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_3591/README.md +163 -0
- last_to_hit_frequency_3591/all_results.json +16 -0
- last_to_hit_frequency_3591/checkpoint-100000/config.json +31 -0
- last_to_hit_frequency_3591/checkpoint-100000/generation_config.json +6 -0
- last_to_hit_frequency_3591/checkpoint-100000/merges.txt +0 -0
- last_to_hit_frequency_3591/checkpoint-100000/model.safetensors +3 -0
- last_to_hit_frequency_3591/checkpoint-100000/optimizer.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-100000/rng_state.pth +3 -0
- last_to_hit_frequency_3591/checkpoint-100000/scaler.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-100000/scheduler.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-100000/special_tokens_map.json +5 -0
- last_to_hit_frequency_3591/checkpoint-100000/tokenizer.json +0 -0
- last_to_hit_frequency_3591/checkpoint-100000/tokenizer_config.json +20 -0
- last_to_hit_frequency_3591/checkpoint-100000/trainer_state.json +0 -0
- last_to_hit_frequency_3591/checkpoint-100000/training_args.bin +3 -0
- last_to_hit_frequency_3591/checkpoint-100000/vocab.json +0 -0
- last_to_hit_frequency_3591/checkpoint-30000/config.json +31 -0
- last_to_hit_frequency_3591/checkpoint-30000/generation_config.json +6 -0
- last_to_hit_frequency_3591/checkpoint-30000/merges.txt +0 -0
- last_to_hit_frequency_3591/checkpoint-30000/model.safetensors +3 -0
- last_to_hit_frequency_3591/checkpoint-30000/optimizer.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-30000/rng_state.pth +3 -0
- last_to_hit_frequency_3591/checkpoint-30000/scaler.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-30000/scheduler.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-30000/special_tokens_map.json +5 -0
- last_to_hit_frequency_3591/checkpoint-30000/tokenizer.json +0 -0
- last_to_hit_frequency_3591/checkpoint-30000/tokenizer_config.json +20 -0
- last_to_hit_frequency_3591/checkpoint-30000/trainer_state.json +0 -0
- last_to_hit_frequency_3591/checkpoint-30000/training_args.bin +3 -0
- last_to_hit_frequency_3591/checkpoint-30000/vocab.json +0 -0
- last_to_hit_frequency_3591/checkpoint-70000/config.json +31 -0
- last_to_hit_frequency_3591/checkpoint-70000/generation_config.json +6 -0
- last_to_hit_frequency_3591/checkpoint-70000/merges.txt +0 -0
- last_to_hit_frequency_3591/checkpoint-70000/model.safetensors +3 -0
- last_to_hit_frequency_3591/checkpoint-70000/optimizer.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-70000/rng_state.pth +3 -0
- last_to_hit_frequency_3591/checkpoint-70000/scaler.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-70000/scheduler.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-70000/special_tokens_map.json +5 -0
- last_to_hit_frequency_3591/checkpoint-70000/tokenizer.json +0 -0
- last_to_hit_frequency_3591/checkpoint-70000/tokenizer_config.json +20 -0
- last_to_hit_frequency_3591/checkpoint-70000/trainer_state.json +0 -0
- last_to_hit_frequency_3591/checkpoint-70000/training_args.bin +3 -0
- last_to_hit_frequency_3591/checkpoint-70000/vocab.json +0 -0
- last_to_hit_frequency_3591/checkpoint-80000/config.json +31 -0
