jordan2889/classify-phishing_real_1
Browse files- README.md +96 -196
- config.json +42 -0
- model.safetensors +3 -0
- trainer_state.json +2499 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,199 +1,99 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
###
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 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]
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: albert/albert-base-v2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
model-index:
|
| 12 |
+
- name: classify-phishing_real_1
|
| 13 |
+
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# classify-phishing_real_1
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.1185
|
| 24 |
+
- Accuracy: 0.9645
|
| 25 |
+
- F1: 0.9645
|
| 26 |
+
- Precision: 0.9645
|
| 27 |
+
- Recall: 0.9645
|
| 28 |
+
- Accuracy Label 0: 0.9708
|
| 29 |
+
- Accuracy Label 1: 0.9559
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 2e-05
|
| 49 |
+
- train_batch_size: 32
|
| 50 |
+
- eval_batch_size: 32
|
| 51 |
+
- seed: 42
|
| 52 |
+
- gradient_accumulation_steps: 2
|
| 53 |
+
- total_train_batch_size: 64
|
| 54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
+
- lr_scheduler_type: linear
|
| 56 |
+
- lr_scheduler_warmup_steps: 500
|
| 57 |
+
- num_epochs: 3
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Accuracy Label 0 | Accuracy Label 1 |
|
| 62 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:----------------:|:----------------:|
|
| 63 |
+
| 0.4991 | 0.1030 | 100 | 0.4748 | 0.7925 | 0.7819 | 0.8136 | 0.7925 | 0.9508 | 0.5747 |
|
| 64 |
+
| 0.3087 | 0.2060 | 200 | 0.3052 | 0.8799 | 0.8793 | 0.8799 | 0.8799 | 0.9189 | 0.8262 |
|
| 65 |
+
| 0.2974 | 0.3090 | 300 | 0.2390 | 0.9093 | 0.9094 | 0.9095 | 0.9093 | 0.9181 | 0.8972 |
|
| 66 |
+
| 0.2644 | 0.4119 | 400 | 0.3068 | 0.8663 | 0.8670 | 0.8887 | 0.8663 | 0.7899 | 0.9715 |
|
| 67 |
+
| 0.223 | 0.5149 | 500 | 0.2122 | 0.9154 | 0.9158 | 0.9195 | 0.9154 | 0.8905 | 0.9495 |
|
| 68 |
+
| 0.215 | 0.6179 | 600 | 0.2011 | 0.9229 | 0.9222 | 0.9252 | 0.9229 | 0.9714 | 0.8561 |
|
| 69 |
+
| 0.1419 | 0.7209 | 700 | 0.1836 | 0.9305 | 0.9300 | 0.9318 | 0.9305 | 0.9690 | 0.8775 |
|
| 70 |
+
| 0.1511 | 0.8239 | 800 | 0.1828 | 0.9305 | 0.9308 | 0.9327 | 0.9305 | 0.9145 | 0.9526 |
|
| 71 |
+
| 0.173 | 0.9269 | 900 | 0.1544 | 0.9430 | 0.9428 | 0.9433 | 0.9430 | 0.9666 | 0.9107 |
|
| 72 |
+
| 0.0986 | 1.0299 | 1000 | 0.1513 | 0.9429 | 0.9430 | 0.9435 | 0.9429 | 0.9384 | 0.9491 |
|
| 73 |
+
| 0.1403 | 1.1329 | 1100 | 0.1515 | 0.9426 | 0.9429 | 0.9444 | 0.9426 | 0.9278 | 0.9631 |
|
| 74 |
+
| 0.1133 | 1.2358 | 1200 | 0.1394 | 0.9475 | 0.9475 | 0.9475 | 0.9475 | 0.9531 | 0.9397 |
|
| 75 |
+
| 0.1117 | 1.3388 | 1300 | 0.1525 | 0.9457 | 0.9459 | 0.9467 | 0.9457 | 0.9371 | 0.9576 |
|
| 76 |
+
| 0.1277 | 1.4418 | 1400 | 0.1311 | 0.9490 | 0.9491 | 0.9492 | 0.9490 | 0.9501 | 0.9475 |
|
| 77 |
+
| 0.0886 | 1.5448 | 1500 | 0.1375 | 0.9503 | 0.9503 | 0.9503 | 0.9503 | 0.9628 | 0.9331 |
|
| 78 |
+
| 0.1273 | 1.6478 | 1600 | 0.1297 | 0.9533 | 0.9533 | 0.9535 | 0.9533 | 0.9536 | 0.9529 |
|
| 79 |
+
| 0.1102 | 1.7508 | 1700 | 0.1136 | 0.9578 | 0.9578 | 0.9578 | 0.9578 | 0.9637 | 0.9498 |
|
| 80 |
+
| 0.0793 | 1.8538 | 1800 | 0.1269 | 0.9562 | 0.9561 | 0.9563 | 0.9562 | 0.9718 | 0.9348 |
|
| 81 |
+
| 0.0995 | 1.9567 | 1900 | 0.1129 | 0.9591 | 0.9590 | 0.9591 | 0.9591 | 0.9702 | 0.9437 |
|
| 82 |
+
| 0.0846 | 2.0597 | 2000 | 0.1362 | 0.9533 | 0.9534 | 0.9543 | 0.9533 | 0.9422 | 0.9685 |
|
| 83 |
+
| 0.096 | 2.1627 | 2100 | 0.1383 | 0.9563 | 0.9564 | 0.9572 | 0.9563 | 0.9467 | 0.9696 |
|
| 84 |
+
| 0.0797 | 2.2657 | 2200 | 0.1137 | 0.9620 | 0.9619 | 0.9619 | 0.9620 | 0.9711 | 0.9494 |
|
| 85 |
+
| 0.0602 | 2.3687 | 2300 | 0.1211 | 0.9609 | 0.9609 | 0.9609 | 0.9609 | 0.9664 | 0.9532 |
|
| 86 |
+
| 0.0951 | 2.4717 | 2400 | 0.1194 | 0.9614 | 0.9615 | 0.9615 | 0.9614 | 0.9628 | 0.9596 |
|
| 87 |
+
| 0.0343 | 2.5747 | 2500 | 0.1237 | 0.9629 | 0.9629 | 0.9630 | 0.9629 | 0.9624 | 0.9634 |
|
| 88 |
+
| 0.0512 | 2.6777 | 2600 | 0.1263 | 0.9625 | 0.9625 | 0.9625 | 0.9625 | 0.9738 | 0.9471 |
|
| 89 |
+
| 0.0532 | 2.7806 | 2700 | 0.1229 | 0.9633 | 0.9633 | 0.9633 | 0.9633 | 0.9706 | 0.9533 |
|
| 90 |
+
| 0.0673 | 2.8836 | 2800 | 0.1206 | 0.9644 | 0.9644 | 0.9644 | 0.9644 | 0.9679 | 0.9596 |
|
| 91 |
+
| 0.0209 | 2.9866 | 2900 | 0.1185 | 0.9645 | 0.9645 | 0.9645 | 0.9645 | 0.9709 | 0.9556 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
### Framework versions
|
| 95 |
+
|
| 96 |
+
- Transformers 4.42.3
|
| 97 |
+
- Pytorch 2.2.1
|
| 98 |
+
- Datasets 2.20.0
|
| 99 |
+
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "albert/albert-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"AlbertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout_prob": 0.1,
|
| 9 |
+
"down_scale_factor": 1,
|
| 10 |
+
"embedding_size": 128,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
+
"gap_size": 0,
|
| 13 |
+
"hidden_act": "gelu_new",
|
| 14 |
+
"hidden_dropout_prob": 0,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "benign",
|
| 18 |
+
"1": "phishing"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"inner_group_num": 1,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"benign": 0,
|
| 25 |
+
"phishing": 1
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-12,
|
| 28 |
+
"max_position_embeddings": 512,
|
| 29 |
+
"model_type": "albert",
|
| 30 |
+
"net_structure_type": 0,
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_hidden_groups": 1,
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"num_memory_blocks": 0,
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"position_embedding_type": "absolute",
|
| 37 |
+
"problem_type": "single_label_classification",
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.42.3",
|
| 40 |
+
"type_vocab_size": 2,
|
| 41 |
+
"vocab_size": 30000
|
| 42 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18b62ebe1c69a653921d7a9bca3909dab9ff269b681ad1022e0433810ee7cfe8
|
| 3 |
+
size 46743912
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2499 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2913,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.010298661174047374,
|
| 13 |
+
"grad_norm": 11.615089416503906,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 0.6748,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02059732234809475,
|
| 20 |
+
"grad_norm": 10.92617130279541,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 0.6647,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.030895983522142123,
|
| 27 |
+
"grad_norm": 10.422063827514648,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 0.6572,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0411946446961895,
|
| 34 |
+
"grad_norm": 11.15770149230957,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 0.6352,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05149330587023687,
|
| 41 |
+
"grad_norm": 9.185620307922363,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 0.6052,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.061791967044284246,
|
| 48 |
+
"grad_norm": 9.457632064819336,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 0.5875,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07209062821833162,
|
| 55 |
+
"grad_norm": 10.167529106140137,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 0.5659,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.082389289392379,
|
| 62 |
+
"grad_norm": 13.378604888916016,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 0.5659,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09268795056642637,
|
| 69 |
+
"grad_norm": 17.715898513793945,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 0.5147,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.10298661174047374,
|
| 76 |
+
"grad_norm": 16.888174057006836,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 0.4991,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.10298661174047374,
|
| 83 |
+
"eval_accuracy": 0.7925463439752832,
|
| 84 |
+
"eval_accuracy_label_0": 0.9507723080342261,
|
| 85 |
+
"eval_accuracy_label_1": 0.5747284687165366,
|
| 86 |
+
"eval_f1": 0.7818901179048853,
|
| 87 |
+
"eval_loss": 0.47476595640182495,
|
| 88 |
+
"eval_precision": 0.8135697505549326,
|
| 89 |
+
"eval_recall": 0.7925463439752832,
|
| 90 |
+
"eval_runtime": 28.6334,
|
| 91 |
+
"eval_samples_per_second": 542.583,
|
| 92 |
+
"eval_steps_per_second": 16.973,
|
| 93 |
+
"step": 100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.11328527291452112,
|
| 97 |
+
"grad_norm": 12.777868270874023,
|
| 98 |
+
"learning_rate": 4.4e-06,
|
| 99 |
+
"loss": 0.4864,
|
| 100 |
+
"step": 110
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.12358393408856849,
|
| 104 |
+
"grad_norm": 14.114547729492188,
|
| 105 |
+
"learning_rate": 4.800000000000001e-06,
|
| 106 |
+
"loss": 0.437,
|
| 107 |
+
"step": 120
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.13388259526261587,
|
| 111 |
+
"grad_norm": 19.731557846069336,
|
| 112 |
+
"learning_rate": 5.2e-06,
|
| 113 |
+
"loss": 0.409,
|
| 114 |
+
"step": 130
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.14418125643666324,
|
| 118 |
+
"grad_norm": 14.552102088928223,
|
| 119 |
+
"learning_rate": 5.600000000000001e-06,
|
| 120 |
+
"loss": 0.4041,
|
| 121 |
+
"step": 140
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.15447991761071062,
|
| 125 |
+
"grad_norm": 13.959667205810547,
|
| 126 |
+
"learning_rate": 6e-06,
|
| 127 |
+
"loss": 0.3836,
|
| 128 |
+
"step": 150
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.164778578784758,
|
| 132 |
+
"grad_norm": 14.573174476623535,
|
| 133 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 134 |
+
"loss": 0.3685,
|
| 135 |
+
"step": 160
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.17507723995880536,
|
| 139 |
+
"grad_norm": 16.22774887084961,
|
| 140 |
+
"learning_rate": 6.800000000000001e-06,
|
| 141 |
+
"loss": 0.3229,
|
| 142 |
+
"step": 170
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.18537590113285274,
|
| 146 |
+
"grad_norm": 19.044815063476562,
|
| 147 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 148 |
+
"loss": 0.3893,
|
| 149 |
+
"step": 180
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1956745623069001,
|
| 153 |
+
"grad_norm": 45.681358337402344,
|
| 154 |
+
"learning_rate": 7.600000000000001e-06,
|
| 155 |
+
"loss": 0.304,
|
| 156 |
+
"step": 190
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2059732234809475,
|
| 160 |
+
"grad_norm": 29.214599609375,
|
| 161 |
+
"learning_rate": 8.000000000000001e-06,
|
| 162 |
+
"loss": 0.3087,
|
| 163 |
+
"step": 200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2059732234809475,
|
| 167 |
+
"eval_accuracy": 0.8798918640576725,
|
| 168 |
+
"eval_accuracy_label_0": 0.9188798755417269,
|
| 169 |
+
"eval_accuracy_label_1": 0.8262199785834481,
|
| 170 |
+
"eval_f1": 0.8792919938020355,
|
| 171 |
+
"eval_loss": 0.3051721453666687,
|
| 172 |
+
"eval_precision": 0.8799368067929555,
|
| 173 |
+
"eval_recall": 0.8798918640576725,
|
| 174 |
+
"eval_runtime": 28.5459,
|
| 175 |
+
"eval_samples_per_second": 544.247,
|
| 176 |
+
"eval_steps_per_second": 17.025,
