Upload 13 files
Browse files- README.md +200 -3
- all_results.json +16 -0
- config.json +62 -0
- eval_results.json +9 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +125 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +938 -0
- train_results.json +11 -0
- trainer_state.json +1540 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,200 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
language: en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: google/flan-t5-base
|
| 6 |
+
tags:
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
- text-preprocessing
|
| 9 |
+
- text-reformatting
|
| 10 |
+
datasets:
|
| 11 |
+
- other
|
| 12 |
+
model-index:
|
| 13 |
+
- name: flan-t5-base-paragrapher
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# flan-t5-base-paragrapher
|
| 18 |
+
|
| 19 |
+
This model is designed to preprocess, clean, and reformat text chunks containing line breaks, word breaks, and references into coherent plain text paragraphs. The resulting paragraphs can be used with other models like [agentlans/flan-t5-small-title](https://huggingface.co/agentlans/flan-t5-small-title) and [agentlans/text-summarization](https://huggingface.co/agentlans/text-summarization).
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
The flan-t5-base-paragrapher is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base), trained on a dataset of open-source introductory social science textbooks. While it was trained on academic texts, it should work well with other types of educational and academic content.
|
| 24 |
+
|
| 25 |
+
The model achieves the following results on the evaluation set:
|
| 26 |
+
- Loss: 1.5175
|
| 27 |
+
- Number of Input Tokens Seen: 49 815 380
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
This model is intended for preprocessing and reformatting text chunks into coherent paragraphs. It can be particularly useful for:
|
| 32 |
+
|
| 33 |
+
1. Cleaning up text extracted from PDFs or OCR systems
|
| 34 |
+
2. Reformatting text with irregular line breaks or word breaks
|
| 35 |
+
3. Preparing text for further processing or analysis
|
| 36 |
+
|
| 37 |
+
Limitations:
|
| 38 |
+
- The model may not perform optimally on highly specialized or technical texts outside its training domain.
|
| 39 |
+
- Very long input sequences may be truncated due to the model's maximum sequence length (512 tokens).
|
| 40 |
+
|
| 41 |
+
## Training and evaluation data
|
| 42 |
+
|
| 43 |
+
The model was trained on a dataset compiled from open-source textbooks. Due to licensing constraints, the specific training data is not published.
|
| 44 |
+
|
| 45 |
+
## Training procedure
|
| 46 |
+
|
| 47 |
+
### Training hyperparameters
|
| 48 |
+
|
| 49 |
+
The following hyperparameters were used during training:
|
| 50 |
+
- Learning rate: 5e-05
|
| 51 |
+
- Train batch size: 8
|
| 52 |
+
- Eval batch size: 8
|
| 53 |
+
- Seed: 42
|
| 54 |
+
- Optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
+
- LR scheduler type: linear
|
| 56 |
+
- Number of epochs: 10.0
|
| 57 |
+
|
| 58 |
+
### Training results
|
| 59 |
+
|
| 60 |
+
<details>
|
| 61 |
+
<summary>Click to expand training results</summary>
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
| 64 |
+
|:-------------:|:------:|:-----:|:---------------:|:-----------------:|
|
| 65 |
+
| 2.0748 | 0.1126 | 500 | 1.7587 | 562752 |
|
| 66 |
+
| 1.9699 | 0.2251 | 1000 | 1.7031 | 1119424 |
|
| 67 |
+
| 1.9177 | 0.3377 | 1500 | 1.6701 | 1676620 |
|
| 68 |
+
| 1.9179 | 0.4502 | 2000 | 1.6647 | 2244928 |
|
| 69 |
+
| 1.8908 | 0.5628 | 2500 | 1.6502 | 2806840 |
|
| 70 |
+
| 1.8666 | 0.6754 | 3000 | 1.6427 | 3364792 |
|
| 71 |
+
| 1.8456 | 0.7879 | 3500 | 1.6245 | 3925172 |
|
| 72 |
+
| 1.8542 | 0.9005 | 4000 | 1.6218 | 4490100 |
|
| 73 |
+
| 1.8305 | 1.0131 | 4500 | 1.6211 | 5052066 |
|
| 74 |
+
| 1.7588 | 1.1256 | 5000 | 1.6040 | 5607258 |
|
| 75 |
+
| 1.7606 | 1.2382 | 5500 | 1.6020 | 6165278 |
|
| 76 |
+
| 1.7426 | 1.3507 | 6000 | 1.5993 | 6727290 |
|
| 77 |
+
| 1.7477 | 1.4633 | 6500 | 1.5869 | 7292338 |
|
| 78 |
+
| 1.7413 | 1.5759 | 7000 | 1.5791 | 7849466 |
|
| 79 |
+
| 1.7342 | 1.6884 | 7500 | 1.5792 | 8415302 |
|
| 80 |
+
| 1.7247 | 1.8010 | 8000 | 1.5759 | 8970490 |
|
| 81 |
+
| 1.7423 | 1.9136 | 8500 | 1.5744 | 9529290 |
|
| 82 |
+
| 1.7138 | 2.0261 | 9000 | 1.5655 | 10091652 |
|
| 83 |
+
| 1.6719 | 2.1387 | 9500 | 1.5630 | 10650544 |
|
| 84 |
+
| 1.6637 | 2.2512 | 10000 | 1.5584 | 11208648 |
|
| 85 |
+
| 1.6415 | 2.3638 | 10500 | 1.5609 | 11776396 |
|
| 86 |
+
| 1.6565 | 2.4764 | 11000 | 1.5558 | 12338500 |
|
| 87 |
+
| 1.6597 | 2.5889 | 11500 | 1.5530 | 12897552 |
|
| 88 |
+
| 1.6709 | 2.7015 | 12000 | 1.5477 | 13460052 |
|
| 89 |
+
| 1.648 | 2.8140 | 12500 | 1.5424 | 14021984 |
|
| 90 |
+
| 1.642 | 2.9266 | 13000 | 1.5433 | 14586256 |
|
| 91 |
+
| 1.6258 | 3.0392 | 13500 | 1.5419 | 15140609 |
|
| 92 |
+
| 1.6067 | 3.1517 | 14000 | 1.5415 | 15700397 |
|
| 93 |
+
| 1.5946 | 3.2643 | 14500 | 1.5450 | 16265849 |
|
| 94 |
+
| 1.5835 | 3.3769 | 15000 | 1.5415 | 16827557 |
|
| 95 |
+
| 1.5996 | 3.4894 | 15500 | 1.5411 | 17384857 |
|
| 96 |
+
| 1.5834 | 3.6020 | 16000 | 1.5382 | 17945909 |
|
| 97 |
+
| 1.5956 | 3.7145 | 16500 | 1.5351 | 18507721 |
|
| 98 |
+
| 1.5825 | 3.8271 | 17000 | 1.5356 | 19069425 |
|
| 99 |
+
| 1.6001 | 3.9397 | 17500 | 1.5294 | 19631905 |
|
| 100 |
+
| 1.5677 | 4.0522 | 18000 | 1.5369 | 20185192 |
|
| 101 |
+
| 1.5415 | 4.1648 | 18500 | 1.5318 | 20739888 |
|
| 102 |
+
| 1.5362 | 4.2774 | 19000 | 1.5311 | 21304584 |
|
| 103 |
+
| 1.5251 | 4.3899 | 19500 | 1.5323 | 21862856 |
|
| 104 |
+
| 1.5388 | 4.5025 | 20000 | 1.5307 | 22427236 |
|
| 105 |
+
| 1.5508 | 4.6150 | 20500 | 1.5282 | 22985184 |
|
| 106 |
+
| 1.5692 | 4.7276 | 21000 | 1.5265 | 23548396 |
|
| 107 |
+
| 1.5391 | 4.8402 | 21500 | 1.5276 | 24111452 |
|
| 108 |
+
| 1.5431 | 4.9527 | 22000 | 1.5270 | 24673344 |
|
| 109 |
+
| 1.5147 | 5.0653 | 22500 | 1.5292 | 25236559 |
|
| 110 |
+
| 1.4908 | 5.1778 | 23000 | 1.5288 | 25799675 |
|
| 111 |
+
| 1.5153 | 5.2904 | 23500 | 1.5288 | 26352767 |
|
| 112 |
+
| 1.5099 | 5.4030 | 24000 | 1.5250 | 26916707 |
|
| 113 |
+
| 1.5064 | 5.5155 | 24500 | 1.5259 | 27483639 |
|
| 114 |
+
| 1.5146 | 5.6281 | 25000 | 1.5249 | 28040307 |
|
| 115 |
+
| 1.4938 | 5.7407 | 25500 | 1.5233 | 28600639 |
|
| 116 |
+
| 1.5034 | 5.8532 | 26000 | 1.5237 | 29164539 |
|
| 117 |
+
| 1.5091 | 5.9658 | 26500 | 1.5219 | 29730199 |
|
| 118 |
+
| 1.4853 | 6.0783 | 27000 | 1.5241 | 30286010 |
|
| 119 |
+
| 1.4797 | 6.1909 | 27500 | 1.5201 | 30840802 |
|
| 120 |
+
| 1.466 | 6.3035 | 28000 | 1.5238 | 31403710 |
|
| 121 |
+
| 1.4666 | 6.4160 | 28500 | 1.5226 | 31962730 |
|
| 122 |
+
| 1.4732 | 6.5286 | 29000 | 1.5199 | 32518854 |
|
| 123 |
+
| 1.4756 | 6.6412 | 29500 | 1.5219 | 33083634 |
|
| 124 |
+
| 1.4778 | 6.7537 | 30000 | 1.5195 | 33644482 |
|
| 125 |
+
| 1.4674 | 6.8663 | 30500 | 1.5182 | 34207738 |
|
| 126 |
+
| 1.4813 | 6.9788 | 31000 | 1.5202 | 34772050 |
|
| 127 |
+
| 1.4543 | 7.0914 | 31500 | 1.5211 | 35331657 |
|
| 128 |
+
| 1.4389 | 7.2040 | 32000 | 1.5221 | 35888749 |
|
| 129 |
+
| 1.4534 | 7.3165 | 32500 | 1.5215 | 36455101 |
|
| 130 |
+
| 1.4401 | 7.4291 | 33000 | 1.5208 | 37016889 |
|
| 131 |
+
| 1.4435 | 7.5416 | 33500 | 1.5212 | 37570517 |
|
| 132 |
+
| 1.4443 | 7.6542 | 34000 | 1.5205 | 38134577 |
|
| 133 |
+
| 1.4533 | 7.7668 | 34500 | 1.5209 | 38700917 |
|
| 134 |
+
| 1.4589 | 7.8793 | 35000 | 1.5218 | 39259257 |
|
| 135 |
+
| 1.4548 | 7.9919 | 35500 | 1.5185 | 39819093 |
|
| 136 |
+
| 1.4322 | 8.1045 | 36000 | 1.5207 | 40382907 |
|
| 137 |
+
| 1.4271 | 8.2170 | 36500 | 1.5220 | 40938983 |
|
| 138 |
+
| 1.4165 | 8.3296 | 37000 | 1.5203 | 41498811 |
|
| 139 |
+
| 1.4273 | 8.4421 | 37500 | 1.5197 | 42053427 |
|
| 140 |
+
| 1.4281 | 8.5547 | 38000 | 1.5195 | 42615135 |
|
| 141 |
+
| 1.4372 | 8.6673 | 38500 | 1.5197 | 43173055 |
|
| 142 |
+
| 1.4374 | 8.7798 | 39000 | 1.5175 | 43737723 |
|
| 143 |
+
| 1.4278 | 8.8924 | 39500 | 1.5211 | 44300547 |
|
| 144 |
+
| 1.442 | 9.0050 | 40000 | 1.5189 | 44864787 |
|
| 145 |
+
| 1.4235 | 9.1175 | 40500 | 1.5226 | 45418155 |
|
| 146 |
+
| 1.413 | 9.2301 | 41000 | 1.5220 | 45985195 |
|
| 147 |
+
| 1.4193 | 9.3426 | 41500 | 1.5201 | 46538675 |
|
| 148 |
+
| 1.414 | 9.4552 | 42000 | 1.5202 | 47101815 |
|
| 149 |
+
| 1.4084 | 9.5678 | 42500 | 1.5191 | 47655583 |
|
| 150 |
+
| 1.408 | 9.6803 | 43000 | 1.5207 | 48217371 |
|
| 151 |
+
| 1.4207 | 9.7929 | 43500 | 1.5200 | 48781351 |
|
| 152 |
+
| 1.4293 | 9.9054 | 44000 | 1.5198 | 49345155 |
|
| 153 |
+
|
| 154 |
+
</details>
