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_2128/README.md +163 -0
- last_to_hit_frequency_2128/all_results.json +16 -0
- last_to_hit_frequency_2128/checkpoint-100000/config.json +31 -0
- last_to_hit_frequency_2128/checkpoint-100000/generation_config.json +6 -0
- last_to_hit_frequency_2128/checkpoint-100000/merges.txt +0 -0
- last_to_hit_frequency_2128/checkpoint-100000/model.safetensors +3 -0
- last_to_hit_frequency_2128/checkpoint-100000/optimizer.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-100000/rng_state.pth +3 -0
- last_to_hit_frequency_2128/checkpoint-100000/scaler.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-100000/scheduler.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-100000/special_tokens_map.json +5 -0
- last_to_hit_frequency_2128/checkpoint-100000/tokenizer.json +0 -0
- last_to_hit_frequency_2128/checkpoint-100000/tokenizer_config.json +20 -0
- last_to_hit_frequency_2128/checkpoint-100000/trainer_state.json +0 -0
- last_to_hit_frequency_2128/checkpoint-100000/training_args.bin +3 -0
- last_to_hit_frequency_2128/checkpoint-100000/vocab.json +0 -0
- last_to_hit_frequency_2128/checkpoint-30000/config.json +31 -0
- last_to_hit_frequency_2128/checkpoint-30000/generation_config.json +6 -0
- last_to_hit_frequency_2128/checkpoint-30000/merges.txt +0 -0
- last_to_hit_frequency_2128/checkpoint-30000/model.safetensors +3 -0
- last_to_hit_frequency_2128/checkpoint-30000/optimizer.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-30000/rng_state.pth +3 -0
- last_to_hit_frequency_2128/checkpoint-30000/scaler.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-30000/scheduler.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-30000/special_tokens_map.json +5 -0
- last_to_hit_frequency_2128/checkpoint-30000/tokenizer.json +0 -0
- last_to_hit_frequency_2128/checkpoint-30000/tokenizer_config.json +20 -0
- last_to_hit_frequency_2128/checkpoint-30000/trainer_state.json +0 -0
- last_to_hit_frequency_2128/checkpoint-30000/training_args.bin +3 -0
- last_to_hit_frequency_2128/checkpoint-30000/vocab.json +0 -0
- last_to_hit_frequency_2128/checkpoint-70000/config.json +31 -0
- last_to_hit_frequency_2128/checkpoint-70000/generation_config.json +6 -0
- last_to_hit_frequency_2128/checkpoint-70000/merges.txt +0 -0
- last_to_hit_frequency_2128/checkpoint-70000/model.safetensors +3 -0
- last_to_hit_frequency_2128/checkpoint-70000/optimizer.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-70000/rng_state.pth +3 -0
- last_to_hit_frequency_2128/checkpoint-70000/scaler.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-70000/scheduler.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-70000/special_tokens_map.json +5 -0
- last_to_hit_frequency_2128/checkpoint-70000/tokenizer.json +0 -0
- last_to_hit_frequency_2128/checkpoint-70000/tokenizer_config.json +20 -0
- last_to_hit_frequency_2128/checkpoint-70000/trainer_state.json +0 -0
- last_to_hit_frequency_2128/checkpoint-70000/training_args.bin +3 -0
- last_to_hit_frequency_2128/checkpoint-70000/vocab.json +0 -0
- last_to_hit_frequency_2128/checkpoint-80000/config.json +31 -0
- last_to_hit_frequency_2128/checkpoint-80000/generation_config.json +6 -0