|
| 177 |
+
"step": 200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.21627188465499486,
|
| 181 |
+
"grad_norm": 15.713203430175781,
|
| 182 |
+
"learning_rate": 8.400000000000001e-06,
|
| 183 |
+
"loss": 0.3222,
|
| 184 |
+
"step": 210
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.22657054582904224,
|
| 188 |
+
"grad_norm": 15.416417121887207,
|
| 189 |
+
"learning_rate": 8.8e-06,
|
| 190 |
+
"loss": 0.3231,
|
| 191 |
+
"step": 220
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2368692070030896,
|
| 195 |
+
"grad_norm": 15.711112022399902,
|
| 196 |
+
"learning_rate": 9.200000000000002e-06,
|
| 197 |
+
"loss": 0.2795,
|
| 198 |
+
"step": 230
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.24716786817713698,
|
| 202 |
+
"grad_norm": 36.23487854003906,
|
| 203 |
+
"learning_rate": 9.600000000000001e-06,
|
| 204 |
+
"loss": 0.3044,
|
| 205 |
+
"step": 240
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.25746652935118436,
|
| 209 |
+
"grad_norm": 34.81510543823242,
|
| 210 |
+
"learning_rate": 1e-05,
|
| 211 |
+
"loss": 0.2941,
|
| 212 |
+
"step": 250
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.26776519052523173,
|
| 216 |
+
"grad_norm": 27.128246307373047,
|
| 217 |
+
"learning_rate": 1.04e-05,
|
| 218 |
+
"loss": 0.2958,
|
| 219 |
+
"step": 260
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2780638516992791,
|
| 223 |
+
"grad_norm": 321.4391174316406,
|
| 224 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 225 |
+
"loss": 0.3246,
|
| 226 |
+
"step": 270
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2883625128733265,
|
| 230 |
+
"grad_norm": 19.725854873657227,
|
| 231 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 232 |
+
"loss": 0.2937,
|
| 233 |
+
"step": 280
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.29866117404737386,
|
| 237 |
+
"grad_norm": 18.257448196411133,
|
| 238 |
+
"learning_rate": 1.16e-05,
|
| 239 |
+
"loss": 0.2814,
|
| 240 |
+
"step": 290
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.30895983522142123,
|
| 244 |
+
"grad_norm": 13.747376441955566,
|
| 245 |
+
"learning_rate": 1.2e-05,
|
| 246 |
+
"loss": 0.2974,
|
| 247 |
+
"step": 300
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.30895983522142123,
|
| 251 |
+
"eval_accuracy": 0.9093074150360453,
|
| 252 |
+
"eval_accuracy_label_0": 0.9181020113345927,
|
| 253 |
+
"eval_accuracy_label_1": 0.8972005507113354,
|
| 254 |
+
"eval_f1": 0.9093673855692345,
|
| 255 |
+
"eval_loss": 0.23899167776107788,
|
| 256 |
+
"eval_precision": 0.9094597674517649,
|
| 257 |
+
"eval_recall": 0.9093074150360453,
|
| 258 |
+
"eval_runtime": 28.6387,
|
| 259 |
+
"eval_samples_per_second": 542.482,
|
| 260 |
+
"eval_steps_per_second": 16.97,
|
| 261 |
+
"step": 300
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.3192584963954686,
|
| 265 |
+
"grad_norm": 33.30331039428711,
|
| 266 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 267 |
+
"loss": 0.2292,
|
| 268 |
+
"step": 310
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.329557157569516,
|
| 272 |
+
"grad_norm": 11.742475509643555,
|
| 273 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 274 |
+
"loss": 0.2624,
|
| 275 |
+
"step": 320
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.33985581874356335,
|
| 279 |
+
"grad_norm": 20.29306411743164,
|
| 280 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 281 |
+
"loss": 0.2521,
|
| 282 |
+
"step": 330
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.35015447991761073,
|
| 286 |
+
"grad_norm": 30.528644561767578,
|
| 287 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 288 |
+
"loss": 0.2194,
|
| 289 |
+
"step": 340
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3604531410916581,
|
| 293 |
+
"grad_norm": 12.220970153808594,
|
| 294 |
+
"learning_rate": 1.4e-05,
|
| 295 |
+
"loss": 0.2429,
|
| 296 |
+
"step": 350
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3707518022657055,
|
| 300 |
+
"grad_norm": 24.19580841064453,
|
| 301 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 302 |
+
"loss": 0.2087,
|
| 303 |
+
"step": 360
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.38105046343975285,
|
| 307 |
+
"grad_norm": 23.321378707885742,
|
| 308 |
+
"learning_rate": 1.48e-05,
|
| 309 |
+
"loss": 0.286,
|
| 310 |
+
"step": 370
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.3913491246138002,
|
| 314 |
+
"grad_norm": 32.3515625,
|
| 315 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 316 |
+
"loss": 0.2545,
|
| 317 |
+
"step": 380
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.4016477857878476,
|
| 321 |
+
"grad_norm": 23.015567779541016,
|
| 322 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 323 |
+
"loss": 0.2302,
|
| 324 |
+
"step": 390
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.411946446961895,
|
| 328 |
+
"grad_norm": 62.823158264160156,
|
| 329 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 330 |
+
"loss": 0.2644,
|
| 331 |
+
"step": 400
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.411946446961895,
|
| 335 |
+
"eval_accuracy": 0.8663105046343975,
|
| 336 |
+
"eval_accuracy_label_0": 0.789865540615624,
|
| 337 |
+
"eval_accuracy_label_1": 0.9715465810004589,
|
| 338 |
+
"eval_f1": 0.8670270957842099,
|
| 339 |
+
"eval_loss": 0.3067936897277832,
|
| 340 |
+
"eval_precision": 0.8886912845830801,
|
| 341 |
+
"eval_recall": 0.8663105046343975,
|
| 342 |
+
"eval_runtime": 28.5898,
|
| 343 |
+
"eval_samples_per_second": 543.41,
|
| 344 |
+
"eval_steps_per_second": 16.999,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.42224510813594235,
|
| 349 |
+
"grad_norm": 17.351797103881836,
|
| 350 |
+
"learning_rate": 1.64e-05,
|
| 351 |
+
"loss": 0.2175,
|
| 352 |
+
"step": 410
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.4325437693099897,
|
| 356 |
+
"grad_norm": 17.912687301635742,
|
| 357 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 358 |
+
"loss": 0.2392,
|
| 359 |
+
"step": 420
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.4428424304840371,
|
| 363 |
+
"grad_norm": 42.50285720825195,
|
| 364 |
+
"learning_rate": 1.72e-05,
|
| 365 |
+
"loss": 0.3647,
|
| 366 |
+
"step": 430
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.45314109165808447,
|
| 370 |
+
"grad_norm": 16.606185913085938,
|
| 371 |
+
"learning_rate": 1.76e-05,
|
| 372 |
+
"loss": 0.2354,
|
| 373 |
+
"step": 440
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.46343975283213185,
|
| 377 |
+
"grad_norm": 16.927104949951172,
|
| 378 |
+
"learning_rate": 1.8e-05,
|
| 379 |
+
"loss": 0.219,
|
| 380 |
+
"step": 450
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.4737384140061792,
|
| 384 |
+
"grad_norm": 21.259096145629883,
|
| 385 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 386 |
+
"loss": 0.2094,
|
| 387 |
+
"step": 460
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.4840370751802266,
|
| 391 |
+
"grad_norm": 24.833669662475586,
|
| 392 |
+
"learning_rate": 1.88e-05,
|
| 393 |
+
"loss": 0.2152,
|
| 394 |
+
"step": 470
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.49433573635427397,
|
| 398 |
+
"grad_norm": 16.225502014160156,
|
| 399 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 400 |
+
"loss": 0.2355,
|
| 401 |
+
"step": 480
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5046343975283213,
|
| 405 |
+
"grad_norm": 22.97551918029785,
|
| 406 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 407 |
+
"loss": 0.2245,
|
| 408 |
+
"step": 490
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.5149330587023687,
|
| 412 |
+
"grad_norm": 6.800662517547607,
|
| 413 |
+
"learning_rate": 2e-05,
|
| 414 |
+
"loss": 0.223,
|
| 415 |
+
"step": 500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5149330587023687,
|
| 419 |
+
"eval_accuracy": 0.9153578784757982,
|
| 420 |
+
"eval_accuracy_label_0": 0.8905433937104122,
|
| 421 |
+
"eval_accuracy_label_1": 0.9495181275814594,
|
| 422 |
+
"eval_f1": 0.9157786272541746,
|
| 423 |
+
"eval_loss": 0.2122022956609726,
|
| 424 |
+
"eval_precision": 0.9194646287255005,
|
| 425 |
+
"eval_recall": 0.9153578784757982,
|
| 426 |
+
"eval_runtime": 28.5689,
|
| 427 |
+
"eval_samples_per_second": 543.809,
|
| 428 |
+
"eval_steps_per_second": 17.012,
|
| 429 |
+
"step": 500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.525231719876416,
|
| 433 |
+
"grad_norm": 8.790451049804688,
|
| 434 |
+
"learning_rate": 1.9917115623704932e-05,
|
| 435 |
+
"loss": 0.2304,
|
| 436 |
+
"step": 510
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.5355303810504635,
|
| 440 |
+
"grad_norm": 34.816078186035156,
|
| 441 |
+
"learning_rate": 1.9834231247409866e-05,
|
| 442 |
+
"loss": 0.1986,
|
| 443 |
+
"step": 520
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.5458290422245108,
|
| 447 |
+
"grad_norm": 25.571226119995117,
|
| 448 |
+
"learning_rate": 1.9751346871114796e-05,
|
| 449 |
+
"loss": 0.2303,
|
| 450 |
+
"step": 530
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.5561277033985582,
|
| 454 |
+
"grad_norm": 30.41813850402832,
|
| 455 |
+
"learning_rate": 1.966846249481973e-05,
|
| 456 |
+
"loss": 0.2466,
|
| 457 |
+
"step": 540
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5664263645726055,
|
| 461 |
+
"grad_norm": 16.801122665405273,
|
| 462 |
+
"learning_rate": 1.958557811852466e-05,
|
| 463 |
+
"loss": 0.2301,
|
| 464 |
+
"step": 550
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.576725025746653,
|
| 468 |
+
"grad_norm": 12.966567993164062,
|
| 469 |
+
"learning_rate": 1.950269374222959e-05,
|
| 470 |
+
"loss": 0.1849,
|
| 471 |
+
"step": 560
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.5870236869207003,
|
| 475 |
+
"grad_norm": 22.240522384643555,
|
| 476 |
+
"learning_rate": 1.9419809365934525e-05,
|
| 477 |
+
"loss": 0.2195,
|
| 478 |
+
"step": 570
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.5973223480947477,
|
| 482 |
+
"grad_norm": 12.580880165100098,
|
| 483 |
+
"learning_rate": 1.9336924989639455e-05,
|
| 484 |
+
"loss": 0.2231,
|
| 485 |
+
"step": 580
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.607621009268795,
|
| 489 |
+
"grad_norm": 16.313684463500977,
|
| 490 |
+
"learning_rate": 1.9254040613344385e-05,
|
| 491 |
+
"loss": 0.1995,
|
| 492 |
+
"step": 590
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.6179196704428425,
|
| 496 |
+
"grad_norm": 22.65012550354004,
|
| 497 |
+
"learning_rate": 1.917115623704932e-05,
|
| 498 |
+
"loss": 0.215,
|
| 499 |
+
"step": 600
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.6179196704428425,
|
| 503 |
+
"eval_accuracy": 0.9228887744593203,
|
| 504 |
+
"eval_accuracy_label_0": 0.9714412712523613,
|
| 505 |
+
"eval_accuracy_label_1": 0.8560501759216766,
|
| 506 |
+
"eval_f1": 0.9221719088414253,
|
| 507 |
+
"eval_loss": 0.20105671882629395,
|
| 508 |
+
"eval_precision": 0.9252341477386846,
|
| 509 |
+
"eval_recall": 0.9228887744593203,
|
| 510 |
+
"eval_runtime": 28.6849,
|
| 511 |
+
"eval_samples_per_second": 541.608,
|
| 512 |
+
"eval_steps_per_second": 16.943,
|
| 513 |
+
"step": 600
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6282183316168898,
|
| 517 |
+
"grad_norm": 13.182197570800781,
|
| 518 |
+
