Upload folder using huggingface_hub
Browse files- README.md +185 -0
- all_results.json +182 -0
- config.json +98 -0
- eval_results.json +91 -0
- model.safetensors +3 -0
- pred_results.json +89 -0
- predictions.pkl +3 -0
- runs/May03_13-07-30_jzxh358/events.out.tfevents.1746270461.jzxh358.1141829.0 +3 -0
- runs/May03_13-07-30_jzxh358/events.out.tfevents.1746271047.jzxh358.1141829.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- train_results.json +8 -0
- trainer_state.json +560 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
datasets:
|
| 4 |
+
- WebOrganizer/TopicAnnotations-Llama-3.1-8B
|
| 5 |
+
- WebOrganizer/TopicAnnotations-Llama-3.1-405B-FP8
|
| 6 |
+
base_model:
|
| 7 |
+
- answerdotai/ModernBERT-base
|
| 8 |
+
---
|
| 9 |
+
# wissamantoun/WebOrganizer-FormatClassifier-ModernBERT
|
| 10 |
+
|
| 11 |
+
[[Paper](https://arxiv.org/abs/2502.10341)] [[Website](https://weborganizer.allenai.org)] [[GitHub](https://github.com/CodeCreator/WebOrganizer)]
|
| 12 |
+
|
| 13 |
+
*All credit goes to the original authors of the model and dataset. This is a retraining of the original model with a different base model*
|
| 14 |
+
|
| 15 |
+
The TopicClassifier organizes web content into 17 categories based on the URL and text contents of web pages.
|
| 16 |
+
The model is a [ModernBERT-base](answerdotai/ModernBERT-base) with 140M parameters fine-tuned on the following training data:
|
| 17 |
+
|
| 18 |
+
1. [WebOrganizer/TopicAnnotations-Llama-3.1-8B](https://huggingface.co/datasets/WebOrganizer/TopicAnnotations-Llama-3.1-8B): 1M documents annotated by Llama-3.1-8B (first-stage training)
|
| 19 |
+
2. [WebOrganizer/TopicAnnotations-Llama-3.1-405B-FP8](https://huggingface.co/datasets/WebOrganizer/TopicAnnotations-Llama-3.1-405B-FP8): 100K documents annotated by Llama-3.1-405B-FP8 (second-stage training)
|
| 20 |
+
|
| 21 |
+
#### All Domain Classifiers
|
| 22 |
+
- [wissamantoun/WebOrganizer-FormatClassifier-ModernBERT](https://huggingface.co/wissamantoun/WebOrganizer-FormatClassifier-ModernBERT) *← you are here!*
|
| 23 |
+
- [wissamantoun/WebOrganizer-TopicClassifier-ModernBERT](https://huggingface.co/wissamantoun/WebOrganizer-TopicClassifier-ModernBERT)
|
| 24 |
+
|
| 25 |
+
## Usage
|
| 26 |
+
|
| 27 |
+
This classifier expects input in the following input format:
|
| 28 |
+
```
|
| 29 |
+
{url}
|
| 30 |
+
|
| 31 |
+
{text}
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
Example:
|
| 35 |
+
```python
|
| 36 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 37 |
+
|
| 38 |
+
tokenizer = AutoTokenizer.from_pretrained("wissamantoun/WebOrganizer-FormatClassifier-ModernBERT")
|
| 39 |
+
model = AutoModelForSequenceClassification.from_pretrained(
|
| 40 |
+
"wissamantoun/WebOrganizer-FormatClassifier-ModernBERT",
|
| 41 |
+
trust_remote_code=True,
|
| 42 |
+
use_memory_efficient_attention=False)
|
| 43 |
+
|
| 44 |
+
web_page = """http://www.example.com
|
| 45 |
+
|
| 46 |
+
How to build a computer from scratch? Here are the components you need..."""
|
| 47 |
+
|
| 48 |
+
inputs = tokenizer([web_page], return_tensors="pt")
|
| 49 |
+
outputs = model(**inputs)
|
| 50 |
+
|
| 51 |
+
probs = outputs.logits.softmax(dim=-1)
|
| 52 |
+
print(probs.argmax(dim=-1))
|
| 53 |
+
# -> 5 ("Hardware" topic)
|
| 54 |
+
```
|
| 55 |
+
|
| 56 |
+
You can convert the `logits` of the model with a softmax to obtain a probability distribution over the following 24 categories (in order of labels, also see `id2label` and `label2id` in the model config):
|
| 57 |
+
1. Adult
|
| 58 |
+
2. Art & Design
|
| 59 |
+
3. Software Dev.
|
| 60 |
+
4. Crime & Law
|
| 61 |
+
5. Education & Jobs
|
| 62 |
+
6. Hardware
|
| 63 |
+
7. Entertainment
|
| 64 |
+
8. Social Life
|
| 65 |
+
9. Fashion & Beauty
|
| 66 |
+
10. Finance & Business
|
| 67 |
+
11. Food & Dining
|
| 68 |
+
12. Games
|
| 69 |
+
13. Health
|
| 70 |
+
14. History
|
| 71 |
+
15. Home & Hobbies
|
| 72 |
+
16. Industrial
|
| 73 |
+
17. Literature
|
| 74 |
+
18. Politics
|
| 75 |
+
19. Religion
|
| 76 |
+
20. Science & Tech.
|
| 77 |
+
21. Software
|
| 78 |
+
22. Sports & Fitness
|
| 79 |
+
23. Transportation
|
| 80 |
+
24. Travel
|
| 81 |
+
|
| 82 |
+
The full definitions of the categories can be found in the [taxonomy config](https://github.com/CodeCreator/WebOrganizer/blob/main/define_domains/taxonomies/topics.yaml).
|
| 83 |
+
|
| 84 |
+
# Scores
|
| 85 |
+
```
|
| 86 |
+
***** pred metrics *****
|
| 87 |
+
test_accuracy = 0.8154
|
| 88 |
+
test_accuracy__0 = 0.855
|
| 89 |
+
test_accuracy__1 = 0.7558
|
| 90 |
+
test_accuracy__10 = 0.9071
|
| 91 |
+
test_accuracy__11 = 0.6869
|
| 92 |
+
test_accuracy__12 = 0.8055
|
| 93 |
+
test_accuracy__13 = 0.7897
|
| 94 |
+
test_accuracy__14 = 0.8592
|
| 95 |
+
test_accuracy__15 = 0.8541
|
| 96 |
+
test_accuracy__16 = 0.8788
|
| 97 |
+
test_accuracy__17 = 0.7733
|
| 98 |
+
test_accuracy__18 = 0.7286
|
| 99 |
+
test_accuracy__19 = 0.6989
|
| 100 |
+
test_accuracy__2 = 0.7474
|
| 101 |
+
test_accuracy__20 = 0.7609
|
| 102 |
+
test_accuracy__21 = 0.7807
|
| 103 |
+
test_accuracy__22 = 0.7703
|
| 104 |
+
test_accuracy__23 = 0.7931
|
| 105 |
+
test_accuracy__3 = 0.6351
|
| 106 |
+
test_accuracy__4 = 0.871
|
| 107 |
+
test_accuracy__5 = 0.8333
|
| 108 |
+
test_accuracy__6 = 0.6125
|
| 109 |
+
test_accuracy__7 = 0.6416
|
| 110 |
+
test_accuracy__8 = 0.78
|
| 111 |
+
test_accuracy__9 = 0.7668
|
| 112 |
+
test_accuracy_conf50 = 0.8312
|
| 113 |
+
test_accuracy_conf50__0 = 0.8852
|
| 114 |
+
test_accuracy_conf50__1 = 0.7651
|
| 115 |
+
test_accuracy_conf50__10 = 0.9167
|
| 116 |
+
test_accuracy_conf50__11 = 0.7168
|
| 117 |
+
test_accuracy_conf50__12 = 0.8256
|
| 118 |
+
test_accuracy_conf50__13 = 0.7996
|
| 119 |
+
test_accuracy_conf50__14 = 0.8696
|
| 120 |
+
test_accuracy_conf50__15 = 0.8684
|
| 121 |
+
test_accuracy_conf50__16 = 0.8878
|
| 122 |
+
test_accuracy_conf50__17 = 0.7838
|
| 123 |
+
test_accuracy_conf50__18 = 0.7663
|
| 124 |
+
test_accuracy_conf50__19 = 0.7276
|
| 125 |
+
test_accuracy_conf50__2 = 0.7609
|
| 126 |
+
test_accuracy_conf50__20 = 0.7907
|
| 127 |
+
test_accuracy_conf50__21 = 0.8
|
| 128 |
+
test_accuracy_conf50__22 = 0.7927
|
| 129 |
+
test_accuracy_conf50__23 = 0.7904
|
| 130 |
+
test_accuracy_conf50__3 = 0.6617
|
| 131 |
+
test_accuracy_conf50__4 = 0.877
|
| 132 |
+
test_accuracy_conf50__5 = 0.8571
|
| 133 |
+
test_accuracy_conf50__6 = 0.6299
|
| 134 |
+
test_accuracy_conf50__7 = 0.6786
|
| 135 |
+
test_accuracy_conf50__8 = 0.7755
|
| 136 |
+
test_accuracy_conf50__9 = 0.7796
|
| 137 |
+
test_accuracy_conf75 = 0.9003 <--- Metric from the paper
|
| 138 |
+
test_accuracy_conf75__0 = 0.9412
|
| 139 |
+
test_accuracy_conf75__1 = 0.8318
|
| 140 |
+
test_accuracy_conf75__10 = 0.9542
|
| 141 |
+
test_accuracy_conf75__11 = 0.8478
|
| 142 |
+
test_accuracy_conf75__12 = 0.8841
|
| 143 |
+
test_accuracy_conf75__13 = 0.8724
|
| 144 |
+
test_accuracy_conf75__14 = 0.914
|
| 145 |
+
test_accuracy_conf75__15 = 0.9345
|
| 146 |
+
test_accuracy_conf75__16 = 0.9316
|
| 147 |
+
test_accuracy_conf75__17 = 0.8667
|
| 148 |
+
test_accuracy_conf75__18 = 0.8446
|
| 149 |
+
test_accuracy_conf75__19 = 0.8209
|
| 150 |
+
test_accuracy_conf75__2 = 0.8333
|
| 151 |
+
test_accuracy_conf75__20 = 0.9333
|
| 152 |
+
test_accuracy_conf75__21 = 0.8587
|
| 153 |
+
test_accuracy_conf75__22 = 0.8708
|
| 154 |
+
test_accuracy_conf75__23 = 0.8309
|
| 155 |
+
test_accuracy_conf75__3 = 0.7292
|
| 156 |
+
test_accuracy_conf75__4 = 0.9357
|
| 157 |
+
test_accuracy_conf75__5 = 0.9032
|
| 158 |
+
test_accuracy_conf75__6 = 0.7816
|
| 159 |
+
test_accuracy_conf75__7 = 0.8011
|
| 160 |
+
test_accuracy_conf75__8 = 0.8409
|
| 161 |
+
test_accuracy_conf75__9 = 0.8592
|
| 162 |
+
test_accuracy_label_average = 0.7744
|
| 163 |
+
test_accuracy_label_average_conf50 = 0.7919
|
| 164 |
+
test_accuracy_label_average_conf75 = 0.8676
|
| 165 |
+
test_accuracy_label_min = 0.6125 <--- Metric from the paper
|
| 166 |
+
test_accuracy_label_min_conf75 = 0.7292
|
| 167 |
+
test_loss = 0.6023
|
| 168 |
+
test_proportion_conf50 = 0.9638
|
| 169 |
+
test_proportion_conf75 = 0.7951
|
| 170 |
+
test_runtime = 0:00:08.38
|
| 171 |
+
test_samples_per_second = 1192.262
|
| 172 |
+
test_steps_per_second = 37.318
|
| 173 |
+
```
|
| 174 |
+
|
| 175 |
+
|
| 176 |
+
|
| 177 |
+
## Citation
|
| 178 |
+
```bibtex
|
| 179 |
+
@article{wettig2025organize,
|
| 180 |
+
title={Organize the Web: Constructing Domains Enhances Pre-Training Data Curation},
|
| 181 |
+
author={Alexander Wettig and Kyle Lo and Sewon Min and Hannaneh Hajishirzi and Danqi Chen and Luca Soldaini},
|
| 182 |
+
journal={arXiv preprint arXiv:2502.10341},
|
| 183 |
+
year={2025}
|
| 184 |
+
}
|
| 185 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.9728,
|
| 3 |
+
"eval_validation.parquet_accuracy": 0.8279,
|
| 4 |
+
"eval_validation.parquet_accuracy__0": 0.831081081081081,
|
| 5 |
+
"eval_validation.parquet_accuracy__1": 0.7971830985915493,
|
| 6 |
+
"eval_validation.parquet_accuracy__10": 0.9108589951377634,
|
| 7 |
+
"eval_validation.parquet_accuracy__11": 0.7390396659707724,
|
| 8 |
+
"eval_validation.parquet_accuracy__12": 0.8164556962025317,
|
| 9 |
+
"eval_validation.parquet_accuracy__13": 0.7906542056074767,
|
| 10 |
+
"eval_validation.parquet_accuracy__14": 0.875,
|
| 11 |
+
"eval_validation.parquet_accuracy__15": 0.8706088992974239,
|
| 12 |
+
"eval_validation.parquet_accuracy__16": 0.8806916426512968,
|
| 13 |
+
"eval_validation.parquet_accuracy__17": 0.8229166666666666,
|
| 14 |
+
"eval_validation.parquet_accuracy__18": 0.7022222222222222,
|
| 15 |
+
"eval_validation.parquet_accuracy__19": 0.7072368421052632,
|
| 16 |
+
"eval_validation.parquet_accuracy__2": 0.717948717948718,
|
| 17 |
+
"eval_validation.parquet_accuracy__20": 0.6097560975609756,
|
| 18 |
+
"eval_validation.parquet_accuracy__21": 0.7575757575757576,
|
| 19 |
+
"eval_validation.parquet_accuracy__22": 0.7551020408163265,
|
| 20 |
+
"eval_validation.parquet_accuracy__23": 0.8111111111111111,
|
| 21 |
+
"eval_validation.parquet_accuracy__3": 0.751937984496124,
|
| 22 |
+
"eval_validation.parquet_accuracy__4": 0.874251497005988,
|
| 23 |
+
"eval_validation.parquet_accuracy__5": 0.8125,
|
| 24 |
+
"eval_validation.parquet_accuracy__6": 0.623574144486692,
|
| 25 |
+
"eval_validation.parquet_accuracy__7": 0.6719367588932806,
|
| 26 |
+
"eval_validation.parquet_accuracy__8": 0.8928571428571429,
|
| 27 |
+
"eval_validation.parquet_accuracy__9": 0.8181818181818182,
|
| 28 |
+
