
"learning_rate": 0.00010587114459959071,
|
| 1044 |
+
"loss": 0.0071,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 7.2682926829268295,
|
| 1049 |
+
"grad_norm": 0.048575662076473236,
|
| 1050 |
+
"learning_rate": 0.00010485096214927002,
|
| 1051 |
+
"loss": 0.0066,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 7.317073170731708,
|
| 1056 |
+
"grad_norm": 0.05991552770137787,
|
| 1057 |
+
"learning_rate": 0.00010383027336900355,
|
| 1058 |
+
"loss": 0.0075,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 7.365853658536586,
|
| 1063 |
+
"grad_norm": 0.08045367151498795,
|
| 1064 |
+
"learning_rate": 0.00010280918479544914,
|
| 1065 |
+
"loss": 0.0062,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 7.414634146341464,
|
| 1070 |
+
"grad_norm": 0.044166866689920425,
|
| 1071 |
+
"learning_rate": 0.00010178780300699395,
|
| 1072 |
+
"loss": 0.008,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 7.463414634146342,
|
| 1077 |
+
"grad_norm": 0.06291426718235016,
|
| 1078 |
+
"learning_rate": 0.00010076623461263018,
|
| 1079 |
+
"loss": 0.0066,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 7.512195121951219,
|
| 1084 |
+
"grad_norm": 0.056730519980192184,
|
| 1085 |
+
"learning_rate": 9.974458624082727e-05,
|
| 1086 |
+
"loss": 0.0063,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 7.560975609756097,
|
| 1091 |
+
"grad_norm": 0.18145255744457245,
|
| 1092 |
+
"learning_rate": 9.872296452840264e-05,
|
| 1093 |
+
"loss": 0.007,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 7.609756097560975,
|
| 1098 |
+
"grad_norm": 0.038042183965444565,
|
| 1099 |
+
"learning_rate": 9.770147610939097e-05,
|
| 1100 |
+
"loss": 0.0071,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 7.658536585365853,
|
| 1105 |
+
"grad_norm": 0.09980273991823196,
|
| 1106 |
+
"learning_rate": 9.668022760391418e-05,
|
| 1107 |
+
"loss": 0.0083,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 7.7073170731707314,
|
| 1112 |
+
"grad_norm": 0.04334135353565216,
|
| 1113 |
+
"learning_rate": 9.565932560705277e-05,
|
| 1114 |
+
"loss": 0.0073,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 7.7560975609756095,
|
| 1119 |
+
"grad_norm": 0.08293572813272476,
|
| 1120 |
+
"learning_rate": 9.463887667771946e-05,
|
| 1121 |
+
"loss": 0.007,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 7.804878048780488,
|
| 1126 |
+
"grad_norm": 0.06575772166252136,
|
| 1127 |
+
"learning_rate": 9.361898732753716e-05,
|
| 1128 |
+
"loss": 0.007,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 7.853658536585366,
|
| 1133 |
+
"grad_norm": 0.13714659214019775,
|
| 1134 |
+
"learning_rate": 9.259976400972147e-05,
|
| 1135 |
+
"loss": 0.0071,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 7.902439024390244,
|
| 1140 |
+
"grad_norm": 0.05362860858440399,
|
| 1141 |
+
"learning_rate": 9.15813131079693e-05,
|
| 1142 |
+
"loss": 0.0069,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 7.951219512195122,
|
| 1147 |
+
"grad_norm": 0.036402106285095215,
|
| 1148 |
+
"learning_rate": 9.056374092535504e-05,
|
| 1149 |
+
"loss": 0.0068,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 8.0,
|
| 1154 |
+
"grad_norm": 0.06819606572389603,
|
| 1155 |
+
"learning_rate": 8.954715367323468e-05,
|
| 1156 |
+
"loss": 0.0074,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 8.048780487804878,
|
| 1161 |
+
"grad_norm": 0.051237184554338455,
|
| 1162 |
+
"learning_rate": 8.853165746015997e-05,
|
| 1163 |
+
"loss": 0.0061,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 8.097560975609756,
|
| 1168 |
+
"grad_norm": 0.04173099994659424,
|
| 1169 |
+
"learning_rate": 8.751735828080308e-05,
|
| 1170 |
+
"loss": 0.0071,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 8.146341463414634,
|
| 1175 |
+
"grad_norm": 0.04740411415696144,
|
| 1176 |
+
"learning_rate": 8.650436200489303e-05,
|
| 1177 |
+
"loss": 0.0062,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 8.195121951219512,
|
| 1182 |
+
"grad_norm": 0.07791474461555481,
|
| 1183 |
+
"learning_rate": 8.549277436616551e-05,
|
| 1184 |
+
"loss": 0.0063,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 8.24390243902439,
