Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +39 -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 +0 -0
- trainer_state.json +1784 -0
- training_args.bin +3 -0
- value_head.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-v0.3
|
| 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 0.15.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/workspace/hf_hub/mistral_7B_instruct_v0.3",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 16,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"v_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"down_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea718566bb0a29f0b222b6987822ad5a866fc092287941e3b2efe94c0cf0eace
|
| 3 |
+
size 167832240
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0349882f19f1bc0879d419ae4915020de56a0dd32f1e27676f2e4f87cf27db98
|
| 3 |
+
size 335956888
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97c553ee6f802e028972ff393a41d5567e08c4184d7ad27df266f748da7e8668
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10662831d356bf899520d4687e0347b23261f4339599d8e4c110841675326bb5
|
| 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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
| 3 |
+
size 587404
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1784 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.9973094170403587,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2508,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01195814648729447,
|
| 14 |
+
"grad_norm": 37.390235900878906,
|
| 15 |
+
"learning_rate": 7.171314741035858e-07,
|
| 16 |
+
"loss": 0.8735,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02391629297458894,
|
| 21 |
+
"grad_norm": 32.51190185546875,
|
| 22 |
+
"learning_rate": 1.5139442231075698e-06,
|
| 23 |
+
"loss": 0.9866,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03587443946188341,
|
| 28 |
+
"grad_norm": 33.959232330322266,
|
| 29 |
+
"learning_rate": 2.310756972111554e-06,
|
| 30 |
+
"loss": 0.9759,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04783258594917788,
|
| 35 |
+
"grad_norm": 36.68806457519531,
|
| 36 |
+
"learning_rate": 3.107569721115538e-06,
|
| 37 |
+
"loss": 0.9863,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.059790732436472344,
|
| 42 |
+
"grad_norm": 45.294288635253906,
|
| 43 |
+
"learning_rate": 3.904382470119522e-06,
|
| 44 |
+
"loss": 1.0019,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07174887892376682,
|
| 49 |
+
"grad_norm": 35.863704681396484,
|
| 50 |
+
"learning_rate": 4.701195219123506e-06,
|
| 51 |
+
"loss": 0.9902,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08370702541106129,
|
| 56 |
+
"grad_norm": 35.59271240234375,
|
| 57 |
+
"learning_rate": 5.49800796812749e-06,
|
| 58 |
+
"loss": 0.8866,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09566517189835576,
|
| 63 |
+
"grad_norm": 37.64653396606445,
|
| 64 |
+
"learning_rate": 6.294820717131475e-06,
|
| 65 |
+
"loss": 0.8977,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.10762331838565023,
|
| 70 |
+
"grad_norm": 41.79659652709961,
|
| 71 |
+
"learning_rate": 7.091633466135459e-06,
|
| 72 |
+
"loss": 0.8981,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.11958146487294469,
|
| 77 |
+
"grad_norm": 47.05972671508789,
|
| 78 |
+
"learning_rate": 7.888446215139443e-06,
|
| 79 |
+
"loss": 1.0321,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13153961136023917,
|
| 84 |
+
"grad_norm": 40.94007873535156,
|
| 85 |
+
"learning_rate": 8.685258964143428e-06,
|
| 86 |
+
"loss": 0.8109,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14349775784753363,
|
| 91 |
+
"grad_norm": 33.521488189697266,
|
| 92 |
+
"learning_rate": 9.482071713147412e-06,
|
| 93 |
+
"loss": 0.9082,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1554559043348281,
|
| 98 |
+
"grad_norm": 35.727088928222656,
|
| 99 |
+
"learning_rate": 1.0278884462151395e-05,
|
| 100 |
+
"loss": 0.9965,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.16741405082212257,
|
| 105 |
+
"grad_norm": 34.38468551635742,
|
| 106 |
+
"learning_rate": 1.1075697211155378e-05,
|
| 107 |
+
"loss": 0.8582,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.17937219730941703,
|
| 112 |
+
"grad_norm": 25.146038055419922,
|
| 113 |
+
"learning_rate": 1.1872509960159364e-05,
|
| 114 |
+
"loss": 0.9339,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.19133034379671152,
|
| 119 |
+
"grad_norm": 31.425004959106445,
|
| 120 |
+
"learning_rate": 1.2669322709163347e-05,
|
| 121 |
+
"loss": 0.9471,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.20328849028400597,
|
| 126 |
+
"grad_norm": 31.385652542114258,
|
| 127 |
+
"learning_rate": 1.3466135458167332e-05,
|
| 128 |
+
"loss": 0.8159,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.21524663677130046,
|
| 133 |
+
"grad_norm": 34.18405532836914,
|
| 134 |
+
"learning_rate": 1.4262948207171316e-05,
|
| 135 |
+
"loss": 0.784,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.22720478325859492,
|
| 140 |
+
"grad_norm": 27.445358276367188,
|
| 141 |
+
"learning_rate": 1.50597609561753e-05,
|
| 142 |
+
"loss": 0.9976,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.23916292974588937,
|
| 147 |
+
"grad_norm": 28.502460479736328,
|
| 148 |
+
"learning_rate": 1.5856573705179282e-05,
|
| 149 |
+
"loss": 0.8827,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.25112107623318386,
|
| 154 |
+
"grad_norm": 26.879541397094727,
|
| 155 |
+
"learning_rate": 1.6653386454183268e-05,
|
| 156 |
+
"loss": 0.8269,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.26307922272047835,
|
| 161 |
+
"grad_norm": 24.565549850463867,
|
| 162 |
+
"learning_rate": 1.745019920318725e-05,
|
| 163 |
+
"loss": 0.7868,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2750373692077728,
|
| 168 |
+
"grad_norm": 31.686193466186523,
|
| 169 |
+
"learning_rate": 1.8247011952191237e-05,
|
| 170 |
+
"loss": 0.8779,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.28699551569506726,
|
| 175 |
+
"grad_norm": 29.901086807250977,
|
| 176 |
+
"learning_rate": 1.904382470119522e-05,
|
| 177 |
+
"loss": 0.8613,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.29895366218236175,
|
| 182 |
+
"grad_norm": 35.48272705078125,
|
| 183 |
+
"learning_rate": 1.9840637450199206e-05,
|
| 184 |
+
"loss": 0.8778,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3109118086696562,
|
| 189 |
+
"grad_norm": 27.91745948791504,
|
| 190 |
+
"learning_rate": 1.9999380013664304e-05,