|
| 155 |
+
|
| 156 |
+
### Framework versions
|
| 157 |
+
|
| 158 |
+
- Transformers 4.44.2
|
| 159 |
+
- PyTorch 2.5.1+cu124
|
| 160 |
+
- Datasets 3.1.0
|
| 161 |
+
- Tokenizers 0.19.1
|
| 162 |
+
|
| 163 |
+
## Usage
|
| 164 |
+
|
| 165 |
+
Here's an example of how to use the model:
|
| 166 |
+
|
| 167 |
+
```python
|
| 168 |
+
from transformers import T5Tokenizer, T5ForConditionalGeneration
|
| 169 |
+
|
| 170 |
+
# Load the tokenizer and model
|
| 171 |
+
tokenizer = T5Tokenizer.from_pretrained("flan-t5-base-paragrapher")
|
| 172 |
+
model = T5ForConditionalGeneration.from_pretrained("flan-t5-base-paragrapher", device_map="auto")
|
| 173 |
+
|
| 174 |
+
# Define input texts
|
| 175 |
+
input_texts = [
|
| 176 |
+
"""ge with a narrative—whether through books, films, or oral traditions—we are invited into another person's experience (Brown & Thompson, 2023). This immersion allows us to see the world through different perspectives, breaking down barriers of misunderstanding and prejudice. For example, novels like Harper Lee's "To Kill a Mockingbird" challenge readers to confront issues of racism and injustice through the eyes of a child (Williams, 2018). Similarly, contemporary works such as Chimamanda Ngozi Adichie's "Americanah" explore themes of identity and belonging in a globalized world (Nguyen & Roberts, 2020). By sharing these experiences through storytelling, authors can cultivate empathy in their audiences, encouraging them to reflect on their own beliefs and biases.
|
| 177 |
+
Shaping Identity Through Narratives
|
| 178 |
+
Stories also play a crucial role in shaping personal and collective identities. From childhood tales told by parents to the myths and legends that define cultural heritage, narratives help individuals understand their place in the world (Anderson & White, 2021). They provide frameworks thro""",
|
| 179 |
+
|
| 180 |
+
"""cia, M., & Patel, R. (2022). Cultural insights through literature: A comparative analysis. International Journal of Cultural Studies, 15(3), 201-215. Johnson, L., & Lee, H. (2019). Oral traditions: Preserving culture through storytelling. Anthropology Today Journal, 34(4), 56-60. Kumar, P. (2021). Epic tales: Literature as a reflection of society. Literary Critique Review, 29(1), 34-50. Lee, J., & Martinez, F. (2021). Voices unheard: Marginalized narratives in digital spaces. Journal of Digital Culture Studies, 7(2), 45-67. Martinez, C., & Chen, Y. (2022). Cultural navigation: Identity in a globalized world. Global Studies Review Jou"""
|
| 181 |
+
]
|
| 182 |
+
|
| 183 |
+
# Tokenize input texts
|
| 184 |
+
input_ids = tokenizer(input_texts, return_tensors="pt", padding=True, truncation=True).input_ids.to("cuda")
|
| 185 |
+
|
| 186 |
+
# Generate outputs
|
| 187 |
+
outputs = model.generate(input_ids, max_length=512)
|
| 188 |
+
|
| 189 |
+
# Print generated outputs
|
| 190 |
+
for output in outputs:
|
| 191 |
+
print(tokenizer.decode(output, skip_special_tokens=True) + "\n")
|
| 192 |
+
```
|
| 193 |
+
|
| 194 |
+
Example output:
|
| 195 |
+
|
| 196 |
+
```
|
| 197 |
+
Through storytelling, we are invited into another person's experience, breaking down barriers of misunderstanding and prejudice. This immersion allows us to see the world through different perspectives, fostering empathy and re-evaluating our own beliefs and biases. For instance, Harper Lee's "To Kill a Mockingbird" challenges readers to confront issues of racism and injustice through the eyes of a child, while contemporary works like Chimamanda Ngozi Adichie's "Americanah" explore themes of identity and belonging in a globalized world. By sharing these experiences through storytelling, authors
|
| 198 |
+
|
| 199 |
+
The study of cultural insights through literature has yielded valuable insights into the world. Ci and Patel (2022) conducted a comparative analysis of cultural insights through literature, highlighting the importance of cultural storytelling in preserving culture. Kumar (2021) argued that oral traditions can preserve culture through storytelling, highlighting the importance of storytelling in preserving culture. Lee and Martinez (2021) explored marginalized narratives in digital spaces, highlighting the need for cultural navigation in a globalized world. These studies collectively demonstrate the importance of cultural navigation in fostering identity and identity in a globalized world.
|
| 200 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 1.5174657106399536,
|
| 4 |
+
"eval_runtime": 6.6354,
|
| 5 |
+
"eval_samples": 1000,
|
| 6 |
+
"eval_samples_per_second": 150.707,
|
| 7 |
+
"eval_steps_per_second": 18.838,
|
| 8 |
+
"num_input_tokens_seen": 49815380,
|
| 9 |
+
"total_flos": 6.662920679892173e+16,
|
| 10 |
+
"train_loss": 1.5719221366734615,
|
| 11 |
+
"train_runtime": 7656.0711,
|
| 12 |
+
"train_samples": 17765,
|
| 13 |
+
"train_samples_per_second": 23.204,
|
| 14 |
+
"train_steps_per_second": 5.802,
|
| 15 |
+
"train_tokens_per_second": 6514.629
|
| 16 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"tie_word_embeddings": false,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.44.2",
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 32128
|
| 62 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 1.5174657106399536,
|
| 4 |
+
"eval_runtime": 6.6354,
|
| 5 |
+
"eval_samples": 1000,
|
| 6 |
+
"eval_samples_per_second": 150.707,
|
| 7 |
+
"eval_steps_per_second": 18.838,
|
| 8 |
+
"num_input_tokens_seen": 49815380
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.44.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9e78e9e467d2f778d8738d335afc6298064d7f95faaef644a00fd49223dfa4a
|
| 3 |
+
size 990345064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,938 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 512,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"sp_model_kwargs": {},
|
| 936 |
+
"tokenizer_class": "T5Tokenizer",
|
| 937 |
+
"unk_token": "<unk>"
|
| 938 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"num_input_tokens_seen": 49815380,
|
| 4 |
+
"total_flos": 6.662920679892173e+16,
|
| 5 |
+
"train_loss": 1.5719221366734615,
|
| 6 |
+
"train_runtime": 7656.0711,
|
| 7 |
+
"train_samples": 17765,
|
| 8 |
+
"train_samples_per_second": 23.204,
|
| 9 |
+
"train_steps_per_second": 5.802,
|
| 10 |
+
"train_tokens_per_second": 6514.629
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1540 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.5174657106399536,
|
| 3 |
+
"best_model_checkpoint": "flan-t5-base-paragrapher/checkpoint-39000",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 44420,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11256190904997748,
|
| 13 |
+
"grad_norm": 2.3381476402282715,
|
| 14 |
+
"learning_rate": 4.9437190454750117e-05,
|
| 15 |
+
"loss": 2.0748,
|
| 16 |
+
"num_input_tokens_seen": 562752,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.11256190904997748,
|
| 21 |
+
"eval_loss": 1.7587194442749023,
|
| 22 |
+
"eval_runtime": 6.6407,
|
| 23 |
+
"eval_samples_per_second": 150.586,
|
| 24 |
+
"eval_steps_per_second": 18.823,
|
| 25 |
+
"num_input_tokens_seen": 562752,
|
| 26 |
+
"step": 500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.22512381809995496,
|
| 30 |
+
"grad_norm": 2.58415150642395,
|
| 31 |
+
"learning_rate": 4.887438090950023e-05,
|
| 32 |
+
"loss": 1.9699,
|
| 33 |
+
"num_input_tokens_seen": 1119424,
|
| 34 |
+
"step": 1000
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.22512381809995496,
|
| 38 |
+
"eval_loss": 1.7031291723251343,
|
| 39 |
+
"eval_runtime": 7.0071,
|
| 40 |
+
"eval_samples_per_second": 142.713,
|
| 41 |
+
"eval_steps_per_second": 17.839,
|
| 42 |
+
"num_input_tokens_seen": 1119424,
|
| 43 |
+
"step": 1000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.33768572714993245,
|
| 47 |
+
"grad_norm": 2.1401476860046387,
|
| 48 |
+
"learning_rate": 4.831157136425034e-05,
|
| 49 |
+
"loss": 1.9177,
|
| 50 |
+
"num_input_tokens_seen": 1676620,
|
| 51 |
+
"step": 1500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.33768572714993245,
|
| 55 |
+
"eval_loss": 1.6701327562332153,
|
| 56 |
+
"eval_runtime": 7.0023,
|
| 57 |
+
"eval_samples_per_second": 142.809,
|
| 58 |
+
"eval_steps_per_second": 17.851,
|
| 59 |
+
"num_input_tokens_seen": 1676620,
|
| 60 |
+
"step": 1500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.45024763619990993,
|
| 64 |
+
"grad_norm": 2.9264276027679443,
|
| 65 |
+
"learning_rate": 4.774876181900045e-05,
|
| 66 |
+
"loss": 1.9179,
|
| 67 |
+