- last_to_hit_frequency_2128/checkpoint-80000/merges.txt +0 -0
- last_to_hit_frequency_2128/checkpoint-80000/model.safetensors +3 -0
- last_to_hit_frequency_2128/checkpoint-80000/optimizer.pt +3 -0
- last_to_hit_frequency_2128/checkpoint-80000/rng_state.pth +3 -0
last_to_hit_frequency_2128/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_2128
|
| 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/x4fq7vdf)
|
| 16 |
+
# exceptions_exp2_last_to_hit_frequency_2128
|
| 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: 3.5762
|
| 21 |
+
- Accuracy: 0.3669
|
| 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: 2128
|
| 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 |
+
| 4.8229 | 0.2913 | 1000 | 0.2537 | 4.7555 |
|
| 57 |
+
| 4.3272 | 0.5826 | 2000 | 0.2996 | 4.2827 |
|
| 58 |
+
| 4.142 | 0.8739 | 3000 | 0.3152 | 4.0961 |
|
| 59 |
+
| 3.9925 | 1.1652 | 4000 | 0.3253 | 3.9905 |
|
| 60 |
+
| 3.9195 | 1.4565 | 5000 | 0.3317 | 3.9143 |
|
| 61 |
+
| 3.8842 | 1.7478 | 6000 | 0.3369 | 3.8600 |
|
| 62 |
+
| 3.7443 | 2.0390 | 7000 | 0.3412 | 3.8168 |
|
| 63 |
+
| 3.7503 | 2.3303 | 8000 | 0.3443 | 3.7862 |
|
| 64 |
+
| 3.7376 | 2.6216 | 9000 | 0.3468 | 3.7569 |
|
| 65 |
+
| 3.7244 | 2.9130 | 10000 | 0.3495 | 3.7275 |
|
| 66 |
+
| 3.6353 | 3.2042 | 11000 | 0.3514 | 3.7176 |
|
| 67 |
+
| 3.6428 | 3.4955 | 12000 | 0.3530 | 3.6977 |
|
| 68 |
+
| 3.646 | 3.7868 | 13000 | 0.3546 | 3.6797 |
|
| 69 |
+
| 3.5479 | 4.0781 | 14000 | 0.3563 | 3.6728 |
|
| 70 |
+
| 3.5782 | 4.3694 | 15000 | 0.3572 | 3.6620 |
|
| 71 |
+
| 3.5819 | 4.6607 | 16000 | 0.3583 | 3.6463 |
|
| 72 |
+
| 3.5792 | 4.9520 | 17000 | 0.3595 | 3.6341 |
|
| 73 |
+
| 3.512 | 5.2432 | 18000 | 0.3602 | 3.6385 |
|
| 74 |
+
| 3.5208 | 5.5345 | 19000 | 0.3610 | 3.6262 |
|
| 75 |
+
| 3.5273 | 5.8259 | 20000 | 0.3621 | 3.6148 |
|
| 76 |
+
| 3.4475 | 6.1171 | 21000 | 0.3623 | 3.6193 |
|
| 77 |
+
| 3.4806 | 6.4084 | 22000 | 0.3629 | 3.6127 |
|
| 78 |
+
| 3.4748 | 6.6997 | 23000 | 0.3639 | 3.6005 |
|
| 79 |
+
| 3.4908 | 6.9910 | 24000 | 0.3644 | 3.5943 |
|
| 80 |
+
| 3.4153 | 7.2823 | 25000 | 0.3642 | 3.6025 |
|
| 81 |
+
| 3.4552 | 7.5736 | 26000 | 0.3650 | 3.5934 |
|
| 82 |
+
| 3.4603 | 7.8649 | 27000 | 0.3657 | 3.5852 |
|
| 83 |
+
| 3.3745 | 8.1561 | 28000 | 0.3660 | 3.5920 |
|
| 84 |
+
| 3.406 | 8.4474 | 29000 | 0.3660 | 3.5856 |
|
| 85 |
+
| 3.429 | 8.7388 | 30000 | 0.3669 | 3.5762 |
|
| 86 |
+
| 3.317 | 9.0300 | 31000 | 0.3673 | 3.5818 |
|
| 87 |
+
| 3.3833 | 9.3213 | 32000 | 0.3672 | 3.5804 |
|
| 88 |
+
| 3.3999 | 9.6126 | 33000 | 0.3681 | 3.5710 |
|
| 89 |
+
| 3.4035 | 9.9039 | 34000 | 0.3680 | 3.5646 |
|
| 90 |
+
| 3.3507 | 10.1952 | 35000 | 0.3683 | 3.5742 |
|
| 91 |
+
| 3.3689 | 10.4865 | 36000 | 0.3684 | 3.5697 |
|
| 92 |
+
| 3.379 | 10.7778 | 37000 | 0.3692 | 3.5598 |
|
| 93 |
+
| 3.2905 | 11.0690 | 38000 | 0.3688 | 3.5722 |
|
| 94 |
+
| 3.3332 | 11.3603 | 39000 | 0.3691 | 3.5677 |
|
| 95 |
+
| 3.3602 | 11.6517 | 40000 | 0.3691 | 3.5606 |
|
| 96 |
+
| 3.3818 | 11.9430 | 41000 | 0.3703 | 3.5513 |
|
| 97 |
+
| 3.2924 | 12.2342 | 42000 | 0.3695 | 3.5651 |
|
| 98 |
+
| 3.3339 | 12.5255 | 43000 | 0.3701 | 3.5587 |