|
| 191 |
+
"loss": 0.8182,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.32286995515695066,
|
| 196 |
+
"grad_norm": 28.299238204956055,
|
| 197 |
+
"learning_rate": 1.999686145093126e-05,
|
| 198 |
+
"loss": 0.9717,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.33482810164424515,
|
| 203 |
+
"grad_norm": 26.9054012298584,
|
| 204 |
+
"learning_rate": 1.9992406050237434e-05,
|
| 205 |
+
"loss": 0.8137,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.34678624813153963,
|
| 210 |
+
"grad_norm": 30.215730667114258,
|
| 211 |
+
"learning_rate": 1.9986014674792683e-05,
|
| 212 |
+
"loss": 0.8826,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.35874439461883406,
|
| 217 |
+
"grad_norm": 31.110383987426758,
|
| 218 |
+
"learning_rate": 1.99776885628915e-05,
|
| 219 |
+
"loss": 0.8745,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.37070254110612855,
|
| 224 |
+
"grad_norm": 28.428905487060547,
|
| 225 |
+
"learning_rate": 1.9967429327673145e-05,
|
| 226 |
+
"loss": 0.7262,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.38266068759342303,
|
| 231 |
+
"grad_norm": 30.152149200439453,
|
| 232 |
+
"learning_rate": 1.9955238956809073e-05,
|
| 233 |
+
"loss": 0.7216,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.39461883408071746,
|
| 238 |
+
"grad_norm": 29.364212036132812,
|
| 239 |
+
"learning_rate": 1.994111981211786e-05,
|
| 240 |
+
"loss": 0.7389,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.40657698056801195,
|
| 245 |
+
"grad_norm": 28.63833999633789,
|
| 246 |
+
"learning_rate": 1.9925074629107598e-05,
|
| 247 |
+
"loss": 0.7152,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.41853512705530643,
|
| 252 |
+
"grad_norm": 27.808225631713867,
|
| 253 |
+
"learning_rate": 1.9907106516445913e-05,
|
| 254 |
+
"loss": 0.7773,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.4304932735426009,
|
| 259 |
+
"grad_norm": 23.987335205078125,
|
| 260 |
+
"learning_rate": 1.9887218955357674e-05,
|
| 261 |
+
"loss": 0.7453,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.44245142002989535,
|
| 266 |
+
"grad_norm": 19.61777687072754,
|
| 267 |
+
"learning_rate": 1.9865415798950525e-05,
|
| 268 |
+
"loss": 0.7485,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.45440956651718983,
|
| 273 |
+
"grad_norm": 14.744634628295898,
|
| 274 |
+
"learning_rate": 1.984170127146836e-05,
|
| 275 |
+
"loss": 0.6819,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4663677130044843,
|
| 280 |
+
"grad_norm": 16.74333953857422,
|
| 281 |
+
"learning_rate": 1.9816079967472915e-05,
|
| 282 |
+
"loss": 0.6501,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.47832585949177875,
|
| 287 |
+
"grad_norm": 15.49389362335205,
|
| 288 |
+
"learning_rate": 1.978855685095358e-05,
|
| 289 |
+
"loss": 0.7326,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.49028400597907323,
|
| 294 |
+
"grad_norm": 13.467843055725098,
|
| 295 |
+
"learning_rate": 1.9759137254365657e-05,
|
| 296 |
+
"loss": 0.6857,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5022421524663677,
|
| 301 |
+
"grad_norm": 11.469218254089355,
|
| 302 |
+
"learning_rate": 1.9727826877597232e-05,
|
| 303 |
+
"loss": 0.6947,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5142002989536621,
|
| 308 |
+
"grad_norm": 11.420854568481445,
|
| 309 |
+
"learning_rate": 1.9694631786864844e-05,
|
| 310 |
+
"loss": 0.6604,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5261584454409567,
|
| 315 |
+
"grad_norm": 12.314785957336426,
|
| 316 |
+
"learning_rate": 1.9659558413538198e-05,
|
| 317 |
+
"loss": 0.6812,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5381165919282511,
|
| 322 |
+
"grad_norm": 11.780921936035156,
|
| 323 |
+
"learning_rate": 1.962261355289411e-05,
|
| 324 |
+
"loss": 0.6669,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.5500747384155455,
|
| 329 |
+
"grad_norm": 12.58080768585205,
|
| 330 |
+
"learning_rate": 1.9583804362799957e-05,
|
| 331 |
+
"loss": 0.6705,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5620328849028401,
|
| 336 |
+
"grad_norm": 12.067771911621094,
|
| 337 |
+
"learning_rate": 1.9543138362326915e-05,
|
| 338 |
+
"loss": 0.6888,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5739910313901345,
|
| 343 |
+
"grad_norm": 11.332785606384277,
|
| 344 |
+
"learning_rate": 1.950062343029312e-05,
|
| 345 |
+
"loss": 0.7459,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.585949177877429,
|
| 350 |
+
"grad_norm": 9.514171600341797,
|
| 351 |
+
"learning_rate": 1.9456267803737243e-05,
|
| 352 |
+
"loss": 0.6961,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5979073243647235,
|
| 357 |
+
"grad_norm": 9.237369537353516,
|
| 358 |
+
"learning_rate": 1.9410080076322565e-05,
|
| 359 |
+
"loss": 0.6845,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6098654708520179,
|
| 364 |
+
"grad_norm": 9.043818473815918,
|
| 365 |
+
"learning_rate": 1.936206919667204e-05,
|
| 366 |
+
"loss": 0.6606,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6218236173393124,
|
| 371 |
+
"grad_norm": 7.798132419586182,
|
| 372 |
+
"learning_rate": 1.9312244466634518e-05,
|
| 373 |
+
"loss": 0.6626,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6337817638266069,
|
| 378 |
+
"grad_norm": 10.63857650756836,
|
| 379 |
+
"learning_rate": 1.9260615539482583e-05,
|
| 380 |
+
"loss": 0.6303,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6457399103139013,
|
| 385 |
+
"grad_norm": 9.348301887512207,
|
| 386 |
+
"learning_rate": 1.9207192418042265e-05,
|
| 387 |
+
"loss": 0.6526,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6576980568011959,
|
| 392 |
+
"grad_norm": 9.094481468200684,
|
| 393 |
+
"learning_rate": 1.9151985452755063e-05,
|
| 394 |
+
"loss": 0.691,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6696562032884903,
|
| 399 |
+
"grad_norm": 9.75300407409668,
|
| 400 |
+
"learning_rate": 1.909500533967259e-05,
|
| 401 |
+
"loss": 0.6896,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6816143497757847,
|
| 406 |
+
"grad_norm": 7.055481910705566,
|
| 407 |
+
"learning_rate": 1.903626311838428e-05,
|
| 408 |
+
"loss": 0.6761,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6935724962630793,
|
| 413 |
+
"grad_norm": 8.242525100708008,
|
| 414 |
+
"learning_rate": 1.8975770169878522e-05,
|
| 415 |
+
"loss": 0.666,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7055306427503737,
|
| 420 |
+
"grad_norm": 8.398313522338867,
|
| 421 |
+
