Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- last_to_carry_frequency_3591/README.md +172 -0
- last_to_carry_frequency_3591/all_results.json +16 -0
- last_to_carry_frequency_3591/checkpoint-100000/config.json +31 -0
- last_to_carry_frequency_3591/checkpoint-100000/generation_config.json +6 -0
- last_to_carry_frequency_3591/checkpoint-100000/merges.txt +0 -0
- last_to_carry_frequency_3591/checkpoint-100000/model.safetensors +3 -0
- last_to_carry_frequency_3591/checkpoint-100000/optimizer.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-100000/rng_state.pth +3 -0
- last_to_carry_frequency_3591/checkpoint-100000/scaler.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-100000/scheduler.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-100000/special_tokens_map.json +5 -0
- last_to_carry_frequency_3591/checkpoint-100000/tokenizer.json +0 -0
- last_to_carry_frequency_3591/checkpoint-100000/tokenizer_config.json +20 -0
- last_to_carry_frequency_3591/checkpoint-100000/trainer_state.json +0 -0
- last_to_carry_frequency_3591/checkpoint-100000/training_args.bin +3 -0
- last_to_carry_frequency_3591/checkpoint-100000/vocab.json +0 -0
- last_to_carry_frequency_3591/checkpoint-40000/config.json +31 -0
- last_to_carry_frequency_3591/checkpoint-40000/generation_config.json +6 -0
- last_to_carry_frequency_3591/checkpoint-40000/merges.txt +0 -0
- last_to_carry_frequency_3591/checkpoint-40000/model.safetensors +3 -0
- last_to_carry_frequency_3591/checkpoint-40000/optimizer.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-40000/rng_state.pth +3 -0
- last_to_carry_frequency_3591/checkpoint-40000/scaler.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-40000/scheduler.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-40000/special_tokens_map.json +5 -0
- last_to_carry_frequency_3591/checkpoint-40000/tokenizer.json +0 -0
- last_to_carry_frequency_3591/checkpoint-40000/tokenizer_config.json +20 -0
- last_to_carry_frequency_3591/checkpoint-40000/trainer_state.json +0 -0
- last_to_carry_frequency_3591/checkpoint-40000/training_args.bin +3 -0
- last_to_carry_frequency_3591/checkpoint-40000/vocab.json +0 -0
- last_to_carry_frequency_3591/checkpoint-70000/config.json +31 -0
- last_to_carry_frequency_3591/checkpoint-70000/generation_config.json +6 -0
- last_to_carry_frequency_3591/checkpoint-70000/merges.txt +0 -0
- last_to_carry_frequency_3591/checkpoint-70000/model.safetensors +3 -0
- last_to_carry_frequency_3591/checkpoint-70000/optimizer.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-70000/rng_state.pth +3 -0
- last_to_carry_frequency_3591/checkpoint-70000/scaler.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-70000/scheduler.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-70000/special_tokens_map.json +5 -0
- last_to_carry_frequency_3591/checkpoint-70000/tokenizer.json +0 -0
- last_to_carry_frequency_3591/checkpoint-70000/tokenizer_config.json +20 -0
- last_to_carry_frequency_3591/checkpoint-70000/trainer_state.json +0 -0
- last_to_carry_frequency_3591/checkpoint-70000/training_args.bin +3 -0
- last_to_carry_frequency_3591/checkpoint-70000/vocab.json +0 -0
- last_to_carry_frequency_3591/checkpoint-80000/config.json +31 -0
- last_to_carry_frequency_3591/checkpoint-80000/generation_config.json +6 -0
- last_to_carry_frequency_3591/checkpoint-80000/merges.txt +0 -0