"num_input_tokens_seen": 2244928,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.45024763619990993,
|
| 72 |
+
"eval_loss": 1.6646634340286255,
|
| 73 |
+
"eval_runtime": 6.7352,
|
| 74 |
+
"eval_samples_per_second": 148.473,
|
| 75 |
+
"eval_steps_per_second": 18.559,
|
| 76 |
+
"num_input_tokens_seen": 2244928,
|
| 77 |
+
"step": 2000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.5628095452498875,
|
| 81 |
+
"grad_norm": 1.9992469549179077,
|
| 82 |
+
"learning_rate": 4.7185952273750566e-05,
|
| 83 |
+
"loss": 1.8908,
|
| 84 |
+
"num_input_tokens_seen": 2806840,
|
| 85 |
+
"step": 2500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.5628095452498875,
|
| 89 |
+
"eval_loss": 1.650177240371704,
|
| 90 |
+
"eval_runtime": 6.9902,
|
| 91 |
+
"eval_samples_per_second": 143.057,
|
| 92 |
+
"eval_steps_per_second": 17.882,
|
| 93 |
+
"num_input_tokens_seen": 2806840,
|
| 94 |
+
"step": 2500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.6753714542998649,
|
| 98 |
+
"grad_norm": 2.2747724056243896,
|
| 99 |
+
"learning_rate": 4.662314272850068e-05,
|
| 100 |
+
"loss": 1.8666,
|
| 101 |
+
"num_input_tokens_seen": 3364792,
|
| 102 |
+
"step": 3000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.6753714542998649,
|
| 106 |
+
"eval_loss": 1.6427327394485474,
|
| 107 |
+
"eval_runtime": 6.7654,
|
| 108 |
+
"eval_samples_per_second": 147.81,
|
| 109 |
+
"eval_steps_per_second": 18.476,
|
| 110 |
+
"num_input_tokens_seen": 3364792,
|
| 111 |
+
"step": 3000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.7879333633498424,
|
| 115 |
+
"grad_norm": 2.3144521713256836,
|
| 116 |
+
"learning_rate": 4.6060333183250794e-05,
|
| 117 |
+
"loss": 1.8456,
|
| 118 |
+
"num_input_tokens_seen": 3925172,
|
| 119 |
+
"step": 3500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.7879333633498424,
|
| 123 |
+
"eval_loss": 1.6245118379592896,
|
| 124 |
+
"eval_runtime": 7.045,
|
| 125 |
+
"eval_samples_per_second": 141.944,
|
| 126 |
+
"eval_steps_per_second": 17.743,
|
| 127 |
+
"num_input_tokens_seen": 3925172,
|
| 128 |
+
"step": 3500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9004952723998199,
|
| 132 |
+
"grad_norm": 2.394990921020508,
|
| 133 |
+
"learning_rate": 4.54975236380009e-05,
|
| 134 |
+
"loss": 1.8542,
|
| 135 |
+
"num_input_tokens_seen": 4490100,
|
| 136 |
+
"step": 4000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.9004952723998199,
|
| 140 |
+
"eval_loss": 1.6217968463897705,
|
| 141 |
+
"eval_runtime": 7.1659,
|
| 142 |
+
"eval_samples_per_second": 139.549,
|
| 143 |
+
"eval_steps_per_second": 17.444,
|
| 144 |
+
"num_input_tokens_seen": 4490100,
|
| 145 |
+
"step": 4000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.0130571814497973,
|
| 149 |
+
"grad_norm": 2.0307397842407227,
|
| 150 |
+
"learning_rate": 4.4934714092751016e-05,
|
| 151 |
+
"loss": 1.8305,
|
| 152 |
+
"num_input_tokens_seen": 5052066,
|
| 153 |
+
"step": 4500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.0130571814497973,
|
| 157 |
+
"eval_loss": 1.6211210489273071,
|
| 158 |
+
"eval_runtime": 6.7485,
|
| 159 |
+
"eval_samples_per_second": 148.18,
|
| 160 |
+
"eval_steps_per_second": 18.523,
|
| 161 |
+
"num_input_tokens_seen": 5052066,
|
| 162 |
+
"step": 4500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.125619090499775,
|
| 166 |
+
"grad_norm": 2.627432346343994,
|
| 167 |
+
"learning_rate": 4.437190454750112e-05,
|
| 168 |
+
"loss": 1.7588,
|
| 169 |
+
"num_input_tokens_seen": 5607258,
|
| 170 |
+
"step": 5000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.125619090499775,
|
| 174 |
+
"eval_loss": 1.6039692163467407,
|
| 175 |
+
"eval_runtime": 6.9517,
|
| 176 |
+
"eval_samples_per_second": 143.85,
|
| 177 |
+
"eval_steps_per_second": 17.981,
|
| 178 |
+
"num_input_tokens_seen": 5607258,
|
| 179 |
+
"step": 5000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.2381809995497524,
|
| 183 |
+
"grad_norm": 2.0901269912719727,
|
| 184 |
+
"learning_rate": 4.380909500225124e-05,
|
| 185 |
+
"loss": 1.7606,
|
| 186 |
+
"num_input_tokens_seen": 6165278,
|
| 187 |
+
"step": 5500
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.2381809995497524,
|
| 191 |
+
"eval_loss": 1.6020277738571167,
|
| 192 |
+
"eval_runtime": 6.7991,
|
| 193 |
+
"eval_samples_per_second": 147.079,
|
| 194 |
+
"eval_steps_per_second": 18.385,
|
| 195 |
+
"num_input_tokens_seen": 6165278,
|
| 196 |
+
"step": 5500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.3507429085997298,
|
| 200 |
+
"grad_norm": 2.733879804611206,
|
| 201 |
+
"learning_rate": 4.324628545700135e-05,
|
| 202 |
+
"loss": 1.7426,
|
| 203 |
+
"num_input_tokens_seen": 6727290,
|
| 204 |
+
"step": 6000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.3507429085997298,
|
| 208 |
+
"eval_loss": 1.5992920398712158,
|
| 209 |
+
"eval_runtime": 6.9187,
|
| 210 |
+
"eval_samples_per_second": 144.535,
|
| 211 |
+
"eval_steps_per_second": 18.067,
|
| 212 |
+
"num_input_tokens_seen": 6727290,
|
| 213 |
+
"step": 6000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.4633048176497074,
|
| 217 |
+
"grad_norm": 2.134584665298462,
|
| 218 |
+
"learning_rate": 4.2683475911751466e-05,
|
| 219 |
+
"loss": 1.7477,
|
| 220 |
+
"num_input_tokens_seen": 7292338,
|
| 221 |
+
"step": 6500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.4633048176497074,
|
| 225 |
+
"eval_loss": 1.5869497060775757,
|
| 226 |
+
"eval_runtime": 7.0346,
|
| 227 |
+
"eval_samples_per_second": 142.154,
|
| 228 |
+
"eval_steps_per_second": 17.769,
|
| 229 |
+
"num_input_tokens_seen": 7292338,
|
| 230 |
+
"step": 6500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.5758667266996849,
|
| 234 |
+
"grad_norm": 2.1596298217773438,
|
| 235 |
+
"learning_rate": 4.212066636650158e-05,
|
| 236 |
+
"loss": 1.7413,
|
| 237 |
+
"num_input_tokens_seen": 7849466,
|
| 238 |
+
"step": 7000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.5758667266996849,
|
| 242 |
+
"eval_loss": 1.5790966749191284,
|
| 243 |
+
"eval_runtime": 7.0544,
|
| 244 |
+
"eval_samples_per_second": 141.755,
|
| 245 |
+
"eval_steps_per_second": 17.719,
|
| 246 |
+
"num_input_tokens_seen": 7849466,
|
| 247 |
+
"step": 7000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.6884286357496623,
|
| 251 |
+
"grad_norm": 2.1379499435424805,
|
| 252 |
+
"learning_rate": 4.155785682125169e-05,
|
| 253 |
+
"loss": 1.7342,
|
| 254 |
+
"num_input_tokens_seen": 8415302,
|
| 255 |
+
"step": 7500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.6884286357496623,
|
| 259 |
+
"eval_loss": 1.5791916847229004,
|
| 260 |
+
"eval_runtime": 6.899,
|
| 261 |
+
"eval_samples_per_second": 144.949,
|
| 262 |
+
"eval_steps_per_second": 18.119,
|
| 263 |
+
"num_input_tokens_seen": 8415302,
|
| 264 |
+
"step": 7500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.8009905447996397,
|
| 268 |
+
"grad_norm": 3.6986210346221924,
|
| 269 |
+
"learning_rate": 4.09950472760018e-05,
|
| 270 |
+
"loss": 1.7247,
|
| 271 |
+
"num_input_tokens_seen": 8970490,
|
| 272 |
+
"step": 8000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.8009905447996397,
|
| 276 |
+
"eval_loss": 1.5758883953094482,
|
| 277 |
+
"eval_runtime": 7.0586,
|
| 278 |
+
"eval_samples_per_second": 141.671,
|
| 279 |
+
"eval_steps_per_second": 17.709,
|
| 280 |
+
"num_input_tokens_seen": 8970490,
|
| 281 |
+
"step": 8000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.9135524538496171,
|
| 285 |
+
"grad_norm": 2.2056398391723633,
|
| 286 |
+
"learning_rate": 4.0432237730751915e-05,
|
| 287 |
+
"loss": 1.7423,
|
| 288 |
+
"num_input_tokens_seen": 9529290,
|
| 289 |
+
"step": 8500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.9135524538496171,
|
| 293 |
+
"eval_loss": 1.574432134628296,
|
| 294 |
+
"eval_runtime": 7.087,
|
| 295 |
+
"eval_samples_per_second": 141.104,
|
| 296 |
+
"eval_steps_per_second": 17.638,
|
| 297 |
+
"num_input_tokens_seen": 9529290,
|
| 298 |
+
"step": 8500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.0261143628995946,
|
| 302 |
+
"grad_norm": 2.6801469326019287,
|
| 303 |
+
"learning_rate": 3.986942818550203e-05,
|
| 304 |
+
"loss": 1.7138,
|
| 305 |
+
"num_input_tokens_seen": 10091652,
|
| 306 |
+
"step": 9000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.0261143628995946,
|
| 310 |
+
"eval_loss": 1.5655481815338135,
|
| 311 |
+
"eval_runtime": 6.8545,
|
| 312 |
+
"eval_samples_per_second": 145.889,
|
| 313 |
+
"eval_steps_per_second": 18.236,
|
| 314 |
+
"num_input_tokens_seen": 10091652,
|
| 315 |
+
"step": 9000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.1386762719495724,
|
| 319 |
+