"learning_rate": 1.8913538214337654e-05,
|
| 422 |
+
"loss": 0.6363,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.7174887892376681,
|
| 427 |
+
"grad_norm": 8.253714561462402,
|
| 428 |
+
"learning_rate": 1.884957930886724e-05,
|
| 429 |
+
"loss": 0.6396,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.7294469357249627,
|
| 434 |
+
"grad_norm": 7.084671497344971,
|
| 435 |
+
"learning_rate": 1.878390584516008e-05,
|
| 436 |
+
"loss": 0.6893,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.7414050822122571,
|
| 441 |
+
"grad_norm": 6.189998149871826,
|
| 442 |
+
"learning_rate": 1.871653054709538e-05,
|
| 443 |
+
"loss": 0.6898,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7533632286995515,
|
| 448 |
+
"grad_norm": 6.633572101593018,
|
| 449 |
+
"learning_rate": 1.864746646827357e-05,
|
| 450 |
+
"loss": 0.6832,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7653213751868461,
|
| 455 |
+
"grad_norm": 5.838533878326416,
|
| 456 |
+
"learning_rate": 1.8576726989487235e-05,
|
| 457 |
+
"loss": 0.6972,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7772795216741405,
|
| 462 |
+
"grad_norm": 5.878692626953125,
|
| 463 |
+
"learning_rate": 1.8504325816128662e-05,
|
| 464 |
+
"loss": 0.6535,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7892376681614349,
|
| 469 |
+
"grad_norm": 5.515905380249023,
|
| 470 |
+
"learning_rate": 1.8430276975534493e-05,
|
| 471 |
+
"loss": 0.6612,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.8011958146487295,
|
| 476 |
+
"grad_norm": 5.784304141998291,
|
| 477 |
+
"learning_rate": 1.835459481426801e-05,
|
| 478 |
+
"loss": 0.6722,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.8131539611360239,
|
| 483 |
+
"grad_norm": 5.234633445739746,
|
| 484 |
+
"learning_rate": 1.8277293995339566e-05,
|
| 485 |
+
"loss": 0.648,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.8251121076233184,
|
| 490 |
+
"grad_norm": 5.553504467010498,
|
| 491 |
+
"learning_rate": 1.8198389495365693e-05,
|
| 492 |
+
"loss": 0.6739,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.8370702541106129,
|
| 497 |
+
"grad_norm": 6.108278274536133,
|
| 498 |
+
"learning_rate": 1.811789660166747e-05,
|
| 499 |
+
"loss": 0.64,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8490284005979073,
|
| 504 |
+
"grad_norm": 6.565439701080322,
|
| 505 |
+
"learning_rate": 1.8035830909308693e-05,
|
| 506 |
+
"loss": 0.7097,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8609865470852018,
|
| 511 |
+
"grad_norm": 6.120002746582031,
|
| 512 |
+
"learning_rate": 1.7952208318074417e-05,
|
| 513 |
+
"loss": 0.635,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.8729446935724963,
|
| 518 |
+
"grad_norm": 5.392818927764893,
|
| 519 |
+
"learning_rate": 1.7867045029390447e-05,
|
| 520 |
+
"loss": 0.6712,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.8849028400597907,
|
| 525 |
+
"grad_norm": 6.204085350036621,
|
| 526 |
+
"learning_rate": 1.7780357543184396e-05,
|
| 527 |
+
"loss": 0.6825,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8968609865470852,
|
| 532 |
+
"grad_norm": 6.639048099517822,
|
| 533 |
+
"learning_rate": 1.7692162654688942e-05,
|
| 534 |
+
"loss": 0.6572,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.9088191330343797,
|
| 539 |
+
"grad_norm": 5.861717700958252,
|
| 540 |
+
"learning_rate": 1.7602477451187803e-05,
|
| 541 |
+
"loss": 0.6803,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.9207772795216741,
|
| 546 |
+
"grad_norm": 5.450317859649658,
|
| 547 |
+
"learning_rate": 1.7511319308705198e-05,
|
| 548 |
+
"loss": 0.6544,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.9327354260089686,
|
| 553 |
+
"grad_norm": 5.517683506011963,
|
| 554 |
+
"learning_rate": 1.7418705888639328e-05,
|
| 555 |
+
"loss": 0.7076,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.9446935724962631,
|
| 560 |
+
"grad_norm": 12.713557243347168,
|
| 561 |
+
"learning_rate": 1.732465513434056e-05,
|
| 562 |
+
"loss": 0.6266,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.9566517189835575,
|
| 567 |
+
"grad_norm": 8.854741096496582,
|
| 568 |
+
"learning_rate": 1.722918526763503e-05,
|
| 569 |
+
"loss": 0.627,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.968609865470852,
|
| 574 |
+
"grad_norm": 5.114956855773926,
|
| 575 |
+
"learning_rate": 1.713231478529422e-05,
|
| 576 |
+
"loss": 0.7058,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.9805680119581465,
|
| 581 |
+
"grad_norm": 4.991177558898926,
|
| 582 |
+
"learning_rate": 1.703406245545136e-05,
|
| 583 |
+
"loss": 0.6661,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.992526158445441,
|
| 588 |
+
"grad_norm": 5.7872490882873535,
|
| 589 |
+
"learning_rate": 1.6934447313965163e-05,
|
| 590 |
+
"loss": 0.6704,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0035874439461883,
|
| 595 |
+
"grad_norm": 6.510074615478516,
|
| 596 |
+
"learning_rate": 1.683348866073174e-05,
|
| 597 |
+
"loss": 0.5799,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.015545590433483,
|
| 602 |
+
"grad_norm": 5.4888482093811035,
|
| 603 |
+
"learning_rate": 1.6731206055945367e-05,
|
| 604 |
+
"loss": 0.5789,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.0275037369207773,
|
| 609 |
+
"grad_norm": 6.0650634765625,
|
| 610 |
+
"learning_rate": 1.662761931630878e-05,
|
| 611 |
+
"loss": 0.6513,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.0394618834080718,
|
| 616 |
+
"grad_norm": 5.280655860900879,
|
| 617 |
+
"learning_rate": 1.65227485111938e-05,
|
| 618 |
+
"loss": 0.6068,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.0514200298953662,
|
| 623 |
+
"grad_norm": 5.293959140777588,
|
| 624 |
+
"learning_rate": 1.6416613958753022e-05,
|
| 625 |
+
"loss": 0.626,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.0633781763826606,
|
| 630 |
+
"grad_norm": 5.393914222717285,
|
| 631 |
+
"learning_rate": 1.6309236221983244e-05,
|
| 632 |
+
"loss": 0.6207,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.075336322869955,
|
| 637 |
+
"grad_norm": 7.5375189781188965,
|
| 638 |
+
"learning_rate": 1.6200636104741533e-05,
|
| 639 |
+
"loss": 0.6237,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.0872944693572497,
|
| 644 |
+
"grad_norm": 5.487838268280029,
|
| 645 |
+
"learning_rate": 1.6090834647714573e-05,
|
| 646 |
+
"loss": 0.6432,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.0992526158445441,
|
| 651 |
+
"grad_norm": 4.94726037979126,
|
| 652 |
+
"learning_rate": 1.5979853124342154e-05,