- last_to_hit_frequency_3591/checkpoint-80000/generation_config.json +6 -0
- last_to_hit_frequency_3591/checkpoint-80000/merges.txt +0 -0
- last_to_hit_frequency_3591/checkpoint-80000/model.safetensors +3 -0
- last_to_hit_frequency_3591/checkpoint-80000/optimizer.pt +3 -0
- last_to_hit_frequency_3591/checkpoint-80000/rng_state.pth +3 -0
last_to_hit_frequency_3591/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_3591
|
| 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/if6hk380)
|
| 16 |
+
# exceptions_exp2_last_to_hit_frequency_3591
|
| 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: 3.5747
|
| 21 |
+
- Accuracy: 0.3673
|
| 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: 3591
|
| 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 |
+
| 4.8516 | 0.2913 | 1000 | 0.2507 | 4.7821 |
|
| 57 |
+
| 4.342 | 0.5826 | 2000 | 0.2995 | 4.2843 |
|
| 58 |
+
| 4.1349 | 0.8739 | 3000 | 0.3162 | 4.0937 |
|
| 59 |
+
| 3.9879 | 1.1652 | 4000 | 0.3260 | 3.9845 |
|
| 60 |
+
| 3.9229 | 1.4565 | 5000 | 0.3325 | 3.9095 |
|
| 61 |
+
| 3.8805 | 1.7478 | 6000 | 0.3377 | 3.8516 |
|
| 62 |
+
| 3.7313 | 2.0390 | 7000 | 0.3422 | 3.8093 |
|
| 63 |
+
| 3.7565 | 2.3303 | 8000 | 0.3449 | 3.7804 |
|
| 64 |
+
| 3.7287 | 2.6216 | 9000 | 0.3479 | 3.7482 |
|
| 65 |
+
| 3.7117 | 2.9130 | 10000 | 0.3501 | 3.7232 |
|
| 66 |
+
| 3.6328 | 3.2042 | 11000 | 0.3520 | 3.7118 |
|
| 67 |
+
| 3.6393 | 3.4955 | 12000 | 0.3538 | 3.6953 |
|
| 68 |
+
| 3.6428 | 3.7868 | 13000 | 0.3553 | 3.6764 |
|
| 69 |
+
| 3.5319 | 4.0781 | 14000 | 0.3565 | 3.6683 |
|
| 70 |
+
| 3.5417 | 4.3694 | 15000 | 0.3574 | 3.6595 |
|
| 71 |
+
| 3.5679 | 4.6607 | 16000 | 0.3588 | 3.6458 |
|
| 72 |
+
| 3.5802 | 4.9520 | 17000 | 0.3600 | 3.6297 |
|
| 73 |
+
| 3.4929 | 5.2432 | 18000 | 0.3606 | 3.6342 |
|
| 74 |
+
| 3.5125 | 5.5345 | 19000 | 0.3612 | 3.6249 |
|
| 75 |
+
| 3.5162 | 5.8259 | 20000 | 0.3622 | 3.6125 |
|
| 76 |
+
| 3.4304 | 6.1171 | 21000 | 0.3630 | 3.6169 |
|
| 77 |
+
| 3.4737 | 6.4084 | 22000 | 0.3632 | 3.6076 |
|
| 78 |
+
| 3.4775 | 6.6997 | 23000 | 0.3641 | 3.5995 |
|
| 79 |
+
| 3.49 | 6.9910 | 24000 | 0.3652 | 3.5868 |
|
| 80 |
+
| 3.4352 | 7.2823 | 25000 | 0.3647 | 3.5988 |
|
| 81 |
+
| 3.4508 | 7.5736 | 26000 | 0.3654 | 3.5895 |
|
| 82 |
+
| 3.4523 | 7.8649 | 27000 | 0.3661 | 3.5810 |
|
| 83 |
+
| 3.3762 | 8.1561 | 28000 | 0.3663 | 3.5881 |
|
| 84 |
+
| 3.4033 | 8.4474 | 29000 | 0.3669 | 3.5829 |
|
| 85 |
+
| 3.4225 | 8.7388 | 30000 | 0.3673 | 3.5747 |
|
| 86 |
+
| 3.3258 | 9.0300 | 31000 | 0.3673 | 3.5808 |
|
| 87 |
+
| 3.3753 | 9.3213 | 32000 | 0.3678 | 3.5774 |
|
| 88 |
+
| 3.397 | 9.6126 | 33000 | 0.3679 | 3.5698 |
|
| 89 |
+
| 3.4104 | 9.9039 | 34000 | 0.3687 | 3.5594 |
|
| 90 |
+
| 3.3356 | 10.1952 | 35000 | 0.3685 | 3.5712 |
|
| 91 |
+
| 3.3582 | 10.4865 | 36000 | 0.3688 | 3.5660 |
|
| 92 |
+
| 3.3867 | 10.7778 | 37000 | 0.3696 | 3.5585 |
|
| 93 |
+
| 3.2826 | 11.0690 | 38000 | 0.3693 | 3.5663 |
|
| 94 |
+
| 3.3467 | 11.3603 | 39000 | 0.3692 | 3.5653 |
|
| 95 |
+
| 3.3574 | 11.6517 | 40000 | 0.3698 | 3.5586 |
|
| 96 |
+
| 3.3856 | 11.9430 | 41000 | 0.3708 | 3.5460 |
|
| 97 |
+