"grad_norm": 1.9888643026351929,
|
| 320 |
+
"learning_rate": 3.9306618640252144e-05,
|
| 321 |
+
"loss": 1.6719,
|
| 322 |
+
"num_input_tokens_seen": 10650544,
|
| 323 |
+
"step": 9500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.1386762719495724,
|
| 327 |
+
"eval_loss": 1.562954306602478,
|
| 328 |
+
"eval_runtime": 6.8029,
|
| 329 |
+
"eval_samples_per_second": 146.995,
|
| 330 |
+
"eval_steps_per_second": 18.374,
|
| 331 |
+
"num_input_tokens_seen": 10650544,
|
| 332 |
+
"step": 9500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.25123818099955,
|
| 336 |
+
"grad_norm": 2.0444724559783936,
|
| 337 |
+
"learning_rate": 3.874380909500225e-05,
|
| 338 |
+
"loss": 1.6637,
|
| 339 |
+
"num_input_tokens_seen": 11208648,
|
| 340 |
+
"step": 10000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.25123818099955,
|
| 344 |
+
"eval_loss": 1.5584429502487183,
|
| 345 |
+
"eval_runtime": 6.8702,
|
| 346 |
+
"eval_samples_per_second": 145.557,
|
| 347 |
+
"eval_steps_per_second": 18.195,
|
| 348 |
+
"num_input_tokens_seen": 11208648,
|
| 349 |
+
"step": 10000
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.3638000900495273,
|
| 353 |
+
"grad_norm": 3.0980803966522217,
|
| 354 |
+
"learning_rate": 3.8180999549752365e-05,
|
| 355 |
+
"loss": 1.6415,
|
| 356 |
+
"num_input_tokens_seen": 11776396,
|
| 357 |
+
"step": 10500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.3638000900495273,
|
| 361 |
+
"eval_loss": 1.5608967542648315,
|
| 362 |
+
"eval_runtime": 6.9589,
|
| 363 |
+
"eval_samples_per_second": 143.702,
|
| 364 |
+
"eval_steps_per_second": 17.963,
|
| 365 |
+
"num_input_tokens_seen": 11776396,
|
| 366 |
+
"step": 10500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.4763619990995047,
|
| 370 |
+
"grad_norm": 2.2694685459136963,
|
| 371 |
+
"learning_rate": 3.761819000450248e-05,
|
| 372 |
+
"loss": 1.6565,
|
| 373 |
+
"num_input_tokens_seen": 12338500,
|
| 374 |
+
"step": 11000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.4763619990995047,
|
| 378 |
+
"eval_loss": 1.5557788610458374,
|
| 379 |
+
"eval_runtime": 6.8357,
|
| 380 |
+
"eval_samples_per_second": 146.29,
|
| 381 |
+
"eval_steps_per_second": 18.286,
|
| 382 |
+
"num_input_tokens_seen": 12338500,
|
| 383 |
+
"step": 11000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.588923908149482,
|
| 387 |
+
"grad_norm": 2.054405689239502,
|
| 388 |
+
"learning_rate": 3.705538045925259e-05,
|
| 389 |
+
"loss": 1.6597,
|
| 390 |
+
"num_input_tokens_seen": 12897552,
|
| 391 |
+
"step": 11500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.588923908149482,
|
| 395 |
+
"eval_loss": 1.5530343055725098,
|
| 396 |
+
"eval_runtime": 6.9444,
|
| 397 |
+
"eval_samples_per_second": 144.001,
|
| 398 |
+
"eval_steps_per_second": 18.0,
|
| 399 |
+
"num_input_tokens_seen": 12897552,
|
| 400 |
+
"step": 11500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.7014858171994596,
|
| 404 |
+
"grad_norm": 2.121612548828125,
|
| 405 |
+
"learning_rate": 3.649257091400271e-05,
|
| 406 |
+
"loss": 1.6709,
|
| 407 |
+
"num_input_tokens_seen": 13460052,
|
| 408 |
+
"step": 12000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.7014858171994596,
|
| 412 |
+
"eval_loss": 1.547659993171692,
|
| 413 |
+
"eval_runtime": 6.9397,
|
| 414 |
+
"eval_samples_per_second": 144.099,
|
| 415 |
+
"eval_steps_per_second": 18.012,
|
| 416 |
+
"num_input_tokens_seen": 13460052,
|
| 417 |
+
"step": 12000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.814047726249437,
|
| 421 |
+
"grad_norm": 2.2037246227264404,
|
| 422 |
+
"learning_rate": 3.5929761368752815e-05,
|
| 423 |
+
"loss": 1.648,
|
| 424 |
+
"num_input_tokens_seen": 14021984,
|
| 425 |
+
"step": 12500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.814047726249437,
|
| 429 |
+
"eval_loss": 1.5424396991729736,
|
| 430 |
+
"eval_runtime": 6.9369,
|
| 431 |
+
"eval_samples_per_second": 144.156,
|
| 432 |
+
"eval_steps_per_second": 18.019,
|
| 433 |
+
"num_input_tokens_seen": 14021984,
|
| 434 |
+
"step": 12500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.926609635299415,
|
| 438 |
+
"grad_norm": 3.3693389892578125,
|
| 439 |
+
"learning_rate": 3.536695182350293e-05,
|
| 440 |
+
"loss": 1.642,
|
| 441 |
+
"num_input_tokens_seen": 14586256,
|
| 442 |
+
"step": 13000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.926609635299415,
|
| 446 |
+
"eval_loss": 1.5432666540145874,
|
| 447 |
+
"eval_runtime": 6.899,
|
| 448 |
+
"eval_samples_per_second": 144.948,
|
| 449 |
+
"eval_steps_per_second": 18.119,
|
| 450 |
+
"num_input_tokens_seen": 14586256,
|
| 451 |
+
"step": 13000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 3.0391715443493923,
|
| 455 |
+
"grad_norm": 2.0641028881073,
|
| 456 |
+
"learning_rate": 3.480414227825304e-05,
|
| 457 |
+
"loss": 1.6258,
|
| 458 |
+
"num_input_tokens_seen": 15140609,
|
| 459 |
+
"step": 13500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.0391715443493923,
|
| 463 |
+
"eval_loss": 1.541858196258545,
|
| 464 |
+
"eval_runtime": 6.9082,
|
| 465 |
+
"eval_samples_per_second": 144.756,
|
| 466 |
+
"eval_steps_per_second": 18.095,
|
| 467 |
+
"num_input_tokens_seen": 15140609,
|
| 468 |
+
"step": 13500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.1517334533993697,
|
| 472 |
+
"grad_norm": 2.103282928466797,
|
| 473 |
+
"learning_rate": 3.424133273300315e-05,
|
| 474 |
+
"loss": 1.6067,
|
| 475 |
+
"num_input_tokens_seen": 15700397,
|
| 476 |
+
"step": 14000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.1517334533993697,
|
| 480 |
+
"eval_loss": 1.541473627090454,
|
| 481 |
+
"eval_runtime": 6.8691,
|
| 482 |
+
"eval_samples_per_second": 145.579,
|
| 483 |
+
"eval_steps_per_second": 18.197,
|
| 484 |
+
"num_input_tokens_seen": 15700397,
|
| 485 |
+
"step": 14000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.264295362449347,
|
| 489 |
+
"grad_norm": 1.831855297088623,
|
| 490 |
+
"learning_rate": 3.3678523187753265e-05,
|
| 491 |
+
"loss": 1.5946,
|
| 492 |
+
"num_input_tokens_seen": 16265849,
|
| 493 |
+
"step": 14500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 3.264295362449347,
|
| 497 |
+
"eval_loss": 1.54502272605896,
|
| 498 |
+
"eval_runtime": 6.9275,
|
| 499 |
+
"eval_samples_per_second": 144.353,
|
| 500 |
+
"eval_steps_per_second": 18.044,
|
| 501 |
+
"num_input_tokens_seen": 16265849,
|
| 502 |
+
"step": 14500
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 3.3768572714993246,
|
| 506 |
+
"grad_norm": 1.8841536045074463,
|
| 507 |
+
"learning_rate": 3.311571364250338e-05,
|
| 508 |
+
"loss": 1.5835,
|
| 509 |
+
"num_input_tokens_seen": 16827557,
|
| 510 |
+
"step": 15000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.3768572714993246,
|
| 514 |
+
"eval_loss": 1.5415329933166504,
|
| 515 |
+
"eval_runtime": 7.0688,
|
| 516 |
+
"eval_samples_per_second": 141.466,
|
| 517 |
+
"eval_steps_per_second": 17.683,
|
| 518 |
+
"num_input_tokens_seen": 16827557,
|
| 519 |
+
"step": 15000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.489419180549302,
|
| 523 |
+
"grad_norm": 2.257237672805786,
|
| 524 |
+
"learning_rate": 3.2552904097253486e-05,
|
| 525 |
+
"loss": 1.5996,
|
| 526 |
+
"num_input_tokens_seen": 17384857,
|
| 527 |
+
"step": 15500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 3.489419180549302,
|
| 531 |
+
"eval_loss": 1.5411442518234253,
|
| 532 |
+
"eval_runtime": 6.997,
|
| 533 |
+
"eval_samples_per_second": 142.919,
|
| 534 |
+
"eval_steps_per_second": 17.865,
|
| 535 |
+
"num_input_tokens_seen": 17384857,
|
| 536 |
+
"step": 15500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.6019810895992794,
|
| 540 |
+
"grad_norm": 3.1065425872802734,
|
| 541 |
+
"learning_rate": 3.19900945520036e-05,
|
| 542 |
+
"loss": 1.5834,
|
| 543 |
+
"num_input_tokens_seen": 17945909,
|
| 544 |
+
"step": 16000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 3.6019810895992794,
|
| 548 |
+
"eval_loss": 1.5382109880447388,
|
| 549 |
+
"eval_runtime": 7.0342,
|
| 550 |
+
"eval_samples_per_second": 142.163,
|
| 551 |
+
"eval_steps_per_second": 17.77,
|
| 552 |
+
"num_input_tokens_seen": 17945909,
|
| 553 |
+
"step": 16000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.7145429986492573,
|
| 557 |
+
"grad_norm": 2.736241579055786,
|
| 558 |
+
"learning_rate": 3.1427285006753714e-05,
|
| 559 |
+
"loss": 1.5956,
|
| 560 |
+
"num_input_tokens_seen": 18507721,
|
| 561 |
+
"step": 16500
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.7145429986492573,
|
| 565 |
+
"eval_loss": 1.5350807905197144,
|
| 566 |
+
"eval_runtime": 6.9983,
|
| 567 |
+