|
| 653 |
+
"loss": 0.6367,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1112107623318386,
|
| 658 |
+
"grad_norm": 5.868317127227783,
|
| 659 |
+
"learning_rate": 1.5867713036695547e-05,
|
| 660 |
+
"loss": 0.634,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.123168908819133,
|
| 665 |
+
"grad_norm": 7.249979019165039,
|
| 666 |
+
"learning_rate": 1.5754436111311596e-05,
|
| 667 |
+
"loss": 0.645,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1351270553064274,
|
| 672 |
+
"grad_norm": 5.741177558898926,
|
| 673 |
+
"learning_rate": 1.564004429498333e-05,
|
| 674 |
+
"loss": 0.5886,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.1470852017937219,
|
| 679 |
+
"grad_norm": 6.459995746612549,
|
| 680 |
+
"learning_rate": 1.5524559750507876e-05,
|
| 681 |
+
"loss": 0.5297,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.1590433482810165,
|
| 686 |
+
"grad_norm": 8.16454792022705,
|
| 687 |
+
"learning_rate": 1.540800485239254e-05,
|
| 688 |
+
"loss": 0.6248,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.171001494768311,
|
| 693 |
+
"grad_norm": 6.695009231567383,
|
| 694 |
+
"learning_rate": 1.529040218251989e-05,
|
| 695 |
+
"loss": 0.6084,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.1829596412556054,
|
| 700 |
+
"grad_norm": 7.415663719177246,
|
| 701 |
+
"learning_rate": 1.5171774525772591e-05,
|
| 702 |
+
"loss": 0.582,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.1949177877428998,
|
| 707 |
+
"grad_norm": 8.063408851623535,
|
| 708 |
+
"learning_rate": 1.5052144865618996e-05,
|
| 709 |
+
"loss": 0.6072,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.2068759342301942,
|
| 714 |
+
"grad_norm": 9.53238296508789,
|
| 715 |
+
"learning_rate": 1.4931536379660214e-05,
|
| 716 |
+
"loss": 0.6143,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.2188340807174889,
|
| 721 |
+
"grad_norm": 7.271851539611816,
|
| 722 |
+
"learning_rate": 1.480997243513957e-05,
|
| 723 |
+
"loss": 0.692,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.2307922272047833,
|
| 728 |
+
"grad_norm": 6.271056175231934,
|
| 729 |
+
"learning_rate": 1.4687476584415326e-05,
|
| 730 |
+
"loss": 0.5915,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.2427503736920777,
|
| 735 |
+
"grad_norm": 5.996524333953857,
|
| 736 |
+
"learning_rate": 1.4564072560397542e-05,
|
| 737 |
+
"loss": 0.5845,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.2547085201793722,
|
| 742 |
+
"grad_norm": 7.27435302734375,
|
| 743 |
+
"learning_rate": 1.443978427194996e-05,
|
| 744 |
+
"loss": 0.6509,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.2666666666666666,
|
| 749 |
+
"grad_norm": 6.653409481048584,
|
| 750 |
+
"learning_rate": 1.4314635799257776e-05,
|
| 751 |
+
"loss": 0.6321,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.2786248131539613,
|
| 756 |
+
"grad_norm": 5.741835594177246,
|
| 757 |
+
"learning_rate": 1.4188651389162243e-05,
|
| 758 |
+
"loss": 0.6089,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.2905829596412555,
|
| 763 |
+
"grad_norm": 6.0159759521484375,
|
| 764 |
+
"learning_rate": 1.4061855450462977e-05,
|
| 765 |
+
"loss": 0.6081,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.3025411061285501,
|
| 770 |
+
"grad_norm": 6.8276262283325195,
|
| 771 |
+
"learning_rate": 1.3934272549188888e-05,
|
| 772 |
+
"loss": 0.613,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.3144992526158445,
|
| 777 |
+
"grad_norm": 6.349780082702637,
|
| 778 |
+
"learning_rate": 1.3805927403838621e-05,
|
| 779 |
+
"loss": 0.5929,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.326457399103139,
|
| 784 |
+
"grad_norm": 6.844293594360352,
|
| 785 |
+
"learning_rate": 1.3676844880591513e-05,
|
| 786 |
+
"loss": 0.6261,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.3384155455904334,
|
| 791 |
+
"grad_norm": 6.020809650421143,
|
| 792 |
+
"learning_rate": 1.3547049988489884e-05,
|
| 793 |
+
"loss": 0.6161,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.3503736920777278,
|
| 798 |
+
"grad_norm": 8.073211669921875,
|
| 799 |
+
"learning_rate": 1.3416567874593681e-05,
|
| 800 |
+
"loss": 0.6617,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.3623318385650225,
|
| 805 |
+
"grad_norm": 6.915843963623047,
|
| 806 |
+
"learning_rate": 1.3285423819108349e-05,
|
| 807 |
+
"loss": 0.6312,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.374289985052317,
|
| 812 |
+
"grad_norm": 6.248181343078613,
|
| 813 |
+
"learning_rate": 1.3153643230486964e-05,
|
| 814 |
+
"loss": 0.6088,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.3862481315396114,
|
| 819 |
+
"grad_norm": 6.5323333740234375,
|
| 820 |
+
"learning_rate": 1.3021251640507449e-05,
|
| 821 |
+
"loss": 0.647,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.3982062780269058,
|
| 826 |
+
"grad_norm": 7.27913761138916,
|
| 827 |
+
"learning_rate": 1.2888274699325948e-05,
|
| 828 |
+
"loss": 0.6038,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.4101644245142002,
|
| 833 |
+
"grad_norm": 6.83669376373291,
|
| 834 |
+
"learning_rate": 1.2754738170507243e-05,
|
| 835 |
+
"loss": 0.5719,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.4221225710014949,
|
| 840 |
+
"grad_norm": 7.551515579223633,
|
| 841 |
+
"learning_rate": 1.2620667926033199e-05,
|
| 842 |
+
"loss": 0.5647,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.4340807174887893,
|
| 847 |
+
"grad_norm": 8.500528335571289,
|
| 848 |
+
"learning_rate": 1.2486089941290207e-05,
|
| 849 |
+
"loss": 0.666,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.4460388639760837,
|
| 854 |
+
"grad_norm": 6.871554851531982,
|
| 855 |
+
"learning_rate": 1.2351030290036598e-05,
|
| 856 |
+
"loss": 0.5973,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.4579970104633782,
|
| 861 |
+
"grad_norm": 6.109719753265381,
|
| 862 |
+
"learning_rate": 1.221551513935099e-05,
|
| 863 |
+
"loss": 0.5934,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.4699551569506726,
|
| 868 |
+
"grad_norm": 7.8550848960876465,
|
| 869 |
+
"learning_rate": 1.2079570744562559e-05,
|
| 870 |
+
"loss": 0.6238,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.4819133034379672,
|
| 875 |
+
"grad_norm": 6.051307201385498,
|
| 876 |
+
"learning_rate": 1.1943223444164205e-05,
|
| 877 |
+
"loss": 0.6231,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.4938714499252617,
|
| 882 |
+
"grad_norm": 6.325740814208984,
|
| 883 |
+
"learning_rate": 1.1806499654709622e-05,