"eval_validation.parquet_accuracy_conf50": 0.8428349715468184,
|
| 29 |
+
"eval_validation.parquet_accuracy_conf50__0": 0.8540145985401459,
|
| 30 |
+
"eval_validation.parquet_accuracy_conf50__1": 0.8159057437407953,
|
| 31 |
+
"eval_validation.parquet_accuracy_conf50__10": 0.9169407894736842,
|
| 32 |
+
"eval_validation.parquet_accuracy_conf50__11": 0.7593818984547461,
|
| 33 |
+
"eval_validation.parquet_accuracy_conf50__12": 0.8377483443708609,
|
| 34 |
+
"eval_validation.parquet_accuracy_conf50__13": 0.8062015503875969,
|
| 35 |
+
"eval_validation.parquet_accuracy_conf50__14": 0.8918918918918919,
|
| 36 |
+
"eval_validation.parquet_accuracy_conf50__15": 0.8822822822822823,
|
| 37 |
+
"eval_validation.parquet_accuracy_conf50__16": 0.887905604719764,
|
| 38 |
+
"eval_validation.parquet_accuracy_conf50__17": 0.8229166666666666,
|
| 39 |
+
"eval_validation.parquet_accuracy_conf50__18": 0.7183098591549296,
|
| 40 |
+
"eval_validation.parquet_accuracy_conf50__19": 0.7353951890034365,
|
| 41 |
+
"eval_validation.parquet_accuracy_conf50__2": 0.7333333333333333,
|
| 42 |
+
"eval_validation.parquet_accuracy_conf50__20": 0.6578947368421053,
|
| 43 |
+
"eval_validation.parquet_accuracy_conf50__21": 0.7653061224489796,
|
| 44 |
+
"eval_validation.parquet_accuracy_conf50__22": 0.7808641975308642,
|
| 45 |
+
"eval_validation.parquet_accuracy_conf50__23": 0.8202247191011236,
|
| 46 |
+
"eval_validation.parquet_accuracy_conf50__3": 0.775,
|
| 47 |
+
"eval_validation.parquet_accuracy_conf50__4": 0.8803030303030303,
|
| 48 |
+
"eval_validation.parquet_accuracy_conf50__5": 0.8125,
|
| 49 |
+
"eval_validation.parquet_accuracy_conf50__6": 0.6470588235294118,
|
| 50 |
+
"eval_validation.parquet_accuracy_conf50__7": 0.7205240174672489,
|
| 51 |
+
"eval_validation.parquet_accuracy_conf50__8": 0.8928571428571429,
|
| 52 |
+
"eval_validation.parquet_accuracy_conf50__9": 0.8224852071005917,
|
| 53 |
+
"eval_validation.parquet_accuracy_conf75": 0.9034977352793155,
|
| 54 |
+
"eval_validation.parquet_accuracy_conf75__0": 0.8947368421052632,
|
| 55 |
+
"eval_validation.parquet_accuracy_conf75__1": 0.8790613718411552,
|
| 56 |
+
"eval_validation.parquet_accuracy_conf75__10": 0.9492619926199262,
|
| 57 |
+
"eval_validation.parquet_accuracy_conf75__11": 0.8811188811188811,
|
| 58 |
+
"eval_validation.parquet_accuracy_conf75__12": 0.8793774319066148,
|
| 59 |
+
"eval_validation.parquet_accuracy_conf75__13": 0.8762135922330098,
|
| 60 |
+
"eval_validation.parquet_accuracy_conf75__14": 0.9235294117647059,
|
| 61 |
+
"eval_validation.parquet_accuracy_conf75__15": 0.9338181818181818,
|
| 62 |
+
"eval_validation.parquet_accuracy_conf75__16": 0.9240506329113924,
|
| 63 |
+
"eval_validation.parquet_accuracy_conf75__17": 0.9240506329113924,
|
| 64 |
+
"eval_validation.parquet_accuracy_conf75__18": 0.7861635220125787,
|
| 65 |
+
"eval_validation.parquet_accuracy_conf75__19": 0.8385650224215246,
|
| 66 |
+
"eval_validation.parquet_accuracy_conf75__2": 0.7627118644067796,
|
| 67 |
+
"eval_validation.parquet_accuracy_conf75__20": 0.7777777777777778,
|
| 68 |
+
"eval_validation.parquet_accuracy_conf75__21": 0.88,
|
| 69 |
+
"eval_validation.parquet_accuracy_conf75__22": 0.8735632183908046,
|
| 70 |
+
"eval_validation.parquet_accuracy_conf75__23": 0.8656716417910447,
|
| 71 |
+
"eval_validation.parquet_accuracy_conf75__3": 0.8390804597701149,
|
| 72 |
+
"eval_validation.parquet_accuracy_conf75__4": 0.9387755102040817,
|
| 73 |
+
"eval_validation.parquet_accuracy_conf75__5": 0.8888888888888888,
|
| 74 |
+
"eval_validation.parquet_accuracy_conf75__6": 0.7543859649122807,
|
| 75 |
+
"eval_validation.parquet_accuracy_conf75__7": 0.7965116279069767,
|
| 76 |
+
"eval_validation.parquet_accuracy_conf75__8": 0.94,
|
| 77 |
+
"eval_validation.parquet_accuracy_conf75__9": 0.9015151515151515,
|
| 78 |
+
"eval_validation.parquet_accuracy_label_average": 0.7850284202694991,
|
| 79 |
+
"eval_validation.parquet_accuracy_label_average_conf50": 0.801551906216693,
|
| 80 |
+
"eval_validation.parquet_accuracy_label_average_conf75": 0.8712012342178551,
|
| 81 |
+
"eval_validation.parquet_accuracy_label_min": 0.6097560975609756,
|
| 82 |
+
"eval_validation.parquet_accuracy_label_min_conf50": 0.6470588235294118,
|
| 83 |
+
"eval_validation.parquet_accuracy_label_min_conf75": 0.7543859649122807,
|
| 84 |
+
"eval_validation.parquet_loss": 0.6012852787971497,
|
| 85 |
+
"eval_validation.parquet_proportion_conf50": 0.9665,
|
| 86 |
+
"eval_validation.parquet_proportion_conf75": 0.7948,
|
| 87 |
+
"eval_validation.parquet_runtime": 8.4553,
|
| 88 |
+
"eval_validation.parquet_samples_per_second": 1182.688,
|
| 89 |
+
"eval_validation.parquet_steps_per_second": 37.018,
|
| 90 |
+
"num_input_tokens_seen": 1949274656,
|
| 91 |
+
"test_accuracy": 0.8154,
|
| 92 |
+
"test_accuracy__0": 0.8549618320610687,
|
| 93 |
+
"test_accuracy__1": 0.7558139534883721,
|
| 94 |
+
"test_accuracy__10": 0.9070830159939071,
|
| 95 |
+
"test_accuracy__11": 0.6868686868686869,
|
| 96 |
+
"test_accuracy__12": 0.8054607508532423,
|
| 97 |
+
"test_accuracy__13": 0.7896749521988528,
|
| 98 |
+
"test_accuracy__14": 0.8591549295774648,
|
| 99 |
+
"test_accuracy__15": 0.8541416566626651,
|
| 100 |
+
"test_accuracy__16": 0.8787535410764873,
|
| 101 |
+
"test_accuracy__17": 0.7733333333333333,
|
| 102 |
+
"test_accuracy__18": 0.7286432160804021,
|
| 103 |
+
"test_accuracy__19": 0.6988847583643123,
|
| 104 |
+
"test_accuracy__2": 0.7473684210526316,
|
| 105 |
+
"test_accuracy__20": 0.7608695652173914,
|
| 106 |
+
"test_accuracy__21": 0.7807017543859649,
|
| 107 |
+
"test_accuracy__22": 0.7703488372093024,
|
| 108 |
+
"test_accuracy__23": 0.7931034482758621,
|
| 109 |
+
"test_accuracy__3": 0.6351351351351351,
|
| 110 |
+
"test_accuracy__4": 0.8709677419354839,
|
| 111 |
+
"test_accuracy__5": 0.8333333333333334,
|
| 112 |
+
"test_accuracy__6": 0.6125461254612546,
|
| 113 |
+
"test_accuracy__7": 0.6415770609318996,
|
| 114 |
+
"test_accuracy__8": 0.78,
|
| 115 |
+
"test_accuracy__9": 0.7668393782383419,
|
| 116 |
+
"test_accuracy_conf50": 0.8311890433699938,
|
| 117 |
+
"test_accuracy_conf50__0": 0.8852459016393442,
|
| 118 |
+
"test_accuracy_conf50__1": 0.7650602409638554,
|
| 119 |
+
"test_accuracy_conf50__10": 0.9167315175097276,
|
| 120 |
+
"test_accuracy_conf50__11": 0.7167755991285403,
|
| 121 |
+
"test_accuracy_conf50__12": 0.8256227758007118,
|
| 122 |
+
"test_accuracy_conf50__13": 0.7995991983967936,
|
| 123 |
+
"test_accuracy_conf50__14": 0.8695652173913043,
|
| 124 |
+
"test_accuracy_conf50__15": 0.8683559950556242,
|
| 125 |
+
"test_accuracy_conf50__16": 0.8877964141122036,
|
| 126 |
+
"test_accuracy_conf50__17": 0.7837837837837838,
|
| 127 |
+
"test_accuracy_conf50__18": 0.7663043478260869,
|
| 128 |
+
"test_accuracy_conf50__19": 0.7276264591439688,
|
| 129 |
+
"test_accuracy_conf50__2": 0.7608695652173914,
|
| 130 |
+
"test_accuracy_conf50__20": 0.7906976744186046,
|
| 131 |
+
"test_accuracy_conf50__21": 0.8,
|
| 132 |
+
"test_accuracy_conf50__22": 0.7926829268292683,
|
| 133 |
+
"test_accuracy_conf50__23": 0.7904191616766467,
|
| 134 |
+
"test_accuracy_conf50__3": 0.6616541353383458,
|
| 135 |
+
"test_accuracy_conf50__4": 0.8770491803278688,
|
| 136 |
+
"test_accuracy_conf50__5": 0.8571428571428571,
|
| 137 |
+
"test_accuracy_conf50__6": 0.6299212598425197,
|
| 138 |
+
"test_accuracy_conf50__7": 0.6785714285714286,
|
| 139 |
+
"test_accuracy_conf50__8": 0.7755102040816326,
|
| 140 |
+
"test_accuracy_conf50__9": 0.7795698924731183,
|
| 141 |
+
"test_accuracy_conf75": 0.9002641177210414,
|
| 142 |
+
"test_accuracy_conf75__0": 0.9411764705882353,
|
| 143 |
+
"test_accuracy_conf75__1": 0.831758034026465,
|
| 144 |
+
"test_accuracy_conf75__10": 0.9541850220264317,
|
| 145 |
+
"test_accuracy_conf75__11": 0.8477508650519031,
|
| 146 |
+
"test_accuracy_conf75__12": 0.8841201716738197,
|
| 147 |
+
"test_accuracy_conf75__13": 0.8724489795918368,
|
| 148 |
+
"test_accuracy_conf75__14": 0.9139784946236559,
|
| 149 |
+
"test_accuracy_conf75__15": 0.9345238095238095,
|
| 150 |
+
"test_accuracy_conf75__16": 0.9315687540348612,
|
| 151 |
+
"test_accuracy_conf75__17": 0.8666666666666667,
|
| 152 |
+
"test_accuracy_conf75__18": 0.8445945945945946,
|
| 153 |
+
"test_accuracy_conf75__19": 0.8208955223880597,
|
| 154 |
+
"test_accuracy_conf75__2": 0.8333333333333334,
|
| 155 |
+
"test_accuracy_conf75__20": 0.9333333333333333,
|
| 156 |
+
"test_accuracy_conf75__21": 0.8586956521739131,
|
| 157 |
+
"test_accuracy_conf75__22": 0.8708487084870848,
|
| 158 |
+
"test_accuracy_conf75__23": 0.8308823529411765,
|
| 159 |
+
"test_accuracy_conf75__3": 0.7291666666666666,
|
| 160 |
+
"test_accuracy_conf75__4": 0.935672514619883,
|
| 161 |
+
"test_accuracy_conf75__5": 0.9032258064516129,
|
| 162 |
+
"test_accuracy_conf75__6": 0.7816091954022989,
|
| 163 |
+
"test_accuracy_conf75__7": 0.8011363636363636,
|
| 164 |
+
"test_accuracy_conf75__8": 0.8409090909090909,
|
| 165 |
+
"test_accuracy_conf75__9": 0.8591549295774648,
|
| 166 |
+
"test_accuracy_label_average": 0.7743985594889748,
|
| 167 |
+
"test_accuracy_label_average_conf50": 0.7919398223613178,
|
| 168 |
+
"test_accuracy_label_average_conf75": 0.8675681388467735,
|
| 169 |
+
"test_accuracy_label_min": 0.6125461254612546,
|
| 170 |
+
"test_accuracy_label_min_conf50": 0.6299212598425197,
|
| 171 |
+
"test_accuracy_label_min_conf75": 0.7291666666666666,
|
| 172 |
+
"test_loss": 0.6023229956626892,
|
| 173 |
+
"test_proportion_conf50": 0.9638,
|
| 174 |
+
"test_proportion_conf75": 0.7951,
|
| 175 |
+
"test_runtime": 8.3874,
|
| 176 |
+
"test_samples_per_second": 1192.262,
|
| 177 |
+
"test_steps_per_second": 37.318,
|
| 178 |
+
"train_loss": 2.327354235526843,
|
| 179 |
+
"train_runtime": 577.2472,
|
| 180 |
+
"train_samples_per_second": 692.944,
|
| 181 |
+
"train_steps_per_second": 1.351
|
| 182 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"embedding_dropout": 0.0,
|
| 16 |
+
"eos_token_id": 50282,
|
| 17 |
+
"global_attn_every_n_layers": 3,
|
| 18 |
+
"global_rope_theta": 160000.0,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 768,
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "Academic Writing",
|
| 24 |
+
"1": "Content Listing",
|
| 25 |
+
"10": "News Article",
|
| 26 |
+
"11": "Nonfiction Writing",
|
| 27 |
+
"12": "About (Org.)",
|
| 28 |
+
"13": "News (Org.)",
|
| 29 |
+
"14": "About (Pers.)",
|
| 30 |
+
"15": "Personal Blog",
|
| 31 |
+
"16": "Product Page",
|
| 32 |
+
"17": "Q&A Forum",
|
| 33 |
+
"18": "Spam / Ads",