"eval_samples_per_second": 142.893,
|
| 568 |
+
"eval_steps_per_second": 17.862,
|
| 569 |
+
"num_input_tokens_seen": 18507721,
|
| 570 |
+
"step": 16500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 3.8271049076992347,
|
| 574 |
+
"grad_norm": 2.040745973587036,
|
| 575 |
+
"learning_rate": 3.086447546150383e-05,
|
| 576 |
+
"loss": 1.5825,
|
| 577 |
+
"num_input_tokens_seen": 19069425,
|
| 578 |
+
"step": 17000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.8271049076992347,
|
| 582 |
+
"eval_loss": 1.5356193780899048,
|
| 583 |
+
"eval_runtime": 6.7845,
|
| 584 |
+
"eval_samples_per_second": 147.395,
|
| 585 |
+
"eval_steps_per_second": 18.424,
|
| 586 |
+
"num_input_tokens_seen": 19069425,
|
| 587 |
+
"step": 17000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 3.939666816749212,
|
| 591 |
+
"grad_norm": 1.7128684520721436,
|
| 592 |
+
"learning_rate": 3.030166591625394e-05,
|
| 593 |
+
"loss": 1.6001,
|
| 594 |
+
"num_input_tokens_seen": 19631905,
|
| 595 |
+
"step": 17500
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 3.939666816749212,
|
| 599 |
+
"eval_loss": 1.5294198989868164,
|
| 600 |
+
"eval_runtime": 6.8242,
|
| 601 |
+
"eval_samples_per_second": 146.538,
|
| 602 |
+
"eval_steps_per_second": 18.317,
|
| 603 |
+
"num_input_tokens_seen": 19631905,
|
| 604 |
+
"step": 17500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 4.052228725799189,
|
| 608 |
+
"grad_norm": 2.3983848094940186,
|
| 609 |
+
"learning_rate": 2.9738856371004053e-05,
|
| 610 |
+
"loss": 1.5677,
|
| 611 |
+
"num_input_tokens_seen": 20185192,
|
| 612 |
+
"step": 18000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 4.052228725799189,
|
| 616 |
+
"eval_loss": 1.5368764400482178,
|
| 617 |
+
"eval_runtime": 6.9147,
|
| 618 |
+
"eval_samples_per_second": 144.619,
|
| 619 |
+
"eval_steps_per_second": 18.077,
|
| 620 |
+
"num_input_tokens_seen": 20185192,
|
| 621 |
+
"step": 18000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 4.164790634849167,
|
| 625 |
+
"grad_norm": 2.142731189727783,
|
| 626 |
+
"learning_rate": 2.9176046825754167e-05,
|
| 627 |
+
"loss": 1.5415,
|
| 628 |
+
"num_input_tokens_seen": 20739888,
|
| 629 |
+
"step": 18500
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 4.164790634849167,
|
| 633 |
+
"eval_loss": 1.5318347215652466,
|
| 634 |
+
"eval_runtime": 6.8209,
|
| 635 |
+
"eval_samples_per_second": 146.608,
|
| 636 |
+
"eval_steps_per_second": 18.326,
|
| 637 |
+
"num_input_tokens_seen": 20739888,
|
| 638 |
+
"step": 18500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.277352543899145,
|
| 642 |
+
"grad_norm": 2.7573177814483643,
|
| 643 |
+
"learning_rate": 2.8613237280504278e-05,
|
| 644 |
+
"loss": 1.5362,
|
| 645 |
+
"num_input_tokens_seen": 21304584,
|
| 646 |
+
"step": 19000
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 4.277352543899145,
|
| 650 |
+
"eval_loss": 1.531069278717041,
|
| 651 |
+
"eval_runtime": 6.7833,
|
| 652 |
+
"eval_samples_per_second": 147.42,
|
| 653 |
+
"eval_steps_per_second": 18.428,
|
| 654 |
+
"num_input_tokens_seen": 21304584,
|
| 655 |
+
"step": 19000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 4.389914452949122,
|
| 659 |
+
"grad_norm": 3.4846112728118896,
|
| 660 |
+
"learning_rate": 2.8050427735254392e-05,
|
| 661 |
+
"loss": 1.5251,
|
| 662 |
+
"num_input_tokens_seen": 21862856,
|
| 663 |
+
"step": 19500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 4.389914452949122,
|
| 667 |
+
"eval_loss": 1.5322602987289429,
|
| 668 |
+
"eval_runtime": 6.8222,
|
| 669 |
+
"eval_samples_per_second": 146.58,
|
| 670 |
+
"eval_steps_per_second": 18.323,
|
| 671 |
+
"num_input_tokens_seen": 21862856,
|
| 672 |
+
"step": 19500
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 4.5024763619991,
|
| 676 |
+
"grad_norm": 1.7864114046096802,
|
| 677 |
+
"learning_rate": 2.7487618190004506e-05,
|
| 678 |
+
"loss": 1.5388,
|
| 679 |
+
"num_input_tokens_seen": 22427236,
|
| 680 |
+
"step": 20000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.5024763619991,
|
| 684 |
+
"eval_loss": 1.5306612253189087,
|
| 685 |
+
"eval_runtime": 6.7822,
|
| 686 |
+
"eval_samples_per_second": 147.445,
|
| 687 |
+
"eval_steps_per_second": 18.431,
|
| 688 |
+
"num_input_tokens_seen": 22427236,
|
| 689 |
+
"step": 20000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 4.615038271049077,
|
| 693 |
+
"grad_norm": 2.4305617809295654,
|
| 694 |
+
"learning_rate": 2.6924808644754617e-05,
|
| 695 |
+
"loss": 1.5508,
|
| 696 |
+
"num_input_tokens_seen": 22985184,
|
| 697 |
+
"step": 20500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 4.615038271049077,
|
| 701 |
+
"eval_loss": 1.528159260749817,
|
| 702 |
+
"eval_runtime": 6.7935,
|
| 703 |
+
"eval_samples_per_second": 147.2,
|
| 704 |
+
"eval_steps_per_second": 18.4,
|
| 705 |
+
"num_input_tokens_seen": 22985184,
|
| 706 |
+
"step": 20500
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 4.727600180099055,
|
| 710 |
+
"grad_norm": 2.421140193939209,
|
| 711 |
+
"learning_rate": 2.636199909950473e-05,
|
| 712 |
+
"loss": 1.5692,
|
| 713 |
+
"num_input_tokens_seen": 23548396,
|
| 714 |
+
"step": 21000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 4.727600180099055,
|
| 718 |
+
"eval_loss": 1.5264862775802612,
|
| 719 |
+
"eval_runtime": 6.7777,
|
| 720 |
+
"eval_samples_per_second": 147.543,
|
| 721 |
+
"eval_steps_per_second": 18.443,
|
| 722 |
+
"num_input_tokens_seen": 23548396,
|
| 723 |
+
"step": 21000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 4.8401620891490325,
|
| 727 |
+
"grad_norm": 2.5409975051879883,
|
| 728 |
+
"learning_rate": 2.5799189554254842e-05,
|
| 729 |
+
"loss": 1.5391,
|
| 730 |
+
"num_input_tokens_seen": 24111452,
|
| 731 |
+
"step": 21500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 4.8401620891490325,
|
| 735 |
+
"eval_loss": 1.5276471376419067,
|
| 736 |
+
"eval_runtime": 6.7577,
|
| 737 |
+
"eval_samples_per_second": 147.979,
|
| 738 |
+
"eval_steps_per_second": 18.497,
|
| 739 |
+
"num_input_tokens_seen": 24111452,
|
| 740 |
+
"step": 21500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.952723998199009,
|
| 744 |
+
"grad_norm": 2.3315558433532715,
|
| 745 |
+
"learning_rate": 2.5236380009004956e-05,
|
| 746 |
+
"loss": 1.5431,
|
| 747 |
+
"num_input_tokens_seen": 24673344,
|
| 748 |
+
"step": 22000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 4.952723998199009,
|
| 752 |
+
"eval_loss": 1.5270482301712036,
|
| 753 |
+
"eval_runtime": 6.7599,
|
| 754 |
+
"eval_samples_per_second": 147.932,
|
| 755 |
+
"eval_steps_per_second": 18.491,
|
| 756 |
+
"num_input_tokens_seen": 24673344,
|
| 757 |
+
"step": 22000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 5.065285907248987,
|
| 761 |
+
"grad_norm": 1.7638120651245117,
|
| 762 |
+
"learning_rate": 2.4673570463755067e-05,
|
| 763 |
+
"loss": 1.5147,
|
| 764 |
+
"num_input_tokens_seen": 25236559,
|
| 765 |
+
"step": 22500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 5.065285907248987,
|
| 769 |
+
"eval_loss": 1.529248833656311,
|
| 770 |
+
"eval_runtime": 6.7621,
|
| 771 |
+
"eval_samples_per_second": 147.883,
|
| 772 |
+
"eval_steps_per_second": 18.485,
|
| 773 |
+
"num_input_tokens_seen": 25236559,
|
| 774 |
+
"step": 22500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 5.177847816298964,
|
| 778 |
+
"grad_norm": 2.1643288135528564,
|
| 779 |
+
"learning_rate": 2.4110760918505178e-05,
|
| 780 |
+
"loss": 1.4908,
|
| 781 |
+
"num_input_tokens_seen": 25799675,
|
| 782 |
+
"step": 23000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 5.177847816298964,
|
| 786 |
+
"eval_loss": 1.5288372039794922,
|
| 787 |
+
"eval_runtime": 6.7612,
|
| 788 |
+
"eval_samples_per_second": 147.902,
|
| 789 |
+
"eval_steps_per_second": 18.488,
|
| 790 |
+
"num_input_tokens_seen": 25799675,
|
| 791 |
+
"step": 23000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 5.290409725348942,
|
| 795 |
+
"grad_norm": 2.620457172393799,
|
| 796 |
+
"learning_rate": 2.3547951373255292e-05,
|
| 797 |
+
"loss": 1.5153,
|
| 798 |
+
"num_input_tokens_seen": 26352767,
|
| 799 |
+
"step": 23500
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 5.290409725348942,
|
| 803 |
+
"eval_loss": 1.5288450717926025,
|
| 804 |
+
"eval_runtime": 6.7495,
|
| 805 |
+
"eval_samples_per_second": 148.159,
|
| 806 |
+
"eval_steps_per_second": 18.52,
|
| 807 |
+
"num_input_tokens_seen": 26352767,
|
| 808 |
+
"step": 23500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 5.402971634398919,
|
| 812 |
+
"grad_norm": 1.847611427307129,
|
| 813 |
+
"learning_rate": 2.2985141828005406e-05,