"learning_rate": 1.908827186075425e-05,
|
| 519 |
+
"loss": 0.2018,
|
| 520 |
+
"step": 610
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.6385169927909372,
|
| 524 |
+
"grad_norm": 17.625165939331055,
|
| 525 |
+
"learning_rate": 1.900538748445918e-05,
|
| 526 |
+
"loss": 0.2005,
|
| 527 |
+
"step": 620
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.6488156539649845,
|
| 531 |
+
"grad_norm": 31.007543563842773,
|
| 532 |
+
"learning_rate": 1.892250310816411e-05,
|
| 533 |
+
"loss": 0.2392,
|
| 534 |
+
"step": 630
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.659114315139032,
|
| 538 |
+
"grad_norm": 12.987165451049805,
|
| 539 |
+
"learning_rate": 1.8839618731869044e-05,
|
| 540 |
+
"loss": 0.2064,
|
| 541 |
+
"step": 640
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6694129763130793,
|
| 545 |
+
"grad_norm": 14.435954093933105,
|
| 546 |
+
"learning_rate": 1.8756734355573975e-05,
|
| 547 |
+
"loss": 0.1576,
|
| 548 |
+
"step": 650
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.6797116374871267,
|
| 552 |
+
"grad_norm": 20.525474548339844,
|
| 553 |
+
"learning_rate": 1.867384997927891e-05,
|
| 554 |
+
"loss": 0.1876,
|
| 555 |
+
"step": 660
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.690010298661174,
|
| 559 |
+
"grad_norm": 16.95576286315918,
|
| 560 |
+
"learning_rate": 1.859096560298384e-05,
|
| 561 |
+
"loss": 0.2114,
|
| 562 |
+
"step": 670
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7003089598352215,
|
| 566 |
+
"grad_norm": 36.12498092651367,
|
| 567 |
+
"learning_rate": 1.850808122668877e-05,
|
| 568 |
+
"loss": 0.2061,
|
| 569 |
+
"step": 680
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.7106076210092688,
|
| 573 |
+
"grad_norm": 22.316720962524414,
|
| 574 |
+
"learning_rate": 1.8425196850393703e-05,
|
| 575 |
+
"loss": 0.1984,
|
| 576 |
+
"step": 690
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.7209062821833162,
|
| 580 |
+
"grad_norm": 7.638524532318115,
|
| 581 |
+
"learning_rate": 1.8342312474098633e-05,
|
| 582 |
+
"loss": 0.1419,
|
| 583 |
+
"step": 700
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.7209062821833162,
|
| 587 |
+
"eval_accuracy": 0.9304840370751802,
|
| 588 |
+
"eval_accuracy_label_0": 0.9689965551727969,
|
| 589 |
+
"eval_accuracy_label_1": 0.877466727856815,
|
| 590 |
+
"eval_f1": 0.9300182365736557,
|
| 591 |
+
"eval_loss": 0.18355503678321838,
|
| 592 |
+
"eval_precision": 0.931752271905432,
|
| 593 |
+
"eval_recall": 0.9304840370751802,
|
| 594 |
+
"eval_runtime": 28.6805,
|
| 595 |
+
"eval_samples_per_second": 541.692,
|
| 596 |
+
"eval_steps_per_second": 16.945,
|
| 597 |
+
"step": 700
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.7312049433573635,
|
| 601 |
+
"grad_norm": 13.644458770751953,
|
| 602 |
+
"learning_rate": 1.8259428097803567e-05,
|
| 603 |
+
"loss": 0.1721,
|
| 604 |
+
"step": 710
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.741503604531411,
|
| 608 |
+
"grad_norm": 17.838420867919922,
|
| 609 |
+
"learning_rate": 1.8176543721508498e-05,
|
| 610 |
+
"loss": 0.1458,
|
| 611 |
+
"step": 720
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.7518022657054583,
|
| 615 |
+
"grad_norm": 27.161771774291992,
|
| 616 |
+
"learning_rate": 1.8093659345213428e-05,
|
| 617 |
+
"loss": 0.1231,
|
| 618 |
+
"step": 730
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.7621009268795057,
|
| 622 |
+
"grad_norm": 22.936689376831055,
|
| 623 |
+
"learning_rate": 1.8010774968918362e-05,
|
| 624 |
+
"loss": 0.2046,
|
| 625 |
+
"step": 740
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.772399588053553,
|
| 629 |
+
"grad_norm": 20.51582908630371,
|
| 630 |
+
"learning_rate": 1.7927890592623292e-05,
|
| 631 |
+
"loss": 0.1781,
|
| 632 |
+
"step": 750
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.7826982492276005,
|
| 636 |
+
"grad_norm": 20.982328414916992,
|
| 637 |
+
"learning_rate": 1.7845006216328226e-05,
|
| 638 |
+
"loss": 0.1914,
|
| 639 |
+
"step": 760
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.7929969104016478,
|
| 643 |
+
"grad_norm": 16.1798038482666,
|
| 644 |
+
"learning_rate": 1.7762121840033156e-05,
|
| 645 |
+
"loss": 0.2076,
|
| 646 |
+
"step": 770
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.8032955715756952,
|
| 650 |
+
"grad_norm": 26.379657745361328,
|
| 651 |
+
"learning_rate": 1.7679237463738087e-05,
|
| 652 |
+
"loss": 0.1707,
|
| 653 |
+
"step": 780
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.8135942327497425,
|
| 657 |
+
"grad_norm": 7.800419807434082,
|
| 658 |
+
"learning_rate": 1.7596353087443017e-05,
|
| 659 |
+
"loss": 0.142,
|
| 660 |
+
"step": 790
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.82389289392379,
|
| 664 |
+
"grad_norm": 10.589848518371582,
|
| 665 |
+
"learning_rate": 1.751346871114795e-05,
|
| 666 |
+
"loss": 0.1511,
|
| 667 |
+
"step": 800
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.82389289392379,
|
| 671 |
+
"eval_accuracy": 0.930548403707518,
|
| 672 |
+
"eval_accuracy_label_0": 0.9145460606734082,
|
| 673 |
+
"eval_accuracy_label_1": 0.9525776350007649,
|
| 674 |
+
"eval_f1": 0.9308174189927962,
|
| 675 |
+
"eval_loss": 0.18278397619724274,
|
| 676 |
+
"eval_precision": 0.9327234594811592,
|
| 677 |
+
"eval_recall": 0.930548403707518,
|
| 678 |
+
"eval_runtime": 28.6416,
|
| 679 |
+
"eval_samples_per_second": 542.428,
|
| 680 |
+
"eval_steps_per_second": 16.968,
|
| 681 |
+
"step": 800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.8341915550978373,
|
| 685 |
+
"grad_norm": 12.684349060058594,
|
| 686 |
+
"learning_rate": 1.743058433485288e-05,
|
| 687 |
+
"loss": 0.2034,
|
| 688 |
+
"step": 810
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.8444902162718847,
|
| 692 |
+
"grad_norm": 13.458330154418945,
|
| 693 |
+
"learning_rate": 1.7347699958557812e-05,
|
| 694 |
+
"loss": 0.1508,
|
| 695 |
+
"step": 820
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.854788877445932,
|
| 699 |
+
"grad_norm": 52.44272232055664,
|
| 700 |
+
"learning_rate": 1.7264815582262742e-05,
|
| 701 |
+
"loss": 0.2015,
|
| 702 |
+
"step": 830
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.8650875386199794,
|
| 706 |
+
"grad_norm": 12.620824813842773,
|
| 707 |
+
"learning_rate": 1.7181931205967676e-05,
|
| 708 |
+
"loss": 0.2104,
|
| 709 |
+
"step": 840
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.8753861997940268,
|
| 713 |
+
"grad_norm": 22.93926429748535,
|
| 714 |
+
"learning_rate": 1.7099046829672606e-05,
|
| 715 |
+
"loss": 0.1698,
|
| 716 |
+
"step": 850
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.8856848609680742,
|
| 720 |
+
"grad_norm": 43.46416091918945,
|
| 721 |
+
"learning_rate": 1.701616245337754e-05,
|
| 722 |
+
"loss": 0.2122,
|
| 723 |
+
"step": 860
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.8959835221421215,
|
| 727 |
+
"grad_norm": 13.863987922668457,
|
| 728 |
+
"learning_rate": 1.693327807708247e-05,
|
| 729 |
+
"loss": 0.1794,
|
| 730 |
+
"step": 870
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9062821833161689,
|
| 734 |
+
"grad_norm": 13.215469360351562,
|
| 735 |
+
"learning_rate": 1.68503937007874e-05,
|
| 736 |
+
"loss": 0.1822,
|
| 737 |
+
"step": 880
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.9165808444902163,
|
| 741 |
+
"grad_norm": 10.52542495727539,
|
| 742 |
+
"learning_rate": 1.6767509324492335e-05,
|
| 743 |
+
"loss": 0.1605,
|
| 744 |
+
"step": 890
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.9268795056642637,
|
| 748 |
+
"grad_norm": 15.559625625610352,
|
| 749 |
+
"learning_rate": 1.6684624948197265e-05,
|
| 750 |
+
"loss": 0.173,
|
| 751 |
+
"step": 900
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.9268795056642637,
|
| 755 |
+
"eval_accuracy": 0.9430355303810505,
|
| 756 |
+
"eval_accuracy_label_0": 0.9665518390932326,
|
| 757 |
+
"eval_accuracy_label_1": 0.9106623833562797,
|
| 758 |
+
"eval_f1": 0.942846283646341,
|
| 759 |
+
"eval_loss": 0.15442048013210297,
|
| 760 |
+
"eval_precision": 0.9433049100473271,
|
| 761 |
+
"eval_recall": 0.9430355303810505,
|
| 762 |
+
"eval_runtime": 28.6287,
|
| 763 |
+
"eval_samples_per_second": 542.672,
|
| 764 |
+
"eval_steps_per_second": 16.976,
|
| 765 |
+
"step": 900
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.937178166838311,
|
| 769 |
+
"grad_norm": 16.371034622192383,
|
| 770 |
+
"learning_rate": 1.66017405719022e-05,
|
| 771 |
+
"loss": 0.1453,
|
| 772 |
+
"step": 910
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.9474768280123584,
|
| 776 |
+
"grad_norm": 11.040371894836426,
|
| 777 |
+
"learning_rate": 1.651885619560713e-05,
|
| 778 |
+
"loss": 0.1388,
|
| 779 |
+
"step": 920
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.9577754891864058,
|
| 783 |
+
"grad_norm": 24.066585540771484,
|
| 784 |
+
"learning_rate": 1.6435971819312063e-05,
|
| 785 |
+
"loss": 0.1822,
|
| 786 |
+
"step": 930
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.9680741503604532,
|
| 790 |
+
"grad_norm": 12.861708641052246,
|
| 791 |
+
"learning_rate": 1.6353087443016994e-05,
|
| 792 |
+
"loss": 0.1382,
|
| 793 |
+
"step": 940
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.9783728115345005,
|
| 797 |
+
"grad_norm": 11.843149185180664,
|
| 798 |
+
"learning_rate": 1.6270203066721924e-05,
|
| 799 |
+
"loss": 0.1766,
|
| 800 |
+
"step": 950
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.9886714727085479,
|
| 804 |
+
"grad_norm": 37.507041931152344,
|
| 805 |
+
"learning_rate": 1.6187318690426858e-05,
|
| 806 |
+
"loss": 0.1511,
|
| 807 |
+
"step": 960
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.9989701338825953,
|
| 811 |
+
"grad_norm": 15.694278717041016,
|
| 812 |
+
"learning_rate": 1.6104434314131788e-05,
|
| 813 |
+
"loss": 0.1444,
|
| 814 |
+
"step": 970
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.0092687950566426,
|
| 818 |
+
"grad_norm": 13.906076431274414,
|
| 819 |
+
"learning_rate": 1.602154993783672e-05,
|
| 820 |
+
"loss": 0.1528,
|
| 821 |
+
"step": 980
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.01956745623069,
|
| 825 |
+
"grad_norm": 7.0642571449279785,
|
| 826 |
+
"learning_rate": 1.5938665561541652e-05,
|
| 827 |
+
"loss": 0.1619,
|
| 828 |
+
"step": 990
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.0298661174047374,
|
| 832 |
+
"grad_norm": 9.03572940826416,
|
| 833 |
+
"learning_rate": 1.5855781185246583e-05,
|
| 834 |
+
"loss": 0.0986,
|
| 835 |
+
"step": 1000
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.0298661174047374,
|
| 839 |
+
"eval_accuracy": 0.9429067971163748,
|
| 840 |
+
"eval_accuracy_label_0": 0.9384376041782421,
|
| 841 |
+
"eval_accuracy_label_1": 0.9490592014685636,
|
| 842 |
+
"eval_f1": 0.9430264358268661,
|
| 843 |
+
"eval_loss": 0.1512954831123352,
|
| 844 |
+
"eval_precision": 0.9435332838620341,
|
| 845 |
+
"eval_recall": 0.9429067971163748,
|
| 846 |
+
"eval_runtime": 28.6625,
|
| 847 |
+
"eval_samples_per_second": 542.033,
|
| 848 |
+
"eval_steps_per_second": 16.956,
|
| 849 |
+
"step": 1000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.0401647785787849,
|
| 853 |
+
"grad_norm": 14.95033073425293,
|
| 854 |
+
"learning_rate": 1.5772896808951513e-05,