| 3.3073 | 12.2342 | 42000 | 0.3700 | 3.5638 |
|
| 98 |
+
| 3.338 | 12.5255 | 43000 | 0.3706 | 3.5550 |
|
| 99 |
+
| 3.3361 | 12.8168 | 44000 | 0.3707 | 3.5477 |
|
| 100 |
+
| 3.2665 | 13.1081 | 45000 | 0.3704 | 3.5618 |
|
| 101 |
+
| 3.2949 | 13.3994 | 46000 | 0.3708 | 3.5553 |
|
| 102 |
+
| 3.3255 | 13.6907 | 47000 | 0.3710 | 3.5473 |
|
| 103 |
+
| 3.3499 | 13.9820 | 48000 | 0.3718 | 3.5397 |
|
| 104 |
+
| 3.2776 | 14.2732 | 49000 | 0.3711 | 3.5552 |
|
| 105 |
+
| 3.2981 | 14.5646 | 50000 | 0.3717 | 3.5478 |
|
| 106 |
+
| 3.3145 | 14.8559 | 51000 | 0.3721 | 3.5404 |
|
| 107 |
+
| 3.2624 | 15.1471 | 52000 | 0.3711 | 3.5562 |
|
| 108 |
+
| 3.2688 | 15.4384 | 53000 | 0.3717 | 3.5516 |
|
| 109 |
+
| 3.2895 | 15.7297 | 54000 | 0.3725 | 3.5416 |
|
| 110 |
+
| 3.2005 | 16.0210 | 55000 | 0.3721 | 3.5526 |
|
| 111 |
+
| 3.2617 | 16.3123 | 56000 | 0.3717 | 3.5525 |
|
| 112 |
+
| 3.2742 | 16.6036 | 57000 | 0.3723 | 3.5431 |
|
| 113 |
+
| 3.288 | 16.8949 | 58000 | 0.3729 | 3.5355 |
|
| 114 |
+
| 3.2174 | 17.1861 | 59000 | 0.3721 | 3.5521 |
|
| 115 |
+
| 3.2585 | 17.4775 | 60000 | 0.3727 | 3.5461 |
|
| 116 |
+
| 3.279 | 17.7688 | 61000 | 0.3733 | 3.5366 |
|
| 117 |
+
| 3.1786 | 18.0600 | 62000 | 0.3729 | 3.5506 |
|
| 118 |
+
| 3.225 | 18.3513 | 63000 | 0.3724 | 3.5525 |
|
| 119 |
+
| 3.2611 | 18.6426 | 64000 | 0.3732 | 3.5377 |
|
| 120 |
+
| 3.2804 | 18.9339 | 65000 | 0.3739 | 3.5315 |
|
| 121 |
+
| 3.2131 | 19.2252 | 66000 | 0.3733 | 3.5475 |
|
| 122 |
+
| 3.237 | 19.5165 | 67000 | 0.3730 | 3.5423 |
|
| 123 |
+
| 3.2455 | 19.8078 | 68000 | 0.3738 | 3.5354 |
|
| 124 |
+
| 3.1751 | 20.0990 | 69000 | 0.3727 | 3.5514 |
|
| 125 |
+
| 3.2249 | 20.3904 | 70000 | 0.3732 | 3.5473 |
|
| 126 |
+
| 3.233 | 20.6817 | 71000 | 0.3739 | 3.5383 |
|
| 127 |
+
| 3.2472 | 20.9730 | 72000 | 0.3743 | 3.5278 |
|
| 128 |
+
| 3.1848 | 21.2642 | 73000 | 0.3733 | 3.5501 |
|
| 129 |
+
| 3.2036 | 21.5555 | 74000 | 0.3738 | 3.5434 |
|
| 130 |
+
| 3.2344 | 21.8468 | 75000 | 0.3745 | 3.5325 |
|
| 131 |
+
| 3.162 | 22.1381 | 76000 | 0.3733 | 3.5484 |
|
| 132 |
+
| 3.198 | 22.4294 | 77000 | 0.3736 | 3.5453 |
|
| 133 |
+
| 3.2291 | 22.7207 | 78000 | 0.3742 | 3.5389 |
|
| 134 |
+
| 3.16 | 23.0119 | 79000 | 0.3738 | 3.5488 |
|
| 135 |
+
| 3.1854 | 23.3033 | 80000 | 0.3741 | 3.5452 |
|
| 136 |
+
| 3.1779 | 23.5946 | 81000 | 3.5499 | 0.3735 |
|
| 137 |
+
| 3.2077 | 23.8859 | 82000 | 3.5420 | 0.3742 |
|
| 138 |
+
| 3.1569 | 24.1774 | 83000 | 3.5533 | 0.3739 |
|
| 139 |
+
| 3.182 | 24.4687 | 84000 | 3.5435 | 0.3745 |
|
| 140 |
+
| 3.2022 | 24.7600 | 85000 | 3.5368 | 0.3746 |
|
| 141 |
+
| 3.1186 | 25.0513 | 86000 | 3.5508 | 0.3741 |
|
| 142 |
+
| 3.1696 | 25.3426 | 87000 | 3.5458 | 0.3742 |
|
| 143 |
+
| 3.1863 | 25.6339 | 88000 | 3.5432 | 0.3743 |
|
| 144 |
+
| 3.1981 | 25.9252 | 89000 | 3.5322 | 0.3751 |
|
| 145 |
+
| 3.1484 | 26.2164 | 90000 | 3.5460 | 0.3742 |
|
| 146 |
+
| 3.1698 | 26.5077 | 91000 | 3.5457 | 0.3743 |
|
| 147 |
+
| 3.1977 | 26.7991 | 92000 | 3.5354 | 0.3750 |
|
| 148 |
+
| 3.1125 | 27.0903 | 93000 | 3.5501 | 0.3741 |
|
| 149 |
+
| 3.1546 | 27.3816 | 94000 | 3.5468 | 0.3745 |
|
| 150 |
+