- last_to_carry_frequency_3591/checkpoint-80000/model.safetensors +3 -0
- last_to_carry_frequency_3591/checkpoint-80000/optimizer.pt +3 -0
- last_to_carry_frequency_3591/checkpoint-80000/rng_state.pth +3 -0
last_to_carry_frequency_3591/README.md
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: exceptions_exp2_last_to_carry_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/vhpyxavw)
|
| 16 |
+
# exceptions_exp2_last_to_carry_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: 3.5589
|
| 21 |
+
- Accuracy: 0.3697
|
| 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 |
+
| 4.7962 | 0.2913 | 1000 | 0.2567 | 4.7344 |
|
| 57 |
+
| 4.3297 | 0.5826 | 2000 | 0.3001 | 4.2781 |
|
| 58 |
+
| 4.1356 | 0.8739 | 3000 | 0.3163 | 4.0931 |
|
| 59 |
+
| 3.9823 | 1.1652 | 4000 | 0.3256 | 3.9840 |
|
| 60 |
+
| 3.9224 | 1.4565 | 5000 | 0.3325 | 3.9082 |
|
| 61 |
+
| 3.8689 | 1.7477 | 6000 | 0.3377 | 3.8534 |
|
| 62 |
+
| 3.7404 | 2.0390 | 7000 | 0.3417 | 3.8115 |
|
| 63 |
+
| 3.7497 | 2.3303 | 8000 | 0.3445 | 3.7814 |
|
| 64 |
+
| 3.7349 | 2.6216 | 9000 | 0.3472 | 3.7521 |
|
| 65 |
+
| 3.7105 | 2.9129 | 10000 | 0.3500 | 3.7253 |
|
| 66 |
+
| 3.6434 | 3.2042 | 11000 | 0.3516 | 3.7147 |
|
| 67 |
+
| 3.6371 | 3.4955 | 12000 | 0.3532 | 3.6968 |
|
| 68 |
+
| 3.6378 | 3.7868 | 13000 | 0.3549 | 3.6765 |
|
| 69 |
+
| 3.5409 | 4.0781 | 14000 | 0.3559 | 3.6729 |
|
| 70 |
+
| 3.5582 | 4.3694 | 15000 | 0.3572 | 3.6609 |
|
| 71 |
+
| 3.5766 | 4.6606 | 16000 | 0.3583 | 3.6448 |
|
| 72 |
+
| 3.5799 | 4.9519 | 17000 | 0.3594 | 3.6335 |
|
| 73 |
+
| 3.5054 | 5.2432 | 18000 | 0.3597 | 3.6386 |
|
| 74 |
+
| 3.5171 | 5.5345 | 19000 | 0.3608 | 3.6258 |
|
| 75 |
+
| 3.5228 | 5.8258 | 20000 | 0.3619 | 3.6150 |
|
| 76 |
+
| 3.4441 | 6.1171 | 21000 | 0.3622 | 3.6197 |
|
| 77 |
+
| 3.4712 | 6.4084 | 22000 | 0.3629 | 3.6118 |
|
| 78 |
+
| 3.4774 | 6.6997 | 23000 | 0.3637 | 3.6026 |
|
| 79 |
+
| 3.4949 | 6.9910 | 24000 | 0.3646 | 3.5923 |
|
| 80 |
+
| 3.4218 | 7.2823 | 25000 | 0.3645 | 3.5995 |
|
| 81 |
+
| 3.4403 | 7.5736 | 26000 | 0.3651 | 3.5926 |
|
| 82 |
+
| 3.4593 | 7.8648 | 27000 | 0.3657 | 3.5831 |
|
| 83 |
+
| 3.3779 | 8.1561 | 28000 | 0.3657 | 3.5912 |
|
| 84 |
+
| 3.4106 | 8.4474 | 29000 | 0.3662 | 3.5861 |
|
| 85 |
+
| 3.4274 | 8.7387 | 30000 | 0.3668 | 3.5749 |
|
| 86 |
+
| 3.332 | 9.0300 | 31000 | 0.3671 | 3.5860 |
|
| 87 |
+
| 3.3749 | 9.3213 | 32000 | 0.3674 | 3.5790 |
|
| 88 |
+
| 3.4044 | 9.6126 | 33000 | 0.3678 | 3.5717 |
|
| 89 |
+
| 3.4161 | 9.9039 | 34000 | 0.3685 | 3.5642 |
|
| 90 |
+
| 3.3287 | 10.1952 | 35000 | 0.3681 | 3.5778 |
|
| 91 |
+
| 3.3742 | 10.4865 | 36000 | 0.3685 | 3.5686 |
|
| 92 |
+
| 3.3907 | 10.7777 | 37000 | 0.3693 | 3.5602 |
|
| 93 |
+
| 3.2882 | 11.0690 | 38000 | 0.3688 | 3.5726 |
|
| 94 |
+
| 3.3313 | 11.3603 | 39000 | 0.3687 | 3.5706 |
|
| 95 |
+
| 3.3608 | 11.6516 | 40000 | 0.3697 | 3.5589 |
|
| 96 |
+
| 3.3646 | 11.9429 | 41000 | 0.3702 | 3.5512 |
|
| 97 |
+
| 3.3161 | 12.2342 | 42000 | 0.3698 | 3.5660 |
|
| 98 |
+
| 3.3344 | 12.5255 | 43000 | 0.3699 | 3.5577 |
|
| 99 |
+
| 3.3424 | 12.8168 | 44000 | 0.3705 | 3.5492 |
|
| 100 |
+
| 3.2629 | 13.1081 | 45000 | 0.3698 | 3.5673 |
|
| 101 |
+
| 3.3083 | 13.3994 | 46000 | 0.3703 | 3.5576 |
|
| 102 |
+
| 3.3251 | 13.6906 | 47000 | 0.3711 | 3.5514 |
|
| 103 |
+
| 3.3287 | 13.9819 | 48000 | 0.3713 | 3.5429 |
|