|
| 34 |
+
"19": "Structured Data",
|
| 35 |
+
"2": "Creative Writing",
|
| 36 |
+
"20": "Documentation",
|
| 37 |
+
"21": "Audio Transcript",
|
| 38 |
+
"22": "Tutorial",
|
| 39 |
+
"23": "User Review",
|
| 40 |
+
"3": "Customer Support",
|
| 41 |
+
"4": "Comment Section",
|
| 42 |
+
"5": "FAQ",
|
| 43 |
+
"6": "Truncated",
|
| 44 |
+
"7": "Knowledge Article",
|
| 45 |
+
"8": "Legal Notices",
|
| 46 |
+
"9": "Listicle"
|
| 47 |
+
},
|
| 48 |
+
"initializer_cutoff_factor": 2.0,
|
| 49 |
+
"initializer_range": 0.02,
|
| 50 |
+
"intermediate_size": 1152,
|
| 51 |
+
"label2id": {
|
| 52 |
+
"About (Org.)": 12,
|
| 53 |
+
"About (Pers.)": 14,
|
| 54 |
+
"Academic Writing": 0,
|
| 55 |
+
"Audio Transcript": 21,
|
| 56 |
+
"Comment Section": 4,
|
| 57 |
+
"Content Listing": 1,
|
| 58 |
+
"Creative Writing": 2,
|
| 59 |
+
"Customer Support": 3,
|
| 60 |
+
"Documentation": 20,
|
| 61 |
+
"FAQ": 5,
|
| 62 |
+
"Knowledge Article": 7,
|
| 63 |
+
"Legal Notices": 8,
|
| 64 |
+
"Listicle": 9,
|
| 65 |
+
"News (Org.)": 13,
|
| 66 |
+
"News Article": 10,
|
| 67 |
+
"Nonfiction Writing": 11,
|
| 68 |
+
"Personal Blog": 15,
|
| 69 |
+
"Product Page": 16,
|
| 70 |
+
"Q&A Forum": 17,
|
| 71 |
+
"Spam / Ads": 18,
|
| 72 |
+
"Structured Data": 19,
|
| 73 |
+
"Truncated": 6,
|
| 74 |
+
"Tutorial": 22,
|
| 75 |
+
"User Review": 23
|
| 76 |
+
},
|
| 77 |
+
"layer_norm_eps": 1e-05,
|
| 78 |
+
"local_attention": 128,
|
| 79 |
+
"local_rope_theta": 10000.0,
|
| 80 |
+
"max_position_embeddings": 8192,
|
| 81 |
+
"mlp_bias": false,
|
| 82 |
+
"mlp_dropout": 0.0,
|
| 83 |
+
"model_type": "modernbert",
|
| 84 |
+
"norm_bias": false,
|
| 85 |
+
"norm_eps": 1e-05,
|
| 86 |
+
"num_attention_heads": 12,
|
| 87 |
+
"num_hidden_layers": 22,
|
| 88 |
+
"pad_token_id": 50283,
|
| 89 |
+
"position_embedding_type": "absolute",
|
| 90 |
+
"reference_compile": true,
|
| 91 |
+
"repad_logits_with_grad": false,
|
| 92 |
+
"sep_token_id": 50282,
|
| 93 |
+
"sparse_pred_ignore_index": -100,
|
| 94 |
+
"sparse_prediction": false,
|
| 95 |
+
"torch_dtype": "bfloat16",
|
| 96 |
+
"transformers_version": "4.50.0",
|
| 97 |
+
"vocab_size": 50368
|
| 98 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.9728,
|
| 3 |
+
"eval_validation.parquet_accuracy": 0.8279,
|
| 4 |
+
"eval_validation.parquet_accuracy__0": 0.831081081081081,
|
| 5 |
+
"eval_validation.parquet_accuracy__1": 0.7971830985915493,
|
| 6 |
+
"eval_validation.parquet_accuracy__10": 0.9108589951377634,
|
| 7 |
+
"eval_validation.parquet_accuracy__11": 0.7390396659707724,
|
| 8 |
+
"eval_validation.parquet_accuracy__12": 0.8164556962025317,
|
| 9 |
+
"eval_validation.parquet_accuracy__13": 0.7906542056074767,
|
| 10 |
+
"eval_validation.parquet_accuracy__14": 0.875,
|
| 11 |
+
"eval_validation.parquet_accuracy__15": 0.8706088992974239,
|
| 12 |
+
"eval_validation.parquet_accuracy__16": 0.8806916426512968,
|
| 13 |
+
"eval_validation.parquet_accuracy__17": 0.8229166666666666,
|
| 14 |
+
"eval_validation.parquet_accuracy__18": 0.7022222222222222,
|
| 15 |
+
"eval_validation.parquet_accuracy__19": 0.7072368421052632,
|
| 16 |
+
"eval_validation.parquet_accuracy__2": 0.717948717948718,
|
| 17 |
+
"eval_validation.parquet_accuracy__20": 0.6097560975609756,
|
| 18 |
+
"eval_validation.parquet_accuracy__21": 0.7575757575757576,
|
| 19 |
+
"eval_validation.parquet_accuracy__22": 0.7551020408163265,
|
| 20 |
+
"eval_validation.parquet_accuracy__23": 0.8111111111111111,
|
| 21 |
+
"eval_validation.parquet_accuracy__3": 0.751937984496124,
|
| 22 |
+
"eval_validation.parquet_accuracy__4": 0.874251497005988,
|
| 23 |
+
"eval_validation.parquet_accuracy__5": 0.8125,
|
| 24 |
+
"eval_validation.parquet_accuracy__6": 0.623574144486692,
|
| 25 |
+
"eval_validation.parquet_accuracy__7": 0.6719367588932806,
|
| 26 |
+
"eval_validation.parquet_accuracy__8": 0.8928571428571429,
|
| 27 |
+
"eval_validation.parquet_accuracy__9": 0.8181818181818182,
|
| 28 |
+
"eval_validation.parquet_accuracy_conf50": 0.8428349715468184,
|
| 29 |
+
"eval_validation.parquet_accuracy_conf50__0": 0.8540145985401459,
|
| 30 |
+
"eval_validation.parquet_accuracy_conf50__1": 0.8159057437407953,
|
| 31 |
+
"eval_validation.parquet_accuracy_conf50__10": 0.9169407894736842,
|
| 32 |
+
"eval_validation.parquet_accuracy_conf50__11": 0.7593818984547461,
|
| 33 |
+
"eval_validation.parquet_accuracy_conf50__12": 0.8377483443708609,
|
| 34 |
+
"eval_validation.parquet_accuracy_conf50__13": 0.8062015503875969,
|
| 35 |
+
"eval_validation.parquet_accuracy_conf50__14": 0.8918918918918919,
|
| 36 |
+
"eval_validation.parquet_accuracy_conf50__15": 0.8822822822822823,
|
| 37 |
+
"eval_validation.parquet_accuracy_conf50__16": 0.887905604719764,
|
| 38 |
+
"eval_validation.parquet_accuracy_conf50__17": 0.8229166666666666,
|
| 39 |
+
"eval_validation.parquet_accuracy_conf50__18": 0.7183098591549296,
|
| 40 |
+
"eval_validation.parquet_accuracy_conf50__19": 0.7353951890034365,
|
| 41 |
+
"eval_validation.parquet_accuracy_conf50__2": 0.7333333333333333,
|
| 42 |
+
"eval_validation.parquet_accuracy_conf50__20": 0.6578947368421053,
|
| 43 |
+
"eval_validation.parquet_accuracy_conf50__21": 0.7653061224489796,
|
| 44 |
+
"eval_validation.parquet_accuracy_conf50__22": 0.7808641975308642,
|
| 45 |
+
"eval_validation.parquet_accuracy_conf50__23": 0.8202247191011236,
|
| 46 |
+
"eval_validation.parquet_accuracy_conf50__3": 0.775,
|
| 47 |
+
"eval_validation.parquet_accuracy_conf50__4": 0.8803030303030303,
|
| 48 |
+
"eval_validation.parquet_accuracy_conf50__5": 0.8125,
|
| 49 |
+
"eval_validation.parquet_accuracy_conf50__6": 0.6470588235294118,
|
| 50 |
+
"eval_validation.parquet_accuracy_conf50__7": 0.7205240174672489,
|
| 51 |
+
"eval_validation.parquet_accuracy_conf50__8": 0.8928571428571429,
|
| 52 |
+
"eval_validation.parquet_accuracy_conf50__9": 0.8224852071005917,
|
| 53 |
+
"eval_validation.parquet_accuracy_conf75": 0.9034977352793155,
|
| 54 |
+
"eval_validation.parquet_accuracy_conf75__0": 0.8947368421052632,
|
| 55 |
+
"eval_validation.parquet_accuracy_conf75__1": 0.8790613718411552,
|
| 56 |
+
"eval_validation.parquet_accuracy_conf75__10": 0.9492619926199262,
|
| 57 |
+
"eval_validation.parquet_accuracy_conf75__11": 0.8811188811188811,
|
| 58 |
+
"eval_validation.parquet_accuracy_conf75__12": 0.8793774319066148,
|
| 59 |
+
"eval_validation.parquet_accuracy_conf75__13": 0.8762135922330098,
|
| 60 |
+
"eval_validation.parquet_accuracy_conf75__14": 0.9235294117647059,
|
| 61 |
+
"eval_validation.parquet_accuracy_conf75__15": 0.9338181818181818,
|
| 62 |
+
"eval_validation.parquet_accuracy_conf75__16": 0.9240506329113924,
|
| 63 |
+
"eval_validation.parquet_accuracy_conf75__17": 0.9240506329113924,
|
| 64 |
+
"eval_validation.parquet_accuracy_conf75__18": 0.7861635220125787,
|
| 65 |
+
"eval_validation.parquet_accuracy_conf75__19": 0.8385650224215246,
|
| 66 |
+
"eval_validation.parquet_accuracy_conf75__2": 0.7627118644067796,
|
| 67 |
+
"eval_validation.parquet_accuracy_conf75__20": 0.7777777777777778,
|
| 68 |
+
"eval_validation.parquet_accuracy_conf75__21": 0.88,
|
| 69 |
+
"eval_validation.parquet_accuracy_conf75__22": 0.8735632183908046,
|
| 70 |
+
"eval_validation.parquet_accuracy_conf75__23": 0.8656716417910447,
|
| 71 |
+
"eval_validation.parquet_accuracy_conf75__3": 0.8390804597701149,
|
| 72 |
+
"eval_validation.parquet_accuracy_conf75__4": 0.9387755102040817,
|
| 73 |
+
"eval_validation.parquet_accuracy_conf75__5": 0.8888888888888888,
|
| 74 |
+
"eval_validation.parquet_accuracy_conf75__6": 0.7543859649122807,
|
| 75 |
+
"eval_validation.parquet_accuracy_conf75__7": 0.7965116279069767,
|
| 76 |
+
"eval_validation.parquet_accuracy_conf75__8": 0.94,
|
| 77 |
+
"eval_validation.parquet_accuracy_conf75__9": 0.9015151515151515,
|
| 78 |
+
"eval_validation.parquet_accuracy_label_average": 0.7850284202694991,
|
| 79 |
+
"eval_validation.parquet_accuracy_label_average_conf50": 0.801551906216693,
|
| 80 |
+
"eval_validation.parquet_accuracy_label_average_conf75": 0.8712012342178551,
|
| 81 |
+
"eval_validation.parquet_accuracy_label_min": 0.6097560975609756,
|
| 82 |
+
"eval_validation.parquet_accuracy_label_min_conf50": 0.6470588235294118,
|
| 83 |
+
"eval_validation.parquet_accuracy_label_min_conf75": 0.7543859649122807,
|
| 84 |
+
"eval_validation.parquet_loss": 0.6012852787971497,
|
| 85 |
+
"eval_validation.parquet_proportion_conf50": 0.9665,
|
| 86 |
+
"eval_validation.parquet_proportion_conf75": 0.7948,
|
| 87 |
+
"eval_validation.parquet_runtime": 8.4553,
|
| 88 |
+
"eval_validation.parquet_samples_per_second": 1182.688,
|
| 89 |
+
"eval_validation.parquet_steps_per_second": 37.018,
|
| 90 |
+
"num_input_tokens_seen": 1949274656
|
| 91 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6c578b7042f23c1bac76a95f56e5db721ebb02f8d4d59b1b55b12f4ab462a8d
|
| 3 |
+
size 299260928
|
pred_results.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"test_accuracy": 0.8154,
|
| 3 |
+
"test_accuracy__0": 0.8549618320610687,
|
| 4 |
+
"test_accuracy__1": 0.7558139534883721,
|
| 5 |
+
"test_accuracy__10": 0.9070830159939071,
|
| 6 |
+
"test_accuracy__11": 0.6868686868686869,
|
| 7 |
+
"test_accuracy__12": 0.8054607508532423,
|
| 8 |
+
"test_accuracy__13": 0.7896749521988528,
|
| 9 |
+
"test_accuracy__14": 0.8591549295774648,
|
| 10 |
+
"test_accuracy__15": 0.8541416566626651,
|
| 11 |
+
"test_accuracy__16": 0.8787535410764873,
|
| 12 |
+
"test_accuracy__17": 0.7733333333333333,
|
| 13 |
+
"test_accuracy__18": 0.7286432160804021,
|
| 14 |
+
"test_accuracy__19": 0.6988847583643123,
|
| 15 |
+
"test_accuracy__2": 0.7473684210526316,
|
| 16 |
+
"test_accuracy__20": 0.7608695652173914,
|
| 17 |
+
"test_accuracy__21": 0.7807017543859649,
|
| 18 |
+
"test_accuracy__22": 0.7703488372093024,
|
| 19 |
+
"test_accuracy__23": 0.7931034482758621,
|
| 20 |
+
"test_accuracy__3": 0.6351351351351351,
|
| 21 |
+
"test_accuracy__4": 0.8709677419354839,
|
| 22 |
+
"test_accuracy__5": 0.8333333333333334,
|
| 23 |
+
"test_accuracy__6": 0.6125461254612546,
|
| 24 |
+
"test_accuracy__7": 0.6415770609318996,
|
| 25 |
+
"test_accuracy__8": 0.78,
|
| 26 |
+
"test_accuracy__9": 0.7668393782383419,
|
| 27 |
+
"test_accuracy_conf50": 0.8311890433699938,
|
| 28 |
+
"test_accuracy_conf50__0": 0.8852459016393442,
|
| 29 |
+
"test_accuracy_conf50__1": 0.7650602409638554,
|
| 30 |
+
"test_accuracy_conf50__10": 0.9167315175097276,
|
| 31 |
+
"test_accuracy_conf50__11": 0.7167755991285403,
|
| 32 |
+
"test_accuracy_conf50__12": 0.8256227758007118,