|
| 855 |
+
"loss": 0.127,
|
| 856 |
+
"step": 1010
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.050463439752832,
|
| 860 |
+
"grad_norm": 11.197813034057617,
|
| 861 |
+
"learning_rate": 1.5690012432656444e-05,
|
| 862 |
+
"loss": 0.1089,
|
| 863 |
+
"step": 1020
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.0607621009268795,
|
| 867 |
+
"grad_norm": 29.581073760986328,
|
| 868 |
+
"learning_rate": 1.5607128056361377e-05,
|
| 869 |
+
"loss": 0.1313,
|
| 870 |
+
"step": 1030
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.071060762100927,
|
| 874 |
+
"grad_norm": 9.089577674865723,
|
| 875 |
+
"learning_rate": 1.5524243680066308e-05,
|
| 876 |
+
"loss": 0.1005,
|
| 877 |
+
"step": 1040
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.0813594232749741,
|
| 881 |
+
"grad_norm": 11.24911117553711,
|
| 882 |
+
"learning_rate": 1.5441359303771238e-05,
|
| 883 |
+
"loss": 0.1182,
|
| 884 |
+
"step": 1050
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.0916580844490216,
|
| 888 |
+
"grad_norm": 12.69548511505127,
|
| 889 |
+
"learning_rate": 1.5358474927476172e-05,
|
| 890 |
+
"loss": 0.1086,
|
| 891 |
+
"step": 1060
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.101956745623069,
|
| 895 |
+
"grad_norm": 6.551661491394043,
|
| 896 |
+
"learning_rate": 1.5275590551181102e-05,
|
| 897 |
+
"loss": 0.1795,
|
| 898 |
+
"step": 1070
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.1122554067971164,
|
| 902 |
+
"grad_norm": 7.627679347991943,
|
| 903 |
+
"learning_rate": 1.5192706174886036e-05,
|
| 904 |
+
"loss": 0.1228,
|
| 905 |
+
"step": 1080
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.1225540679711639,
|
| 909 |
+
"grad_norm": 9.827099800109863,
|
| 910 |
+
"learning_rate": 1.5109821798590967e-05,
|
| 911 |
+
"loss": 0.1744,
|
| 912 |
+
"step": 1090
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.132852729145211,
|
| 916 |
+
"grad_norm": 16.760608673095703,
|
| 917 |
+
"learning_rate": 1.5026937422295897e-05,
|
| 918 |
+
"loss": 0.1403,
|
| 919 |
+
"step": 1100
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.132852729145211,
|
| 923 |
+
"eval_accuracy": 0.9426493305870237,
|
| 924 |
+
"eval_accuracy_label_0": 0.9277697521946883,
|
| 925 |
+
"eval_accuracy_label_1": 0.9631329355973688,
|
| 926 |
+
"eval_f1": 0.9428523899715144,
|
| 927 |
+
"eval_loss": 0.15147006511688232,
|
| 928 |
+
"eval_precision": 0.9443742901764207,
|
| 929 |
+
"eval_recall": 0.9426493305870237,
|
| 930 |
+
"eval_runtime": 28.672,
|
| 931 |
+
"eval_samples_per_second": 541.852,
|
| 932 |
+
"eval_steps_per_second": 16.95,
|
| 933 |
+
"step": 1100
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.1431513903192585,
|
| 937 |
+
"grad_norm": 13.244966506958008,
|
| 938 |
+
"learning_rate": 1.4944053046000831e-05,
|
| 939 |
+
"loss": 0.1337,
|
| 940 |
+
"step": 1110
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.153450051493306,
|
| 944 |
+
"grad_norm": 16.159469604492188,
|
| 945 |
+
"learning_rate": 1.4861168669705761e-05,
|
| 946 |
+
"loss": 0.1257,
|
| 947 |
+
"step": 1120
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.1637487126673531,
|
| 951 |
+
"grad_norm": 8.31472396850586,
|
| 952 |
+
"learning_rate": 1.4778284293410693e-05,
|
| 953 |
+
"loss": 0.1138,
|
| 954 |
+
"step": 1130
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.1740473738414006,
|
| 958 |
+
"grad_norm": 20.465499877929688,
|
| 959 |
+
"learning_rate": 1.4695399917115625e-05,
|
| 960 |
+
"loss": 0.1145,
|
| 961 |
+
"step": 1140
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.184346035015448,
|
| 965 |
+
"grad_norm": 14.761605262756348,
|
| 966 |
+
"learning_rate": 1.4612515540820556e-05,
|
| 967 |
+
"loss": 0.1319,
|
| 968 |
+
"step": 1150
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.1946446961894954,
|
| 972 |
+
"grad_norm": 14.083001136779785,
|
| 973 |
+
"learning_rate": 1.4529631164525488e-05,
|
| 974 |
+
"loss": 0.1596,
|
| 975 |
+
"step": 1160
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.2049433573635429,
|
| 979 |
+
"grad_norm": 15.79395866394043,
|
| 980 |
+
"learning_rate": 1.4446746788230418e-05,
|
| 981 |
+
"loss": 0.1195,
|
| 982 |
+
"step": 1170
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.21524201853759,
|
| 986 |
+
"grad_norm": 19.134933471679688,
|
| 987 |
+
"learning_rate": 1.4363862411935352e-05,
|
| 988 |
+
"loss": 0.1326,
|
| 989 |
+
"step": 1180
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.2255406797116375,
|
| 993 |
+
"grad_norm": 8.911842346191406,
|
| 994 |
+
"learning_rate": 1.4280978035640283e-05,
|
| 995 |
+
"loss": 0.1658,
|
| 996 |
+
"step": 1190
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.235839340885685,
|
| 1000 |
+
"grad_norm": 13.809399604797363,
|
| 1001 |
+
"learning_rate": 1.4198093659345216e-05,
|
| 1002 |
+
"loss": 0.1133,
|
| 1003 |
+
"step": 1200
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.235839340885685,
|
| 1007 |
+
"eval_accuracy": 0.9474768280123584,
|
| 1008 |
+
"eval_accuracy_label_0": 0.9531059006556284,
|
| 1009 |
+
"eval_accuracy_label_1": 0.9397277038396818,
|
| 1010 |
+
"eval_f1": 0.9474920315228875,
|
| 1011 |
+
"eval_loss": 0.1394452601671219,
|
| 1012 |
+
"eval_precision": 0.9475135239059512,
|
| 1013 |
+
"eval_recall": 0.9474768280123584,
|
| 1014 |
+
"eval_runtime": 28.6446,
|
| 1015 |
+
"eval_samples_per_second": 542.371,
|
| 1016 |
+
"eval_steps_per_second": 16.967,
|
| 1017 |
+
"step": 1200
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.2461380020597321,
|
| 1021 |
+
"grad_norm": 6.037145137786865,
|
| 1022 |
+
"learning_rate": 1.4115209283050147e-05,
|
| 1023 |
+
"loss": 0.1181,
|
| 1024 |
+
"step": 1210
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.2564366632337796,
|
| 1028 |
+
"grad_norm": 12.423005104064941,
|
| 1029 |
+
"learning_rate": 1.4032324906755077e-05,
|
| 1030 |
+
"loss": 0.1262,
|
| 1031 |
+
"step": 1220
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.266735324407827,
|
| 1035 |
+
"grad_norm": 4.064807415008545,
|
| 1036 |
+
"learning_rate": 1.394944053046001e-05,
|
| 1037 |
+
"loss": 0.127,
|
| 1038 |
+
"step": 1230
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.2770339855818744,
|
| 1042 |
+
"grad_norm": 12.577651023864746,
|
| 1043 |
+
"learning_rate": 1.3866556154164941e-05,
|
| 1044 |
+
"loss": 0.0983,
|
| 1045 |
+
"step": 1240
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.2873326467559219,
|
| 1049 |
+
"grad_norm": 29.784053802490234,
|
| 1050 |
+
"learning_rate": 1.3783671777869873e-05,
|
| 1051 |
+
"loss": 0.1294,
|
| 1052 |
+
"step": 1250
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.297631307929969,
|
| 1056 |
+
"grad_norm": 10.433960914611816,
|
| 1057 |
+
"learning_rate": 1.3700787401574804e-05,
|
| 1058 |
+
"loss": 0.1268,
|
| 1059 |
+
"step": 1260
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.3079299691040165,
|
| 1063 |
+
"grad_norm": 23.706260681152344,
|
| 1064 |
+
"learning_rate": 1.3617903025279734e-05,
|
| 1065 |
+
"loss": 0.1508,
|
| 1066 |
+
"step": 1270
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.318228630278064,
|
| 1070 |
+
"grad_norm": 8.82191276550293,
|
| 1071 |
+
"learning_rate": 1.3535018648984668e-05,
|
| 1072 |
+
"loss": 0.1419,
|
| 1073 |
+
"step": 1280
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.3285272914521111,
|
| 1077 |
+
"grad_norm": 15.989568710327148,
|
| 1078 |
+
"learning_rate": 1.3452134272689598e-05,
|
| 1079 |
+
"loss": 0.1148,
|
| 1080 |
+
"step": 1290
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.3388259526261586,
|
| 1084 |
+
"grad_norm": 18.397598266601562,
|
| 1085 |
+
"learning_rate": 1.3369249896394532e-05,
|
| 1086 |
+
"loss": 0.1117,
|
| 1087 |
+
"step": 1300
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.3388259526261586,
|
| 1091 |
+
"eval_accuracy": 0.9457389289392379,
|
| 1092 |
+
"eval_accuracy_label_0": 0.9371041226802979,
|
| 1093 |
+
"eval_accuracy_label_1": 0.9576258222426189,
|
| 1094 |
+
"eval_f1": 0.9458829241092044,
|
| 1095 |
+
"eval_loss": 0.15250205993652344,
|
| 1096 |
+
"eval_precision": 0.9466897814987169,
|
| 1097 |
+
"eval_recall": 0.9457389289392379,
|
| 1098 |
+
"eval_runtime": 28.6931,
|
| 1099 |
+
"eval_samples_per_second": 541.455,
|
| 1100 |
+
"eval_steps_per_second": 16.938,
|
| 1101 |
+
"step": 1300
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.349124613800206,
|
| 1105 |
+
"grad_norm": 8.94162368774414,
|
| 1106 |
+
"learning_rate": 1.3286365520099463e-05,
|
| 1107 |
+
"loss": 0.1298,
|
| 1108 |
+
"step": 1310
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.3594232749742534,
|
| 1112 |
+
"grad_norm": 8.949539184570312,
|
| 1113 |
+
"learning_rate": 1.3203481143804393e-05,
|
| 1114 |
+
"loss": 0.1136,
|
| 1115 |
+
"step": 1320
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.3697219361483008,
|
| 1119 |
+
"grad_norm": 9.650628089904785,
|
| 1120 |
+
"learning_rate": 1.3120596767509325e-05,
|
| 1121 |
+
"loss": 0.1107,
|
| 1122 |
+
"step": 1330
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.380020597322348,
|
| 1126 |
+
"grad_norm": 20.57952308654785,
|
| 1127 |
+
"learning_rate": 1.3037712391214257e-05,
|
| 1128 |
+
"loss": 0.1305,
|
| 1129 |
+
"step": 1340
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.3903192584963955,
|
| 1133 |
+
"grad_norm": 6.576913833618164,
|
| 1134 |
+
"learning_rate": 1.295482801491919e-05,
|
| 1135 |
+
"loss": 0.1008,
|
| 1136 |
+
"step": 1350
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.400617919670443,
|
| 1140 |
+
"grad_norm": 8.591489791870117,
|
| 1141 |
+
"learning_rate": 1.287194363862412e-05,
|
| 1142 |
+
"loss": 0.1142,
|
| 1143 |
+
"step": 1360
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.4109165808444901,
|
| 1147 |
+
"grad_norm": 21.97450065612793,
|
| 1148 |
+
"learning_rate": 1.2789059262329052e-05,
|
| 1149 |
+
"loss": 0.1098,
|
| 1150 |
+
"step": 1370
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.4212152420185376,
|
| 1154 |
+
"grad_norm": 13.194725036621094,
|
| 1155 |
+
"learning_rate": 1.2706174886033984e-05,
|
| 1156 |
+
"loss": 0.115,
|
| 1157 |
+
"step": 1380
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.431513903192585,
|
| 1161 |
+
"grad_norm": 17.651912689208984,
|
| 1162 |
+
"learning_rate": 1.2623290509738914e-05,
|
| 1163 |
+
"loss": 0.1392,
|
| 1164 |
+
"step": 1390
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.4418125643666324,
|
| 1168 |
+
"grad_norm": 10.665314674377441,
|
| 1169 |
+
"learning_rate": 1.2540406133443848e-05,
|
| 1170 |
+
"loss": 0.1277,
|
| 1171 |
+
"step": 1400
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.4418125643666324,
|
| 1175 |
+
"eval_accuracy": 0.9490216271884655,
|
| 1176 |
+
"eval_accuracy_label_0": 0.950105567285254,
|
| 1177 |
+
"eval_accuracy_label_1": 0.9475294477589108,
|
| 1178 |
+
"eval_f1": 0.9490756146391877,
|
| 1179 |
+
"eval_loss": 0.13106246292591095,
|
| 1180 |
+
"eval_precision": 0.9492196286028385,
|
| 1181 |
+
"eval_recall": 0.9490216271884655,
|
| 1182 |
+
"eval_runtime": 28.6067,
|
| 1183 |
+
"eval_samples_per_second": 543.09,
|
| 1184 |
+
"eval_steps_per_second": 16.989,
|
| 1185 |
+
"step": 1400