|
| 99 |
+
| 3.352 | 12.8168 | 44000 | 0.3709 | 3.5511 |
|
| 100 |
+
| 3.2587 | 13.1081 | 45000 | 0.3704 | 3.5614 |
|
| 101 |
+
| 3.3059 | 13.3994 | 46000 | 0.3704 | 3.5590 |
|
| 102 |
+
| 3.3337 | 13.6907 | 47000 | 0.3709 | 3.5515 |
|
| 103 |
+
| 3.3343 | 13.9820 | 48000 | 0.3714 | 3.5442 |
|
| 104 |
+
| 3.2804 | 14.2732 | 49000 | 0.3708 | 3.5584 |
|
| 105 |
+
| 3.293 | 14.5646 | 50000 | 0.3713 | 3.5531 |
|
| 106 |
+
| 3.3208 | 14.8559 | 51000 | 0.3716 | 3.5444 |
|
| 107 |
+
| 3.2449 | 15.1471 | 52000 | 0.3711 | 3.5573 |
|
| 108 |
+
| 3.2765 | 15.4384 | 53000 | 0.3717 | 3.5522 |
|
| 109 |
+
| 3.2996 | 15.7297 | 54000 | 0.3719 | 3.5449 |
|
| 110 |
+
| 3.195 | 16.0210 | 55000 | 0.3716 | 3.5555 |
|
| 111 |
+
| 3.2685 | 16.3123 | 56000 | 0.3718 | 3.5511 |
|
| 112 |
+
| 3.2776 | 16.6036 | 57000 | 0.3719 | 3.5490 |
|
| 113 |
+
| 3.3034 | 16.8949 | 58000 | 0.3726 | 3.5382 |
|
| 114 |
+
| 3.2318 | 17.1861 | 59000 | 0.3719 | 3.5549 |
|
| 115 |
+
| 3.2693 | 17.4775 | 60000 | 0.3726 | 3.5509 |
|
| 116 |
+
| 3.2845 | 17.7688 | 61000 | 0.3728 | 3.5412 |
|
| 117 |
+
| 3.2022 | 18.0600 | 62000 | 0.3724 | 3.5512 |
|
| 118 |
+
| 3.2434 | 18.3513 | 63000 | 0.3726 | 3.5515 |
|
| 119 |
+
| 3.2583 | 18.6426 | 64000 | 0.3728 | 3.5427 |
|
| 120 |
+
| 3.2754 | 18.9339 | 65000 | 0.3732 | 3.5360 |
|
| 121 |
+
| 3.1981 | 19.2252 | 66000 | 0.3726 | 3.5563 |
|
| 122 |
+
| 3.2406 | 19.5165 | 67000 | 0.3731 | 3.5442 |
|
| 123 |
+
| 3.2603 | 19.8078 | 68000 | 0.3735 | 3.5391 |
|
| 124 |
+
| 3.1759 | 20.0990 | 69000 | 0.3731 | 3.5492 |
|
| 125 |
+
| 3.2213 | 20.3904 | 70000 | 0.3732 | 3.5476 |
|
| 126 |
+
| 3.2306 | 20.6817 | 71000 | 0.3734 | 3.5419 |
|
| 127 |
+
| 3.259 | 20.9730 | 72000 | 0.3741 | 3.5322 |
|
| 128 |
+
| 3.2027 | 21.2642 | 73000 | 0.3728 | 3.5526 |
|
| 129 |
+
| 3.2301 | 21.5555 | 74000 | 0.3735 | 3.5442 |
|
| 130 |
+
| 3.2353 | 21.8468 | 75000 | 0.3741 | 3.5360 |
|
| 131 |
+
| 3.1793 | 22.1381 | 76000 | 0.3731 | 3.5540 |
|
| 132 |
+
| 3.2118 | 22.4294 | 77000 | 0.3734 | 3.5473 |
|
| 133 |
+
| 3.2325 | 22.7207 | 78000 | 0.3739 | 3.5397 |
|
| 134 |
+
| 3.1549 | 23.0119 | 79000 | 0.3738 | 3.5458 |
|
| 135 |
+
| 3.1875 | 23.3033 | 80000 | 0.3732 | 3.5524 |
|
| 136 |
+
| 3.1815 | 23.5946 | 81000 | 3.5515 | 0.3736 |
|
| 137 |
+
| 3.2017 | 23.8859 | 82000 | 3.5459 | 0.3737 |
|
| 138 |
+
| 3.1608 | 24.1774 | 83000 | 3.5538 | 0.3733 |
|
| 139 |
+
| 3.1977 | 24.4687 | 84000 | 3.5465 | 0.3740 |
|
| 140 |
+
| 3.2052 | 24.7600 | 85000 | 3.5396 | 0.3745 |
|
| 141 |
+
| 3.122 | 25.0513 | 86000 | 3.5503 | 0.3738 |
|
| 142 |
+
| 3.1656 | 25.3426 | 87000 | 3.5481 | 0.3739 |
|
| 143 |
+
| 3.1894 | 25.6339 | 88000 | 3.5432 | 0.3742 |
|
| 144 |
+
| 3.2088 | 25.9252 | 89000 | 3.5323 | 0.3746 |
|
| 145 |
+
| 3.1508 | 26.2164 | 90000 | 3.5524 | 0.3737 |
|
| 146 |
+
| 3.1713 | 26.5077 | 91000 | 3.5424 | 0.3743 |
|
| 147 |
+
| 3.1843 | 26.7991 | 92000 | 3.5353 | 0.3747 |
|
| 148 |
+
| 3.1242 | 27.0903 | 93000 | 3.5492 | 0.3741 |
|
| 149 |
+
| 3.1564 | 27.3816 | 94000 | 3.5455 | 0.3745 |
|
| 150 |
+
| 3.1625 | 27.6729 | 95000 | 3.5386 | 0.3750 |
|
| 151 |
+
| 3.1875 | 27.9642 | 96000 | 3.5359 | 0.3748 |
|
| 152 |
+