|
| 33 |
+
"test_accuracy_conf50__13": 0.7995991983967936,
|
| 34 |
+
"test_accuracy_conf50__14": 0.8695652173913043,
|
| 35 |
+
"test_accuracy_conf50__15": 0.8683559950556242,
|
| 36 |
+
"test_accuracy_conf50__16": 0.8877964141122036,
|
| 37 |
+
"test_accuracy_conf50__17": 0.7837837837837838,
|
| 38 |
+
"test_accuracy_conf50__18": 0.7663043478260869,
|
| 39 |
+
"test_accuracy_conf50__19": 0.7276264591439688,
|
| 40 |
+
"test_accuracy_conf50__2": 0.7608695652173914,
|
| 41 |
+
"test_accuracy_conf50__20": 0.7906976744186046,
|
| 42 |
+
"test_accuracy_conf50__21": 0.8,
|
| 43 |
+
"test_accuracy_conf50__22": 0.7926829268292683,
|
| 44 |
+
"test_accuracy_conf50__23": 0.7904191616766467,
|
| 45 |
+
"test_accuracy_conf50__3": 0.6616541353383458,
|
| 46 |
+
"test_accuracy_conf50__4": 0.8770491803278688,
|
| 47 |
+
"test_accuracy_conf50__5": 0.8571428571428571,
|
| 48 |
+
"test_accuracy_conf50__6": 0.6299212598425197,
|
| 49 |
+
"test_accuracy_conf50__7": 0.6785714285714286,
|
| 50 |
+
"test_accuracy_conf50__8": 0.7755102040816326,
|
| 51 |
+
"test_accuracy_conf50__9": 0.7795698924731183,
|
| 52 |
+
"test_accuracy_conf75": 0.9002641177210414,
|
| 53 |
+
"test_accuracy_conf75__0": 0.9411764705882353,
|
| 54 |
+
"test_accuracy_conf75__1": 0.831758034026465,
|
| 55 |
+
"test_accuracy_conf75__10": 0.9541850220264317,
|
| 56 |
+
"test_accuracy_conf75__11": 0.8477508650519031,
|
| 57 |
+
"test_accuracy_conf75__12": 0.8841201716738197,
|
| 58 |
+
"test_accuracy_conf75__13": 0.8724489795918368,
|
| 59 |
+
"test_accuracy_conf75__14": 0.9139784946236559,
|
| 60 |
+
"test_accuracy_conf75__15": 0.9345238095238095,
|
| 61 |
+
"test_accuracy_conf75__16": 0.9315687540348612,
|
| 62 |
+
"test_accuracy_conf75__17": 0.8666666666666667,
|
| 63 |
+
"test_accuracy_conf75__18": 0.8445945945945946,
|
| 64 |
+
"test_accuracy_conf75__19": 0.8208955223880597,
|
| 65 |
+
"test_accuracy_conf75__2": 0.8333333333333334,
|
| 66 |
+
"test_accuracy_conf75__20": 0.9333333333333333,
|
| 67 |
+
"test_accuracy_conf75__21": 0.8586956521739131,
|
| 68 |
+
"test_accuracy_conf75__22": 0.8708487084870848,
|
| 69 |
+
"test_accuracy_conf75__23": 0.8308823529411765,
|
| 70 |
+
"test_accuracy_conf75__3": 0.7291666666666666,
|
| 71 |
+
"test_accuracy_conf75__4": 0.935672514619883,
|
| 72 |
+
"test_accuracy_conf75__5": 0.9032258064516129,
|
| 73 |
+
"test_accuracy_conf75__6": 0.7816091954022989,
|
| 74 |
+
"test_accuracy_conf75__7": 0.8011363636363636,
|
| 75 |
+
"test_accuracy_conf75__8": 0.8409090909090909,
|
| 76 |
+
"test_accuracy_conf75__9": 0.8591549295774648,
|
| 77 |
+
"test_accuracy_label_average": 0.7743985594889748,
|
| 78 |
+
"test_accuracy_label_average_conf50": 0.7919398223613178,
|
| 79 |
+
"test_accuracy_label_average_conf75": 0.8675681388467735,
|
| 80 |
+
"test_accuracy_label_min": 0.6125461254612546,
|
| 81 |
+
"test_accuracy_label_min_conf50": 0.6299212598425197,
|
| 82 |
+
"test_accuracy_label_min_conf75": 0.7291666666666666,
|
| 83 |
+
"test_loss": 0.6023229956626892,
|
| 84 |
+
"test_proportion_conf50": 0.9638,
|
| 85 |
+
"test_proportion_conf75": 0.7951,
|
| 86 |
+
"test_runtime": 8.3874,
|
| 87 |
+
"test_samples_per_second": 1192.262,
|
| 88 |
+
"test_steps_per_second": 37.318
|
| 89 |
+
}
|
predictions.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:579f40424a84ed1df4a5e78c7c04e408b8937ad0dd6590975736131a235f7de3
|
| 3 |
+
size 1920210
|
runs/May03_13-07-30_jzxh358/events.out.tfevents.1746270461.jzxh358.1141829.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7993f79ee9b696b057f484f9c4e0f199da3871de81840641bc8c9a71f343ecc8
|
| 3 |
+
size 45705
|
runs/May03_13-07-30_jzxh358/events.out.tfevents.1746271047.jzxh358.1141829.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4edb4d74806a2ba1d9d081c4e9fcf15f818a05843c03afd33df2fa670cfde16f
|
| 3 |
+
size 7120
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "|||IP_ADDRESS|||",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|padding|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"50254": {
|
| 20 |
+
"content": " ",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"50255": {
|
| 28 |
+
"content": " ",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"50256": {
|
| 36 |
+
"content": " ",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"50257": {
|
| 44 |
+
"content": " ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"50258": {
|
| 52 |
+
"content": " ",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"50259": {
|
| 60 |
+
"content": " ",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"50260": {
|
| 68 |
+
"content": " ",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"50261": {
|
| 76 |
+
"content": " ",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"50262": {
|
| 84 |
+
"content": " ",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"50263": {
|
| 92 |
+
"content": " ",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"50264": {
|
| 100 |
+
"content": " ",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"50265": {
|
| 108 |
+
"content": " ",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"50266": {
|
| 116 |
+
"content": " ",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"50267": {
|
| 124 |
+
"content": " ",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"50268": {
|
| 132 |
+
"content": " ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"50269": {
|
| 140 |
+
"content": " ",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"50270": {
|
| 148 |
+
"content": " ",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"50271": {
|
| 156 |
+
"content": " ",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"50272": {
|
| 164 |
+
"content": " ",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"50273": {
|
| 172 |
+
"content": " ",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"50274": {
|
| 180 |
+
"content": " ",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"50275": {
|
| 188 |
+
"content": " ",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"50276": {
|
| 196 |
+
"content": " ",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"50277": {
|
| 204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"50278": {
|
| 212 |
+
"content": "|||PHONE_NUMBER|||",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"50279": {
|
| 220 |
+
"content": "<|endoftext|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"50280": {
|
| 228 |
+
"content": "[UNK]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"50281": {
|
| 236 |
+
"content": "[CLS]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"50282": {
|
| 244 |
+
"content": "[SEP]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"50283": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"50284": {
|
| 260 |
+
"content": "[MASK]",
|
| 261 |
+
"lstrip": true,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"50285": {
|
| 268 |
+
"content": "[unused0]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"50286": {
|
| 276 |
+
"content": "[unused1]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"50287": {
|
| 284 |
+
"content": "[unused2]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"50288": {
|
| 292 |
+
"content": "[unused3]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"50289": {
|
| 300 |
+
"content": "[unused4]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"50290": {
|
| 308 |
+
"content": "[unused5]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"50291": {
|
| 316 |
+
"content": "[unused6]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"50292": {
|
| 324 |
+
"content": "[unused7]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"50293": {
|
| 332 |
+
"content": "[unused8]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"50294": {
|
| 340 |
+
"content": "[unused9]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"50295": {
|
| 348 |
+
"content": "[unused10]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"50296": {
|
| 356 |
+
"content": "[unused11]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"50297": {
|
| 364 |
+
"content": "[unused12]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"50298": {
|
| 372 |
+
"content": "[unused13]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"50299": {
|
| 380 |
+
"content": "[unused14]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"50300": {
|
| 388 |
+
"content": "[unused15]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"50301": {
|
| 396 |
+
"content": "[unused16]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"50302": {
|
| 404 |
+
"content": "[unused17]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"50303": {
|
| 412 |
+
"content": "[unused18]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"50304": {
|
| 420 |
+
"content": "[unused19]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"50305": {
|
| 428 |
+
"content": "[unused20]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"50306": {
|
| 436 |
+
"content": "[unused21]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"50307": {
|
| 444 |
+
"content": "[unused22]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"50308": {
|
| 452 |
+
"content": "[unused23]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"50309": {
|
| 460 |
+
"content": "[unused24]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"50310": {
|
| 468 |
+
"content": "[unused25]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"50311": {
|
| 476 |
+
"content": "[unused26]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"50312": {
|
| 484 |
+
"content": "[unused27]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"50313": {
|
| 492 |
+
"content": "[unused28]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"50314": {
|
| 500 |
+
"content": "[unused29]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"50315": {
|
| 508 |
+
"content": "[unused30]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"50316": {
|
| 516 |
+
"content": "[unused31]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"50317": {
|
| 524 |
+
"content": "[unused32]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"50318": {
|
| 532 |
+
"content": "[unused33]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"50319": {
|
| 540 |
+
"content": "[unused34]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"50320": {
|
| 548 |
+
"content": "[unused35]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"50321": {
|
| 556 |
+
"content": "[unused36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"50322": {