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.4521112255406798,
|
| 1189 |
+
"grad_norm": 26.829360961914062,
|
| 1190 |
+
"learning_rate": 1.2457521757148779e-05,
|
| 1191 |
+
"loss": 0.1164,
|
| 1192 |
+
"step": 1410
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.462409886714727,
|
| 1196 |
+
"grad_norm": 12.50798225402832,
|
| 1197 |
+
"learning_rate": 1.2374637380853709e-05,
|
| 1198 |
+
"loss": 0.1368,
|
| 1199 |
+
"step": 1420
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.4727085478887745,
|
| 1203 |
+
"grad_norm": 10.048441886901855,
|
| 1204 |
+
"learning_rate": 1.2291753004558643e-05,
|
| 1205 |
+
"loss": 0.0953,
|
| 1206 |
+
"step": 1430
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.483007209062822,
|
| 1210 |
+
"grad_norm": 9.52072811126709,
|
| 1211 |
+
"learning_rate": 1.2208868628263573e-05,
|
| 1212 |
+
"loss": 0.1373,
|
| 1213 |
+
"step": 1440
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.4933058702368691,
|
| 1217 |
+
"grad_norm": 10.079704284667969,
|
| 1218 |
+
"learning_rate": 1.2125984251968505e-05,
|
| 1219 |
+
"loss": 0.0797,
|
| 1220 |
+
"step": 1450
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.5036045314109165,
|
| 1224 |
+
"grad_norm": 16.81131935119629,
|
| 1225 |
+
"learning_rate": 1.2043099875673436e-05,
|
| 1226 |
+
"loss": 0.1407,
|
| 1227 |
+
"step": 1460
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.513903192584964,
|
| 1231 |
+
"grad_norm": 9.030206680297852,
|
| 1232 |
+
"learning_rate": 1.196021549937837e-05,
|
| 1233 |
+
"loss": 0.1378,
|
| 1234 |
+
"step": 1470
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.5242018537590112,
|
| 1238 |
+
"grad_norm": 25.010522842407227,
|
| 1239 |
+
"learning_rate": 1.18773311230833e-05,
|
| 1240 |
+
"loss": 0.1205,
|
| 1241 |
+
"step": 1480
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.5345005149330588,
|
| 1245 |
+
"grad_norm": 23.806989669799805,
|
| 1246 |
+
"learning_rate": 1.179444674678823e-05,
|
| 1247 |
+
"loss": 0.1473,
|
| 1248 |
+
"step": 1490
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.544799176107106,
|
| 1252 |
+
"grad_norm": 8.146597862243652,
|
| 1253 |
+
"learning_rate": 1.1711562370493164e-05,
|
| 1254 |
+
"loss": 0.0886,
|
| 1255 |
+
"step": 1500
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.544799176107106,
|
| 1259 |
+
"eval_accuracy": 0.9503089598352215,
|
| 1260 |
+
"eval_accuracy_label_0": 0.962773641515724,
|
| 1261 |
+
"eval_accuracy_label_1": 0.933149762888175,
|
| 1262 |
+
"eval_f1": 0.9502536107094707,
|
| 1263 |
+
"eval_loss": 0.1374950259923935,
|
| 1264 |
+
"eval_precision": 0.9502824202007619,
|
| 1265 |
+
"eval_recall": 0.9503089598352215,
|
| 1266 |
+
"eval_runtime": 28.5942,
|
| 1267 |
+
"eval_samples_per_second": 543.328,
|
| 1268 |
+
"eval_steps_per_second": 16.996,
|
| 1269 |
+
"step": 1500
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.5550978372811535,
|
| 1273 |
+
"grad_norm": 11.416892051696777,
|
| 1274 |
+
"learning_rate": 1.1628677994198094e-05,
|
| 1275 |
+
"loss": 0.1135,
|
| 1276 |
+
"step": 1510
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.565396498455201,
|
| 1280 |
+
"grad_norm": 19.61497688293457,
|
| 1281 |
+
"learning_rate": 1.1545793617903027e-05,
|
| 1282 |
+
"loss": 0.1169,
|
| 1283 |
+
"step": 1520
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.575695159629248,
|
| 1287 |
+
"grad_norm": 11.90202808380127,
|
| 1288 |
+
"learning_rate": 1.1462909241607959e-05,
|
| 1289 |
+
"loss": 0.1339,
|
| 1290 |
+
"step": 1530
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.5859938208032955,
|
| 1294 |
+
"grad_norm": 6.188625812530518,
|
| 1295 |
+
"learning_rate": 1.1380024865312889e-05,
|
| 1296 |
+
"loss": 0.07,
|
| 1297 |
+
"step": 1540
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.596292481977343,
|
| 1301 |
+
"grad_norm": 14.50114631652832,
|
| 1302 |
+
"learning_rate": 1.1297140489017821e-05,
|
| 1303 |
+
"loss": 0.1047,
|
| 1304 |
+
"step": 1550
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.6065911431513902,
|
| 1308 |
+
"grad_norm": 18.257389068603516,
|
| 1309 |
+
"learning_rate": 1.1214256112722752e-05,
|
| 1310 |
+
"loss": 0.1098,
|
| 1311 |
+
"step": 1560
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.6168898043254378,
|
| 1315 |
+
"grad_norm": 12.986026763916016,
|
| 1316 |
+
"learning_rate": 1.1131371736427685e-05,
|
| 1317 |
+
"loss": 0.1248,
|
| 1318 |
+
"step": 1570
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.627188465499485,
|
| 1322 |
+
"grad_norm": 13.668187141418457,
|
| 1323 |
+
"learning_rate": 1.1048487360132616e-05,
|
| 1324 |
+
"loss": 0.0758,
|
| 1325 |
+
"step": 1580
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.6374871266735325,
|
| 1329 |
+
"grad_norm": 24.57569694519043,
|
| 1330 |
+
"learning_rate": 1.0965602983837546e-05,
|
| 1331 |
+
"loss": 0.1076,
|
| 1332 |
+
"step": 1590
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.64778578784758,
|
| 1336 |
+
"grad_norm": 8.269564628601074,
|
| 1337 |
+
"learning_rate": 1.088271860754248e-05,
|
| 1338 |
+
"loss": 0.1273,
|
| 1339 |
+
"step": 1600
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.64778578784758,
|
| 1343 |
+
"eval_accuracy": 0.95326982492276,
|
| 1344 |
+
"eval_accuracy_label_0": 0.9535503944882765,
|
| 1345 |
+
"eval_accuracy_label_1": 0.9528835857426954,
|
| 1346 |
+
"eval_f1": 0.9533210896239291,
|
| 1347 |
+
"eval_loss": 0.12969127297401428,
|
| 1348 |
+
"eval_precision": 0.9534697447214137,
|
| 1349 |
+
"eval_recall": 0.95326982492276,
|
| 1350 |
+
"eval_runtime": 28.6188,
|
| 1351 |
+
"eval_samples_per_second": 542.861,
|
| 1352 |
+
"eval_steps_per_second": 16.982,
|
| 1353 |
+
"step": 1600
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.658084449021627,
|
| 1357 |
+
"grad_norm": 13.074461936950684,
|
| 1358 |
+
"learning_rate": 1.079983423124741e-05,
|
| 1359 |
+
"loss": 0.134,
|
| 1360 |
+
"step": 1610
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.6683831101956745,
|
| 1364 |
+
"grad_norm": 17.92150115966797,
|
| 1365 |
+
"learning_rate": 1.0716949854952342e-05,
|
| 1366 |
+
"loss": 0.138,
|
| 1367 |
+
"step": 1620
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.678681771369722,
|
| 1371 |
+
"grad_norm": 6.528224468231201,
|
| 1372 |
+
"learning_rate": 1.0634065478657275e-05,
|
| 1373 |
+
"loss": 0.1281,
|
| 1374 |
+
"step": 1630
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.6889804325437692,
|
| 1378 |
+
"grad_norm": 15.4542236328125,
|
| 1379 |
+
"learning_rate": 1.0551181102362205e-05,
|
| 1380 |
+
"loss": 0.1272,
|
| 1381 |
+
"step": 1640
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.6992790937178168,
|
| 1385 |
+
"grad_norm": 7.588622570037842,
|
| 1386 |
+
"learning_rate": 1.0468296726067137e-05,
|
| 1387 |
+
"loss": 0.0765,
|
| 1388 |
+
"step": 1650
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.709577754891864,
|
| 1392 |
+
"grad_norm": 14.380094528198242,
|
| 1393 |
+
"learning_rate": 1.0385412349772067e-05,
|
| 1394 |
+
"loss": 0.1326,
|
| 1395 |
+
"step": 1660
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.7198764160659115,
|
| 1399 |
+
"grad_norm": 17.22504997253418,
|
| 1400 |
+
"learning_rate": 1.0302527973477001e-05,
|
| 1401 |
+
"loss": 0.1725,
|
| 1402 |
+
"step": 1670
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.730175077239959,
|
| 1406 |
+
"grad_norm": 21.660451889038086,
|
| 1407 |
+
"learning_rate": 1.0219643597181932e-05,
|
| 1408 |
+
"loss": 0.1201,
|
| 1409 |
+
"step": 1680
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.740473738414006,
|
| 1413 |
+
"grad_norm": 12.858647346496582,
|
| 1414 |
+
"learning_rate": 1.0136759220886862e-05,
|
| 1415 |
+
"loss": 0.1303,
|
| 1416 |
+
"step": 1690
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.7507723995880535,
|
| 1420 |
+
"grad_norm": 7.619086742401123,
|
| 1421 |
+
"learning_rate": 1.0053874844591796e-05,
|
| 1422 |
+
"loss": 0.1102,
|
| 1423 |
+
"step": 1700
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.7507723995880535,
|
| 1427 |
+
"eval_accuracy": 0.9578398558187435,
|
| 1428 |
+
"eval_accuracy_label_0": 0.9636626291810201,
|
| 1429 |
+
"eval_accuracy_label_1": 0.9498240783233899,
|
| 1430 |
+
"eval_f1": 0.9578394145096656,
|
| 1431 |
+
"eval_loss": 0.11356295645236969,
|
| 1432 |
+
"eval_precision": 0.9578389813236798,
|
| 1433 |
+
"eval_recall": 0.9578398558187435,
|
| 1434 |
+
"eval_runtime": 28.6352,
|
| 1435 |
+
"eval_samples_per_second": 542.548,
|
| 1436 |
+
"eval_steps_per_second": 16.972,
|
| 1437 |
+
"step": 1700
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.761071060762101,
|
| 1441 |
+
"grad_norm": 11.526819229125977,
|
| 1442 |
+
"learning_rate": 9.970990468296728e-06,
|
| 1443 |
+
"loss": 0.0705,
|
| 1444 |
+
"step": 1710
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.7713697219361482,
|
| 1448 |
+
"grad_norm": 11.57654857635498,
|
| 1449 |
+
"learning_rate": 9.888106092001658e-06,
|
| 1450 |
+
"loss": 0.1298,
|
| 1451 |
+
"step": 1720
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.7816683831101958,
|
| 1455 |
+
"grad_norm": 11.508631706237793,
|
| 1456 |
+
"learning_rate": 9.80522171570659e-06,
|
| 1457 |
+
"loss": 0.0818,
|
| 1458 |
+
"step": 1730
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.791967044284243,
|
| 1462 |
+
"grad_norm": 15.72537612915039,
|
| 1463 |
+
"learning_rate": 9.722337339411521e-06,
|
| 1464 |
+
"loss": 0.1334,
|
| 1465 |
+
"step": 1740
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.8022657054582905,
|
| 1469 |
+
"grad_norm": 19.711965560913086,
|
| 1470 |
+
"learning_rate": 9.639452963116453e-06,
|
| 1471 |
+
"loss": 0.0747,
|
| 1472 |
+
"step": 1750
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.8125643666323379,
|
| 1476 |
+
"grad_norm": 14.697903633117676,
|
| 1477 |
+
"learning_rate": 9.556568586821385e-06,
|
| 1478 |
+
"loss": 0.0819,
|
| 1479 |
+
"step": 1760
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.822863027806385,
|
| 1483 |
+
"grad_norm": 9.13084888458252,
|
| 1484 |
+
"learning_rate": 9.473684210526315e-06,
|
| 1485 |
+
"loss": 0.076,
|
| 1486 |
+
"step": 1770
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.8331616889804325,
|
| 1490 |
+
"grad_norm": 6.7411909103393555,
|
| 1491 |
+
"learning_rate": 9.390799834231248e-06,
|
| 1492 |
+
"loss": 0.117,
|
| 1493 |
+
"step": 1780
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.84346035015448,
|
| 1497 |
+
"grad_norm": 9.10245132446289,
|
| 1498 |
+
"learning_rate": 9.30791545793618e-06,
|
| 1499 |
+
"loss": 0.099,
|
| 1500 |
+
"step": 1790
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.8537590113285272,
|
| 1504 |
+
"grad_norm": 12.770278930664062,
|
| 1505 |
+
"learning_rate": 9.225031081641112e-06,
|
| 1506 |
+
"loss": 0.0793,
|
| 1507 |
+
"step": 1800
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.8537590113285272,
|
| 1511 |
+
"eval_accuracy": 0.9562306900102987,
|
| 1512 |
+
"eval_accuracy_label_0": 0.9717746416268475,
|
| 1513 |
+
"eval_accuracy_label_1": 0.934832491968793,
|
| 1514 |
+
"eval_f1": 0.9561461033354728,
|
| 1515 |
+
"eval_loss": 0.12691599130630493,
|
| 1516 |
+
"eval_precision": 0.9563031504820825,
|
| 1517 |
+