|
| 884 |
+
"loss": 0.5754,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.505829596412556,
|
| 889 |
+
"grad_norm": 9.00317096710205,
|
| 890 |
+
"learning_rate": 1.1669425865695223e-05,
|
| 891 |
+
"loss": 0.5843,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.5177877428998505,
|
| 896 |
+
"grad_norm": 10.153903007507324,
|
| 897 |
+
"learning_rate": 1.153202863442795e-05,
|
| 898 |
+
"loss": 0.6274,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.529745889387145,
|
| 903 |
+
"grad_norm": 6.388274192810059,
|
| 904 |
+
"learning_rate": 1.1394334580879932e-05,
|
| 905 |
+
"loss": 0.6072,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.5417040358744396,
|
| 910 |
+
"grad_norm": 6.760703086853027,
|
| 911 |
+
"learning_rate": 1.1256370382531017e-05,
|
| 912 |
+
"loss": 0.5512,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.5536621823617338,
|
| 917 |
+
"grad_norm": 8.285782814025879,
|
| 918 |
+
"learning_rate": 1.1118162769200148e-05,
|
| 919 |
+
"loss": 0.6307,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.5656203288490285,
|
| 924 |
+
"grad_norm": 6.265937805175781,
|
| 925 |
+
"learning_rate": 1.0979738517866601e-05,
|
| 926 |
+
"loss": 0.5465,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.577578475336323,
|
| 931 |
+
"grad_norm": 7.3016157150268555,
|
| 932 |
+
"learning_rate": 1.0841124447482116e-05,
|
| 933 |
+
"loss": 0.5826,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.5895366218236173,
|
| 938 |
+
"grad_norm": 8.863776206970215,
|
| 939 |
+
"learning_rate": 1.0702347413774832e-05,
|
| 940 |
+
"loss": 0.6321,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.6014947683109118,
|
| 945 |
+
"grad_norm": 10.67763900756836,
|
| 946 |
+
"learning_rate": 1.0563434304046152e-05,
|
| 947 |
+
"loss": 0.5816,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.6134529147982062,
|
| 952 |
+
"grad_norm": 14.390294075012207,
|
| 953 |
+
"learning_rate": 1.0424412031961485e-05,
|
| 954 |
+
"loss": 0.6203,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.6254110612855008,
|
| 959 |
+
"grad_norm": 7.504568576812744,
|
| 960 |
+
"learning_rate": 1.0285307532335847e-05,
|
| 961 |
+
"loss": 0.6106,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.6373692077727953,
|
| 966 |
+
"grad_norm": 9.697796821594238,
|
| 967 |
+
"learning_rate": 1.0146147755915407e-05,
|
| 968 |
+
"loss": 0.6332,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.6493273542600897,
|
| 973 |
+
"grad_norm": 8.285871505737305,
|
| 974 |
+
"learning_rate": 1.0006959664155903e-05,
|
| 975 |
+
"loss": 0.6347,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.6612855007473841,
|
| 980 |
+
"grad_norm": 6.742907524108887,
|
| 981 |
+
"learning_rate": 9.867770223999029e-06,
|
| 982 |
+
"loss": 0.6079,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.6732436472346786,
|
| 987 |
+
"grad_norm": 8.353972434997559,
|
| 988 |
+
"learning_rate": 9.728606402647706e-06,
|
| 989 |
+
"loss": 0.5911,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.6852017937219732,
|
| 994 |
+
"grad_norm": 7.566013813018799,
|
| 995 |
+
"learning_rate": 9.589495162341374e-06,
|
| 996 |
+
"loss": 0.5708,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.6971599402092674,
|
| 1001 |
+
"grad_norm": 8.332974433898926,
|
| 1002 |
+
"learning_rate": 9.450463455132159e-06,
|
| 1003 |
+
"loss": 0.5775,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.709118086696562,
|
| 1008 |
+
"grad_norm": 7.9301042556762695,
|
| 1009 |
+
"learning_rate": 9.311538217663084e-06,
|
| 1010 |
+
"loss": 0.6064,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.7210762331838565,
|
| 1015 |
+
"grad_norm": 8.32680892944336,
|
| 1016 |
+
"learning_rate": 9.172746365949245e-06,
|
| 1017 |
+
"loss": 0.604,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.733034379671151,
|
| 1022 |
+
"grad_norm": 7.546978950500488,
|
| 1023 |
+
"learning_rate": 9.034114790162952e-06,
|
| 1024 |
+
"loss": 0.6238,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.7449925261584456,
|
| 1029 |
+
"grad_norm": 7.25153923034668,
|
| 1030 |
+
"learning_rate": 8.89567034942393e-06,
|
| 1031 |
+
"loss": 0.6403,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.7569506726457398,
|
| 1036 |
+
"grad_norm": 8.115947723388672,
|
| 1037 |
+
"learning_rate": 8.75743986659549e-06,
|
| 1038 |
+
"loss": 0.6034,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.7689088191330344,
|
| 1043 |
+
"grad_norm": 12.475451469421387,
|
| 1044 |
+
"learning_rate": 8.619450123087758e-06,
|
| 1045 |
+
"loss": 0.5326,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.7808669656203289,
|
| 1050 |
+
"grad_norm": 9.76746940612793,
|
| 1051 |
+
"learning_rate": 8.48172785366892e-06,
|
| 1052 |
+
"loss": 0.6896,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.7928251121076233,
|
| 1057 |
+
"grad_norm": 9.600249290466309,
|
| 1058 |
+
"learning_rate": 8.344299741285486e-06,
|
| 1059 |
+
"loss": 0.6343,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.804783258594918,
|
| 1064 |
+
"grad_norm": 8.809874534606934,
|
| 1065 |
+
"learning_rate": 8.207192411892645e-06,
|
| 1066 |
+
"loss": 0.6169,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.8167414050822122,
|
| 1071 |
+
"grad_norm": 7.852496147155762,
|
| 1072 |
+
"learning_rate": 8.070432429295599e-06,
|
| 1073 |
+
"loss": 0.5506,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.8286995515695068,
|
| 1078 |
+
"grad_norm": 6.440410614013672,
|
| 1079 |
+
"learning_rate": 7.934046290002991e-06,
|
| 1080 |
+
"loss": 0.5423,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.8406576980568012,
|
| 1085 |
+
"grad_norm": 7.717318058013916,
|
| 1086 |
+
"learning_rate": 7.79806041809334e-06,
|
| 1087 |
+
"loss": 0.5229,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.8526158445440957,
|
| 1092 |
+
"grad_norm": 12.041263580322266,
|
| 1093 |
+
"learning_rate": 7.66250116009551e-06,
|
| 1094 |
+
"loss": 0.7032,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.86457399103139,
|
| 1099 |
+
"grad_norm": 7.217101097106934,
|
| 1100 |
+
"learning_rate": 7.5273947798842405e-06,
|
| 1101 |
+
"loss": 0.6158,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.8765321375186845,
|
| 1106 |
+
"grad_norm": 7.625624179840088,
|
| 1107 |
+
"learning_rate": 7.392767453591623e-06,
|
| 1108 |
+
"loss": 0.582,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.8884902840059792,
|
| 1113 |
+
"grad_norm": 11.00538158416748,
|
| 1114 |
+