|
| 564 |
+
"content": "[unused37]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"50323": {
|
| 572 |
+
"content": "[unused38]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"50324": {
|
| 580 |
+
"content": "[unused39]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"50325": {
|
| 588 |
+
"content": "[unused40]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"50326": {
|
| 596 |
+
"content": "[unused41]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"50327": {
|
| 604 |
+
"content": "[unused42]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"50328": {
|
| 612 |
+
"content": "[unused43]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"50329": {
|
| 620 |
+
"content": "[unused44]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"50330": {
|
| 628 |
+
"content": "[unused45]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"50331": {
|
| 636 |
+
"content": "[unused46]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"50332": {
|
| 644 |
+
"content": "[unused47]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"50333": {
|
| 652 |
+
"content": "[unused48]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"50334": {
|
| 660 |
+
"content": "[unused49]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"50335": {
|
| 668 |
+
"content": "[unused50]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"50336": {
|
| 676 |
+
"content": "[unused51]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"50337": {
|
| 684 |
+
"content": "[unused52]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"50338": {
|
| 692 |
+
"content": "[unused53]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"50339": {
|
| 700 |
+
"content": "[unused54]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"50340": {
|
| 708 |
+
"content": "[unused55]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"50341": {
|
| 716 |
+
"content": "[unused56]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"50342": {
|
| 724 |
+
"content": "[unused57]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"50343": {
|
| 732 |
+
"content": "[unused58]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"50344": {
|
| 740 |
+
"content": "[unused59]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"50345": {
|
| 748 |
+
"content": "[unused60]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"50346": {
|
| 756 |
+
"content": "[unused61]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"50347": {
|
| 764 |
+
"content": "[unused62]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"50348": {
|
| 772 |
+
"content": "[unused63]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"50349": {
|
| 780 |
+
"content": "[unused64]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"50350": {
|
| 788 |
+
"content": "[unused65]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"50351": {
|
| 796 |
+
"content": "[unused66]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"50352": {
|
| 804 |
+
"content": "[unused67]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"50353": {
|
| 812 |
+
"content": "[unused68]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": true,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"50354": {
|
| 820 |
+
"content": "[unused69]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": true,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"50355": {
|
| 828 |
+
"content": "[unused70]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": true,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"50356": {
|
| 836 |
+
"content": "[unused71]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"50357": {
|
| 844 |
+
"content": "[unused72]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"50358": {
|
| 852 |
+
"content": "[unused73]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"50359": {
|
| 860 |
+
"content": "[unused74]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"50360": {
|
| 868 |
+
"content": "[unused75]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"50361": {
|
| 876 |
+
"content": "[unused76]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"50362": {
|
| 884 |
+
"content": "[unused77]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"50363": {
|
| 892 |
+
"content": "[unused78]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"50364": {
|
| 900 |
+
"content": "[unused79]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"50365": {
|
| 908 |
+
"content": "[unused80]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"50366": {
|
| 916 |
+
"content": "[unused81]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"50367": {
|
| 924 |
+
"content": "[unused82]",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
}
|
| 931 |
+
},
|
| 932 |
+
"clean_up_tokenization_spaces": true,
|
| 933 |
+
"cls_token": "[CLS]",
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"mask_token": "[MASK]",
|
| 936 |
+
"model_input_names": [
|
| 937 |
+
"input_ids",
|
| 938 |
+
"attention_mask"
|
| 939 |
+
],
|
| 940 |
+
"model_max_length": 8192,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.9728,
|
| 3 |
+
"num_input_tokens_seen": 1949274656,
|
| 4 |
+
"train_loss": 2.327354235526843,
|
| 5 |
+
"train_runtime": 577.2472,
|
| 6 |
+
"train_samples_per_second": 692.944,
|
| 7 |
+
"train_steps_per_second": 1.351
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,560 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 471,
|
| 3 |
+
"best_metric": 0.6097560975609756,
|
| 4 |
+
"best_model_checkpoint": "/linkhome/rech/genini01/udd26kf/scratch/weborganizer/models/runs/answerdotai--ModernBERT-base_FormatAnnotations-Llama-3.1-8B_bsz512_lr1e-4_epochs5_warmup0.1_url1_FormatAnnotations-Llama-3.1-405B-FP8_bsz512_lr1e-4_epochs5_warmup0.1_url1/checkpoint-471",
|
| 5 |
+
"epoch": 4.9728,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 780,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.64,
|
| 14 |
+
"grad_norm": 23.25,
|
| 15 |
+
"learning_rate": 9.686609686609687e-05,
|
| 16 |
+
"loss": 3.0414,
|
| 17 |
+
"num_input_tokens_seen": 249204064,
|
| 18 |
+
"step": 100
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.0,
|
| 22 |
+
"eval_validation.parquet_accuracy": 0.8204,
|
| 23 |
+
"eval_validation.parquet_accuracy__0": 0.8175675675675675,
|
| 24 |
+
"eval_validation.parquet_accuracy__1": 0.7605633802816901,
|
| 25 |
+
"eval_validation.parquet_accuracy__10": 0.9124797406807131,
|
| 26 |
+
"eval_validation.parquet_accuracy__11": 0.6826722338204593,
|
| 27 |
+
"eval_validation.parquet_accuracy__12": 0.7278481012658228,
|
| 28 |
+
"eval_validation.parquet_accuracy__13": 0.794392523364486,
|
| 29 |
+
"eval_validation.parquet_accuracy__14": 0.8229166666666666,
|
| 30 |
+
"eval_validation.parquet_accuracy__15": 0.8694379391100703,
|
| 31 |
+
"eval_validation.parquet_accuracy__16": 0.8818443804034583,
|
| 32 |
+
"eval_validation.parquet_accuracy__17": 0.7916666666666666,
|
| 33 |
+
"eval_validation.parquet_accuracy__18": 0.76,
|
| 34 |
+
"eval_validation.parquet_accuracy__19": 0.7697368421052632,
|
| 35 |
+
"eval_validation.parquet_accuracy__2": 0.7435897435897436,
|
| 36 |
+
"eval_validation.parquet_accuracy__20": 0.5609756097560976,
|
| 37 |
+
"eval_validation.parquet_accuracy__21": 0.696969696969697,
|
| 38 |
+
"eval_validation.parquet_accuracy__22": 0.7434402332361516,
|
| 39 |
+
"eval_validation.parquet_accuracy__23": 0.8166666666666667,
|
| 40 |
+
"eval_validation.parquet_accuracy__3": 0.751937984496124,
|
| 41 |
+
"eval_validation.parquet_accuracy__4": 0.8727544910179641,
|
| 42 |
+
"eval_validation.parquet_accuracy__5": 0.78125,
|
| 43 |
+
"eval_validation.parquet_accuracy__6": 0.6387832699619772,
|
| 44 |
+
"eval_validation.parquet_accuracy__7": 0.6719367588932806,
|
| 45 |
+
"eval_validation.parquet_accuracy__8": 0.8928571428571429,
|
| 46 |
+
"eval_validation.parquet_accuracy__9": 0.7727272727272727,
|
| 47 |
+
"eval_validation.parquet_accuracy_conf50": 0.8353854112778065,
|
| 48 |
+
"eval_validation.parquet_accuracy_conf50__0": 0.8394160583941606,
|
| 49 |
+
"eval_validation.parquet_accuracy_conf50__1": 0.7776141384388807,
|
| 50 |
+
"eval_validation.parquet_accuracy_conf50__10": 0.9185855263157895,
|
| 51 |
+
"eval_validation.parquet_accuracy_conf50__11": 0.7041942604856513,
|
| 52 |
+
"eval_validation.parquet_accuracy_conf50__12": 0.7582781456953642,
|
| 53 |
+
"eval_validation.parquet_accuracy_conf50__13": 0.810077519379845,
|
| 54 |
+
"eval_validation.parquet_accuracy_conf50__14": 0.8432432432432433,
|
| 55 |
+
"eval_validation.parquet_accuracy_conf50__15": 0.8792792792792793,
|
| 56 |
+
"eval_validation.parquet_accuracy_conf50__16": 0.8890855457227138,
|
| 57 |
+
"eval_validation.parquet_accuracy_conf50__17": 0.7916666666666666,
|
| 58 |
+
"eval_validation.parquet_accuracy_conf50__18": 0.7699530516431925,
|
| 59 |
+
"eval_validation.parquet_accuracy_conf50__19": 0.7903780068728522,
|
| 60 |
+
"eval_validation.parquet_accuracy_conf50__2": 0.76,
|
| 61 |
+
"eval_validation.parquet_accuracy_conf50__20": 0.6052631578947368,
|
| 62 |
+
"eval_validation.parquet_accuracy_conf50__21": 0.7040816326530612,
|
| 63 |
+
"eval_validation.parquet_accuracy_conf50__22": 0.7716049382716049,
|
| 64 |
+
"eval_validation.parquet_accuracy_conf50__23": 0.8258426966292135,
|
| 65 |
+
"eval_validation.parquet_accuracy_conf50__3": 0.775,
|
| 66 |
+
"eval_validation.parquet_accuracy_conf50__4": 0.8803030303030303,
|
| 67 |
+
"eval_validation.parquet_accuracy_conf50__5": 0.78125,
|
| 68 |
+
"eval_validation.parquet_accuracy_conf50__6": 0.6680672268907563,
|
| 69 |
+
"eval_validation.parquet_accuracy_conf50__7": 0.7205240174672489,
|
| 70 |
+
"eval_validation.parquet_accuracy_conf50__8": 0.8928571428571429,
|
| 71 |
+
"eval_validation.parquet_accuracy_conf50__9": 0.7810650887573964,
|
| 72 |
+
"eval_validation.parquet_accuracy_conf75": 0.8959486663311524,
|
| 73 |
+
"eval_validation.parquet_accuracy_conf75__0": 0.8859649122807017,
|
| 74 |
+
"eval_validation.parquet_accuracy_conf75__1": 0.8411552346570397,
|
| 75 |
+
"eval_validation.parquet_accuracy_conf75__10": 0.9511070110701108,
|
| 76 |
+
"eval_validation.parquet_accuracy_conf75__11": 0.8146853146853147,
|
| 77 |
+
"eval_validation.parquet_accuracy_conf75__12": 0.8326848249027238,
|
| 78 |
+
"eval_validation.parquet_accuracy_conf75__13": 0.8713592233009708,
|
| 79 |
+
"eval_validation.parquet_accuracy_conf75__14": 0.8823529411764706,
|
| 80 |
+
"eval_validation.parquet_accuracy_conf75__15": 0.9323636363636364,
|
| 81 |
+