|
| 1189 |
+
"grad_norm": 0.10498108714818954,
|
| 1190 |
+
"learning_rate": 8.448270095132652e-05,
|
| 1191 |
+
"loss": 0.0061,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 8.292682926829269,
|
| 1196 |
+
"grad_norm": 0.07452121376991272,
|
| 1197 |
+
"learning_rate": 8.347424718903151e-05,
|
| 1198 |
+
"loss": 0.0063,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 8.341463414634147,
|
| 1203 |
+
"grad_norm": 0.07632943242788315,
|
| 1204 |
+
"learning_rate": 8.246751833888122e-05,
|
| 1205 |
+
"loss": 0.0067,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 8.390243902439025,
|
| 1210 |
+
"grad_norm": 0.040240757167339325,
|
| 1211 |
+
"learning_rate": 8.146261948043485e-05,
|
| 1212 |
+
"loss": 0.0063,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 8.439024390243903,
|
| 1217 |
+
"grad_norm": 0.06094524264335632,
|
| 1218 |
+
"learning_rate": 8.0459655502242e-05,
|
| 1219 |
+
"loss": 0.0061,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 8.487804878048781,
|
| 1224 |
+
"grad_norm": 0.09173769503831863,
|
| 1225 |
+
"learning_rate": 7.945873109089503e-05,
|
| 1226 |
+
"loss": 0.0066,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 8.536585365853659,
|
| 1231 |
+
"grad_norm": 0.07450529932975769,
|
| 1232 |
+
"learning_rate": 7.845995072010188e-05,
|
| 1233 |
+
"loss": 0.0065,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 8.585365853658537,
|
| 1238 |
+
"grad_norm": 0.07175474613904953,
|
| 1239 |
+
"learning_rate": 7.74634186397815e-05,
|
| 1240 |
+
"loss": 0.0063,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 8.634146341463415,
|
| 1245 |
+
"grad_norm": 0.1444873958826065,
|
| 1246 |
+
"learning_rate": 7.646923886518264e-05,
|
| 1247 |
+
"loss": 0.0066,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 8.682926829268293,
|
| 1252 |
+
"grad_norm": 0.06203252822160721,
|
| 1253 |
+
"learning_rate": 7.54775151660267e-05,
|
| 1254 |
+
"loss": 0.0061,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 8.731707317073171,
|
| 1259 |
+
"grad_norm": 0.07840217649936676,
|
| 1260 |
+
"learning_rate": 7.448835105567696e-05,
|
| 1261 |
+
"loss": 0.0066,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 8.78048780487805,
|
| 1266 |
+
"grad_norm": 0.05611024424433708,
|
| 1267 |
+
"learning_rate": 7.350184978033386e-05,
|
| 1268 |
+
"loss": 0.0063,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 8.829268292682928,
|
| 1273 |
+
"grad_norm": 0.05446132645010948,
|
| 1274 |
+
"learning_rate": 7.251811430825846e-05,
|
| 1275 |
+
"loss": 0.0072,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 8.878048780487806,
|
| 1280 |
+
"grad_norm": 0.06147909164428711,
|
| 1281 |
+
"learning_rate": 7.153724731902506e-05,
|
| 1282 |
+
"loss": 0.0063,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 8.926829268292684,
|
| 1287 |
+
"grad_norm": 0.137003555893898,
|
| 1288 |
+
"learning_rate": 7.055935119280369e-05,
|
| 1289 |
+
"loss": 0.0066,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 8.975609756097562,
|
| 1294 |
+
"grad_norm": 0.15653973817825317,
|
| 1295 |
+
"learning_rate": 6.958452799967385e-05,
|
| 1296 |
+
"loss": 0.007,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 9.024390243902438,
|
| 1301 |
+
"grad_norm": 0.06786433607339859,
|
| 1302 |
+
"learning_rate": 6.861287948897091e-05,
|
| 1303 |
+
"loss": 0.0069,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 9.073170731707316,
|
| 1308 |
+
"grad_norm": 0.07620502263307571,
|
| 1309 |
+
"learning_rate": 6.764450707866576e-05,
|
| 1310 |
+
"loss": 0.0062,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 9.121951219512194,
|
| 1315 |
+
"grad_norm": 0.05350011587142944,
|
| 1316 |
+
"learning_rate": 6.667951184477893e-05,
|
| 1317 |
+
"loss": 0.0059,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 9.170731707317072,
|
| 1322 |
+
"grad_norm": 0.05874161049723625,
|
| 1323 |
+
"learning_rate": 6.57179945108307e-05,
|
| 1324 |
+
"loss": 0.0054,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 9.21951219512195,
|
| 1329 |
+
"grad_norm": 0.07297080755233765,
|
| 1330 |
+
"learning_rate": 6.476005543732782e-05,
|