"eval_recall": 0.9562306900102987,
|
| 1518 |
+
"eval_runtime": 28.648,
|
| 1519 |
+
"eval_samples_per_second": 542.306,
|
| 1520 |
+
"eval_steps_per_second": 16.965,
|
| 1521 |
+
"step": 1800
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.8640576725025748,
|
| 1525 |
+
"grad_norm": 10.909438133239746,
|
| 1526 |
+
"learning_rate": 9.142146705346044e-06,
|
| 1527 |
+
"loss": 0.094,
|
| 1528 |
+
"step": 1810
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.874356333676622,
|
| 1532 |
+
"grad_norm": 24.187469482421875,
|
| 1533 |
+
"learning_rate": 9.059262329050974e-06,
|
| 1534 |
+
"loss": 0.1057,
|
| 1535 |
+
"step": 1820
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.8846549948506695,
|
| 1539 |
+
"grad_norm": 12.352056503295898,
|
| 1540 |
+
"learning_rate": 8.976377952755906e-06,
|
| 1541 |
+
"loss": 0.0996,
|
| 1542 |
+
"step": 1830
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.8949536560247169,
|
| 1546 |
+
"grad_norm": 18.231224060058594,
|
| 1547 |
+
"learning_rate": 8.893493576460838e-06,
|
| 1548 |
+
"loss": 0.1419,
|
| 1549 |
+
"step": 1840
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.905252317198764,
|
| 1553 |
+
"grad_norm": 13.484111785888672,
|
| 1554 |
+
"learning_rate": 8.810609200165769e-06,
|
| 1555 |
+
"loss": 0.0816,
|
| 1556 |
+
"step": 1850
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.9155509783728115,
|
| 1560 |
+
"grad_norm": 7.332424640655518,
|
| 1561 |
+
"learning_rate": 8.727724823870701e-06,
|
| 1562 |
+
"loss": 0.1034,
|
| 1563 |
+
"step": 1860
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.925849639546859,
|
| 1567 |
+
"grad_norm": 10.0885648727417,
|
| 1568 |
+
"learning_rate": 8.644840447575633e-06,
|
| 1569 |
+
"loss": 0.0846,
|
| 1570 |
+
"step": 1870
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.9361483007209062,
|
| 1574 |
+
"grad_norm": 7.032443046569824,
|
| 1575 |
+
"learning_rate": 8.561956071280563e-06,
|
| 1576 |
+
"loss": 0.1134,
|
| 1577 |
+
"step": 1880
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.9464469618949538,
|
| 1581 |
+
"grad_norm": 15.94394302368164,
|
| 1582 |
+
"learning_rate": 8.479071694985496e-06,
|
| 1583 |
+
"loss": 0.1097,
|
| 1584 |
+
"step": 1890
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.956745623069001,
|
| 1588 |
+
"grad_norm": 9.909218788146973,
|
| 1589 |
+
"learning_rate": 8.396187318690428e-06,
|
| 1590 |
+
"loss": 0.0995,
|
| 1591 |
+
"step": 1900
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.956745623069001,
|
| 1595 |
+
"eval_accuracy": 0.9590628218331617,
|
| 1596 |
+
"eval_accuracy_label_0": 0.9702189132125791,
|
| 1597 |
+
"eval_accuracy_label_1": 0.943705063484779,
|
| 1598 |
+
"eval_f1": 0.9590181542400875,
|
| 1599 |
+
"eval_loss": 0.11290641874074936,
|
| 1600 |
+
"eval_precision": 0.9590551602931409,
|
| 1601 |
+
"eval_recall": 0.9590628218331617,
|
| 1602 |
+
"eval_runtime": 28.6377,
|
| 1603 |
+
"eval_samples_per_second": 542.502,
|
| 1604 |
+
"eval_steps_per_second": 16.971,
|
| 1605 |
+
"step": 1900
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.9670442842430484,
|
| 1609 |
+
"grad_norm": 15.3870210647583,
|
| 1610 |
+
"learning_rate": 8.31330294239536e-06,
|
| 1611 |
+
"loss": 0.1248,
|
| 1612 |
+
"step": 1910
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.9773429454170959,
|
| 1616 |
+
"grad_norm": 8.369405746459961,
|
| 1617 |
+
"learning_rate": 8.230418566100292e-06,
|
| 1618 |
+
"loss": 0.0975,
|
| 1619 |
+
"step": 1920
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.987641606591143,
|
| 1623 |
+
"grad_norm": 20.09193992614746,
|
| 1624 |
+
"learning_rate": 8.147534189805222e-06,
|
| 1625 |
+
"loss": 0.1065,
|
| 1626 |
+
"step": 1930
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.9979402677651905,
|
| 1630 |
+
"grad_norm": 12.807772636413574,
|
| 1631 |
+
"learning_rate": 8.064649813510154e-06,
|
| 1632 |
+
"loss": 0.1091,
|
| 1633 |
+
"step": 1940
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.008238928939238,
|
| 1637 |
+
"grad_norm": 11.321664810180664,
|
| 1638 |
+
"learning_rate": 7.981765437215085e-06,
|
| 1639 |
+
"loss": 0.0707,
|
| 1640 |
+
"step": 1950
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.018537590113285,
|
| 1644 |
+
"grad_norm": 6.500060081481934,
|
| 1645 |
+
"learning_rate": 7.898881060920017e-06,
|
| 1646 |
+
"loss": 0.0548,
|
| 1647 |
+
"step": 1960
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.028836251287333,
|
| 1651 |
+
"grad_norm": 6.183711528778076,
|
| 1652 |
+
"learning_rate": 7.815996684624949e-06,
|
| 1653 |
+
"loss": 0.0596,
|
| 1654 |
+
"step": 1970
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.03913491246138,
|
| 1658 |
+
"grad_norm": 10.278242111206055,
|
| 1659 |
+
"learning_rate": 7.733112308329881e-06,
|
| 1660 |
+
"loss": 0.0768,
|
| 1661 |
+
"step": 1980
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.049433573635427,
|
| 1665 |
+
"grad_norm": 36.13182067871094,
|
| 1666 |
+
"learning_rate": 7.650227932034812e-06,
|
| 1667 |
+
"loss": 0.1081,
|
| 1668 |
+
"step": 1990
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.059732234809475,
|
| 1672 |
+
"grad_norm": 18.672588348388672,
|
| 1673 |
+
"learning_rate": 7.567343555739744e-06,
|
| 1674 |
+
"loss": 0.0846,
|
| 1675 |
+
"step": 2000
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.059732234809475,
|
| 1679 |
+
"eval_accuracy": 0.95326982492276,
|
| 1680 |
+
"eval_accuracy_label_0": 0.9422158017557506,
|
| 1681 |
+
"eval_accuracy_label_1": 0.9684870735811534,
|
| 1682 |
+
"eval_f1": 0.9534029516094716,
|
| 1683 |
+
"eval_loss": 0.1361849009990692,
|
| 1684 |
+
"eval_precision": 0.9543244872259893,
|
| 1685 |
+
"eval_recall": 0.95326982492276,
|
| 1686 |
+
"eval_runtime": 28.6073,
|
| 1687 |
+
"eval_samples_per_second": 543.078,
|
| 1688 |
+
"eval_steps_per_second": 16.989,
|
| 1689 |
+
"step": 2000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.070030895983522,
|
| 1693 |
+
"grad_norm": 8.882670402526855,
|
| 1694 |
+
"learning_rate": 7.484459179444675e-06,
|
| 1695 |
+
"loss": 0.0747,
|
| 1696 |
+
"step": 2010
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.0803295571575697,
|
| 1700 |
+
"grad_norm": 9.687372207641602,
|
| 1701 |
+
"learning_rate": 7.401574803149607e-06,
|
| 1702 |
+
"loss": 0.0447,
|
| 1703 |
+
"step": 2020
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.090628218331617,
|
| 1707 |
+
"grad_norm": 10.967034339904785,
|
| 1708 |
+
"learning_rate": 7.318690426854539e-06,
|
| 1709 |
+
"loss": 0.0504,
|
| 1710 |
+
"step": 2030
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.100926879505664,
|
| 1714 |
+
"grad_norm": 16.16581153869629,
|
| 1715 |
+
"learning_rate": 7.2358060505594695e-06,
|
| 1716 |
+
"loss": 0.078,
|
| 1717 |
+
"step": 2040
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.111225540679712,
|
| 1721 |
+
"grad_norm": 10.206809997558594,
|
| 1722 |
+
"learning_rate": 7.1529216742644016e-06,
|
| 1723 |
+
"loss": 0.0731,
|
| 1724 |
+
"step": 2050
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.121524201853759,
|
| 1728 |
+
"grad_norm": 3.9291794300079346,
|
| 1729 |
+
"learning_rate": 7.070037297969334e-06,
|
| 1730 |
+
"loss": 0.0573,
|
| 1731 |
+
"step": 2060
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.131822863027806,
|
| 1735 |
+
"grad_norm": 3.0698776245117188,
|
| 1736 |
+
"learning_rate": 6.987152921674265e-06,
|
| 1737 |
+
"loss": 0.0734,
|
| 1738 |
+
"step": 2070
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.142121524201854,
|
| 1742 |
+
"grad_norm": 23.81843376159668,
|
| 1743 |
+
"learning_rate": 6.904268545379197e-06,
|
| 1744 |
+
"loss": 0.0821,
|
| 1745 |
+
"step": 2080
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.152420185375901,
|
| 1749 |
+
"grad_norm": 7.545326232910156,
|
| 1750 |
+
"learning_rate": 6.821384169084129e-06,
|
| 1751 |
+
"loss": 0.0453,
|
| 1752 |
+
"step": 2090
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.1627188465499483,
|
| 1756 |
+
"grad_norm": 17.654476165771484,
|
| 1757 |
+
"learning_rate": 6.7384997927890595e-06,
|
| 1758 |
+
"loss": 0.096,
|
| 1759 |
+
"step": 2100
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.1627188465499483,
|
| 1763 |
+
"eval_accuracy": 0.9562950566426365,
|
| 1764 |
+
"eval_accuracy_label_0": 0.9466607400822313,
|
| 1765 |
+
"eval_accuracy_label_1": 0.9695579011779104,
|
| 1766 |
+
"eval_f1": 0.9564082597816722,
|
| 1767 |
+
"eval_loss": 0.1383037120103836,
|
| 1768 |
+
"eval_precision": 0.9571555565808465,
|
| 1769 |
+
"eval_recall": 0.9562950566426365,
|
| 1770 |
+
"eval_runtime": 28.6473,
|
| 1771 |
+
"eval_samples_per_second": 542.321,
|
| 1772 |
+
"eval_steps_per_second": 16.965,
|
| 1773 |
+
"step": 2100
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.173017507723996,
|
| 1777 |
+
"grad_norm": 9.992446899414062,
|
| 1778 |
+
"learning_rate": 6.655615416493992e-06,
|
| 1779 |
+
"loss": 0.027,
|
| 1780 |
+
"step": 2110
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.183316168898043,
|
| 1784 |
+
"grad_norm": 6.128831386566162,
|
| 1785 |
+
"learning_rate": 6.572731040198923e-06,
|
| 1786 |
+
"loss": 0.0743,
|
| 1787 |
+
"step": 2120
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.193614830072091,
|
| 1791 |
+
"grad_norm": 18.08496856689453,
|
| 1792 |
+
"learning_rate": 6.489846663903855e-06,
|
| 1793 |
+
"loss": 0.0483,
|
| 1794 |
+
"step": 2130
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.203913491246138,
|
| 1798 |
+
"grad_norm": 20.862857818603516,
|
| 1799 |
+
"learning_rate": 6.406962287608787e-06,
|
| 1800 |
+
"loss": 0.0872,
|
| 1801 |
+
"step": 2140
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.214212152420185,
|
| 1805 |
+
"grad_norm": 6.609086513519287,
|
| 1806 |
+
"learning_rate": 6.3240779113137175e-06,
|
| 1807 |
+
"loss": 0.1039,
|
| 1808 |
+
"step": 2150
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.224510813594233,
|
| 1812 |
+
"grad_norm": 9.900079727172852,
|
| 1813 |
+
"learning_rate": 6.2411935350186496e-06,
|
| 1814 |
+
"loss": 0.08,
|
| 1815 |
+
"step": 2160
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.23480947476828,
|
| 1819 |
+
"grad_norm": 6.2700700759887695,
|
| 1820 |
+
"learning_rate": 6.158309158723581e-06,
|
| 1821 |
+
"loss": 0.051,
|
| 1822 |
+
"step": 2170
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.2451081359423277,
|
| 1826 |
+
"grad_norm": 12.434645652770996,
|
| 1827 |
+
"learning_rate": 6.075424782428513e-06,
|
| 1828 |
+
"loss": 0.058,
|
| 1829 |
+
"step": 2180
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.255406797116375,
|
| 1833 |
+
"grad_norm": 7.681482791900635,
|
| 1834 |
+
"learning_rate": 5.992540406133445e-06,
|
| 1835 |
+
"loss": 0.0752,
|
| 1836 |
+
"step": 2190
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.265705458290422,
|
| 1840 |
+
"grad_norm": 24.001230239868164,
|
| 1841 |
+
"learning_rate": 5.909656029838376e-06,
|
| 1842 |
+
"loss": 0.0797,
|
| 1843 |
+
"step": 2200
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 2.265705458290422,
|
| 1847 |
+
"eval_accuracy": 0.9619593202883625,
|
| 1848 |
+
"eval_accuracy_label_0": 0.9711079008778754,
|
| 1849 |
+
"eval_accuracy_label_1": 0.9493651522104941,
|