"eval_validation.parquet_accuracy_conf75__16": 0.9233844103930713,
|
| 82 |
+
"eval_validation.parquet_accuracy_conf75__17": 0.9113924050632911,
|
| 83 |
+
"eval_validation.parquet_accuracy_conf75__18": 0.8301886792452831,
|
| 84 |
+
"eval_validation.parquet_accuracy_conf75__19": 0.8878923766816144,
|
| 85 |
+
"eval_validation.parquet_accuracy_conf75__2": 0.7796610169491526,
|
| 86 |
+
"eval_validation.parquet_accuracy_conf75__20": 0.7407407407407407,
|
| 87 |
+
"eval_validation.parquet_accuracy_conf75__21": 0.8266666666666667,
|
| 88 |
+
"eval_validation.parquet_accuracy_conf75__22": 0.8582375478927203,
|
| 89 |
+
"eval_validation.parquet_accuracy_conf75__23": 0.8656716417910447,
|
| 90 |
+
"eval_validation.parquet_accuracy_conf75__3": 0.8390804597701149,
|
| 91 |
+
"eval_validation.parquet_accuracy_conf75__4": 0.9332096474953617,
|
| 92 |
+
"eval_validation.parquet_accuracy_conf75__5": 0.8518518518518519,
|
| 93 |
+
"eval_validation.parquet_accuracy_conf75__6": 0.7719298245614035,
|
| 94 |
+
"eval_validation.parquet_accuracy_conf75__7": 0.7790697674418605,
|
| 95 |
+
"eval_validation.parquet_accuracy_conf75__8": 0.94,
|
| 96 |
+
"eval_validation.parquet_accuracy_conf75__9": 0.8863636363636364,
|
| 97 |
+
"eval_validation.parquet_accuracy_label_average": 0.7722922880043742,
|
| 98 |
+
"eval_validation.parquet_accuracy_label_average_conf50": 0.7890679322442429,
|
| 99 |
+
"eval_validation.parquet_accuracy_label_average_conf75": 0.8598755738060326,
|
| 100 |
+
"eval_validation.parquet_accuracy_label_min": 0.5609756097560976,
|
| 101 |
+
"eval_validation.parquet_accuracy_label_min_conf50": 0.6052631578947368,
|
| 102 |
+
"eval_validation.parquet_accuracy_label_min_conf75": 0.7407407407407407,
|
| 103 |
+
"eval_validation.parquet_loss": 0.6205468773841858,
|
| 104 |
+
"eval_validation.parquet_proportion_conf50": 0.9665,
|
| 105 |
+
"eval_validation.parquet_proportion_conf75": 0.7948,
|
| 106 |
+
"eval_validation.parquet_runtime": 10.5515,
|
| 107 |
+
"eval_validation.parquet_samples_per_second": 947.73,
|
| 108 |
+
"eval_validation.parquet_steps_per_second": 29.664,
|
| 109 |
+
"num_input_tokens_seen": 390215936,
|
| 110 |
+
"step": 157
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.2752,
|
| 114 |
+
"grad_norm": 11.8125,
|
| 115 |
+
"learning_rate": 8.262108262108262e-05,
|
| 116 |
+
"loss": 2.4648,
|
| 117 |
+
"num_input_tokens_seen": 499147424,
|
| 118 |
+
"step": 200
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.9152,
|
| 122 |
+
"grad_norm": 15.375,
|
| 123 |
+
"learning_rate": 6.837606837606838e-05,
|
| 124 |
+
"loss": 2.3634,
|
| 125 |
+
"num_input_tokens_seen": 751160992,
|
| 126 |
+
"step": 300
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.0,
|
| 130 |
+
"eval_validation.parquet_accuracy": 0.824,
|
| 131 |
+
"eval_validation.parquet_accuracy__0": 0.777027027027027,
|
| 132 |
+
"eval_validation.parquet_accuracy__1": 0.780281690140845,
|
| 133 |
+
"eval_validation.parquet_accuracy__10": 0.9149108589951378,
|
| 134 |
+
"eval_validation.parquet_accuracy__11": 0.8225469728601252,
|
| 135 |
+
"eval_validation.parquet_accuracy__12": 0.7436708860759493,
|
| 136 |
+
"eval_validation.parquet_accuracy__13": 0.7158878504672898,
|
| 137 |
+
"eval_validation.parquet_accuracy__14": 0.8229166666666666,
|
| 138 |
+
"eval_validation.parquet_accuracy__15": 0.8852459016393442,
|
| 139 |
+
"eval_validation.parquet_accuracy__16": 0.8818443804034583,
|
| 140 |
+
"eval_validation.parquet_accuracy__17": 0.84375,
|
| 141 |
+
"eval_validation.parquet_accuracy__18": 0.6711111111111111,
|
| 142 |
+
"eval_validation.parquet_accuracy__19": 0.756578947368421,
|
| 143 |
+
"eval_validation.parquet_accuracy__2": 0.717948717948718,
|
| 144 |
+
"eval_validation.parquet_accuracy__20": 0.6097560975609756,
|
| 145 |
+
"eval_validation.parquet_accuracy__21": 0.7777777777777778,
|
| 146 |
+
"eval_validation.parquet_accuracy__22": 0.7725947521865889,
|
| 147 |
+
"eval_validation.parquet_accuracy__23": 0.7888888888888889,
|
| 148 |
+
"eval_validation.parquet_accuracy__3": 0.7364341085271318,
|
| 149 |
+
"eval_validation.parquet_accuracy__4": 0.8622754491017964,
|
| 150 |
+
"eval_validation.parquet_accuracy__5": 0.78125,
|
| 151 |
+
"eval_validation.parquet_accuracy__6": 0.5513307984790875,
|
| 152 |
+
"eval_validation.parquet_accuracy__7": 0.6640316205533597,
|
| 153 |
+
"eval_validation.parquet_accuracy__8": 0.8928571428571429,
|
| 154 |
+
"eval_validation.parquet_accuracy__9": 0.8181818181818182,
|
| 155 |
+
"eval_validation.parquet_accuracy_conf50": 0.8392136575271598,
|
| 156 |
+
"eval_validation.parquet_accuracy_conf50__0": 0.8102189781021898,
|
| 157 |
+
"eval_validation.parquet_accuracy_conf50__1": 0.7997054491899853,
|
| 158 |
+
"eval_validation.parquet_accuracy_conf50__10": 0.9210526315789473,
|
| 159 |
+
"eval_validation.parquet_accuracy_conf50__11": 0.8410596026490066,
|
| 160 |
+
"eval_validation.parquet_accuracy_conf50__12": 0.7715231788079471,
|
| 161 |
+
"eval_validation.parquet_accuracy_conf50__13": 0.7344961240310077,
|
| 162 |
+
"eval_validation.parquet_accuracy_conf50__14": 0.8486486486486486,
|
| 163 |
+
"eval_validation.parquet_accuracy_conf50__15": 0.8942942942942943,
|
| 164 |
+
"eval_validation.parquet_accuracy_conf50__16": 0.8896755162241888,
|
| 165 |
+
"eval_validation.parquet_accuracy_conf50__17": 0.84375,
|
| 166 |
+
"eval_validation.parquet_accuracy_conf50__18": 0.6854460093896714,
|
| 167 |
+
"eval_validation.parquet_accuracy_conf50__19": 0.7766323024054983,
|
| 168 |
+
"eval_validation.parquet_accuracy_conf50__2": 0.7333333333333333,
|
| 169 |
+
"eval_validation.parquet_accuracy_conf50__20": 0.6578947368421053,
|
| 170 |
+
"eval_validation.parquet_accuracy_conf50__21": 0.7857142857142857,
|
| 171 |
+
"eval_validation.parquet_accuracy_conf50__22": 0.7932098765432098,
|
| 172 |
+
"eval_validation.parquet_accuracy_conf50__23": 0.797752808988764,
|
| 173 |
+
"eval_validation.parquet_accuracy_conf50__3": 0.7666666666666667,
|
| 174 |
+
"eval_validation.parquet_accuracy_conf50__4": 0.8696969696969697,
|
| 175 |
+
"eval_validation.parquet_accuracy_conf50__5": 0.78125,
|
| 176 |
+
"eval_validation.parquet_accuracy_conf50__6": 0.5756302521008403,
|
| 177 |
+
"eval_validation.parquet_accuracy_conf50__7": 0.7161572052401747,
|
| 178 |
+
"eval_validation.parquet_accuracy_conf50__8": 0.8928571428571429,
|
| 179 |
+
"eval_validation.parquet_accuracy_conf50__9": 0.8224852071005917,
|
| 180 |
+
"eval_validation.parquet_accuracy_conf75": 0.8993457473578259,
|
| 181 |
+
"eval_validation.parquet_accuracy_conf75__0": 0.8771929824561403,
|
| 182 |
+
"eval_validation.parquet_accuracy_conf75__1": 0.8646209386281588,
|
| 183 |
+
"eval_validation.parquet_accuracy_conf75__10": 0.9566420664206642,
|
| 184 |
+
"eval_validation.parquet_accuracy_conf75__11": 0.9405594405594405,
|
| 185 |
+
"eval_validation.parquet_accuracy_conf75__12": 0.8326848249027238,
|
| 186 |
+
"eval_validation.parquet_accuracy_conf75__13": 0.8106796116504854,
|
| 187 |
+
"eval_validation.parquet_accuracy_conf75__14": 0.8823529411764706,
|
| 188 |
+
"eval_validation.parquet_accuracy_conf75__15": 0.944,
|
| 189 |
+
"eval_validation.parquet_accuracy_conf75__16": 0.9227181878747501,
|
| 190 |
+
"eval_validation.parquet_accuracy_conf75__17": 0.9493670886075949,
|
| 191 |
+
"eval_validation.parquet_accuracy_conf75__18": 0.7672955974842768,
|
| 192 |
+
"eval_validation.parquet_accuracy_conf75__19": 0.8834080717488789,
|
| 193 |
+
"eval_validation.parquet_accuracy_conf75__2": 0.7627118644067796,
|
| 194 |
+
"eval_validation.parquet_accuracy_conf75__20": 0.7777777777777778,
|
| 195 |
+
"eval_validation.parquet_accuracy_conf75__21": 0.8933333333333333,
|
| 196 |
+
"eval_validation.parquet_accuracy_conf75__22": 0.8735632183908046,
|
| 197 |
+
"eval_validation.parquet_accuracy_conf75__23": 0.8432835820895522,
|
| 198 |
+
"eval_validation.parquet_accuracy_conf75__3": 0.8390804597701149,
|
| 199 |
+
"eval_validation.parquet_accuracy_conf75__4": 0.9294990723562152,
|
| 200 |
+
"eval_validation.parquet_accuracy_conf75__5": 0.8518518518518519,
|
| 201 |
+
"eval_validation.parquet_accuracy_conf75__6": 0.6900584795321637,
|
| 202 |
+
"eval_validation.parquet_accuracy_conf75__7": 0.7674418604651163,
|
| 203 |
+
"eval_validation.parquet_accuracy_conf75__8": 0.94,
|
| 204 |
+
"eval_validation.parquet_accuracy_conf75__9": 0.9090909090909091,
|
| 205 |
+
"eval_validation.parquet_accuracy_label_average": 0.7745458110341109,
|
| 206 |
+
"eval_validation.parquet_accuracy_label_average_conf50": 0.7920479675168944,
|
| 207 |
+
"eval_validation.parquet_accuracy_label_average_conf75": 0.8628839233572584,
|
| 208 |
+
"eval_validation.parquet_accuracy_label_min": 0.5513307984790875,
|
| 209 |
+
"eval_validation.parquet_accuracy_label_min_conf50": 0.5756302521008403,
|
| 210 |
+
"eval_validation.parquet_accuracy_label_min_conf75": 0.6900584795321637,
|
| 211 |
+
"eval_validation.parquet_loss": 0.6139147281646729,
|
| 212 |
+
"eval_validation.parquet_proportion_conf50": 0.9665,
|
| 213 |
+
"eval_validation.parquet_proportion_conf75": 0.7948,
|
| 214 |
+
"eval_validation.parquet_runtime": 8.3891,
|
| 215 |
+
"eval_validation.parquet_samples_per_second": 1192.017,
|
| 216 |
+
"eval_validation.parquet_steps_per_second": 37.31,
|
| 217 |
+
"num_input_tokens_seen": 783399104,
|
| 218 |
+
"step": 314
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.5504,
|
| 222 |
+
"grad_norm": 9.25,
|
| 223 |
+
"learning_rate": 5.413105413105414e-05,
|
| 224 |
+
"loss": 2.2093,
|
| 225 |
+
"num_input_tokens_seen": 999700736,
|
| 226 |
+
"step": 400
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.0,
|
| 230 |
+
"eval_validation.parquet_accuracy": 0.8279,
|
| 231 |
+
"eval_validation.parquet_accuracy__0": 0.831081081081081,
|
| 232 |
+
"eval_validation.parquet_accuracy__1": 0.7971830985915493,
|
| 233 |
+
"eval_validation.parquet_accuracy__10": 0.9108589951377634,
|
| 234 |
+
"eval_validation.parquet_accuracy__11": 0.7390396659707724,
|
| 235 |
+
"eval_validation.parquet_accuracy__12": 0.8164556962025317,
|
| 236 |
+
"eval_validation.parquet_accuracy__13": 0.7906542056074767,
|
| 237 |
+
"eval_validation.parquet_accuracy__14": 0.875,
|
| 238 |
+
"eval_validation.parquet_accuracy__15": 0.8706088992974239,
|
| 239 |
+
"eval_validation.parquet_accuracy__16": 0.8806916426512968,
|
| 240 |
+
"eval_validation.parquet_accuracy__17": 0.8229166666666666,
|
| 241 |
+
"eval_validation.parquet_accuracy__18": 0.7022222222222222,
|
| 242 |
+
