Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- last_to_hit_frequency_1001/README.md +163 -0
- last_to_hit_frequency_1001/all_results.json +16 -0
- last_to_hit_frequency_1001/checkpoint-100000/config.json +31 -0
- last_to_hit_frequency_1001/checkpoint-100000/generation_config.json +6 -0
- last_to_hit_frequency_1001/checkpoint-100000/merges.txt +0 -0
- last_to_hit_frequency_1001/checkpoint-100000/model.safetensors +3 -0
- last_to_hit_frequency_1001/checkpoint-100000/optimizer.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-100000/rng_state.pth +3 -0
- last_to_hit_frequency_1001/checkpoint-100000/scaler.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-100000/scheduler.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-100000/special_tokens_map.json +5 -0
- last_to_hit_frequency_1001/checkpoint-100000/tokenizer.json +0 -0
- last_to_hit_frequency_1001/checkpoint-100000/tokenizer_config.json +20 -0
- last_to_hit_frequency_1001/checkpoint-100000/trainer_state.json +0 -0
- last_to_hit_frequency_1001/checkpoint-100000/training_args.bin +3 -0
- last_to_hit_frequency_1001/checkpoint-100000/vocab.json +0 -0
- last_to_hit_frequency_1001/checkpoint-40000/config.json +31 -0
- last_to_hit_frequency_1001/checkpoint-40000/generation_config.json +6 -0
- last_to_hit_frequency_1001/checkpoint-40000/merges.txt +0 -0
- last_to_hit_frequency_1001/checkpoint-40000/model.safetensors +3 -0
- last_to_hit_frequency_1001/checkpoint-40000/optimizer.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-40000/rng_state.pth +3 -0
- last_to_hit_frequency_1001/checkpoint-40000/scaler.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-40000/scheduler.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-40000/special_tokens_map.json +5 -0
- last_to_hit_frequency_1001/checkpoint-40000/tokenizer.json +0 -0
- last_to_hit_frequency_1001/checkpoint-40000/tokenizer_config.json +20 -0
- last_to_hit_frequency_1001/checkpoint-40000/trainer_state.json +0 -0
- last_to_hit_frequency_1001/checkpoint-40000/training_args.bin +3 -0
- last_to_hit_frequency_1001/checkpoint-40000/vocab.json +0 -0
- last_to_hit_frequency_1001/checkpoint-70000/config.json +31 -0
- last_to_hit_frequency_1001/checkpoint-70000/generation_config.json +6 -0
- last_to_hit_frequency_1001/checkpoint-70000/merges.txt +0 -0
- last_to_hit_frequency_1001/checkpoint-70000/model.safetensors +3 -0
- last_to_hit_frequency_1001/checkpoint-70000/optimizer.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-70000/rng_state.pth +3 -0
- last_to_hit_frequency_1001/checkpoint-70000/scaler.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-70000/scheduler.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-70000/special_tokens_map.json +5 -0
- last_to_hit_frequency_1001/checkpoint-70000/tokenizer.json +0 -0
- last_to_hit_frequency_1001/checkpoint-70000/tokenizer_config.json +20 -0
- last_to_hit_frequency_1001/checkpoint-70000/trainer_state.json +0 -0
- last_to_hit_frequency_1001/checkpoint-70000/training_args.bin +3 -0
- last_to_hit_frequency_1001/checkpoint-70000/vocab.json +0 -0
- last_to_hit_frequency_1001/checkpoint-80000/config.json +31 -0
- last_to_hit_frequency_1001/checkpoint-80000/generation_config.json +6 -0
- last_to_hit_frequency_1001/checkpoint-80000/merges.txt +0 -0
- last_to_hit_frequency_1001/checkpoint-80000/model.safetensors +3 -0
- last_to_hit_frequency_1001/checkpoint-80000/optimizer.pt +3 -0