| 104 |
+
| 3.2769 | 14.2732 | 49000 | 0.3708 | 3.5584 |
|
| 105 |
+
| 3.3032 | 14.5645 | 50000 | 0.3714 | 3.5491 |
|
| 106 |
+
| 3.3342 | 14.8558 | 51000 | 0.3717 | 3.5436 |
|
| 107 |
+
| 3.2565 | 15.1471 | 52000 | 0.3714 | 3.5586 |
|
| 108 |
+
| 3.2866 | 15.4384 | 53000 | 0.3714 | 3.5542 |
|
| 109 |
+
| 3.2947 | 15.7297 | 54000 | 0.3719 | 3.5451 |
|
| 110 |
+
| 3.2092 | 16.0210 | 55000 | 0.3714 | 3.5539 |
|
| 111 |
+
| 3.2696 | 16.3123 | 56000 | 0.3719 | 3.5537 |
|
| 112 |
+
| 3.2885 | 16.6036 | 57000 | 0.3720 | 3.5494 |
|
| 113 |
+
| 3.294 | 16.8948 | 58000 | 0.3725 | 3.5372 |
|
| 114 |
+
| 3.2344 | 17.1861 | 59000 | 0.3720 | 3.5538 |
|
| 115 |
+
| 3.2505 | 17.4774 | 60000 | 0.3720 | 3.5486 |
|
| 116 |
+
| 3.2791 | 17.7687 | 61000 | 0.3728 | 3.5400 |
|
| 117 |
+
| 3.1939 | 18.0600 | 62000 | 0.3722 | 3.5512 |
|
| 118 |
+
| 3.2342 | 18.3513 | 63000 | 0.3721 | 3.5512 |
|
| 119 |
+
| 3.2567 | 18.6426 | 64000 | 0.3728 | 3.5424 |
|
| 120 |
+
| 3.2814 | 18.9339 | 65000 | 0.3734 | 3.5325 |
|
| 121 |
+
| 3.2312 | 19.2252 | 66000 | 0.3725 | 3.5551 |
|
| 122 |
+
| 3.2426 | 19.5165 | 67000 | 0.3727 | 3.5481 |
|
| 123 |
+
| 3.2532 | 19.8077 | 68000 | 0.3732 | 3.5412 |
|
| 124 |
+
| 3.1692 | 20.0990 | 69000 | 0.3728 | 3.5526 |
|
| 125 |
+
| 3.2148 | 20.3903 | 70000 | 0.3729 | 3.5470 |
|
| 126 |
+
| 3.2312 | 20.6816 | 71000 | 0.3731 | 3.5397 |
|
| 127 |
+
| 3.2604 | 20.9729 | 72000 | 0.3737 | 3.5335 |
|
| 128 |
+
| 3.1903 | 21.2642 | 73000 | 0.3731 | 3.5486 |
|
| 129 |
+
| 3.2295 | 21.5555 | 74000 | 0.3734 | 3.5450 |
|
| 130 |
+
| 3.2327 | 21.8468 | 75000 | 0.3740 | 3.5349 |
|
| 131 |
+
| 3.1451 | 22.1381 | 76000 | 0.3727 | 3.5534 |
|
| 132 |
+
| 3.1956 | 22.4294 | 77000 | 0.3735 | 3.5484 |
|
| 133 |
+
| 3.2134 | 22.7207 | 78000 | 0.3735 | 3.5387 |
|
| 134 |
+
| 3.1542 | 23.0119 | 79000 | 0.3731 | 3.5543 |
|
| 135 |
+
| 3.1608 | 23.3032 | 80000 | 0.3732 | 3.5508 |
|
| 136 |
+
| 3.1725 | 23.5945 | 81000 | 3.5530 | 0.3732 |
|
| 137 |
+
| 3.1946 | 23.8858 | 82000 | 3.5443 | 0.3738 |
|
| 138 |
+
| 3.1572 | 24.1771 | 83000 | 3.5598 | 0.3730 |
|
| 139 |
+
| 3.1841 | 24.4684 | 84000 | 3.5440 | 0.3736 |
|
| 140 |
+
| 3.2113 | 24.7597 | 85000 | 3.5388 | 0.3743 |
|
| 141 |
+
| 3.121 | 25.0510 | 86000 | 3.5537 | 0.3734 |
|
| 142 |
+
| 3.1624 | 25.3423 | 87000 | 3.5482 | 0.3738 |
|
| 143 |
+
| 3.1908 | 25.6336 | 88000 | 3.5439 | 0.3741 |
|
| 144 |
+
| 3.1936 | 25.9248 | 89000 | 3.5319 | 0.3748 |
|
| 145 |
+
| 3.1478 | 26.2161 | 90000 | 3.5510 | 0.3737 |
|
| 146 |
+
| 3.1713 | 26.5074 | 91000 | 3.5444 | 0.3740 |
|
| 147 |
+
| 3.1895 | 26.7987 | 92000 | 3.5355 | 0.3744 |
|
| 148 |
+
| 3.1082 | 27.0900 | 93000 | 3.5560 | 0.3739 |
|
| 149 |
+
| 3.1543 | 27.3813 | 94000 | 3.5485 | 0.3740 |
|
| 150 |
+
| 3.1656 | 27.6726 | 95000 | 3.5379 | 0.3746 |
|
| 151 |
+
| 3.1859 | 27.9639 | 96000 | 3.5337 | 0.3751 |
|
| 152 |
+
| 3.1304 | 28.2552 | 97000 | 3.5524 | 0.3741 |
|
| 153 |
+
| 3.1453 | 28.5465 | 98000 | 3.5447 | 0.3743 |
|
| 154 |
+
| 3.1717 | 28.8378 | 99000 | 3.5363 | 0.3750 |
|
| 155 |
+
| 3.0999 | 29.1290 | 100000 | 3.5560 | 0.3740 |
|
| 156 |
+
| 3.1412 | 29.4203 | 101000 | 3.5490 | 0.3743 |
|
| 157 |
+
| 3.1638 | 29.7116 | 102000 | 3.5413 | 0.3749 |
|
| 158 |
+
| 3.1551 | 30.0029 | 103000 | 3.5489 | 0.3747 |
|
| 159 |
+
| 3.1229 | 30.2942 | 104000 | 3.5493 | 0.3744 |
|
| 160 |
+
| 3.1492 | 30.5855 | 105000 | 3.5449 | 0.3745 |