"eval_validation.parquet_accuracy__19": 0.7072368421052632,
|
| 243 |
+
"eval_validation.parquet_accuracy__2": 0.717948717948718,
|
| 244 |
+
"eval_validation.parquet_accuracy__20": 0.6097560975609756,
|
| 245 |
+
"eval_validation.parquet_accuracy__21": 0.7575757575757576,
|
| 246 |
+
"eval_validation.parquet_accuracy__22": 0.7551020408163265,
|
| 247 |
+
"eval_validation.parquet_accuracy__23": 0.8111111111111111,
|
| 248 |
+
"eval_validation.parquet_accuracy__3": 0.751937984496124,
|
| 249 |
+
"eval_validation.parquet_accuracy__4": 0.874251497005988,
|
| 250 |
+
"eval_validation.parquet_accuracy__5": 0.8125,
|
| 251 |
+
"eval_validation.parquet_accuracy__6": 0.623574144486692,
|
| 252 |
+
"eval_validation.parquet_accuracy__7": 0.6719367588932806,
|
| 253 |
+
"eval_validation.parquet_accuracy__8": 0.8928571428571429,
|
| 254 |
+
"eval_validation.parquet_accuracy__9": 0.8181818181818182,
|
| 255 |
+
"eval_validation.parquet_accuracy_conf50": 0.8428349715468184,
|
| 256 |
+
"eval_validation.parquet_accuracy_conf50__0": 0.8540145985401459,
|
| 257 |
+
"eval_validation.parquet_accuracy_conf50__1": 0.8159057437407953,
|
| 258 |
+
"eval_validation.parquet_accuracy_conf50__10": 0.9169407894736842,
|
| 259 |
+
"eval_validation.parquet_accuracy_conf50__11": 0.7593818984547461,
|
| 260 |
+
"eval_validation.parquet_accuracy_conf50__12": 0.8377483443708609,
|
| 261 |
+
"eval_validation.parquet_accuracy_conf50__13": 0.8062015503875969,
|
| 262 |
+
"eval_validation.parquet_accuracy_conf50__14": 0.8918918918918919,
|
| 263 |
+
"eval_validation.parquet_accuracy_conf50__15": 0.8822822822822823,
|
| 264 |
+
"eval_validation.parquet_accuracy_conf50__16": 0.887905604719764,
|
| 265 |
+
"eval_validation.parquet_accuracy_conf50__17": 0.8229166666666666,
|
| 266 |
+
"eval_validation.parquet_accuracy_conf50__18": 0.7183098591549296,
|
| 267 |
+
"eval_validation.parquet_accuracy_conf50__19": 0.7353951890034365,
|
| 268 |
+
"eval_validation.parquet_accuracy_conf50__2": 0.7333333333333333,
|
| 269 |
+
"eval_validation.parquet_accuracy_conf50__20": 0.6578947368421053,
|
| 270 |
+
"eval_validation.parquet_accuracy_conf50__21": 0.7653061224489796,
|
| 271 |
+
"eval_validation.parquet_accuracy_conf50__22": 0.7808641975308642,
|
| 272 |
+
"eval_validation.parquet_accuracy_conf50__23": 0.8202247191011236,
|
| 273 |
+
"eval_validation.parquet_accuracy_conf50__3": 0.775,
|
| 274 |
+
"eval_validation.parquet_accuracy_conf50__4": 0.8803030303030303,
|
| 275 |
+
"eval_validation.parquet_accuracy_conf50__5": 0.8125,
|
| 276 |
+
"eval_validation.parquet_accuracy_conf50__6": 0.6470588235294118,
|
| 277 |
+
"eval_validation.parquet_accuracy_conf50__7": 0.7205240174672489,
|
| 278 |
+
"eval_validation.parquet_accuracy_conf50__8": 0.8928571428571429,
|
| 279 |
+
"eval_validation.parquet_accuracy_conf50__9": 0.8224852071005917,
|
| 280 |
+
"eval_validation.parquet_accuracy_conf75": 0.9034977352793155,
|
| 281 |
+
"eval_validation.parquet_accuracy_conf75__0": 0.8947368421052632,
|
| 282 |
+
"eval_validation.parquet_accuracy_conf75__1": 0.8790613718411552,
|
| 283 |
+
"eval_validation.parquet_accuracy_conf75__10": 0.9492619926199262,
|
| 284 |
+
"eval_validation.parquet_accuracy_conf75__11": 0.8811188811188811,
|
| 285 |
+
"eval_validation.parquet_accuracy_conf75__12": 0.8793774319066148,
|
| 286 |
+
"eval_validation.parquet_accuracy_conf75__13": 0.8762135922330098,
|
| 287 |
+
"eval_validation.parquet_accuracy_conf75__14": 0.9235294117647059,
|
| 288 |
+
"eval_validation.parquet_accuracy_conf75__15": 0.9338181818181818,
|
| 289 |
+
"eval_validation.parquet_accuracy_conf75__16": 0.9240506329113924,
|
| 290 |
+
"eval_validation.parquet_accuracy_conf75__17": 0.9240506329113924,
|
| 291 |
+
"eval_validation.parquet_accuracy_conf75__18": 0.7861635220125787,
|
| 292 |
+
"eval_validation.parquet_accuracy_conf75__19": 0.8385650224215246,
|
| 293 |
+
"eval_validation.parquet_accuracy_conf75__2": 0.7627118644067796,
|
| 294 |
+
"eval_validation.parquet_accuracy_conf75__20": 0.7777777777777778,
|
| 295 |
+
"eval_validation.parquet_accuracy_conf75__21": 0.88,
|
| 296 |
+
"eval_validation.parquet_accuracy_conf75__22": 0.8735632183908046,
|
| 297 |
+
"eval_validation.parquet_accuracy_conf75__23": 0.8656716417910447,
|
| 298 |
+
"eval_validation.parquet_accuracy_conf75__3": 0.8390804597701149,
|
| 299 |
+
"eval_validation.parquet_accuracy_conf75__4": 0.9387755102040817,
|
| 300 |
+
"eval_validation.parquet_accuracy_conf75__5": 0.8888888888888888,
|
| 301 |
+
"eval_validation.parquet_accuracy_conf75__6": 0.7543859649122807,
|
| 302 |
+
"eval_validation.parquet_accuracy_conf75__7": 0.7965116279069767,
|
| 303 |
+
"eval_validation.parquet_accuracy_conf75__8": 0.94,
|
| 304 |
+
"eval_validation.parquet_accuracy_conf75__9": 0.9015151515151515,
|
| 305 |
+
"eval_validation.parquet_accuracy_label_average": 0.7850284202694991,
|
| 306 |
+
"eval_validation.parquet_accuracy_label_average_conf50": 0.801551906216693,
|
| 307 |
+
"eval_validation.parquet_accuracy_label_average_conf75": 0.8712012342178551,
|
| 308 |
+
"eval_validation.parquet_accuracy_label_min": 0.6097560975609756,
|
| 309 |
+
"eval_validation.parquet_accuracy_label_min_conf50": 0.6470588235294118,
|
| 310 |
+
"eval_validation.parquet_accuracy_label_min_conf75": 0.7543859649122807,
|
| 311 |
+
"eval_validation.parquet_loss": 0.6012852787971497,
|
| 312 |
+
"eval_validation.parquet_proportion_conf50": 0.9665,
|
| 313 |
+
"eval_validation.parquet_proportion_conf75": 0.7948,
|
| 314 |
+
"eval_validation.parquet_runtime": 8.4045,
|
| 315 |
+
"eval_validation.parquet_samples_per_second": 1189.832,
|
| 316 |
+
"eval_validation.parquet_steps_per_second": 37.242,
|
| 317 |
+
"num_input_tokens_seen": 1176307328,
|
| 318 |
+
"step": 471
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.1856,
|
| 322 |
+
"grad_norm": 11.125,
|
| 323 |
+
"learning_rate": 3.988603988603989e-05,
|
| 324 |
+
"loss": 2.1824,
|
| 325 |
+
"num_input_tokens_seen": 1250925472,
|
| 326 |
+
"step": 500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.8256,
|
| 330 |
+
"grad_norm": 10.3125,
|
| 331 |
+
"learning_rate": 2.564102564102564e-05,
|
| 332 |
+
"loss": 2.1124,
|
| 333 |
+
"num_input_tokens_seen": 1499507040,
|
| 334 |
+
"step": 600
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 4.0,
|
| 338 |
+
"eval_validation.parquet_accuracy": 0.8296,
|
| 339 |
+
"eval_validation.parquet_accuracy__0": 0.8378378378378378,
|
| 340 |
+
"eval_validation.parquet_accuracy__1": 0.8140845070422535,
|
| 341 |
+
"eval_validation.parquet_accuracy__10": 0.9181523500810372,
|
| 342 |
+
"eval_validation.parquet_accuracy__11": 0.7536534446764092,
|
| 343 |
+
"eval_validation.parquet_accuracy__12": 0.8037974683544303,
|
| 344 |
+
"eval_validation.parquet_accuracy__13": 0.7738317757009345,
|
| 345 |
+
"eval_validation.parquet_accuracy__14": 0.8645833333333334,
|
| 346 |
+
"eval_validation.parquet_accuracy__15": 0.8600702576112412,
|
| 347 |
+
"eval_validation.parquet_accuracy__16": 0.8737752161383285,
|
| 348 |
+
"eval_validation.parquet_accuracy__17": 0.8229166666666666,
|
| 349 |
+
"eval_validation.parquet_accuracy__18": 0.7466666666666667,
|
| 350 |
+
"eval_validation.parquet_accuracy__19": 0.7138157894736842,
|
| 351 |
+
"eval_validation.parquet_accuracy__2": 0.782051282051282,
|
| 352 |
+
"eval_validation.parquet_accuracy__20": 0.6097560975609756,
|
| 353 |
+
"eval_validation.parquet_accuracy__21": 0.7474747474747475,
|
| 354 |
+
"eval_validation.parquet_accuracy__22": 0.7900874635568513,
|
| 355 |
+
"eval_validation.parquet_accuracy__23": 0.7722222222222223,
|
| 356 |
+
"eval_validation.parquet_accuracy__3": 0.751937984496124,
|
| 357 |
+
"eval_validation.parquet_accuracy__4": 0.8937125748502994,
|
| 358 |
+
"eval_validation.parquet_accuracy__5": 0.78125,
|
| 359 |
+
"eval_validation.parquet_accuracy__6": 0.596958174904943,
|
| 360 |
+
"eval_validation.parquet_accuracy__7": 0.6996047430830039,
|
| 361 |
+
"eval_validation.parquet_accuracy__8": 0.8928571428571429,
|
| 362 |
+
"eval_validation.parquet_accuracy__9": 0.8181818181818182,
|
| 363 |
+
"eval_validation.parquet_accuracy_conf50": 0.8443869632695292,
|
| 364 |
+
"eval_validation.parquet_accuracy_conf50__0": 0.8540145985401459,
|
| 365 |
+
"eval_validation.parquet_accuracy_conf50__1": 0.8306332842415317,
|
| 366 |
+
"eval_validation.parquet_accuracy_conf50__10": 0.9243421052631579,
|
| 367 |
+
"eval_validation.parquet_accuracy_conf50__11": 0.7748344370860927,
|
| 368 |
+
"eval_validation.parquet_accuracy_conf50__12": 0.8278145695364238,
|
| 369 |
+
"eval_validation.parquet_accuracy_conf50__13": 0.7906976744186046,
|
| 370 |
+
"eval_validation.parquet_accuracy_conf50__14": 0.8864864864864865,
|
| 371 |
+
"eval_validation.parquet_accuracy_conf50__15": 0.8714714714714715,
|
| 372 |
+
"eval_validation.parquet_accuracy_conf50__16": 0.8825958702064897,
|
| 373 |
+
"eval_validation.parquet_accuracy_conf50__17": 0.8229166666666666,
|
| 374 |
+
"eval_validation.parquet_accuracy_conf50__18": 0.755868544600939,
|
| 375 |
+
"eval_validation.parquet_accuracy_conf50__19": 0.738831615120275,
|
| 376 |
+
"eval_validation.parquet_accuracy_conf50__2": 0.8,
|
| 377 |
+
"eval_validation.parquet_accuracy_conf50__20": 0.6578947368421053,
|
| 378 |
+
"eval_validation.parquet_accuracy_conf50__21": 0.7551020408163265,
|
| 379 |
+
"eval_validation.parquet_accuracy_conf50__22": 0.808641975308642,
|
| 380 |
+
"eval_validation.parquet_accuracy_conf50__23": 0.7808988764044944,
|
| 381 |
+
"eval_validation.parquet_accuracy_conf50__3": 0.775,
|
| 382 |
+
"eval_validation.parquet_accuracy_conf50__4": 0.9,
|
| 383 |
+
"eval_validation.parquet_accuracy_conf50__5": 0.78125,
|
| 384 |
+
"eval_validation.parquet_accuracy_conf50__6": 0.6176470588235294,
|
| 385 |
+
"eval_validation.parquet_accuracy_conf50__7": 0.7510917030567685,
|
| 386 |
+
"eval_validation.parquet_accuracy_conf50__8": 0.8928571428571429,
|
| 387 |
+
"eval_validation.parquet_accuracy_conf50__9": 0.8284023668639053,
|
| 388 |
+
"eval_validation.parquet_accuracy_conf75": 0.903749370910921,
|
| 389 |
+
"eval_validation.parquet_accuracy_conf75__0": 0.9035087719298246,
|
| 390 |
+
"eval_validation.parquet_accuracy_conf75__1": 0.8916967509025271,
|
| 391 |
+
"eval_validation.parquet_accuracy_conf75__10": 0.9529520295202952,
|
| 392 |
+
"eval_validation.parquet_accuracy_conf75__11": 0.8811188811188811,
|
| 393 |
+
"eval_validation.parquet_accuracy_conf75__12": 0.8793774319066148,
|
| 394 |
+
"eval_validation.parquet_accuracy_conf75__13": 0.8640776699029126,