| 1850 |
+
"eval_f1": 0.9619302021150672,
|
| 1851 |
+
"eval_loss": 0.11368735879659653,
|
| 1852 |
+
"eval_precision": 0.9619423362488065,
|
| 1853 |
+
"eval_recall": 0.9619593202883625,
|
| 1854 |
+
"eval_runtime": 28.6312,
|
| 1855 |
+
"eval_samples_per_second": 542.625,
|
| 1856 |
+
"eval_steps_per_second": 16.974,
|
| 1857 |
+
"step": 2200
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.27600411946447,
|
| 1861 |
+
"grad_norm": 14.428683280944824,
|
| 1862 |
+
"learning_rate": 5.8267716535433075e-06,
|
| 1863 |
+
"loss": 0.0506,
|
| 1864 |
+
"step": 2210
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.286302780638517,
|
| 1868 |
+
"grad_norm": 8.54249382019043,
|
| 1869 |
+
"learning_rate": 5.743887277248239e-06,
|
| 1870 |
+
"loss": 0.06,
|
| 1871 |
+
"step": 2220
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.296601441812564,
|
| 1875 |
+
"grad_norm": 19.03498077392578,
|
| 1876 |
+
"learning_rate": 5.661002900953171e-06,
|
| 1877 |
+
"loss": 0.0668,
|
| 1878 |
+
"step": 2230
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.306900102986612,
|
| 1882 |
+
"grad_norm": 10.844647407531738,
|
| 1883 |
+
"learning_rate": 5.578118524658103e-06,
|
| 1884 |
+
"loss": 0.0449,
|
| 1885 |
+
"step": 2240
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 2.317198764160659,
|
| 1889 |
+
"grad_norm": 14.049932479858398,
|
| 1890 |
+
"learning_rate": 5.495234148363034e-06,
|
| 1891 |
+
"loss": 0.1016,
|
| 1892 |
+
"step": 2250
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 2.3274974253347063,
|
| 1896 |
+
"grad_norm": 6.799467086791992,
|
| 1897 |
+
"learning_rate": 5.4123497720679655e-06,
|
| 1898 |
+
"loss": 0.0576,
|
| 1899 |
+
"step": 2260
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 2.337796086508754,
|
| 1903 |
+
"grad_norm": 3.510343551635742,
|
| 1904 |
+
"learning_rate": 5.329465395772897e-06,
|
| 1905 |
+
"loss": 0.0354,
|
| 1906 |
+
"step": 2270
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.348094747682801,
|
| 1910 |
+
"grad_norm": 17.81386947631836,
|
| 1911 |
+
"learning_rate": 5.246581019477829e-06,
|
| 1912 |
+
"loss": 0.1046,
|
| 1913 |
+
"step": 2280
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 2.358393408856849,
|
| 1917 |
+
"grad_norm": 1.548386573791504,
|
| 1918 |
+
"learning_rate": 5.163696643182761e-06,
|
| 1919 |
+
"loss": 0.0688,
|
| 1920 |
+
"step": 2290
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.368692070030896,
|
| 1924 |
+
"grad_norm": 19.792476654052734,
|
| 1925 |
+
"learning_rate": 5.080812266887692e-06,
|
| 1926 |
+
"loss": 0.0602,
|
| 1927 |
+
"step": 2300
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.368692070030896,
|
| 1931 |
+
"eval_accuracy": 0.96086508753862,
|
| 1932 |
+
"eval_accuracy_label_0": 0.9664407156350706,
|
| 1933 |
+
"eval_accuracy_label_1": 0.953189536484626,
|
| 1934 |
+
"eval_f1": 0.9608634468691928,
|
| 1935 |
+
"eval_loss": 0.12112918496131897,
|
| 1936 |
+
"eval_precision": 0.9608619366174393,
|
| 1937 |
+
"eval_recall": 0.96086508753862,
|
| 1938 |
+
"eval_runtime": 28.6488,
|
| 1939 |
+
"eval_samples_per_second": 542.291,
|
| 1940 |
+
"eval_steps_per_second": 16.964,
|
| 1941 |
+
"step": 2300
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.378990731204943,
|
| 1945 |
+
"grad_norm": 14.4805269241333,
|
| 1946 |
+
"learning_rate": 4.997927890592623e-06,
|
| 1947 |
+
"loss": 0.0683,
|
| 1948 |
+
"step": 2310
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 2.389289392378991,
|
| 1952 |
+
"grad_norm": 23.142452239990234,
|
| 1953 |
+
"learning_rate": 4.9150435142975555e-06,
|
| 1954 |
+
"loss": 0.0669,
|
| 1955 |
+
"step": 2320
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 2.399588053553038,
|
| 1959 |
+
"grad_norm": 17.42975616455078,
|
| 1960 |
+
"learning_rate": 4.832159138002487e-06,
|
| 1961 |
+
"loss": 0.0774,
|
| 1962 |
+
"step": 2330
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 2.4098867147270857,
|
| 1966 |
+
"grad_norm": 20.081676483154297,
|
| 1967 |
+
"learning_rate": 4.749274761707419e-06,
|
| 1968 |
+
"loss": 0.0714,
|
| 1969 |
+
"step": 2340
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 2.420185375901133,
|
| 1973 |
+
"grad_norm": 15.057238578796387,
|
| 1974 |
+
"learning_rate": 4.66639038541235e-06,
|
| 1975 |
+
"loss": 0.0702,
|
| 1976 |
+
"step": 2350
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 2.43048403707518,
|
| 1980 |
+
"grad_norm": 15.039963722229004,
|
| 1981 |
+
"learning_rate": 4.583506009117281e-06,
|
| 1982 |
+
"loss": 0.0548,
|
| 1983 |
+
"step": 2360
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 2.4407826982492278,
|
| 1987 |
+
"grad_norm": 10.758746147155762,
|
| 1988 |
+
"learning_rate": 4.5006216328222135e-06,
|
| 1989 |
+
"loss": 0.0444,
|
| 1990 |
+
"step": 2370
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 2.451081359423275,
|
| 1994 |
+
"grad_norm": 18.213958740234375,
|
| 1995 |
+
"learning_rate": 4.417737256527145e-06,
|
| 1996 |
+
"loss": 0.0559,
|
| 1997 |
+
"step": 2380
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 2.461380020597322,
|
| 2001 |
+
"grad_norm": 17.926952362060547,
|
| 2002 |
+
"learning_rate": 4.334852880232077e-06,
|
| 2003 |
+
"loss": 0.0675,
|
| 2004 |
+
"step": 2390
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 2.47167868177137,
|
| 2008 |
+
"grad_norm": 7.6708807945251465,
|
| 2009 |
+
"learning_rate": 4.251968503937008e-06,
|
| 2010 |
+
"loss": 0.0951,
|
| 2011 |
+
"step": 2400
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 2.47167868177137,
|
| 2015 |
+
"eval_accuracy": 0.9614443872296602,
|
| 2016 |
+
"eval_accuracy_label_0": 0.962773641515724,
|
| 2017 |
+
"eval_accuracy_label_1": 0.9596145020651675,
|
| 2018 |
+
"eval_f1": 0.9614721624380318,
|
| 2019 |
+
"eval_loss": 0.1193719357252121,
|
| 2020 |
+
"eval_precision": 0.9615409347691732,
|
| 2021 |
+
"eval_recall": 0.9614443872296602,
|
| 2022 |
+
"eval_runtime": 28.6329,
|
| 2023 |
+
"eval_samples_per_second": 542.592,
|
| 2024 |
+
"eval_steps_per_second": 16.973,
|
| 2025 |
+
"step": 2400
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 2.481977342945417,
|
| 2029 |
+
"grad_norm": 15.066208839416504,
|
| 2030 |
+
"learning_rate": 4.169084127641939e-06,
|
| 2031 |
+
"loss": 0.0683,
|
| 2032 |
+
"step": 2410
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 2.4922760041194643,
|
| 2036 |
+
"grad_norm": 23.18450355529785,
|
| 2037 |
+
"learning_rate": 4.086199751346871e-06,
|
| 2038 |
+
"loss": 0.0626,
|
| 2039 |
+
"step": 2420
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 2.502574665293512,
|
| 2043 |
+
"grad_norm": 0.8303961753845215,
|
| 2044 |
+
"learning_rate": 4.003315375051803e-06,
|
| 2045 |
+
"loss": 0.0476,
|
| 2046 |
+
"step": 2430
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 2.512873326467559,
|
| 2050 |
+
"grad_norm": 20.618289947509766,
|
| 2051 |
+
"learning_rate": 3.920430998756735e-06,
|
| 2052 |
+
"loss": 0.0582,
|
| 2053 |
+
"step": 2440
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 2.5231719876416063,
|
| 2057 |
+
"grad_norm": 6.84626579284668,
|
| 2058 |
+
"learning_rate": 3.837546622461666e-06,
|
| 2059 |
+
"loss": 0.057,
|
| 2060 |
+
"step": 2450
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 2.533470648815654,
|
| 2064 |
+
"grad_norm": 4.529855251312256,
|
| 2065 |
+
"learning_rate": 3.7546622461665977e-06,
|
| 2066 |
+
"loss": 0.0523,
|
| 2067 |
+
"step": 2460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 2.543769309989701,
|
| 2071 |
+
"grad_norm": 14.540194511413574,
|
| 2072 |
+
"learning_rate": 3.6717778698715294e-06,
|
| 2073 |
+
"loss": 0.0906,
|
| 2074 |
+
"step": 2470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 2.554067971163749,
|
| 2078 |
+
"grad_norm": 25.749385833740234,
|
| 2079 |
+
"learning_rate": 3.5888934935764615e-06,
|
| 2080 |
+
"loss": 0.0516,
|
| 2081 |
+
"step": 2480
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 2.564366632337796,
|
| 2085 |
+
"grad_norm": 12.172739028930664,
|
| 2086 |
+
"learning_rate": 3.5060091172813927e-06,
|
| 2087 |
+
"loss": 0.0597,
|
| 2088 |
+
"step": 2490
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 2.5746652935118437,
|
| 2092 |
+
"grad_norm": 1.8584766387939453,
|
| 2093 |
+
"learning_rate": 3.4231247409863244e-06,
|
| 2094 |
+
"loss": 0.0343,
|
| 2095 |
+
"step": 2500
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 2.5746652935118437,
|
| 2099 |
+
"eval_accuracy": 0.9628604531410917,
|
| 2100 |
+
"eval_accuracy_label_0": 0.9624402711412379,
|
| 2101 |
+
"eval_accuracy_label_1": 0.9634388863392994,
|
| 2102 |
+
"eval_f1": 0.962897301831431,
|
| 2103 |
+
"eval_loss": 0.12369329482316971,
|
| 2104 |
+
"eval_precision": 0.9630139003703244,
|
| 2105 |
+
"eval_recall": 0.9628604531410917,
|
| 2106 |
+
"eval_runtime": 28.6342,
|
| 2107 |
+
"eval_samples_per_second": 542.569,
|
| 2108 |
+
"eval_steps_per_second": 16.973,
|
| 2109 |
+
"step": 2500
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 2.584963954685891,
|
| 2113 |
+
"grad_norm": 15.55650520324707,
|
| 2114 |
+
"learning_rate": 3.340240364691256e-06,
|
| 2115 |
+
"loss": 0.0645,
|
| 2116 |
+
"step": 2510
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 2.595262615859938,
|
| 2120 |
+
"grad_norm": 5.339417934417725,
|
| 2121 |
+
"learning_rate": 3.2573559883961873e-06,
|
| 2122 |
+
"loss": 0.0497,
|
| 2123 |
+
"step": 2520
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 2.6055612770339858,
|
| 2127 |
+
"grad_norm": 18.813339233398438,
|
| 2128 |
+
"learning_rate": 3.1744716121011194e-06,
|
| 2129 |
+
"loss": 0.0856,
|
| 2130 |
+
"step": 2530
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 2.615859938208033,
|
| 2134 |
+
"grad_norm": 18.912582397460938,
|
| 2135 |
+
"learning_rate": 3.0915872358060507e-06,
|
| 2136 |
+
"loss": 0.0684,
|
| 2137 |
+
"step": 2540
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 2.62615859938208,
|
| 2141 |
+
"grad_norm": 29.817142486572266,
|
| 2142 |
+
"learning_rate": 3.0087028595109823e-06,
|
| 2143 |
+
"loss": 0.0742,
|
| 2144 |
+
"step": 2550
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 2.636457260556128,
|
| 2148 |
+
"grad_norm": 20.53231430053711,
|
| 2149 |
+
"learning_rate": 2.925818483215914e-06,
|
| 2150 |
+
"loss": 0.0675,
|
| 2151 |
+
"step": 2560
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 2.646755921730175,
|
| 2155 |
+
"grad_norm": 1.9606025218963623,
|
| 2156 |
+
"learning_rate": 2.8429341069208453e-06,
|
| 2157 |
+
"loss": 0.0319,
|
| 2158 |
+
"step": 2570
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 2.6570545829042223,
|
| 2162 |
+
"grad_norm": 15.020525932312012,
|
| 2163 |
+
"learning_rate": 2.7600497306257774e-06,
|
| 2164 |
+
"loss": 0.0681,
|
| 2165 |
+
"step": 2580
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 2.66735324407827,
|
| 2169 |
+
"grad_norm": 13.114953994750977,
|
| 2170 |
+
"learning_rate": 2.677165354330709e-06,
|
| 2171 |
+
"loss": 0.0348,
|
| 2172 |
+
"step": 2590
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 2.677651905252317,
|
| 2176 |
+
"grad_norm": 25.307437896728516,
|
| 2177 |
+
"learning_rate": 2.5942809780356403e-06,
|
| 2178 |
+
"loss": 0.0512,
|
| 2179 |
+