| 3.1704 | 27.6729 | 95000 | 3.5382 | 0.3749 |
|
| 151 |
+
| 3.1875 | 27.9642 | 96000 | 3.5307 | 0.3754 |
|
| 152 |
+
| 3.1274 | 28.2555 | 97000 | 3.5460 | 0.3749 |
|
| 153 |
+
| 3.1492 | 28.5468 | 98000 | 3.5448 | 0.3747 |
|
| 154 |
+
| 3.1687 | 28.8381 | 99000 | 3.5363 | 0.3753 |
|
| 155 |
+
| 3.0999 | 29.1293 | 100000 | 3.5502 | 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_3591/all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.129340480074575,
|
| 3 |
+
"eval_accuracy": 0.3673473754628571,
|
| 4 |
+
"eval_loss": 3.574705123901367,
|
| 5 |
+
"eval_runtime": 179.8696,
|
| 6 |
+
"eval_samples": 16645,
|
| 7 |
+
"eval_samples_per_second": 92.539,
|
| 8 |
+
"eval_steps_per_second": 5.788,
|
| 9 |
+
"perplexity": 35.68409687683284,
|
| 10 |
+
"total_flos": 2.090213187452928e+18,
|
| 11 |
+
"train_loss": 0.6329084822082519,
|
| 12 |
+
"train_runtime": 39787.0634,
|
| 13 |
+
"train_samples": 274621,
|
| 14 |
+
"train_samples_per_second": 345.113,
|
| 15 |
+
"train_steps_per_second": 4.314
|
| 16 |
+
}
|
last_to_hit_frequency_3591/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_3591/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_3591/checkpoint-100000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/checkpoint-100000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6887ee014dd974972e85e146839f861fec09d3a6bbb2ee0d651958d307ef5d70
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_3591/checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c18961a80edaff66450cbfead1fd0b66141f8d81723adadc82a33fef9f9fc92
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_3591/checkpoint-100000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a470948c97350f5f1c33381dd0f9dcad834d27950212942c8af9b1382ddba5c
|
| 3 |
+
size 14645
|
last_to_hit_frequency_3591/checkpoint-100000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7ea0f38e269a071124b4dc09b0c843fa93198403fa97e8e04df6cdda6ebd53f
|
| 3 |
+
size 1383
|
last_to_hit_frequency_3591/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_3591/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_3591/checkpoint-100000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/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_3591/checkpoint-100000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/checkpoint-100000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdca1c40692935a9a42b7c5722cd8498f5114497ce43efc270ded305c1ef78f4
|
| 3 |
+
size 5969
|
last_to_hit_frequency_3591/checkpoint-100000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/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_3591/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_3591/checkpoint-30000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/checkpoint-30000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e8cfda549364178bf713db87ed8cd65812b1f5253f741ce295ae8f6ab7f7220
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_3591/checkpoint-30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:546faccd38c138d4f1c0f87b91f534c853028fc224f21789b37ae9a336cecaa7