- last_to_hit_frequency_1001/checkpoint-80000/rng_state.pth +3 -0
last_to_hit_frequency_1001/README.md
ADDED
|
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: exceptions_exp2_last_to_hit_frequency_1001
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/craaaa/exceptions_exp2/runs/dezzskfr)
|
| 16 |
+
# exceptions_exp2_last_to_hit_frequency_1001
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 3.5548
|
| 21 |
+
- Accuracy: 0.3698
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0006
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 16
|
| 43 |
+
- seed: 1001
|
| 44 |
+
- gradient_accumulation_steps: 5
|
| 45 |
+
- total_train_batch_size: 80
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 100
|
| 49 |
+
- num_epochs: 50.0
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 55 |
+
|:-------------:|:-------:|:------:|:--------:|:---------------:|
|
| 56 |
+
| 4.8292 | 0.2913 | 1000 | 0.2526 | 4.7625 |
|
| 57 |
+
| 4.343 | 0.5826 | 2000 | 0.3001 | 4.2776 |
|
| 58 |
+
| 4.1519 | 0.8739 | 3000 | 0.3163 | 4.0912 |
|
| 59 |
+
| 3.9832 | 1.1652 | 4000 | 0.3257 | 3.9874 |
|
| 60 |
+
| 3.9231 | 1.4565 | 5000 | 0.3321 | 3.9133 |
|
| 61 |
+
| 3.8709 | 1.7478 | 6000 | 0.3377 | 3.8519 |
|
| 62 |
+
| 3.753 | 2.0390 | 7000 | 0.3421 | 3.8120 |
|
| 63 |
+
| 3.7469 | 2.3303 | 8000 | 0.3452 | 3.7808 |
|
| 64 |
+
| 3.7452 | 2.6216 | 9000 | 0.3478 | 3.7518 |
|
| 65 |
+
| 3.7285 | 2.9130 | 10000 | 0.3500 | 3.7232 |
|
| 66 |
+
| 3.6361 | 3.2042 | 11000 | 0.3520 | 3.7125 |
|
| 67 |
+
| 3.6428 | 3.4955 | 12000 | 0.3536 | 3.6946 |
|
| 68 |
+
| 3.6387 | 3.7868 | 13000 | 0.3550 | 3.6745 |
|
| 69 |
+
| 3.5437 | 4.0781 | 14000 | 0.3564 | 3.6677 |
|
| 70 |
+
| 3.5684 | 4.3694 | 15000 | 0.3577 | 3.6582 |
|
| 71 |
+
| 3.5745 | 4.6607 | 16000 | 0.3586 | 3.6439 |
|
| 72 |
+
| 3.5827 | 4.9520 | 17000 | 0.3600 | 3.6305 |
|
| 73 |
+
| 3.4979 | 5.2432 | 18000 | 0.3600 | 3.6367 |
|
| 74 |
+
| 3.5219 | 5.5345 | 19000 | 0.3613 | 3.6236 |
|
| 75 |
+
| 3.5406 | 5.8259 | 20000 | 0.3626 | 3.6113 |
|
| 76 |
+
| 3.4266 | 6.1171 | 21000 | 0.3626 | 3.6177 |
|
| 77 |
+
| 3.4681 | 6.4084 | 22000 | 0.3632 | 3.6071 |
|
| 78 |
+
| 3.4797 | 6.6997 | 23000 | 0.3642 | 3.6002 |
|
| 79 |
+
| 3.4969 | 6.9910 | 24000 | 0.3649 | 3.5869 |
|
| 80 |
+
| 3.4076 | 7.2823 | 25000 | 0.3645 | 3.5990 |
|
| 81 |
+
| 3.4535 | 7.5736 | 26000 | 0.3653 | 3.5888 |
|
| 82 |
+
| 3.4522 | 7.8649 | 27000 | 0.3663 | 3.5791 |
|
| 83 |
+
| 3.3902 | 8.1561 | 28000 | 0.3659 | 3.5893 |
|
| 84 |
+
| 3.4024 | 8.4474 | 29000 | 0.3666 | 3.5801 |
|
| 85 |
+
| 3.4241 | 8.7388 | 30000 | 0.3672 | 3.5716 |
|
| 86 |
+
| 3.3306 | 9.0300 | 31000 | 0.3669 | 3.5815 |
|
| 87 |
+
| 3.3808 | 9.3213 | 32000 | 0.3676 | 3.5776 |
|
| 88 |
+
| 3.3982 | 9.6126 | 33000 | 0.3681 | 3.5693 |
|
| 89 |
+
| 3.4131 | 9.9039 | 34000 | 0.3685 | 3.5598 |
|
| 90 |
+
| 3.3494 | 10.1952 | 35000 | 0.3685 | 3.5712 |
|
| 91 |
+
| 3.3611 | 10.4865 | 36000 | 0.3689 | 3.5644 |
|
| 92 |
+
| 3.3847 | 10.7778 | 37000 | 0.3694 | 3.5581 |
|
| 93 |
+
| 3.2988 | 11.0690 | 38000 | 0.3692 | 3.5659 |
|
| 94 |
+
| 3.3317 | 11.3603 | 39000 | 0.3696 | 3.5602 |
|
| 95 |
+
| 3.3584 | 11.6517 | 40000 | 0.3698 | 3.5548 |
|
| 96 |
+
| 3.3695 | 11.9430 | 41000 | 0.3705 | 3.5487 |
|
| 97 |
+
| 3.3134 | 12.2342 | 42000 | 0.3702 | 3.5608 |
|
| 98 |
+
| 3.3341 | 12.5255 | 43000 | 0.3702 | 3.5564 |
|
| 99 |
+
| 3.34 | 12.8168 | 44000 | 0.3711 | 3.5469 |