| 3.1266 | 28.2555 | 97000 | 3.5481 | 0.3743 |
|
| 153 |
+
| 3.1698 | 28.5468 | 98000 | 3.5439 | 0.3747 |
|
| 154 |
+
| 3.1624 | 28.8381 | 99000 | 3.5402 | 0.3750 |
|
| 155 |
+
| 3.1128 | 29.1293 | 100000 | 3.5496 | 0.3746 |
|
| 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_2128/all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.129340480074575,
|
| 3 |
+
"eval_accuracy": 0.36692130297762826,
|
| 4 |
+
"eval_loss": 3.57623028755188,
|
| 5 |
+
"eval_runtime": 179.9348,
|
| 6 |
+
"eval_samples": 16645,
|
| 7 |
+
"eval_samples_per_second": 92.506,
|
| 8 |
+
"eval_steps_per_second": 5.785,
|
| 9 |
+
"perplexity": 35.73856248821829,
|
| 10 |
+
"total_flos": 2.090213187452928e+18,
|
| 11 |
+
"train_loss": 0.6336719000244141,
|
| 12 |
+
"train_runtime": 39937.4764,
|
| 13 |
+
"train_samples": 274621,
|
| 14 |
+
"train_samples_per_second": 343.814,
|
| 15 |
+
"train_steps_per_second": 4.298
|
| 16 |
+
}
|
last_to_hit_frequency_2128/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_2128/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_2128/checkpoint-100000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/checkpoint-100000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98d40503cfbfc209ff2de0fdeaa5f3102c0fb1b47bdf27d7550627d7648d2a3b
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_2128/checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d00660b67d34503e416e3ada553187952621aadc6db9a65b3fd03452816acdf1
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_2128/checkpoint-100000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:780550a3665842c7a90eae3af13b0c04d56d56279d7c54662892d28daaa7658b
|
| 3 |
+
size 14773
|
last_to_hit_frequency_2128/checkpoint-100000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7382817d931ddd0ed8745522c39cc6a5bafd84459dc40ddca80fcabeebd1ef25
|
| 3 |
+
size 1383
|
last_to_hit_frequency_2128/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_2128/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_2128/checkpoint-100000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/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_2128/checkpoint-100000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/checkpoint-100000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df956b28e00b5bbff9fb2555e07c30b355c743b9aa41913c5261998304bccc7a
|
| 3 |
+
size 5969
|
last_to_hit_frequency_2128/checkpoint-100000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/checkpoint-30000/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_2128/checkpoint-30000/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_2128/checkpoint-30000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/checkpoint-30000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c313e2c9e75033bf0d9701f9d08e694ef7aaf28fad61ded256c8d99c1e19ab67
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_2128/checkpoint-30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5541ffd4c6e7cae48a6a2e377f7bd65ac8a02e4d34ade4650ce98618d86f2890
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_2128/checkpoint-30000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9039a9501615606c9d744debde4b436ff76b7d3194a51bef9f2a3ded01b64a03