"step": 2600
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 2.677651905252317,
|
| 2183 |
+
"eval_accuracy": 0.9625386199794027,
|
| 2184 |
+
"eval_accuracy_label_0": 0.9737748638737638,
|
| 2185 |
+
"eval_accuracy_label_1": 0.947070521646015,
|
| 2186 |
+
"eval_f1": 0.962493472042095,
|
| 2187 |
+
"eval_loss": 0.12632428109645844,
|
| 2188 |
+
"eval_precision": 0.9625475718092084,
|
| 2189 |
+
"eval_recall": 0.9625386199794027,
|
| 2190 |
+
"eval_runtime": 28.7287,
|
| 2191 |
+
"eval_samples_per_second": 540.783,
|
| 2192 |
+
"eval_steps_per_second": 16.917,
|
| 2193 |
+
"step": 2600
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 2.6879505664263643,
|
| 2197 |
+
"grad_norm": 19.501306533813477,
|
| 2198 |
+
"learning_rate": 2.5113966017405724e-06,
|
| 2199 |
+
"loss": 0.0515,
|
| 2200 |
+
"step": 2610
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 2.698249227600412,
|
| 2204 |
+
"grad_norm": 17.550600051879883,
|
| 2205 |
+
"learning_rate": 2.4285122254455037e-06,
|
| 2206 |
+
"loss": 0.0491,
|
| 2207 |
+
"step": 2620
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 2.708547888774459,
|
| 2211 |
+
"grad_norm": 36.03532409667969,
|
| 2212 |
+
"learning_rate": 2.3456278491504353e-06,
|
| 2213 |
+
"loss": 0.085,
|
| 2214 |
+
"step": 2630
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 2.718846549948507,
|
| 2218 |
+
"grad_norm": 11.236651420593262,
|
| 2219 |
+
"learning_rate": 2.262743472855367e-06,
|
| 2220 |
+
"loss": 0.0656,
|
| 2221 |
+
"step": 2640
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 2.729145211122554,
|
| 2225 |
+
"grad_norm": 12.065185546875,
|
| 2226 |
+
"learning_rate": 2.1798590965602987e-06,
|
| 2227 |
+
"loss": 0.0698,
|
| 2228 |
+
"step": 2650
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 2.7394438722966017,
|
| 2232 |
+
"grad_norm": 0.8977580070495605,
|
| 2233 |
+
"learning_rate": 2.0969747202652304e-06,
|
| 2234 |
+
"loss": 0.0646,
|
| 2235 |
+
"step": 2660
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 2.749742533470649,
|
| 2239 |
+
"grad_norm": 14.258803367614746,
|
| 2240 |
+
"learning_rate": 2.0140903439701616e-06,
|
| 2241 |
+
"loss": 0.065,
|
| 2242 |
+
"step": 2670
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 2.760041194644696,
|
| 2246 |
+
"grad_norm": 1.7737594842910767,
|
| 2247 |
+
"learning_rate": 1.9312059676750933e-06,
|
| 2248 |
+
"loss": 0.0412,
|
| 2249 |
+
"step": 2680
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 2.7703398558187438,
|
| 2253 |
+
"grad_norm": 5.75368595123291,
|
| 2254 |
+
"learning_rate": 1.8483215913800252e-06,
|
| 2255 |
+
"loss": 0.0681,
|
| 2256 |
+
"step": 2690
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 2.780638516992791,
|
| 2260 |
+
"grad_norm": 44.601314544677734,
|
| 2261 |
+
"learning_rate": 1.7654372150849566e-06,
|
| 2262 |
+
"loss": 0.0532,
|
| 2263 |
+
"step": 2700
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 2.780638516992791,
|
| 2267 |
+
"eval_accuracy": 0.9633110195674562,
|
| 2268 |
+
"eval_accuracy_label_0": 0.9705522835870652,
|
| 2269 |
+
"eval_accuracy_label_1": 0.9533425118555913,
|
| 2270 |
+
"eval_f1": 0.9632954018759314,
|
| 2271 |
+
"eval_loss": 0.12292636930942535,
|
| 2272 |
+
"eval_precision": 0.963292880058248,
|
| 2273 |
+
"eval_recall": 0.9633110195674562,
|
| 2274 |
+
"eval_runtime": 28.687,
|
| 2275 |
+
"eval_samples_per_second": 541.569,
|
| 2276 |
+
"eval_steps_per_second": 16.941,
|
| 2277 |
+
"step": 2700
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 2.790937178166838,
|
| 2281 |
+
"grad_norm": 12.678955078125,
|
| 2282 |
+
"learning_rate": 1.682552838789888e-06,
|
| 2283 |
+
"loss": 0.0683,
|
| 2284 |
+
"step": 2710
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 2.801235839340886,
|
| 2288 |
+
"grad_norm": 1.118263602256775,
|
| 2289 |
+
"learning_rate": 1.59966846249482e-06,
|
| 2290 |
+
"loss": 0.0303,
|
| 2291 |
+
"step": 2720
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 2.811534500514933,
|
| 2295 |
+
"grad_norm": 14.192521095275879,
|
| 2296 |
+
"learning_rate": 1.5167840861997514e-06,
|
| 2297 |
+
"loss": 0.0681,
|
| 2298 |
+
"step": 2730
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 2.8218331616889802,
|
| 2302 |
+
"grad_norm": 18.46016502380371,
|
| 2303 |
+
"learning_rate": 1.4338997099046831e-06,
|
| 2304 |
+
"loss": 0.0686,
|
| 2305 |
+
"step": 2740
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 2.832131822863028,
|
| 2309 |
+
"grad_norm": 15.062724113464355,
|
| 2310 |
+
"learning_rate": 1.3510153336096146e-06,
|
| 2311 |
+
"loss": 0.0521,
|
| 2312 |
+
"step": 2750
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 2.842430484037075,
|
| 2316 |
+
"grad_norm": 7.8030900955200195,
|
| 2317 |
+
"learning_rate": 1.2681309573145465e-06,
|
| 2318 |
+
"loss": 0.0923,
|
| 2319 |
+
"step": 2760
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 2.8527291452111223,
|
| 2323 |
+
"grad_norm": 5.273398399353027,
|
| 2324 |
+
"learning_rate": 1.185246581019478e-06,
|
| 2325 |
+
"loss": 0.0471,
|
| 2326 |
+
"step": 2770
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 2.86302780638517,
|
| 2330 |
+
"grad_norm": 10.055742263793945,
|
| 2331 |
+
"learning_rate": 1.1023622047244096e-06,
|
| 2332 |
+
"loss": 0.0517,
|
| 2333 |
+
"step": 2780
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 2.873326467559217,
|
| 2337 |
+
"grad_norm": 22.551183700561523,
|
| 2338 |
+
"learning_rate": 1.0194778284293413e-06,
|
| 2339 |
+
"loss": 0.0497,
|
| 2340 |
+
"step": 2790
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 2.883625128733265,
|
| 2344 |
+
"grad_norm": 10.616918563842773,
|
| 2345 |
+
"learning_rate": 9.365934521342727e-07,
|
| 2346 |
+
"loss": 0.0673,
|
| 2347 |
+
"step": 2800
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 2.883625128733265,
|
| 2351 |
+
"eval_accuracy": 0.9644052523171988,
|
| 2352 |
+
"eval_accuracy_label_0": 0.9678853205911768,
|
| 2353 |
+
"eval_accuracy_label_1": 0.9596145020651675,
|
| 2354 |
+
"eval_f1": 0.9644144636556568,
|
| 2355 |
+
"eval_loss": 0.12062814831733704,
|
| 2356 |
+
"eval_precision": 0.9644287833599177,
|
| 2357 |
+
"eval_recall": 0.9644052523171988,
|
| 2358 |
+
"eval_runtime": 28.6805,
|
| 2359 |
+
"eval_samples_per_second": 541.691,
|
| 2360 |
+
"eval_steps_per_second": 16.945,
|
| 2361 |
+
"step": 2800
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 2.893923789907312,
|
| 2365 |
+
"grad_norm": 12.785795211791992,
|
| 2366 |
+
"learning_rate": 8.537090758392044e-07,
|
| 2367 |
+
"loss": 0.0662,
|
| 2368 |
+
"step": 2810
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 2.9042224510813597,
|
| 2372 |
+
"grad_norm": 8.8677396774292,
|
| 2373 |
+
"learning_rate": 7.70824699544136e-07,
|
| 2374 |
+
"loss": 0.0789,
|
| 2375 |
+
"step": 2820
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 2.914521112255407,
|
| 2379 |
+
"grad_norm": 19.09882354736328,
|
| 2380 |
+
"learning_rate": 6.879403232490677e-07,
|
| 2381 |
+
"loss": 0.0358,
|
| 2382 |
+
"step": 2830
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 2.924819773429454,
|
| 2386 |
+
"grad_norm": 13.237493515014648,
|
| 2387 |
+
"learning_rate": 6.050559469539992e-07,
|
| 2388 |
+
"loss": 0.069,
|
| 2389 |
+
"step": 2840
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 2.9351184346035017,
|
| 2393 |
+
"grad_norm": 0.5621568560600281,
|
| 2394 |
+
"learning_rate": 5.221715706589308e-07,
|
| 2395 |
+
"loss": 0.0503,
|
| 2396 |
+
"step": 2850
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 2.945417095777549,
|
| 2400 |
+
"grad_norm": 11.271636009216309,
|
| 2401 |
+
"learning_rate": 4.392871943638625e-07,
|
| 2402 |
+
"loss": 0.0379,
|
| 2403 |
+
"step": 2860
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 2.955715756951596,
|
| 2407 |
+
"grad_norm": 14.567364692687988,
|
| 2408 |
+
"learning_rate": 3.564028180687941e-07,
|
| 2409 |
+
"loss": 0.0489,
|
| 2410 |
+
"step": 2870
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 2.966014418125644,
|
| 2414 |
+
"grad_norm": 11.992318153381348,
|
| 2415 |
+
"learning_rate": 2.7351844177372567e-07,
|
| 2416 |
+
"loss": 0.0569,
|
| 2417 |
+
"step": 2880
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 2.976313079299691,
|
| 2421 |
+
"grad_norm": 9.122631072998047,
|
| 2422 |
+
"learning_rate": 1.9063406547865727e-07,
|
| 2423 |
+
"loss": 0.0704,
|
| 2424 |
+
"step": 2890
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 2.9866117404737382,
|
| 2428 |
+
"grad_norm": 28.3140869140625,
|
| 2429 |
+
"learning_rate": 1.077496891835889e-07,
|
| 2430 |
+
"loss": 0.0209,
|
| 2431 |
+
"step": 2900
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 2.9866117404737382,
|
| 2435 |
+
"eval_accuracy": 0.9644696189495365,
|
| 2436 |
+
"eval_accuracy_label_0": 0.9708856539615512,
|
| 2437 |
+
"eval_accuracy_label_1": 0.9556371424200704,
|
| 2438 |
+
"eval_f1": 0.9644590852602763,
|
| 2439 |
+
"eval_loss": 0.11849933117628098,
|
| 2440 |
+
"eval_precision": 0.9644549735327069,
|
| 2441 |
+
"eval_recall": 0.9644696189495365,
|
| 2442 |
+
"eval_runtime": 28.6233,
|
| 2443 |
+
"eval_samples_per_second": 542.775,
|
| 2444 |
+
"eval_steps_per_second": 16.979,
|
| 2445 |
+
"step": 2900
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 2.996910401647786,
|
| 2449 |
+
"grad_norm": 26.769432067871094,
|
| 2450 |
+
"learning_rate": 2.4865312888520517e-08,
|
| 2451 |
+
"loss": 0.0621,
|
| 2452 |
+
"step": 2910
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 3.0,
|
| 2456 |
+
"step": 2913,
|
| 2457 |
+
"total_flos": 2227577912202240.0,
|
| 2458 |
+
"train_loss": 0.15083247099878697,
|
| 2459 |
+
"train_runtime": 1636.2013,
|
| 2460 |
+
"train_samples_per_second": 113.936,
|
| 2461 |
+
"train_steps_per_second": 1.78
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 3.0,
|
| 2465 |
+
"eval_accuracy": 0.9645339855818743,
|
| 2466 |
+
"eval_accuracy_label_0": 0.9707745305033892,
|
| 2467 |
+
"eval_accuracy_label_1": 0.9559430931620009,
|
| 2468 |
+
"eval_f1": 0.9645246094465593,
|
| 2469 |
+
"eval_loss": 0.11850666999816895,
|
| 2470 |
+
"eval_precision": 0.9645203525935409,
|
| 2471 |
+
"eval_recall": 0.9645339855818743,
|
| 2472 |
+
"eval_runtime": 28.6606,
|
| 2473 |
+
"eval_samples_per_second": 542.068,
|
| 2474 |
+
"eval_steps_per_second": 16.957,
|
| 2475 |
+
"step": 2913
|
| 2476 |
+
}
|
| 2477 |
+
],
|
| 2478 |
+
"logging_steps": 10,
|
| 2479 |
+
"max_steps": 2913,
|
| 2480 |
+
"num_input_tokens_seen": 0,
|
| 2481 |
+
"num_train_epochs": 3,
|
| 2482 |
+
"save_steps": 1000,
|
| 2483 |
+
"stateful_callbacks": {
|
| 2484 |
+
"TrainerControl": {
|
| 2485 |
+
"args": {
|
| 2486 |
+
"should_epoch_stop": false,
|
| 2487 |
+
"should_evaluate": false,
|
| 2488 |
+
"should_log": false,
|
| 2489 |
+
"should_save": true,
|
| 2490 |
+
"should_training_stop": true
|
| 2491 |
+
},
|
| 2492 |
+
"attributes": {}
|
| 2493 |
+
}
|
| 2494 |
+
},
|
| 2495 |
+
"total_flos": 2227577912202240.0,
|
| 2496 |
+
"train_batch_size": 32,
|
| 2497 |
+
"trial_name": null,
|
| 2498 |
+
"trial_params": null
|
| 2499 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b8991243179bbe322d3159dfe9a2a2430235f8765d622db8c000b59736a76f4
|
| 3 |
+
size 5112
|