|
| 100 |
+
| 3.2644 | 13.1081 | 45000 | 0.3703 | 3.5637 |
|
| 101 |
+
| 3.3033 | 13.3994 | 46000 | 0.3706 | 3.5586 |
|
| 102 |
+
| 3.321 | 13.6907 | 47000 | 0.3713 | 3.5462 |
|
| 103 |
+
| 3.3478 | 13.9820 | 48000 | 0.3718 | 3.5400 |
|
| 104 |
+
| 3.2776 | 14.2732 | 49000 | 0.3713 | 3.5559 |
|
| 105 |
+
| 3.3024 | 14.5646 | 50000 | 0.3718 | 3.5450 |
|
| 106 |
+
| 3.3119 | 14.8559 | 51000 | 0.3718 | 3.5443 |
|
| 107 |
+
| 3.242 | 15.1471 | 52000 | 0.3716 | 3.5561 |
|
| 108 |
+
| 3.2813 | 15.4384 | 53000 | 0.3720 | 3.5498 |
|
| 109 |
+
| 3.3013 | 15.7297 | 54000 | 0.3724 | 3.5415 |
|
| 110 |
+
| 3.2009 | 16.0210 | 55000 | 0.3720 | 3.5485 |
|
| 111 |
+
| 3.2631 | 16.3123 | 56000 | 0.3721 | 3.5508 |
|
| 112 |
+
| 3.2698 | 16.6036 | 57000 | 0.3724 | 3.5433 |
|
| 113 |
+
| 3.2943 | 16.8949 | 58000 | 0.3730 | 3.5355 |
|
| 114 |
+
| 3.2083 | 17.1861 | 59000 | 0.3722 | 3.5509 |
|
| 115 |
+
| 3.2538 | 17.4775 | 60000 | 0.3729 | 3.5447 |
|
| 116 |
+
| 3.2726 | 17.7688 | 61000 | 0.3731 | 3.5373 |
|
| 117 |
+
| 3.1734 | 18.0600 | 62000 | 0.3726 | 3.5511 |
|
| 118 |
+
| 3.2302 | 18.3513 | 63000 | 0.3729 | 3.5443 |
|
| 119 |
+
| 3.2384 | 18.6426 | 64000 | 0.3732 | 3.5390 |
|
| 120 |
+
| 3.2662 | 18.9339 | 65000 | 0.3737 | 3.5310 |
|
| 121 |
+
| 3.1971 | 19.2252 | 66000 | 0.3729 | 3.5461 |
|
| 122 |
+
| 3.233 | 19.5165 | 67000 | 0.3734 | 3.5416 |
|
| 123 |
+
| 3.2554 | 19.8078 | 68000 | 0.3740 | 3.5345 |
|
| 124 |
+
| 3.1718 | 20.0990 | 69000 | 0.3731 | 3.5510 |
|
| 125 |
+
| 3.2171 | 20.3904 | 70000 | 0.3733 | 3.5472 |
|
| 126 |
+
| 3.2353 | 20.6817 | 71000 | 0.3739 | 3.5372 |
|
| 127 |
+
| 3.2543 | 20.9730 | 72000 | 0.3746 | 3.5272 |
|
| 128 |
+
| 3.1935 | 21.2642 | 73000 | 0.3736 | 3.5449 |
|
| 129 |
+
| 3.2197 | 21.5555 | 74000 | 0.3737 | 3.5378 |
|
| 130 |
+
| 3.2384 | 21.8468 | 75000 | 0.3743 | 3.5341 |
|
| 131 |
+
| 3.1627 | 22.1381 | 76000 | 0.3734 | 3.5498 |
|
| 132 |
+
| 3.1852 | 22.4294 | 77000 | 0.3738 | 3.5413 |
|
| 133 |
+
| 3.2191 | 22.7207 | 78000 | 0.3743 | 3.5396 |
|
| 134 |
+
| 3.1517 | 23.0119 | 79000 | 0.3740 | 3.5452 |
|
| 135 |
+
| 3.1792 | 23.3033 | 80000 | 0.3740 | 3.5448 |
|
| 136 |
+
| 3.1887 | 23.5946 | 81000 | 3.5474 | 0.3738 |
|
| 137 |
+
| 3.2022 | 23.8859 | 82000 | 3.5414 | 0.3743 |
|
| 138 |
+
| 3.166 | 24.1774 | 83000 | 3.5519 | 0.3738 |
|
| 139 |
+
| 3.1886 | 24.4687 | 84000 | 3.5405 | 0.3742 |
|
| 140 |
+
| 3.1954 | 24.7600 | 85000 | 3.5343 | 0.3745 |
|
| 141 |
+
| 3.1207 | 25.0513 | 86000 | 3.5508 | 0.3741 |
|
| 142 |
+
| 3.1625 | 25.3426 | 87000 | 3.5465 | 0.3743 |
|
| 143 |
+
| 3.1878 | 25.6339 | 88000 | 3.5371 | 0.3749 |
|
| 144 |
+
| 3.2014 | 25.9252 | 89000 | 3.5307 | 0.3751 |
|
| 145 |
+
| 3.1291 | 26.2164 | 90000 | 3.5488 | 0.3742 |
|
| 146 |
+
| 3.1791 | 26.5077 | 91000 | 3.5393 | 0.3748 |
|
| 147 |
+
| 3.1836 | 26.7991 | 92000 | 3.5345 | 0.3753 |
|
| 148 |
+
| 3.105 | 27.0903 | 93000 | 3.5476 | 0.3745 |
|
| 149 |
+
| 3.1532 | 27.3816 | 94000 | 3.5433 | 0.3749 |
|
| 150 |
+
| 3.172 | 27.6729 | 95000 | 3.5368 | 0.3751 |
|
| 151 |
+
| 3.1905 | 27.9642 | 96000 | 3.5282 | 0.3755 |
|
| 152 |
+
| 3.1375 | 28.2555 | 97000 | 3.5473 | 0.3748 |
|
| 153 |
+
| 3.1399 | 28.5468 | 98000 | 3.5383 | 0.3753 |
|
| 154 |
+
| 3.1694 | 28.8381 | 99000 | 3.5353 | 0.3755 |
|
| 155 |
+
| 3.1062 | 29.1293 | 100000 | 3.5500 | 0.3747 |
|
| 156 |
+
|
| 157 |
+
|
| 158 |
+
### Framework versions
|
| 159 |