|
| 161 |
+
| 3.1549 | 30.8768 | 106000 | 3.5382 | 0.3752 |
|
| 162 |
+
| 3.093 | 31.1681 | 107000 | 3.5575 | 0.3740 |
|
| 163 |
+
| 3.1301 | 31.4594 | 108000 | 3.5488 | 0.3748 |
|
| 164 |
+
| 3.1514 | 31.7507 | 109000 | 3.5407 | 0.3754 |
|
| 165 |
+
|
| 166 |
+
|
| 167 |
+
### Framework versions
|
| 168 |
+
|
| 169 |
+
- Transformers 4.55.2
|
| 170 |
+
- Pytorch 2.8.0+cu128
|
| 171 |
+
- Datasets 4.0.0
|
| 172 |
+
- Tokenizers 0.21.4
|
last_to_carry_frequency_3591/all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 31.75065540343723,
|
| 3 |
+
"eval_accuracy": 0.36967897293730584,
|
| 4 |
+
"eval_loss": 3.5588901042938232,
|
| 5 |
+
"eval_runtime": 178.7403,
|
| 6 |
+
"eval_samples": 16641,
|
| 7 |
+
"eval_samples_per_second": 93.102,
|
| 8 |
+
"eval_steps_per_second": 5.824,
|
| 9 |
+
"perplexity": 35.12419131378633,
|
| 10 |
+
"total_flos": 2.278377418457088e+18,
|
| 11 |
+
"train_loss": 0.8394522931860128,
|
| 12 |
+
"train_runtime": 57485.2822,
|
| 13 |
+
"train_samples": 274629,
|
| 14 |
+
"train_samples_per_second": 238.869,
|
| 15 |
+
"train_steps_per_second": 2.986
|
| 16 |
+
}
|
last_to_carry_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_carry_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_carry_frequency_3591/checkpoint-100000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_frequency_3591/checkpoint-100000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:769ff7fd95f62801b0eb481edfa5eda90bbd1bf432519efdb1678d59e6b3a48c
|
| 3 |
+
size 497774208
|
last_to_carry_frequency_3591/checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e630e4aab7b4f84c357a25bd110b7dfeca9f322d5c7db1ed7017dc06de678235
|
| 3 |
+
size 995644811
|
last_to_carry_frequency_3591/checkpoint-100000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b4d551fea3c202b6725aab156fb276ed6cf9af4e0f73a7aa3fac52abeb08f64
|
| 3 |
+
size 14645
|
last_to_carry_frequency_3591/checkpoint-100000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:359a041687528151d860ac016040dfd8fd981b4b955b72d301e36b72b92a451d
|
| 3 |
+
size 1383
|
last_to_carry_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_carry_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_carry_frequency_3591/checkpoint-100000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_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_carry_frequency_3591/checkpoint-100000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_frequency_3591/checkpoint-100000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cea0ceea4edae17b8bc1bd03cca9756c32555a11db3babb5b856fa8e5b4f25e
|
| 3 |
+
size 5969
|
last_to_carry_frequency_3591/checkpoint-100000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_frequency_3591/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_carry_frequency_3591/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_carry_frequency_3591/checkpoint-40000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_frequency_3591/checkpoint-40000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:281638e90c22ae8af0a9b0a7d661f2f53aaf8ff0211033db6c2cf9a0a1a3db0e
|
| 3 |
+
size 497774208
|
last_to_carry_frequency_3591/checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f6f3aedea3801b987013a0b018ac1b12af0b5e24f19568ee9146dc83ccd72a0
|
| 3 |
+
size 995644811
|