"learning_rate": 7.2586452645356485e-06,
|
| 1115 |
+
"loss": 0.6334,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.9004484304932734,
|
| 1120 |
+
"grad_norm": 8.656449317932129,
|
| 1121 |
+
"learning_rate": 7.125054198166701e-06,
|
| 1122 |
+
"loss": 0.598,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.912406576980568,
|
| 1127 |
+
"grad_norm": 7.2763190269470215,
|
| 1128 |
+
"learning_rate": 6.992020137032988e-06,
|
| 1129 |
+
"loss": 0.5746,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.9243647234678625,
|
| 1134 |
+
"grad_norm": 6.870010852813721,
|
| 1135 |
+
"learning_rate": 6.859568855765986e-06,
|
| 1136 |
+
"loss": 0.5905,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.936322869955157,
|
| 1141 |
+
"grad_norm": 9.135017395019531,
|
| 1142 |
+
"learning_rate": 6.727726016086693e-06,
|
| 1143 |
+
"loss": 0.6315,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.9482810164424516,
|
| 1148 |
+
"grad_norm": 7.487800121307373,
|
| 1149 |
+
"learning_rate": 6.596517161833846e-06,
|
| 1150 |
+
"loss": 0.5313,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.9602391629297458,
|
| 1155 |
+
"grad_norm": 7.0159125328063965,
|
| 1156 |
+
"learning_rate": 6.465967714014927e-06,
|
| 1157 |
+
"loss": 0.5524,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.9721973094170404,
|
| 1162 |
+
"grad_norm": 9.8536376953125,
|
| 1163 |
+
"learning_rate": 6.33610296588097e-06,
|
| 1164 |
+
"loss": 0.6285,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.9841554559043348,
|
| 1169 |
+
"grad_norm": 10.726343154907227,
|
| 1170 |
+
"learning_rate": 6.206948078026154e-06,
|
| 1171 |
+
"loss": 0.6212,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.9961136023916293,
|
| 1176 |
+
"grad_norm": 6.811227321624756,
|
| 1177 |
+
"learning_rate": 6.078528073513041e-06,
|
| 1178 |
+
"loss": 0.5934,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.0071748878923765,
|
| 1183 |
+
"grad_norm": 6.4515862464904785,
|
| 1184 |
+
"learning_rate": 5.95086783302453e-06,
|
| 1185 |
+
"loss": 0.4341,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.019133034379671,
|
| 1190 |
+
"grad_norm": 7.675016403198242,
|
| 1191 |
+
"learning_rate": 5.823992090043334e-06,
|
| 1192 |
+
"loss": 0.3742,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.031091180866966,
|
| 1197 |
+
"grad_norm": 10.208675384521484,
|
| 1198 |
+
"learning_rate": 5.697925426059992e-06,
|
| 1199 |
+
"loss": 0.342,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.04304932735426,
|
| 1204 |
+
"grad_norm": 14.233214378356934,
|
| 1205 |
+
"learning_rate": 5.5726922658103795e-06,
|
| 1206 |
+
"loss": 0.3171,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.0550074738415547,
|
| 1211 |
+
"grad_norm": 20.338651657104492,
|
| 1212 |
+
"learning_rate": 5.448316872543509e-06,
|
| 1213 |
+
"loss": 0.3298,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.066965620328849,
|
| 1218 |
+
"grad_norm": 17.314680099487305,
|
| 1219 |
+
"learning_rate": 5.324823343320654e-06,
|
| 1220 |
+
"loss": 0.3816,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.0789237668161435,
|
| 1225 |
+
"grad_norm": 11.820718765258789,
|
| 1226 |
+
"learning_rate": 5.202235604346719e-06,
|
| 1227 |
+
"loss": 0.2167,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.0908819133034378,
|
| 1232 |
+
"grad_norm": 13.863101959228516,
|
| 1233 |
+
"learning_rate": 5.080577406334607e-06,
|
| 1234 |
+
"loss": 0.2743,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.1028400597907324,
|
| 1239 |
+
"grad_norm": 21.656572341918945,
|
| 1240 |
+
"learning_rate": 4.9598723199036865e-06,
|
| 1241 |
+
"loss": 0.2586,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.114798206278027,
|
| 1246 |
+
"grad_norm": 31.249801635742188,
|
| 1247 |
+
"learning_rate": 4.8401437310131146e-06,
|
| 1248 |
+
"loss": 0.2215,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.1267563527653213,
|
| 1253 |
+
"grad_norm": 12.971083641052246,
|
| 1254 |
+
"learning_rate": 4.721414836430894e-06,
|
| 1255 |
+
"loss": 0.3605,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.138714499252616,
|
| 1260 |
+
"grad_norm": 7.397335052490234,
|
| 1261 |
+
"learning_rate": 4.603708639239666e-06,
|
| 1262 |
+
"loss": 0.2441,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.15067264573991,
|
| 1267 |
+
"grad_norm": 9.318166732788086,
|
| 1268 |
+
"learning_rate": 4.487047944379964e-06,
|
| 1269 |
+
"loss": 0.2884,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.162630792227205,
|
| 1274 |
+
"grad_norm": 8.46785831451416,
|
| 1275 |
+
"learning_rate": 4.37145535423189e-06,
|
| 1276 |
+
"loss": 0.2701,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.1745889387144994,
|
| 1281 |
+
"grad_norm": 17.398710250854492,
|
| 1282 |
+
"learning_rate": 4.256953264236029e-06,
|
| 1283 |
+
"loss": 0.3419,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.1865470852017936,
|
| 1288 |
+
"grad_norm": 29.786914825439453,
|
| 1289 |
+
"learning_rate": 4.143563858554428e-06,
|
| 1290 |
+
"loss": 0.2488,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.1985052316890883,
|
| 1295 |
+
"grad_norm": 8.59508991241455,
|
| 1296 |
+
"learning_rate": 4.031309105772567e-06,
|
| 1297 |
+
"loss": 0.2555,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.2104633781763825,
|
| 1302 |
+
"grad_norm": 19.452116012573242,
|
| 1303 |
+
"learning_rate": 3.920210754643045e-06,
|
| 1304 |
+
"loss": 0.3394,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.222421524663677,
|
| 1309 |
+
"grad_norm": 17.935977935791016,
|
| 1310 |
+
"learning_rate": 3.8102903298718816e-06,
|
| 1311 |
+
"loss": 0.2825,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.234379671150972,
|
| 1316 |
+
"grad_norm": 13.720900535583496,
|
| 1317 |
+
"learning_rate": 3.70156912794822e-06,
|
| 1318 |
+
"loss": 0.2757,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.246337817638266,
|
| 1323 |
+
"grad_norm": 12.637280464172363,
|
| 1324 |
+
"learning_rate": 3.594068213018249e-06,
|
| 1325 |
+
"loss": 0.1822,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.2582959641255607,
|
| 1330 |
+
"grad_norm": 12.480120658874512,
|
| 1331 |
+
"learning_rate": 3.4878084128041366e-06,
|
| 1332 |
+
"loss": 0.2021,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.270254110612855,
|
| 1337 |
+
"grad_norm": 27.798078536987305,
|
| 1338 |
+
"learning_rate": 3.382810314568773e-06,
|
| 1339 |
+
"loss": 0.206,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.2822122571001495,