+
|
| 160 |
+
- Transformers 4.55.2
|
| 161 |
+
- Pytorch 2.8.0+cu128
|
| 162 |
+
- Datasets 4.0.0
|
| 163 |
+
- Tokenizers 0.21.4
|
last_to_hit_frequency_1001/all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.129340480074575,
|
| 3 |
+
"eval_accuracy": 0.369777305408969,
|
| 4 |
+
"eval_loss": 3.554752826690674,
|
| 5 |
+
"eval_runtime": 179.1914,
|
| 6 |
+
"eval_samples": 16645,
|
| 7 |
+
"eval_samples_per_second": 92.889,
|
| 8 |
+
"eval_steps_per_second": 5.809,
|
| 9 |
+
"perplexity": 34.97917298114222,
|
| 10 |
+
"total_flos": 2.090213187452928e+18,
|
| 11 |
+
"train_loss": 0.6329426931762695,
|
| 12 |
+
"train_runtime": 39803.2166,
|
| 13 |
+
"train_samples": 274621,
|
| 14 |
+
"train_samples_per_second": 344.973,
|
| 15 |
+
"train_steps_per_second": 4.312
|
| 16 |
+
}
|
last_to_hit_frequency_1001/checkpoint-100000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
last_to_hit_frequency_1001/checkpoint-100000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
last_to_hit_frequency_1001/checkpoint-100000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-100000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec433417dc058ddec81e002d2715ff646a8bf064eaf8f2f8319c0428008d1c29
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_1001/checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10bb23a89e4ca12d8febca14270e0f9a633f91b1025f3940b7a6cdff1ab695d4
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_1001/checkpoint-100000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f23a463e355171a1641828d34d37597cad0549b5c95891fda1afc22ed167eb7
|
| 3 |
+
size 14709
|
last_to_hit_frequency_1001/checkpoint-100000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f4c69075706bf43707855abd048171b9579d059627d19c97c75fd06b923ccd6
|
| 3 |
+
size 1383
|
last_to_hit_frequency_1001/checkpoint-100000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d8cc14034013929dc2b78a5ca034dfe1cc8236010cba220bccccf63051be758
|
| 3 |
+
size 1465
|
last_to_hit_frequency_1001/checkpoint-100000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
last_to_hit_frequency_1001/checkpoint-100000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-100000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
last_to_hit_frequency_1001/checkpoint-100000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-100000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7128f012f418abf8fe3ca62316636b9f7c4869b97a49c9aeeba403875ba98a39
|
| 3 |
+
size 5969
|
last_to_hit_frequency_1001/checkpoint-100000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-40000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
last_to_hit_frequency_1001/checkpoint-40000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
last_to_hit_frequency_1001/checkpoint-40000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-40000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f2d92bde0ea0375760bd98fb2f34aad2c4d63f0f9e9b46cfc1cc37a58addca0
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_1001/checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7002301102fa9d597e4878e7d18e019fafc27a372ef710959d5541d1033712ab
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_1001/checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1280b9d300f2115409d442209b239b63c615268371dacf2be51503cc34930aa2
|
| 3 |
+
size 14709
|