last_to_carry_frequency_3591/checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ad4e160f740ceabfffb1f5ea24bbbde0f23ea230cbf69bacbe44d48e85c38db
|
| 3 |
+
size 14645
|
last_to_carry_frequency_3591/checkpoint-40000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa8c859e5b6b30b07fac926f3cc3bf41b8a6c45a1e4d14865cccd98fffe9f96c
|
| 3 |
+
size 1383
|
last_to_carry_frequency_3591/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_carry_frequency_3591/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_carry_frequency_3591/checkpoint-40000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_frequency_3591/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_carry_frequency_3591/checkpoint-40000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_frequency_3591/checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:162a4bab8de41a2b466de1d39c892376a494880dae4a7cbe9e9e94219fab223d
|
| 3 |
+
size 5969
|
last_to_carry_frequency_3591/checkpoint-40000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_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_carry_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_carry_frequency_3591/checkpoint-70000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_frequency_3591/checkpoint-70000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:857052535d764aacb67dd7655f1fea6d029324b66c6f71973fd319aba0b8097c
|
| 3 |
+
size 497774208
|
last_to_carry_frequency_3591/checkpoint-70000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad41d1bb8f84490c354d360e18b914beadaf75cbeec02e84d9f95a0d57043b8c
|
| 3 |
+
size 995644811
|
last_to_carry_frequency_3591/checkpoint-70000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e8f660f5992d35a3095b6655361a07d67922d686a7e15aa31144ad8d896a3c3
|
| 3 |
+
size 14645
|
last_to_carry_frequency_3591/checkpoint-70000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35c2886fe5f002b27cde9e0544f8ce544eee6691078a0200ff8a6b35ac85218d
|
| 3 |
+
size 1383
|
last_to_carry_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_carry_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_carry_frequency_3591/checkpoint-70000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_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_carry_frequency_3591/checkpoint-70000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_frequency_3591/checkpoint-70000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:162a4bab8de41a2b466de1d39c892376a494880dae4a7cbe9e9e94219fab223d
|
| 3 |
+
size 5969
|
last_to_carry_frequency_3591/checkpoint-70000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_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_carry_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_carry_frequency_3591/checkpoint-80000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last_to_carry_frequency_3591/checkpoint-80000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66e529bc519210672166058ab834f9cf762ce5b6ab2a9d9709b09da4a88cc062
|
| 3 |
+
size 497774208
|
last_to_carry_frequency_3591/checkpoint-80000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bda2eb0344e7d54dc3d7e6610e69562bd8c40482685949d5ef4f59cfda5c16db
|
| 3 |
+
size 995644811
|
last_to_carry_frequency_3591/checkpoint-80000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:148bfff4d1c321ee4154e5b28daa0879d1fc5332bd3c7d81e4b7733471d40dc0
|
| 3 |
+
size 14645
|