|
| 3 |
+
size 14773
|
last_to_hit_frequency_2128/checkpoint-30000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5ebe069a116322b8ff2d53036ece84a2a5d28816592c544a420db9345639af1
|
| 3 |
+
size 1383
|
last_to_hit_frequency_2128/checkpoint-30000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e65c043bc77285c51ceec07c59bfd7d38f73fe546cf4a40dafd475c2cd569e88
|
| 3 |
+
size 1465
|
last_to_hit_frequency_2128/checkpoint-30000/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_2128/checkpoint-30000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/checkpoint-30000/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_2128/checkpoint-30000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23f30a7e825feda2e3fe994bd60ff16e6f98533b8fcff222d48265fd6e833801
|
| 3 |
+
size 5969
|
last_to_hit_frequency_2128/checkpoint-30000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/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_2128/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_2128/checkpoint-70000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/checkpoint-70000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:371cfd0b93d320ea0384152afc3585426c3d05cb7eef8fa2c366b8e562c25a3f
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_2128/checkpoint-70000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc6286a47159bae37dad65ccb179ddde869245462d2ca352ef58c87de551e605
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_2128/checkpoint-70000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6850be39f6174c3c89c128ee4f644088503cd4c1bc4519d6484f98f87c6b0cdb
|
| 3 |
+
size 14773
|
last_to_hit_frequency_2128/checkpoint-70000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:985bb429a14b8100862d6aa4255d5027afc7e83340bbb046eedd3f8be1d23b95
|
| 3 |
+
size 1383
|
last_to_hit_frequency_2128/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_2128/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_2128/checkpoint-70000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/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_2128/checkpoint-70000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/checkpoint-70000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23f30a7e825feda2e3fe994bd60ff16e6f98533b8fcff222d48265fd6e833801
|
| 3 |
+
size 5969
|
last_to_hit_frequency_2128/checkpoint-70000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/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_2128/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_2128/checkpoint-80000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_2128/checkpoint-80000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d7ad0df27ff7eaa290ff9f7116932199905e9315ae18453b8e710e26fc51639
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_2128/checkpoint-80000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:402d2847c288bdcbe92882ff18641eb1b7d8b12b307b77234d79660a5583b992
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_2128/checkpoint-80000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c45ceae437f1a129e4a796c8832a7491b02b60a6ed73498a9a13278aa129e6a
|
| 3 |
+
size 14773
|