| 1331 |
+
"loss": 0.0067,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 9.268292682926829,
|
| 1336 |
+
"grad_norm": 0.08384808897972107,
|
| 1337 |
+
"learning_rate": 6.380579461128819e-05,
|
| 1338 |
+
"loss": 0.0065,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 9.317073170731707,
|
| 1343 |
+
"grad_norm": 0.06501758098602295,
|
| 1344 |
+
"learning_rate": 6.285531163580449e-05,
|
| 1345 |
+
"loss": 0.0058,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 9.365853658536585,
|
| 1350 |
+
"grad_norm": 0.051126834005117416,
|
| 1351 |
+
"learning_rate": 6.190870571964774e-05,
|
| 1352 |
+
"loss": 0.0061,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 9.414634146341463,
|
| 1357 |
+
"grad_norm": 0.07436596602201462,
|
| 1358 |
+
"learning_rate": 6.096607566691235e-05,
|
| 1359 |
+
"loss": 0.0064,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 9.463414634146341,
|
| 1364 |
+
"grad_norm": 0.0661911889910698,
|
| 1365 |
+
"learning_rate": 6.002751986670323e-05,
|
| 1366 |
+
"loss": 0.0061,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 9.512195121951219,
|
| 1371 |
+
"grad_norm": 0.058736588805913925,
|
| 1372 |
+
"learning_rate": 5.909313628286601e-05,
|
| 1373 |
+
"loss": 0.0063,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 9.560975609756097,
|
| 1378 |
+
"grad_norm": 0.051081206649541855,
|
| 1379 |
+
"learning_rate": 5.816302244376206e-05,
|
| 1380 |
+
"loss": 0.0074,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 9.609756097560975,
|
| 1385 |
+
"grad_norm": 0.06269817799329758,
|
| 1386 |
+
"learning_rate": 5.7237275432088664e-05,
|
| 1387 |
+
"loss": 0.0057,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 9.658536585365853,
|
| 1392 |
+
"grad_norm": 0.0546838752925396,
|
| 1393 |
+
"learning_rate": 5.63159918747457e-05,
|
| 1394 |
+
"loss": 0.0063,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 9.707317073170731,
|
| 1399 |
+
"grad_norm": 0.09113246202468872,
|
| 1400 |
+
"learning_rate": 5.539926793275021e-05,
|
| 1401 |
+
"loss": 0.0067,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 9.75609756097561,
|
| 1406 |
+
"grad_norm": 0.06070900708436966,
|
| 1407 |
+
"learning_rate": 5.448719929119915e-05,
|
| 1408 |
+
"loss": 0.0065,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 9.804878048780488,
|
| 1413 |
+
"grad_norm": 0.06381196528673172,
|
| 1414 |
+
"learning_rate": 5.3579881149282204e-05,
|
| 1415 |
+
"loss": 0.0063,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 9.853658536585366,
|
| 1420 |
+
"grad_norm": 0.05914902687072754,
|
| 1421 |
+
"learning_rate": 5.267740821034524e-05,
|
| 1422 |
+
"loss": 0.0059,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 9.902439024390244,
|
| 1427 |
+
"grad_norm": 0.0414993092417717,
|
| 1428 |
+
"learning_rate": 5.177987467200504e-05,
|
| 1429 |
+
"loss": 0.0065,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 9.951219512195122,
|
| 1434 |
+
"grad_norm": 0.051615435630083084,
|
| 1435 |
+
"learning_rate": 5.088737421631767e-05,
|
| 1436 |
+
"loss": 0.0061,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 10.0,
|
| 1441 |
+
"grad_norm": 0.08131363987922668,
|
| 1442 |
+
"learning_rate": 5.000000000000002e-05,
|
| 1443 |
+
"loss": 0.0058,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
}
|
| 1446 |
+
],
|
| 1447 |
+
"logging_steps": 10,
|
| 1448 |
+
"max_steps": 3075,
|
| 1449 |
+
"num_input_tokens_seen": 0,
|
| 1450 |
+
"num_train_epochs": 15,
|
| 1451 |
+
"save_steps": 500,
|
| 1452 |
+
"stateful_callbacks": {
|
| 1453 |
+
"TrainerControl": {
|
| 1454 |
+
"args": {
|
| 1455 |
+
"should_epoch_stop": false,
|
| 1456 |
+
"should_evaluate": false,
|
| 1457 |
+
"should_log": false,
|
| 1458 |
+
"should_save": true,
|
| 1459 |
+
"should_training_stop": false
|
| 1460 |
+
},
|
| 1461 |
+
"attributes": {}
|
| 1462 |
+
}
|
| 1463 |
+
},
|
| 1464 |
+
"total_flos": 8.2158937116672e+16,
|
| 1465 |
+
"train_batch_size": 1,
|
| 1466 |
+
"trial_name": null,
|
| 1467 |
+
"trial_params": null
|
| 1468 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:618d2fd08d5f40db203f14da632df01dd896f66e47028894bfc6986f0921daa4
|
| 3 |
+
size 5432
|