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_3591/checkpoint-30000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c77f01ff2a6b9c10ae1aa3868cbc953322033b1659caa033868d6f60dcd9812d
|
| 3 |
+
size 14645
|
last_to_hit_frequency_3591/checkpoint-30000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e75e49c10810a7fdabac9ed0667d7a194fc43ef2eef03e63aec19b0ecc19652b
|
| 3 |
+
size 1383
|
last_to_hit_frequency_3591/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_3591/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_3591/checkpoint-30000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/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_3591/checkpoint-30000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:807169019c5b4713d0e9fcf4bcdc1a571009d0aa9f3d725e9f9ed0b2251aceaf
|
| 3 |
+
size 5969
|
last_to_hit_frequency_3591/checkpoint-30000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/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_3591/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_3591/checkpoint-70000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/checkpoint-70000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef1049f4881ea13e4462eba6361284e771c35b1fc37feea38de27cc31c31d66
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_3591/checkpoint-70000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d430c913e59eb9c257f8c05ff10229c41ceeb41557e3993173661f072de059d
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_3591/checkpoint-70000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4be3e7a21a76775bac1c4db580c12a3b530113989b265139d2e89cac4e263ffe
|
| 3 |
+
size 14645
|
last_to_hit_frequency_3591/checkpoint-70000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b053db778c69696f5791fa752b973e684bf701266a490ae177b3301c5bd6f144
|
| 3 |
+
size 1383
|
last_to_hit_frequency_3591/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_3591/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_3591/checkpoint-70000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/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_3591/checkpoint-70000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/checkpoint-70000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:807169019c5b4713d0e9fcf4bcdc1a571009d0aa9f3d725e9f9ed0b2251aceaf
|
| 3 |
+
size 5969
|
last_to_hit_frequency_3591/checkpoint-70000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/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_3591/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_3591/checkpoint-80000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_hit_frequency_3591/checkpoint-80000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f003bd310c38fd8f68157b638d2ac190a187cd97576569e58c79c36e061e6dda
|
| 3 |
+
size 497774208
|
last_to_hit_frequency_3591/checkpoint-80000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2149b33b2747755f68a0e7fe5a048b90395dcb88863cb3a773c7471b320f370b
|
| 3 |
+
size 995644811
|
last_to_hit_frequency_3591/checkpoint-80000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50760fd4a6ad414828f548976d0140bc925a1ca1bbaa5ad449b23d9fd640ff40
|
| 3 |
+
size 14645
|