|
| 814 |
+
"loss": 1.5099,
|
| 815 |
+
"num_input_tokens_seen": 26916707,
|
| 816 |
+
"step": 24000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 5.402971634398919,
|
| 820 |
+
"eval_loss": 1.5249587297439575,
|
| 821 |
+
"eval_runtime": 6.5756,
|
| 822 |
+
"eval_samples_per_second": 152.077,
|
| 823 |
+
"eval_steps_per_second": 19.01,
|
| 824 |
+
"num_input_tokens_seen": 26916707,
|
| 825 |
+
"step": 24000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 5.515533543448897,
|
| 829 |
+
"grad_norm": 2.3133625984191895,
|
| 830 |
+
"learning_rate": 2.2422332282755517e-05,
|
| 831 |
+
"loss": 1.5064,
|
| 832 |
+
"num_input_tokens_seen": 27483639,
|
| 833 |
+
"step": 24500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 5.515533543448897,
|
| 837 |
+
"eval_loss": 1.5258936882019043,
|
| 838 |
+
"eval_runtime": 6.6146,
|
| 839 |
+
"eval_samples_per_second": 151.18,
|
| 840 |
+
"eval_steps_per_second": 18.897,
|
| 841 |
+
"num_input_tokens_seen": 27483639,
|
| 842 |
+
"step": 24500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 5.628095452498874,
|
| 846 |
+
"grad_norm": 2.402250289916992,
|
| 847 |
+
"learning_rate": 2.185952273750563e-05,
|
| 848 |
+
"loss": 1.5146,
|
| 849 |
+
"num_input_tokens_seen": 28040307,
|
| 850 |
+
"step": 25000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 5.628095452498874,
|
| 854 |
+
"eval_loss": 1.5248527526855469,
|
| 855 |
+
"eval_runtime": 6.7384,
|
| 856 |
+
"eval_samples_per_second": 148.403,
|
| 857 |
+
"eval_steps_per_second": 18.55,
|
| 858 |
+
"num_input_tokens_seen": 28040307,
|
| 859 |
+
"step": 25000
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 5.740657361548852,
|
| 863 |
+
"grad_norm": 2.146390438079834,
|
| 864 |
+
"learning_rate": 2.129671319225574e-05,
|
| 865 |
+
"loss": 1.4938,
|
| 866 |
+
"num_input_tokens_seen": 28600639,
|
| 867 |
+
"step": 25500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 5.740657361548852,
|
| 871 |
+
"eval_loss": 1.5232993364334106,
|
| 872 |
+
"eval_runtime": 6.8312,
|
| 873 |
+
"eval_samples_per_second": 146.387,
|
| 874 |
+
"eval_steps_per_second": 18.298,
|
| 875 |
+
"num_input_tokens_seen": 28600639,
|
| 876 |
+
"step": 25500
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 5.85321927059883,
|
| 880 |
+
"grad_norm": 2.0159800052642822,
|
| 881 |
+
"learning_rate": 2.0733903647005852e-05,
|
| 882 |
+
"loss": 1.5034,
|
| 883 |
+
"num_input_tokens_seen": 29164539,
|
| 884 |
+
"step": 26000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 5.85321927059883,
|
| 888 |
+
"eval_loss": 1.52369225025177,
|
| 889 |
+
"eval_runtime": 6.8837,
|
| 890 |
+
"eval_samples_per_second": 145.271,
|
| 891 |
+
"eval_steps_per_second": 18.159,
|
| 892 |
+
"num_input_tokens_seen": 29164539,
|
| 893 |
+
"step": 26000
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 5.965781179648807,
|
| 897 |
+
"grad_norm": 2.001739740371704,
|
| 898 |
+
"learning_rate": 2.0171094101755966e-05,
|
| 899 |
+
"loss": 1.5091,
|
| 900 |
+
"num_input_tokens_seen": 29730199,
|
| 901 |
+
"step": 26500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 5.965781179648807,
|
| 905 |
+
"eval_loss": 1.5219199657440186,
|
| 906 |
+
"eval_runtime": 6.8886,
|
| 907 |
+
"eval_samples_per_second": 145.168,
|
| 908 |
+
"eval_steps_per_second": 18.146,
|
| 909 |
+
"num_input_tokens_seen": 29730199,
|
| 910 |
+
"step": 26500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 6.078343088698785,
|
| 914 |
+
"grad_norm": 1.9858044385910034,
|
| 915 |
+
"learning_rate": 1.960828455650608e-05,
|
| 916 |
+
"loss": 1.4853,
|
| 917 |
+
"num_input_tokens_seen": 30286010,
|
| 918 |
+
"step": 27000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 6.078343088698785,
|
| 922 |
+
"eval_loss": 1.5240556001663208,
|
| 923 |
+
"eval_runtime": 6.7755,
|
| 924 |
+
"eval_samples_per_second": 147.591,
|
| 925 |
+
"eval_steps_per_second": 18.449,
|
| 926 |
+
"num_input_tokens_seen": 30286010,
|
| 927 |
+
"step": 27000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 6.190904997748762,
|
| 931 |
+
"grad_norm": 1.812340259552002,
|
| 932 |
+
"learning_rate": 1.904547501125619e-05,
|
| 933 |
+
"loss": 1.4797,
|
| 934 |
+
"num_input_tokens_seen": 30840802,
|
| 935 |
+
"step": 27500
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 6.190904997748762,
|
| 939 |
+
"eval_loss": 1.5201354026794434,
|
| 940 |
+
"eval_runtime": 6.8727,
|
| 941 |
+
"eval_samples_per_second": 145.503,
|
| 942 |
+
"eval_steps_per_second": 18.188,
|
| 943 |
+
"num_input_tokens_seen": 30840802,
|
| 944 |
+
"step": 27500
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 6.3034669067987394,
|
| 948 |
+
"grad_norm": 2.370309829711914,
|
| 949 |
+
"learning_rate": 1.8482665466006305e-05,
|
| 950 |
+
"loss": 1.466,
|
| 951 |
+
"num_input_tokens_seen": 31403710,
|
| 952 |
+
"step": 28000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 6.3034669067987394,
|
| 956 |
+
"eval_loss": 1.5237922668457031,
|
| 957 |
+
"eval_runtime": 6.9361,
|
| 958 |
+
"eval_samples_per_second": 144.174,
|
| 959 |
+
"eval_steps_per_second": 18.022,
|
| 960 |
+
"num_input_tokens_seen": 31403710,
|
| 961 |
+
"step": 28000
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 6.416028815848716,
|
| 965 |
+
"grad_norm": 2.5866804122924805,
|
| 966 |
+
"learning_rate": 1.7919855920756416e-05,
|
| 967 |
+
"loss": 1.4666,
|
| 968 |
+
"num_input_tokens_seen": 31962730,
|
| 969 |
+
"step": 28500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 6.416028815848716,
|
| 973 |
+
"eval_loss": 1.522592306137085,
|
| 974 |
+
"eval_runtime": 6.8335,
|
| 975 |
+
"eval_samples_per_second": 146.339,
|
| 976 |
+
"eval_steps_per_second": 18.292,
|
| 977 |
+
"num_input_tokens_seen": 31962730,
|
| 978 |
+
"step": 28500
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 6.528590724898694,
|
| 982 |
+
"grad_norm": 2.151406764984131,
|
| 983 |
+
"learning_rate": 1.735704637550653e-05,
|
| 984 |
+
"loss": 1.4732,
|
| 985 |
+
"num_input_tokens_seen": 32518854,
|
| 986 |
+
"step": 29000
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 6.528590724898694,
|
| 990 |
+
"eval_loss": 1.519935965538025,
|
| 991 |
+
"eval_runtime": 6.7994,
|
| 992 |
+
"eval_samples_per_second": 147.072,
|
| 993 |
+
"eval_steps_per_second": 18.384,
|
| 994 |
+
"num_input_tokens_seen": 32518854,
|
| 995 |
+
"step": 29000
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 6.641152633948671,
|
| 999 |
+
"grad_norm": 2.2219040393829346,
|
| 1000 |
+
"learning_rate": 1.6794236830256644e-05,
|
| 1001 |
+
"loss": 1.4756,
|
| 1002 |
+
"num_input_tokens_seen": 33083634,
|
| 1003 |
+
"step": 29500
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 6.641152633948671,
|
| 1007 |
+
"eval_loss": 1.5219242572784424,
|
| 1008 |
+
"eval_runtime": 6.7754,
|
| 1009 |
+
"eval_samples_per_second": 147.592,
|
| 1010 |
+
"eval_steps_per_second": 18.449,
|
| 1011 |
+
"num_input_tokens_seen": 33083634,
|
| 1012 |
+
"step": 29500
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 6.753714542998649,
|
| 1016 |
+
"grad_norm": 1.9344135522842407,
|
| 1017 |
+
"learning_rate": 1.6231427285006755e-05,
|
| 1018 |
+
"loss": 1.4778,
|
| 1019 |
+
"num_input_tokens_seen": 33644482,
|
| 1020 |
+
"step": 30000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 6.753714542998649,
|
| 1024 |
+
"eval_loss": 1.519468069076538,
|
| 1025 |
+
"eval_runtime": 6.8057,
|
| 1026 |
+
"eval_samples_per_second": 146.936,
|
| 1027 |
+
"eval_steps_per_second": 18.367,
|
| 1028 |
+
"num_input_tokens_seen": 33644482,
|
| 1029 |
+
"step": 30000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 6.866276452048627,
|
| 1033 |
+
"grad_norm": 1.8874679803848267,
|
| 1034 |
+
"learning_rate": 1.5668617739756866e-05,
|
| 1035 |
+
"loss": 1.4674,
|
| 1036 |
+
"num_input_tokens_seen": 34207738,
|
| 1037 |
+
"step": 30500
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 6.866276452048627,
|
| 1041 |
+
"eval_loss": 1.5181845426559448,
|
| 1042 |
+
"eval_runtime": 6.9025,
|
| 1043 |
+
"eval_samples_per_second": 144.875,
|
| 1044 |
+
"eval_steps_per_second": 18.109,
|
| 1045 |
+
"num_input_tokens_seen": 34207738,
|
| 1046 |
+
"step": 30500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 6.978838361098604,
|
| 1050 |
+
"grad_norm": 1.885331392288208,
|
| 1051 |
+
"learning_rate": 1.510580819450698e-05,
|
| 1052 |
+
"loss": 1.4813,
|
| 1053 |
+
"num_input_tokens_seen": 34772050,
|
| 1054 |
+
"step": 31000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 6.978838361098604,
|
| 1058 |
+
"eval_loss": 1.5201555490493774,
|
| 1059 |
+
"eval_runtime": 6.832,