|
| 1344 |
+
"grad_norm": 30.139259338378906,
|
| 1345 |
+
"learning_rate": 3.279094261127096e-06,
|
| 1346 |
+
"loss": 0.2839,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.2941704035874437,
|
| 1351 |
+
"grad_norm": 10.668841361999512,
|
| 1352 |
+
"learning_rate": 3.1766803469047846e-06,
|
| 1353 |
+
"loss": 0.3664,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.3061285500747384,
|
| 1358 |
+
"grad_norm": 23.277801513671875,
|
| 1359 |
+
"learning_rate": 3.075588414045071e-06,
|
| 1360 |
+
"loss": 0.2859,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.318086696562033,
|
| 1365 |
+
"grad_norm": 21.904115676879883,
|
| 1366 |
+
"learning_rate": 2.975838048564432e-06,
|
| 1367 |
+
"loss": 0.2693,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.3300448430493272,
|
| 1372 |
+
"grad_norm": 21.524389266967773,
|
| 1373 |
+
"learning_rate": 2.877448576557904e-06,
|
| 1374 |
+
"loss": 0.3482,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.342002989536622,
|
| 1379 |
+
"grad_norm": 17.36709976196289,
|
| 1380 |
+
"learning_rate": 2.780439060454756e-06,
|
| 1381 |
+
"loss": 0.3373,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.353961136023916,
|
| 1386 |
+
"grad_norm": 13.623261451721191,
|
| 1387 |
+
"learning_rate": 2.684828295325247e-06,
|
| 1388 |
+
"loss": 0.3022,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.3659192825112108,
|
| 1393 |
+
"grad_norm": 30.28055191040039,
|
| 1394 |
+
"learning_rate": 2.590634805239183e-06,
|
| 1395 |
+
"loss": 0.2011,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.3778774289985054,
|
| 1400 |
+
"grad_norm": 20.75056266784668,
|
| 1401 |
+
"learning_rate": 2.4978768396769824e-06,
|
| 1402 |
+
"loss": 0.2378,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.3898355754857996,
|
| 1407 |
+
"grad_norm": 5.741615295410156,
|
| 1408 |
+
"learning_rate": 2.4065723699939203e-06,
|
| 1409 |
+
"loss": 0.2745,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.4017937219730943,
|
| 1414 |
+
"grad_norm": 13.834797859191895,
|
| 1415 |
+
"learning_rate": 2.316739085938309e-06,
|
| 1416 |
+
"loss": 0.2379,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.4137518684603885,
|
| 1421 |
+
"grad_norm": 24.6688232421875,
|
| 1422 |
+
"learning_rate": 2.228394392224167e-06,
|
| 1423 |
+
"loss": 0.3022,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.425710014947683,
|
| 1428 |
+
"grad_norm": 27.61370086669922,
|
| 1429 |
+
"learning_rate": 2.1415554051591747e-06,
|
| 1430 |
+
"loss": 0.2418,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.4376681614349778,
|
| 1435 |
+
"grad_norm": 25.60787010192871,
|
| 1436 |
+
"learning_rate": 2.056238949328476e-06,
|
| 1437 |
+
"loss": 0.2244,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.449626307922272,
|
| 1442 |
+
"grad_norm": 25.809080123901367,
|
| 1443 |
+
"learning_rate": 1.9724615543349946e-06,
|
| 1444 |
+
"loss": 0.2383,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.4615844544095666,
|
| 1449 |
+
"grad_norm": 17.545751571655273,
|
| 1450 |
+
"learning_rate": 1.8902394515969335e-06,
|
| 1451 |
+
"loss": 0.355,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.473542600896861,
|
| 1456 |
+
"grad_norm": 34.05633544921875,
|
| 1457 |
+
"learning_rate": 1.8095885712030104e-06,
|
| 1458 |
+
"loss": 0.2825,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.4855007473841555,
|
| 1463 |
+
"grad_norm": 27.805438995361328,
|
| 1464 |
+
"learning_rate": 1.7305245388260827e-06,
|
| 1465 |
+
"loss": 0.2491,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.4974588938714497,
|
| 1470 |
+
"grad_norm": 25.247135162353516,
|
| 1471 |
+
"learning_rate": 1.6530626726957876e-06,
|
| 1472 |
+
"loss": 0.2853,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.5094170403587444,
|
| 1477 |
+
"grad_norm": 25.348655700683594,
|
| 1478 |
+
"learning_rate": 1.5772179806306742e-06,
|
| 1479 |
+
"loss": 0.3365,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.521375186846039,
|
| 1484 |
+
"grad_norm": 29.910663604736328,
|
| 1485 |
+
"learning_rate": 1.5030051571305638e-06,
|
| 1486 |
+
"loss": 0.3853,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.533333333333333,
|
| 1491 |
+
"grad_norm": 15.089653968811035,
|
| 1492 |
+
"learning_rate": 1.4304385805295384e-06,
|
| 1493 |
+
"loss": 0.2184,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.545291479820628,
|
| 1498 |
+
"grad_norm": 13.370139122009277,
|
| 1499 |
+
"learning_rate": 1.3595323102102232e-06,
|
| 1500 |
+
"loss": 0.2342,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.5572496263079225,
|
| 1505 |
+
"grad_norm": 30.78978157043457,
|
| 1506 |
+
"learning_rate": 1.290300083879875e-06,
|
| 1507 |
+
"loss": 0.2144,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.5692077727952167,
|
| 1512 |
+
"grad_norm": 15.941715240478516,
|
| 1513 |
+
"learning_rate": 1.2227553149087445e-06,
|
| 1514 |
+
"loss": 0.1547,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.581165919282511,
|
| 1519 |
+
"grad_norm": 40.60525131225586,
|
| 1520 |
+
"learning_rate": 1.1569110897313352e-06,
|
| 1521 |
+
"loss": 0.2678,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.5931240657698056,
|
| 1526 |
+
"grad_norm": 16.133296966552734,
|
| 1527 |
+
"learning_rate": 1.0927801653109681e-06,
|
| 1528 |
+
"loss": 0.2991,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.6050822122571002,
|
| 1533 |
+
"grad_norm": 16.58081817626953,
|
| 1534 |
+
"learning_rate": 1.0303749666681806e-06,
|
| 1535 |
+
"loss": 0.283,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.6170403587443944,
|
| 1540 |
+
"grad_norm": 25.13290786743164,
|
| 1541 |
+
"learning_rate": 9.69707584473457e-07,
|
| 1542 |
+
"loss": 0.1776,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.628998505231689,
|
| 1547 |
+
"grad_norm": 30.819944381713867,
|
| 1548 |
+
"learning_rate": 9.107897727047277e-07,
|
| 1549 |
+
"loss": 0.3401,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.6409566517189837,
|
| 1554 |
+
"grad_norm": 12.338361740112305,
|
| 1555 |
+
"learning_rate": 8.53632946370081e-07,
|
| 1556 |
+
"loss": 0.2611,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.652914798206278,
|
| 1561 |
+
"grad_norm": 10.503249168395996,
|
| 1562 |
+
"learning_rate": 7.98248179296196e-07,
|
| 1563 |
+
"loss": 0.3805,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.6648729446935726,
|
| 1568 |
+
"grad_norm": 15.157049179077148,
|
| 1569 |
+