|
| 395 |
+
"eval_validation.parquet_accuracy_conf75__14": 0.9176470588235294,
|
| 396 |
+
"eval_validation.parquet_accuracy_conf75__15": 0.928,
|
| 397 |
+
"eval_validation.parquet_accuracy_conf75__16": 0.9187208527648234,
|
| 398 |
+
"eval_validation.parquet_accuracy_conf75__17": 0.9240506329113924,
|
| 399 |
+
"eval_validation.parquet_accuracy_conf75__18": 0.8238993710691824,
|
| 400 |
+
"eval_validation.parquet_accuracy_conf75__19": 0.8385650224215246,
|
| 401 |
+
"eval_validation.parquet_accuracy_conf75__2": 0.8305084745762712,
|
| 402 |
+
"eval_validation.parquet_accuracy_conf75__20": 0.7777777777777778,
|
| 403 |
+
"eval_validation.parquet_accuracy_conf75__21": 0.8666666666666667,
|
| 404 |
+
"eval_validation.parquet_accuracy_conf75__22": 0.8850574712643678,
|
| 405 |
+
"eval_validation.parquet_accuracy_conf75__23": 0.835820895522388,
|
| 406 |
+
"eval_validation.parquet_accuracy_conf75__3": 0.8390804597701149,
|
| 407 |
+
"eval_validation.parquet_accuracy_conf75__4": 0.948051948051948,
|
| 408 |
+
"eval_validation.parquet_accuracy_conf75__5": 0.8518518518518519,
|
| 409 |
+
"eval_validation.parquet_accuracy_conf75__6": 0.7309941520467836,
|
| 410 |
+
"eval_validation.parquet_accuracy_conf75__7": 0.813953488372093,
|
| 411 |
+
"eval_validation.parquet_accuracy_conf75__8": 0.94,
|
| 412 |
+
"eval_validation.parquet_accuracy_conf75__9": 0.9090909090909091,
|
| 413 |
+
"eval_validation.parquet_accuracy_label_average": 0.7883033152009263,
|
| 414 |
+
"eval_validation.parquet_accuracy_label_average_conf50": 0.8045538843588002,
|
| 415 |
+
"eval_validation.parquet_accuracy_label_average_conf75": 0.8730195236776117,
|
| 416 |
+
"eval_validation.parquet_accuracy_label_min": 0.596958174904943,
|
| 417 |
+
"eval_validation.parquet_accuracy_label_min_conf50": 0.6176470588235294,
|
| 418 |
+
"eval_validation.parquet_accuracy_label_min_conf75": 0.7309941520467836,
|
| 419 |
+
"eval_validation.parquet_loss": 0.5987765789031982,
|
| 420 |
+
"eval_validation.parquet_proportion_conf50": 0.9665,
|
| 421 |
+
"eval_validation.parquet_proportion_conf75": 0.7948,
|
| 422 |
+
"eval_validation.parquet_runtime": 8.4305,
|
| 423 |
+
"eval_validation.parquet_samples_per_second": 1186.174,
|
| 424 |
+
"eval_validation.parquet_steps_per_second": 37.127,
|
| 425 |
+
"num_input_tokens_seen": 1566401088,
|
| 426 |
+
"step": 628
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 4.4608,
|
| 430 |
+
"grad_norm": 7.875,
|
| 431 |
+
"learning_rate": 1.1396011396011397e-05,
|
| 432 |
+
"loss": 2.0751,
|
| 433 |
+
"num_input_tokens_seen": 1745927840,
|
| 434 |
+
"step": 700
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.9728,
|
| 438 |
+
"eval_validation.parquet_accuracy": 0.8297,
|
| 439 |
+
"eval_validation.parquet_accuracy__0": 0.8378378378378378,
|
| 440 |
+
"eval_validation.parquet_accuracy__1": 0.8014084507042254,
|
| 441 |
+
"eval_validation.parquet_accuracy__10": 0.9173419773095624,
|
| 442 |
+
"eval_validation.parquet_accuracy__11": 0.755741127348643,
|
| 443 |
+
"eval_validation.parquet_accuracy__12": 0.8006329113924051,
|
| 444 |
+
"eval_validation.parquet_accuracy__13": 0.7700934579439253,
|
| 445 |
+
"eval_validation.parquet_accuracy__14": 0.8489583333333334,
|
| 446 |
+
"eval_validation.parquet_accuracy__15": 0.8676814988290398,
|
| 447 |
+
"eval_validation.parquet_accuracy__16": 0.8731988472622478,
|
| 448 |
+
"eval_validation.parquet_accuracy__17": 0.8229166666666666,
|
| 449 |
+
"eval_validation.parquet_accuracy__18": 0.72,
|
| 450 |
+
"eval_validation.parquet_accuracy__19": 0.743421052631579,
|
| 451 |
+
"eval_validation.parquet_accuracy__2": 0.7564102564102564,
|
| 452 |
+
"eval_validation.parquet_accuracy__20": 0.6341463414634146,
|
| 453 |
+
"eval_validation.parquet_accuracy__21": 0.7575757575757576,
|
| 454 |
+
"eval_validation.parquet_accuracy__22": 0.7871720116618076,
|
| 455 |
+
"eval_validation.parquet_accuracy__23": 0.7944444444444444,
|
| 456 |
+
"eval_validation.parquet_accuracy__3": 0.751937984496124,
|
| 457 |
+
"eval_validation.parquet_accuracy__4": 0.8907185628742516,
|
| 458 |
+
"eval_validation.parquet_accuracy__5": 0.8125,
|
| 459 |
+
"eval_validation.parquet_accuracy__6": 0.596958174904943,
|
| 460 |
+
"eval_validation.parquet_accuracy__7": 0.6996047430830039,
|
| 461 |
+
"eval_validation.parquet_accuracy__8": 0.8928571428571429,
|
| 462 |
+
"eval_validation.parquet_accuracy__9": 0.8125,
|
| 463 |
+
"eval_validation.parquet_accuracy_conf50": 0.844593895499224,
|
| 464 |
+
"eval_validation.parquet_accuracy_conf50__0": 0.8540145985401459,
|
| 465 |
+
"eval_validation.parquet_accuracy_conf50__1": 0.8188512518409425,
|
| 466 |
+
"eval_validation.parquet_accuracy_conf50__10": 0.9235197368421053,
|
| 467 |
+
"eval_validation.parquet_accuracy_conf50__11": 0.7770419426048565,
|
| 468 |
+
"eval_validation.parquet_accuracy_conf50__12": 0.8278145695364238,
|
| 469 |
+
"eval_validation.parquet_accuracy_conf50__13": 0.7868217054263565,
|
| 470 |
+
"eval_validation.parquet_accuracy_conf50__14": 0.8702702702702703,
|
| 471 |
+
"eval_validation.parquet_accuracy_conf50__15": 0.8786786786786787,
|
| 472 |
+
"eval_validation.parquet_accuracy_conf50__16": 0.8814159292035398,
|
| 473 |
+
"eval_validation.parquet_accuracy_conf50__17": 0.8229166666666666,
|
| 474 |
+
"eval_validation.parquet_accuracy_conf50__18": 0.7370892018779343,
|
| 475 |
+
"eval_validation.parquet_accuracy_conf50__19": 0.7697594501718213,
|
| 476 |
+
"eval_validation.parquet_accuracy_conf50__2": 0.7733333333333333,
|
| 477 |
+
"eval_validation.parquet_accuracy_conf50__20": 0.6578947368421053,
|
| 478 |
+
"eval_validation.parquet_accuracy_conf50__21": 0.7653061224489796,
|
| 479 |
+
"eval_validation.parquet_accuracy_conf50__22": 0.8055555555555556,
|
| 480 |
+
"eval_validation.parquet_accuracy_conf50__23": 0.8033707865168539,
|
| 481 |
+
"eval_validation.parquet_accuracy_conf50__3": 0.775,
|
| 482 |
+
"eval_validation.parquet_accuracy_conf50__4": 0.896969696969697,
|
| 483 |
+
"eval_validation.parquet_accuracy_conf50__5": 0.8125,
|
| 484 |
+
"eval_validation.parquet_accuracy_conf50__6": 0.6176470588235294,
|
| 485 |
+
"eval_validation.parquet_accuracy_conf50__7": 0.7510917030567685,
|
| 486 |
+
"eval_validation.parquet_accuracy_conf50__8": 0.8928571428571429,
|
| 487 |
+
"eval_validation.parquet_accuracy_conf50__9": 0.8224852071005917,
|
| 488 |
+
"eval_validation.parquet_accuracy_conf75": 0.903749370910921,
|
| 489 |
+
"eval_validation.parquet_accuracy_conf75__0": 0.9035087719298246,
|
| 490 |
+
"eval_validation.parquet_accuracy_conf75__1": 0.8844765342960289,
|
| 491 |
+
"eval_validation.parquet_accuracy_conf75__10": 0.9520295202952029,
|
| 492 |
+
"eval_validation.parquet_accuracy_conf75__11": 0.8846153846153846,
|
| 493 |
+
"eval_validation.parquet_accuracy_conf75__12": 0.8793774319066148,
|
| 494 |
+
"eval_validation.parquet_accuracy_conf75__13": 0.8640776699029126,
|
| 495 |
+
"eval_validation.parquet_accuracy_conf75__14": 0.9058823529411765,
|
| 496 |
+
"eval_validation.parquet_accuracy_conf75__15": 0.9330909090909091,
|
| 497 |
+
"eval_validation.parquet_accuracy_conf75__16": 0.9173884077281812,
|
| 498 |
+
"eval_validation.parquet_accuracy_conf75__17": 0.9240506329113924,
|
| 499 |
+
"eval_validation.parquet_accuracy_conf75__18": 0.8050314465408805,
|
| 500 |
+
"eval_validation.parquet_accuracy_conf75__19": 0.8609865470852018,
|
| 501 |
+
"eval_validation.parquet_accuracy_conf75__2": 0.7966101694915254,
|
| 502 |
+
"eval_validation.parquet_accuracy_conf75__20": 0.7777777777777778,
|
| 503 |
+
"eval_validation.parquet_accuracy_conf75__21": 0.88,
|
| 504 |
+
"eval_validation.parquet_accuracy_conf75__22": 0.8812260536398467,
|
| 505 |
+
"eval_validation.parquet_accuracy_conf75__23": 0.8507462686567164,
|
| 506 |
+
"eval_validation.parquet_accuracy_conf75__3": 0.8390804597701149,
|
| 507 |
+
"eval_validation.parquet_accuracy_conf75__4": 0.9461966604823747,
|
| 508 |
+
"eval_validation.parquet_accuracy_conf75__5": 0.8888888888888888,
|
| 509 |
+
"eval_validation.parquet_accuracy_conf75__6": 0.7309941520467836,
|
| 510 |
+
"eval_validation.parquet_accuracy_conf75__7": 0.8081395348837209,
|
| 511 |
+
"eval_validation.parquet_accuracy_conf75__8": 0.94,
|
| 512 |
+
"eval_validation.parquet_accuracy_conf75__9": 0.9090909090909091,
|
| 513 |
+
"eval_validation.parquet_accuracy_label_average": 0.7894190658762755,
|
| 514 |
+
"eval_validation.parquet_accuracy_label_average_conf50": 0.805091889381846,
|
| 515 |
+
"eval_validation.parquet_accuracy_label_average_conf75": 0.873469436832182,
|
| 516 |
+
"eval_validation.parquet_accuracy_label_min": 0.596958174904943,
|
| 517 |
+
"eval_validation.parquet_accuracy_label_min_conf50": 0.6176470588235294,
|
| 518 |
+
"eval_validation.parquet_accuracy_label_min_conf75": 0.7309941520467836,
|
| 519 |
+
"eval_validation.parquet_loss": 0.5989147424697876,
|
| 520 |
+
"eval_validation.parquet_proportion_conf50": 0.9665,
|
| 521 |
+
"eval_validation.parquet_proportion_conf75": 0.7948,
|
| 522 |
+
"eval_validation.parquet_runtime": 8.5755,
|
| 523 |
+
"eval_validation.parquet_samples_per_second": 1166.109,
|
| 524 |
+
"eval_validation.parquet_steps_per_second": 36.499,
|
| 525 |
+
"num_input_tokens_seen": 1949274656,
|
| 526 |
+
"step": 780
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 4.9728,
|
| 530 |
+
"num_input_tokens_seen": 1949274656,
|
| 531 |
+
"step": 780,
|
| 532 |
+
"total_flos": 1.297523316772307e+18,
|
| 533 |
+
"train_loss": 2.327354235526843,
|
| 534 |
+
"train_runtime": 577.2472,
|
| 535 |
+
"train_samples_per_second": 692.944,
|
| 536 |
+
"train_steps_per_second": 1.351
|
| 537 |
+
}
|
| 538 |
+
],
|
| 539 |
+
"logging_steps": 100,
|
| 540 |
+
"max_steps": 780,
|
| 541 |
+
"num_input_tokens_seen": 1949274656,
|
| 542 |
+
"num_train_epochs": 5,
|
| 543 |
+
"save_steps": 500,
|
| 544 |
+
"stateful_callbacks": {
|
| 545 |
+
"TrainerControl": {
|
| 546 |
+
"args": {
|
| 547 |
+
"should_epoch_stop": false,
|
| 548 |
+
"should_evaluate": false,
|
| 549 |
+
"should_log": false,
|
| 550 |
+
"should_save": true,
|
| 551 |
+
"should_training_stop": true
|
| 552 |
+
},
|
| 553 |
+
"attributes": {}
|
| 554 |
+
}
|
| 555 |
+
},
|
| 556 |
+
"total_flos": 1.297523316772307e+18,
|
| 557 |
+
"train_batch_size": 32,
|
| 558 |
+
"trial_name": null,
|
| 559 |
+
"trial_params": null
|
| 560 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48e0b28b20cfc2427b664a74c37f3f8f8589db64657a770b1a4f827b83141f23
|
| 3 |
+
size 6840
|