|
| 1060 |
+
"eval_samples_per_second": 146.37,
|
| 1061 |
+
"eval_steps_per_second": 18.296,
|
| 1062 |
+
"num_input_tokens_seen": 34772050,
|
| 1063 |
+
"step": 31000
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 7.091400270148582,
|
| 1067 |
+
"grad_norm": 2.135857582092285,
|
| 1068 |
+
"learning_rate": 1.4542998649257092e-05,
|
| 1069 |
+
"loss": 1.4543,
|
| 1070 |
+
"num_input_tokens_seen": 35331657,
|
| 1071 |
+
"step": 31500
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 7.091400270148582,
|
| 1075 |
+
"eval_loss": 1.521092414855957,
|
| 1076 |
+
"eval_runtime": 6.9064,
|
| 1077 |
+
"eval_samples_per_second": 144.792,
|
| 1078 |
+
"eval_steps_per_second": 18.099,
|
| 1079 |
+
"num_input_tokens_seen": 35331657,
|
| 1080 |
+
"step": 31500
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 7.203962179198559,
|
| 1084 |
+
"grad_norm": 2.2138864994049072,
|
| 1085 |
+
"learning_rate": 1.3980189104007205e-05,
|
| 1086 |
+
"loss": 1.4389,
|
| 1087 |
+
"num_input_tokens_seen": 35888749,
|
| 1088 |
+
"step": 32000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 7.203962179198559,
|
| 1092 |
+
"eval_loss": 1.5221294164657593,
|
| 1093 |
+
"eval_runtime": 6.9475,
|
| 1094 |
+
"eval_samples_per_second": 143.937,
|
| 1095 |
+
"eval_steps_per_second": 17.992,
|
| 1096 |
+
"num_input_tokens_seen": 35888749,
|
| 1097 |
+
"step": 32000
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 7.316524088248537,
|
| 1101 |
+
"grad_norm": 2.255690336227417,
|
| 1102 |
+
"learning_rate": 1.3417379558757317e-05,
|
| 1103 |
+
"loss": 1.4534,
|
| 1104 |
+
"num_input_tokens_seen": 36455101,
|
| 1105 |
+
"step": 32500
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 7.316524088248537,
|
| 1109 |
+
"eval_loss": 1.5215495824813843,
|
| 1110 |
+
"eval_runtime": 6.9343,
|
| 1111 |
+
"eval_samples_per_second": 144.211,
|
| 1112 |
+
"eval_steps_per_second": 18.026,
|
| 1113 |
+
"num_input_tokens_seen": 36455101,
|
| 1114 |
+
"step": 32500
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 7.429085997298515,
|
| 1118 |
+
"grad_norm": 1.9412790536880493,
|
| 1119 |
+
"learning_rate": 1.285457001350743e-05,
|
| 1120 |
+
"loss": 1.4401,
|
| 1121 |
+
"num_input_tokens_seen": 37016889,
|
| 1122 |
+
"step": 33000
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 7.429085997298515,
|
| 1126 |
+
"eval_loss": 1.5207875967025757,
|
| 1127 |
+
"eval_runtime": 6.7928,
|
| 1128 |
+
"eval_samples_per_second": 147.215,
|
| 1129 |
+
"eval_steps_per_second": 18.402,
|
| 1130 |
+
"num_input_tokens_seen": 37016889,
|
| 1131 |
+
"step": 33000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 7.541647906348492,
|
| 1135 |
+
"grad_norm": 2.0584607124328613,
|
| 1136 |
+
"learning_rate": 1.2291760468257542e-05,
|
| 1137 |
+
"loss": 1.4435,
|
| 1138 |
+
"num_input_tokens_seen": 37570517,
|
| 1139 |
+
"step": 33500
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 7.541647906348492,
|
| 1143 |
+
"eval_loss": 1.5211970806121826,
|
| 1144 |
+
"eval_runtime": 6.8598,
|
| 1145 |
+
"eval_samples_per_second": 145.776,
|
| 1146 |
+
"eval_steps_per_second": 18.222,
|
| 1147 |
+
"num_input_tokens_seen": 37570517,
|
| 1148 |
+
"step": 33500
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 7.6542098153984695,
|
| 1152 |
+
"grad_norm": 2.090921401977539,
|
| 1153 |
+
"learning_rate": 1.1728950923007654e-05,
|
| 1154 |
+
"loss": 1.4443,
|
| 1155 |
+
"num_input_tokens_seen": 38134577,
|
| 1156 |
+
"step": 34000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 7.6542098153984695,
|
| 1160 |
+
"eval_loss": 1.5204721689224243,
|
| 1161 |
+
"eval_runtime": 6.9765,
|
| 1162 |
+
"eval_samples_per_second": 143.338,
|
| 1163 |
+
"eval_steps_per_second": 17.917,
|
| 1164 |
+
"num_input_tokens_seen": 38134577,
|
| 1165 |
+
"step": 34000
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 7.766771724448446,
|
| 1169 |
+
"grad_norm": 2.349177360534668,
|
| 1170 |
+
"learning_rate": 1.1166141377757767e-05,
|
| 1171 |
+
"loss": 1.4533,
|
| 1172 |
+
"num_input_tokens_seen": 38700917,
|
| 1173 |
+
"step": 34500
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 7.766771724448446,
|
| 1177 |
+
"eval_loss": 1.5209357738494873,
|
| 1178 |
+
"eval_runtime": 7.024,
|
| 1179 |
+
"eval_samples_per_second": 142.37,
|
| 1180 |
+
"eval_steps_per_second": 17.796,
|
| 1181 |
+
"num_input_tokens_seen": 38700917,
|
| 1182 |
+
"step": 34500
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 7.879333633498424,
|
| 1186 |
+
"grad_norm": 2.0737385749816895,
|
| 1187 |
+
"learning_rate": 1.0603331832507881e-05,
|
| 1188 |
+
"loss": 1.4589,
|
| 1189 |
+
"num_input_tokens_seen": 39259257,
|
| 1190 |
+
"step": 35000
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 7.879333633498424,
|
| 1194 |
+
"eval_loss": 1.5217865705490112,
|
| 1195 |
+
"eval_runtime": 6.8333,
|
| 1196 |
+
"eval_samples_per_second": 146.343,
|
| 1197 |
+
"eval_steps_per_second": 18.293,
|
| 1198 |
+
"num_input_tokens_seen": 39259257,
|
| 1199 |
+
"step": 35000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 7.991895542548401,
|
| 1203 |
+
"grad_norm": 2.072783946990967,
|
| 1204 |
+
"learning_rate": 1.0040522287257992e-05,
|
| 1205 |
+
"loss": 1.4548,
|
| 1206 |
+
"num_input_tokens_seen": 39819093,
|
| 1207 |
+
"step": 35500
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 7.991895542548401,
|
| 1211 |
+
"eval_loss": 1.5185105800628662,
|
| 1212 |
+
"eval_runtime": 6.7618,
|
| 1213 |
+
"eval_samples_per_second": 147.889,
|
| 1214 |
+
"eval_steps_per_second": 18.486,
|
| 1215 |
+
"num_input_tokens_seen": 39819093,
|
| 1216 |
+
"step": 35500
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 8.104457451598378,
|
| 1220 |
+
"grad_norm": 2.2963035106658936,
|
| 1221 |
+
"learning_rate": 9.477712742008104e-06,
|
| 1222 |
+
"loss": 1.4322,
|
| 1223 |
+
"num_input_tokens_seen": 40382907,
|
| 1224 |
+
"step": 36000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 8.104457451598378,
|
| 1228 |
+
"eval_loss": 1.520738959312439,
|
| 1229 |
+
"eval_runtime": 6.783,
|
| 1230 |
+
"eval_samples_per_second": 147.428,
|
| 1231 |
+
"eval_steps_per_second": 18.428,
|
| 1232 |
+
"num_input_tokens_seen": 40382907,
|
| 1233 |
+
"step": 36000
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 8.217019360648356,
|
| 1237 |
+
"grad_norm": 2.450338840484619,
|
| 1238 |
+
"learning_rate": 8.914903196758218e-06,
|
| 1239 |
+
"loss": 1.4271,
|
| 1240 |
+
"num_input_tokens_seen": 40938983,
|
| 1241 |
+
"step": 36500
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 8.217019360648356,
|
| 1245 |
+
"eval_loss": 1.5220232009887695,
|
| 1246 |
+
"eval_runtime": 6.9451,
|
| 1247 |
+
"eval_samples_per_second": 143.986,
|
| 1248 |
+
"eval_steps_per_second": 17.998,
|
| 1249 |
+
"num_input_tokens_seen": 40938983,
|
| 1250 |
+
"step": 36500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 8.329581269698334,
|
| 1254 |
+
"grad_norm": 2.414069890975952,
|
| 1255 |
+
"learning_rate": 8.35209365150833e-06,
|
| 1256 |
+
"loss": 1.4165,
|
| 1257 |
+
"num_input_tokens_seen": 41498811,
|
| 1258 |
+
"step": 37000
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 8.329581269698334,
|
| 1262 |
+
"eval_loss": 1.520321011543274,
|
| 1263 |
+
"eval_runtime": 6.9316,
|
| 1264 |
+
"eval_samples_per_second": 144.266,
|
| 1265 |
+
"eval_steps_per_second": 18.033,
|
| 1266 |
+
"num_input_tokens_seen": 41498811,
|
| 1267 |
+
"step": 37000
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 8.442143178748312,
|
| 1271 |
+
"grad_norm": 2.3508474826812744,
|
| 1272 |
+
"learning_rate": 7.789284106258443e-06,
|
| 1273 |
+
"loss": 1.4273,
|
| 1274 |
+
"num_input_tokens_seen": 42053427,
|
| 1275 |
+
"step": 37500
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 8.442143178748312,
|
| 1279 |
+
"eval_loss": 1.5197160243988037,
|
| 1280 |
+
"eval_runtime": 6.8382,
|
| 1281 |
+
"eval_samples_per_second": 146.237,
|
| 1282 |
+
"eval_steps_per_second": 18.28,
|
| 1283 |
+
"num_input_tokens_seen": 42053427,
|
| 1284 |
+
"step": 37500
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 8.55470508779829,
|
| 1288 |
+
"grad_norm": 1.876745581626892,
|
| 1289 |
+
"learning_rate": 7.226474561008555e-06,
|
| 1290 |
+
"loss": 1.4281,
|
| 1291 |
+
"num_input_tokens_seen": 42615135,
|
| 1292 |
+
"step": 38000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 8.55470508779829,
|
| 1296 |
+
"eval_loss": 1.519529104232788,
|
| 1297 |
+
"eval_runtime": 6.7991,
|
| 1298 |
+
"eval_samples_per_second": 147.078,
|
| 1299 |
+
"eval_steps_per_second": 18.385,
|
| 1300 |
+