"learning_rate": 7.446462019828182e-07,
|
| 1570 |
+
"loss": 0.2951,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.676831091180867,
|
| 1575 |
+
"grad_norm": 12.519427299499512,
|
| 1576 |
+
"learning_rate": 6.928373995238046e-07,
|
| 1577 |
+
"loss": 0.2488,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.6887892376681615,
|
| 1582 |
+
"grad_norm": 28.905954360961914,
|
| 1583 |
+
"learning_rate": 6.428318095950648e-07,
|
| 1584 |
+
"loss": 0.2617,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.7007473841554557,
|
| 1589 |
+
"grad_norm": 19.79918098449707,
|
| 1590 |
+
"learning_rate": 5.94639120509799e-07,
|
| 1591 |
+
"loss": 0.2696,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.7127055306427503,
|
| 1596 |
+
"grad_norm": 23.255956649780273,
|
| 1597 |
+
"learning_rate": 5.48268669341463e-07,
|
| 1598 |
+
"loss": 0.2279,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.724663677130045,
|
| 1603 |
+
"grad_norm": 24.377010345458984,
|
| 1604 |
+
"learning_rate": 5.03729440114743e-07,
|
| 1605 |
+
"loss": 0.2196,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.736621823617339,
|
| 1610 |
+
"grad_norm": 14.183038711547852,
|
| 1611 |
+
"learning_rate": 4.610300620649577e-07,
|
| 1612 |
+
"loss": 0.2404,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.748579970104634,
|
| 1617 |
+
"grad_norm": 16.39776611328125,
|
| 1618 |
+
"learning_rate": 4.201788079661928e-07,
|
| 1619 |
+
"loss": 0.2522,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.7605381165919285,
|
| 1624 |
+
"grad_norm": 10.571599960327148,
|
| 1625 |
+
"learning_rate": 3.8118359252848237e-07,
|
| 1626 |
+
"loss": 0.1902,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.7724962630792227,
|
| 1631 |
+
"grad_norm": 23.17461585998535,
|
| 1632 |
+
"learning_rate": 3.440519708643919e-07,
|
| 1633 |
+
"loss": 0.2229,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.7844544095665174,
|
| 1638 |
+
"grad_norm": 34.10865020751953,
|
| 1639 |
+
"learning_rate": 3.087911370252483e-07,
|
| 1640 |
+
"loss": 0.3423,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.7964125560538116,
|
| 1645 |
+
"grad_norm": 14.227197647094727,
|
| 1646 |
+
"learning_rate": 2.754079226073325e-07,
|
| 1647 |
+
"loss": 0.2804,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.808370702541106,
|
| 1652 |
+
"grad_norm": 19.29047966003418,
|
| 1653 |
+
"learning_rate": 2.4390879542829484e-07,
|
| 1654 |
+
"loss": 0.2629,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.8203288490284004,
|
| 1659 |
+
"grad_norm": 16.184885025024414,
|
| 1660 |
+
"learning_rate": 2.1429985827404853e-07,
|
| 1661 |
+
"loss": 0.1936,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.832286995515695,
|
| 1666 |
+
"grad_norm": 28.002437591552734,
|
| 1667 |
+
"learning_rate": 1.8658684771639236e-07,
|
| 1668 |
+
"loss": 0.2346,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.8442451420029897,
|
| 1673 |
+
"grad_norm": 26.8525333404541,
|
| 1674 |
+
"learning_rate": 1.60775133001575e-07,
|
| 1675 |
+
"loss": 0.3029,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.856203288490284,
|
| 1680 |
+
"grad_norm": 12.348111152648926,
|
| 1681 |
+
"learning_rate": 1.368697150100362e-07,
|
| 1682 |
+
"loss": 0.1942,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.8681614349775786,
|
| 1687 |
+
"grad_norm": 21.351673126220703,
|
| 1688 |
+
"learning_rate": 1.1487522528751404e-07,
|
| 1689 |
+
"loss": 0.235,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.880119581464873,
|
| 1694 |
+
"grad_norm": 19.268718719482422,
|
| 1695 |
+
"learning_rate": 9.479592514770485e-08,
|
| 1696 |
+
"loss": 0.2418,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.8920777279521674,
|
| 1701 |
+
"grad_norm": 14.415555000305176,
|
| 1702 |
+
"learning_rate": 7.663570484665706e-08,
|
| 1703 |
+
"loss": 0.2467,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.9040358744394617,
|
| 1708 |
+
"grad_norm": 23.162002563476562,
|
| 1709 |
+
"learning_rate": 6.039808282905735e-08,
|
| 1710 |
+
"loss": 0.2252,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.9159940209267563,
|
| 1715 |
+
"grad_norm": 22.265932083129883,
|
| 1716 |
+
"learning_rate": 4.608620504655048e-08,
|
| 1717 |
+
"loss": 0.2511,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.927952167414051,
|
| 1722 |
+
"grad_norm": 14.412714004516602,
|
| 1723 |
+
"learning_rate": 3.3702844348226796e-08,
|
| 1724 |
+
"loss": 0.324,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.939910313901345,
|
| 1729 |
+
"grad_norm": 30.541522979736328,
|
| 1730 |
+
"learning_rate": 2.3250399943398616e-08,
|
| 1731 |
+
"loss": 0.3021,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.95186846038864,
|
| 1736 |
+
"grad_norm": 19.404844284057617,
|
| 1737 |
+
"learning_rate": 1.4730896936764327e-08,
|
| 1738 |
+
"loss": 0.2123,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.9638266068759345,
|
| 1743 |
+
"grad_norm": 23.300127029418945,
|
| 1744 |
+
"learning_rate": 8.145985936057754e-09,
|
| 1745 |
+
"loss": 0.2354,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.9757847533632287,
|
| 1750 |
+
"grad_norm": 32.36324691772461,
|
| 1751 |
+
"learning_rate": 3.496942732253983e-09,
|
| 1752 |
+
"loss": 0.3228,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.9877428998505233,
|
| 1757 |
+
"grad_norm": 16.98558235168457,
|
| 1758 |
+
"learning_rate": 7.846680523837525e-10,
|
| 1759 |
+
"loss": 0.1955,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
}
|
| 1762 |
+
],
|
| 1763 |
+
"logging_steps": 10,
|
| 1764 |
+
"max_steps": 2508,
|
| 1765 |
+
"num_input_tokens_seen": 0,
|
| 1766 |
+
"num_train_epochs": 3,
|
| 1767 |
+
"save_steps": 1000,
|
| 1768 |
+
"stateful_callbacks": {
|
| 1769 |
+
"TrainerControl": {
|
| 1770 |
+
"args": {
|
| 1771 |
+
"should_epoch_stop": false,
|
| 1772 |
+
"should_evaluate": false,
|
| 1773 |
+
"should_log": false,
|
| 1774 |
+
"should_save": true,
|
| 1775 |
+
"should_training_stop": true
|
| 1776 |
+
},
|
| 1777 |
+
"attributes": {}
|
| 1778 |
+
}
|
| 1779 |
+
},
|
| 1780 |
+
"total_flos": 0.0,
|
| 1781 |
+
"train_batch_size": 2,
|
| 1782 |
+
"trial_name": null,
|
| 1783 |
+
"trial_params": null
|
| 1784 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb09144fb0a69db6ab229f96858510cff49903cb864aa8705f9ed1dec6a073fe
|
| 3 |
+
size 5752
|
value_head.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:340a99c68c579e86af7740a43705a1311ed3fa3bf2132e1c2aba08ab0879834b
|
| 3 |
+
size 16588
|