last_to_hit_frequency_1001/checkpoint-40000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c5ed01cc58ad4fa7346b7fd7260c6249e25553410531c7d5ed5d80b99a064c0
|
| 3 |
+
size 1383
|
last_to_hit_frequency_1001/checkpoint-40000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53496dff2d998b2535c0e9c9088675c7e2e3817cd3fa3a46a14d4d2047c4e946
|
| 3 |
+
size 1465
|
last_to_hit_frequency_1001/checkpoint-40000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
last_to_hit_frequency_1001/checkpoint-40000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-40000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
last_to_hit_frequency_1001/checkpoint-40000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9cc3f5be655533fabab0cf81413a73f3e26be3d98bb71f5cc1db20401b2e7a6
|
| 3 |
+
size 5969
|
last_to_hit_frequency_1001/checkpoint-40000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-70000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
last_to_hit_frequency_1001/checkpoint-70000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
last_to_hit_frequency_1001/checkpoint-70000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-70000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af4f69a6a51b04e00ef4154e95dd0b063a9427d91969981739130ec0100a8e89
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_1001/checkpoint-70000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2295d315fd720cdfafa49a0e78fa16683c101e8310db438461b60032ac74ca6
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_1001/checkpoint-70000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be029b23f983c33d4934150cb32611ad1e0767b5b029f5ea8e51e5c6656f84a6
|
| 3 |
+
size 14709
|
last_to_hit_frequency_1001/checkpoint-70000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ae00c1261ee9c0e70fe05f92640ff0de1911086936667b3e3f0c7240089d49d
|
| 3 |
+
size 1383
|
last_to_hit_frequency_1001/checkpoint-70000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:811c701a16e66283a8bed512455e47f01b80f70540fba9f846d9f0b4e30cd582
|
| 3 |
+
size 1465
|
last_to_hit_frequency_1001/checkpoint-70000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
last_to_hit_frequency_1001/checkpoint-70000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-70000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
last_to_hit_frequency_1001/checkpoint-70000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-70000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9cc3f5be655533fabab0cf81413a73f3e26be3d98bb71f5cc1db20401b2e7a6
|
| 3 |
+
size 5969
|
last_to_hit_frequency_1001/checkpoint-70000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-80000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
last_to_hit_frequency_1001/checkpoint-80000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
last_to_hit_frequency_1001/checkpoint-80000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_1001/checkpoint-80000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:734cc849a161f58d843d1066176de933240627bb3b4d12076b9bc9653e2e92b8
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_1001/checkpoint-80000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:188f85a496739e6ac07461d4b1084e7c8888d1717bf48c8bb253c6b14725447e
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_1001/checkpoint-80000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:647672a463a71dfa06222dd8768e3050da74988223abefc76f9df5a58b72714b
|
| 3 |
+
size 14709
|