"num_input_tokens_seen": 42615135,
|
| 1301 |
+
"step": 38000
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 8.667266996848266,
|
| 1305 |
+
"grad_norm": 2.1636829376220703,
|
| 1306 |
+
"learning_rate": 6.663665015758667e-06,
|
| 1307 |
+
"loss": 1.4372,
|
| 1308 |
+
"num_input_tokens_seen": 43173055,
|
| 1309 |
+
"step": 38500
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 8.667266996848266,
|
| 1313 |
+
"eval_loss": 1.5196864604949951,
|
| 1314 |
+
"eval_runtime": 6.9956,
|
| 1315 |
+
"eval_samples_per_second": 142.947,
|
| 1316 |
+
"eval_steps_per_second": 17.868,
|
| 1317 |
+
"num_input_tokens_seen": 43173055,
|
| 1318 |
+
"step": 38500
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 8.779828905898244,
|
| 1322 |
+
"grad_norm": 2.752340078353882,
|
| 1323 |
+
"learning_rate": 6.1008554705087804e-06,
|
| 1324 |
+
"loss": 1.4374,
|
| 1325 |
+
"num_input_tokens_seen": 43737723,
|
| 1326 |
+
"step": 39000
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 8.779828905898244,
|
| 1330 |
+
"eval_loss": 1.5174657106399536,
|
| 1331 |
+
"eval_runtime": 6.8823,
|
| 1332 |
+
"eval_samples_per_second": 145.301,
|
| 1333 |
+
"eval_steps_per_second": 18.163,
|
| 1334 |
+
"num_input_tokens_seen": 43737723,
|
| 1335 |
+
"step": 39000
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 8.892390814948222,
|
| 1339 |
+
"grad_norm": 2.1042685508728027,
|
| 1340 |
+
"learning_rate": 5.538045925258893e-06,
|
| 1341 |
+
"loss": 1.4278,
|
| 1342 |
+
"num_input_tokens_seen": 44300547,
|
| 1343 |
+
"step": 39500
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 8.892390814948222,
|
| 1347 |
+
"eval_loss": 1.5211328268051147,
|
| 1348 |
+
"eval_runtime": 6.8661,
|
| 1349 |
+
"eval_samples_per_second": 145.644,
|
| 1350 |
+
"eval_steps_per_second": 18.205,
|
| 1351 |
+
"num_input_tokens_seen": 44300547,
|
| 1352 |
+
"step": 39500
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 9.0049527239982,
|
| 1356 |
+
"grad_norm": 2.175323486328125,
|
| 1357 |
+
"learning_rate": 4.975236380009005e-06,
|
| 1358 |
+
"loss": 1.442,
|
| 1359 |
+
"num_input_tokens_seen": 44864787,
|
| 1360 |
+
"step": 40000
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 9.0049527239982,
|
| 1364 |
+
"eval_loss": 1.5188645124435425,
|
| 1365 |
+
"eval_runtime": 6.7745,
|
| 1366 |
+
"eval_samples_per_second": 147.612,
|
| 1367 |
+
"eval_steps_per_second": 18.452,
|
| 1368 |
+
"num_input_tokens_seen": 44864787,
|
| 1369 |
+
"step": 40000
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 9.117514633048177,
|
| 1373 |
+
"grad_norm": 2.275874376296997,
|
| 1374 |
+
"learning_rate": 4.412426834759118e-06,
|
| 1375 |
+
"loss": 1.4235,
|
| 1376 |
+
"num_input_tokens_seen": 45418155,
|
| 1377 |
+
"step": 40500
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 9.117514633048177,
|
| 1381 |
+
"eval_loss": 1.5225725173950195,
|
| 1382 |
+
"eval_runtime": 6.8797,
|
| 1383 |
+
"eval_samples_per_second": 145.354,
|
| 1384 |
+
"eval_steps_per_second": 18.169,
|
| 1385 |
+
"num_input_tokens_seen": 45418155,
|
| 1386 |
+
"step": 40500
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 9.230076542098153,
|
| 1390 |
+
"grad_norm": 2.1484689712524414,
|
| 1391 |
+
"learning_rate": 3.84961728950923e-06,
|
| 1392 |
+
"loss": 1.413,
|
| 1393 |
+
"num_input_tokens_seen": 45985195,
|
| 1394 |
+
"step": 41000
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 9.230076542098153,
|
| 1398 |
+
"eval_loss": 1.5219917297363281,
|
| 1399 |
+
"eval_runtime": 6.7725,
|
| 1400 |
+
"eval_samples_per_second": 147.655,
|
| 1401 |
+
"eval_steps_per_second": 18.457,
|
| 1402 |
+
"num_input_tokens_seen": 45985195,
|
| 1403 |
+
"step": 41000
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 9.342638451148131,
|
| 1407 |
+
"grad_norm": 1.917220115661621,
|
| 1408 |
+
"learning_rate": 3.286807744259343e-06,
|
| 1409 |
+
"loss": 1.4193,
|
| 1410 |
+
"num_input_tokens_seen": 46538675,
|
| 1411 |
+
"step": 41500
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 9.342638451148131,
|
| 1415 |
+
"eval_loss": 1.5200846195220947,
|
| 1416 |
+
"eval_runtime": 6.7567,
|
| 1417 |
+
"eval_samples_per_second": 148.001,
|
| 1418 |
+
"eval_steps_per_second": 18.5,
|
| 1419 |
+
"num_input_tokens_seen": 46538675,
|
| 1420 |
+
"step": 41500
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 9.45520036019811,
|
| 1424 |
+
"grad_norm": 1.9557278156280518,
|
| 1425 |
+
"learning_rate": 2.7239981990094554e-06,
|
| 1426 |
+
"loss": 1.414,
|
| 1427 |
+
"num_input_tokens_seen": 47101815,
|
| 1428 |
+
"step": 42000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 9.45520036019811,
|
| 1432 |
+
"eval_loss": 1.5202205181121826,
|
| 1433 |
+
"eval_runtime": 6.7702,
|
| 1434 |
+
"eval_samples_per_second": 147.707,
|
| 1435 |
+
"eval_steps_per_second": 18.463,
|
| 1436 |
+
"num_input_tokens_seen": 47101815,
|
| 1437 |
+
"step": 42000
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 9.567762269248087,
|
| 1441 |
+
"grad_norm": 2.2344467639923096,
|
| 1442 |
+
"learning_rate": 2.161188653759568e-06,
|
| 1443 |
+
"loss": 1.4084,
|
| 1444 |
+
"num_input_tokens_seen": 47655583,
|
| 1445 |
+
"step": 42500
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 9.567762269248087,
|
| 1449 |
+
"eval_loss": 1.5190742015838623,
|
| 1450 |
+
"eval_runtime": 6.853,
|
| 1451 |
+
"eval_samples_per_second": 145.921,
|
| 1452 |
+
"eval_steps_per_second": 18.24,
|
| 1453 |
+
"num_input_tokens_seen": 47655583,
|
| 1454 |
+
"step": 42500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 9.680324178298063,
|
| 1458 |
+
"grad_norm": 2.065092086791992,
|
| 1459 |
+
"learning_rate": 1.5983791085096803e-06,
|
| 1460 |
+
"loss": 1.408,
|
| 1461 |
+
"num_input_tokens_seen": 48217371,
|
| 1462 |
+
"step": 43000
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 9.680324178298063,
|
| 1466 |
+
"eval_loss": 1.5206738710403442,
|
| 1467 |
+
"eval_runtime": 6.9763,
|
| 1468 |
+
"eval_samples_per_second": 143.343,
|
| 1469 |
+
"eval_steps_per_second": 17.918,
|
| 1470 |
+
"num_input_tokens_seen": 48217371,
|
| 1471 |
+
"step": 43000
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 9.792886087348041,
|
| 1475 |
+
"grad_norm": 2.3241419792175293,
|
| 1476 |
+
"learning_rate": 1.035569563259793e-06,
|
| 1477 |
+
"loss": 1.4207,
|
| 1478 |
+
"num_input_tokens_seen": 48781351,
|
| 1479 |
+
"step": 43500
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 9.792886087348041,
|
| 1483 |
+
"eval_loss": 1.5199604034423828,
|
| 1484 |
+
"eval_runtime": 6.8579,
|
| 1485 |
+
"eval_samples_per_second": 145.818,
|
| 1486 |
+
"eval_steps_per_second": 18.227,
|
| 1487 |
+
"num_input_tokens_seen": 48781351,
|
| 1488 |
+
"step": 43500
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 9.905447996398019,
|
| 1492 |
+
"grad_norm": 2.3469886779785156,
|
| 1493 |
+
"learning_rate": 4.727600180099055e-07,
|
| 1494 |
+
"loss": 1.4293,
|
| 1495 |
+
"num_input_tokens_seen": 49345155,
|
| 1496 |
+
"step": 44000
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 9.905447996398019,
|
| 1500 |
+
"eval_loss": 1.519752860069275,
|
| 1501 |
+
"eval_runtime": 6.7637,
|
| 1502 |
+
"eval_samples_per_second": 147.848,
|
| 1503 |
+
"eval_steps_per_second": 18.481,
|
| 1504 |
+
"num_input_tokens_seen": 49345155,
|
| 1505 |
+
"step": 44000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 10.0,
|
| 1509 |
+
"num_input_tokens_seen": 49815380,
|
| 1510 |
+
"step": 44420,
|
| 1511 |
+
"total_flos": 6.662920679892173e+16,
|
| 1512 |
+
"train_loss": 1.5719221366734615,
|
| 1513 |
+
"train_runtime": 7656.0711,
|
| 1514 |
+
"train_samples_per_second": 23.204,
|
| 1515 |
+
"train_steps_per_second": 5.802,
|
| 1516 |
+
"train_tokens_per_second": 6514.629
|
| 1517 |
+
}
|
| 1518 |
+
],
|
| 1519 |
+
"logging_steps": 500,
|
| 1520 |
+
"max_steps": 44420,
|
| 1521 |
+
"num_input_tokens_seen": 49815380,
|
| 1522 |
+
"num_train_epochs": 10,
|
| 1523 |
+
"save_steps": 500,
|
| 1524 |
+
"stateful_callbacks": {
|
| 1525 |
+
"TrainerControl": {
|
| 1526 |
+
"args": {
|
| 1527 |
+
"should_epoch_stop": false,
|
| 1528 |
+
"should_evaluate": false,
|
| 1529 |
+
"should_log": false,
|
| 1530 |
+
"should_save": true,
|
| 1531 |
+
"should_training_stop": true
|
| 1532 |
+
},
|
| 1533 |
+
"attributes": {}
|
| 1534 |
+
}
|
| 1535 |
+
},
|
| 1536 |
+
"total_flos": 6.662920679892173e+16,
|
| 1537 |
+
"train_batch_size": 4,
|
| 1538 |
+
"trial_name": null,
|
| 1539 |
+
"trial_params": null
|
| 1540 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5654cc319448f1580c94ba476edf95f08e308f0e6e5b151b7ed9581ad8ce3d3c
|
| 3 |
+
size 5368
|