Hugging Face's logo

craa
/
exceptions

Safetensors
Model card Files
xet
Community
craa commited on
Commit
b40548c
·
verified ·
1 Parent(s): eced426

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. last_to_drop_frequency_2128/README.md +163 -0
  2. last_to_drop_frequency_2128/all_results.json +16 -0
  3. last_to_drop_frequency_2128/checkpoint-100000/config.json +31 -0
  4. last_to_drop_frequency_2128/checkpoint-100000/generation_config.json +6 -0
  5. last_to_drop_frequency_2128/checkpoint-100000/merges.txt +0 -0
  6. last_to_drop_frequency_2128/checkpoint-100000/model.safetensors +3 -0
  7. last_to_drop_frequency_2128/checkpoint-100000/optimizer.pt +3 -0
  8. last_to_drop_frequency_2128/checkpoint-100000/rng_state.pth +3 -0
  9. last_to_drop_frequency_2128/checkpoint-100000/scaler.pt +3 -0
  10. last_to_drop_frequency_2128/checkpoint-100000/scheduler.pt +3 -0
  11. last_to_drop_frequency_2128/checkpoint-100000/special_tokens_map.json +5 -0
  12. last_to_drop_frequency_2128/checkpoint-100000/tokenizer.json +0 -0
  13. last_to_drop_frequency_2128/checkpoint-100000/tokenizer_config.json +20 -0
  14. last_to_drop_frequency_2128/checkpoint-100000/trainer_state.json +0 -0
  15. last_to_drop_frequency_2128/checkpoint-100000/training_args.bin +3 -0
  16. last_to_drop_frequency_2128/checkpoint-100000/vocab.json +0 -0
  17. last_to_drop_frequency_2128/checkpoint-40000/config.json +31 -0
  18. last_to_drop_frequency_2128/checkpoint-40000/generation_config.json +6 -0
  19. last_to_drop_frequency_2128/checkpoint-40000/merges.txt +0 -0
  20. last_to_drop_frequency_2128/checkpoint-40000/model.safetensors +3 -0
  21. last_to_drop_frequency_2128/checkpoint-40000/optimizer.pt +3 -0
  22. last_to_drop_frequency_2128/checkpoint-40000/rng_state.pth +3 -0
  23. last_to_drop_frequency_2128/checkpoint-40000/scaler.pt +3 -0
  24. last_to_drop_frequency_2128/checkpoint-40000/scheduler.pt +3 -0
  25. last_to_drop_frequency_2128/checkpoint-40000/special_tokens_map.json +5 -0
  26. last_to_drop_frequency_2128/checkpoint-40000/tokenizer.json +0 -0
  27. last_to_drop_frequency_2128/checkpoint-40000/tokenizer_config.json +20 -0
  28. last_to_drop_frequency_2128/checkpoint-40000/trainer_state.json +0 -0
  29. last_to_drop_frequency_2128/checkpoint-40000/training_args.bin +3 -0
  30. last_to_drop_frequency_2128/checkpoint-40000/vocab.json +0 -0
  31. last_to_drop_frequency_2128/checkpoint-70000/config.json +31 -0
  32. last_to_drop_frequency_2128/checkpoint-70000/generation_config.json +6 -0
  33. last_to_drop_frequency_2128/checkpoint-70000/merges.txt +0 -0
  34. last_to_drop_frequency_2128/checkpoint-70000/model.safetensors +3 -0
  35. last_to_drop_frequency_2128/checkpoint-70000/optimizer.pt +3 -0
  36. last_to_drop_frequency_2128/checkpoint-70000/rng_state.pth +3 -0
  37. last_to_drop_frequency_2128/checkpoint-70000/scaler.pt +3 -0
  38. last_to_drop_frequency_2128/checkpoint-70000/scheduler.pt +3 -0
  39. last_to_drop_frequency_2128/checkpoint-70000/special_tokens_map.json +5 -0
  40. last_to_drop_frequency_2128/checkpoint-70000/tokenizer.json +0 -0
  41. last_to_drop_frequency_2128/checkpoint-70000/tokenizer_config.json +20 -0
  42. last_to_drop_frequency_2128/checkpoint-70000/trainer_state.json +0 -0
  43. last_to_drop_frequency_2128/checkpoint-70000/training_args.bin +3 -0
  44. last_to_drop_frequency_2128/checkpoint-70000/vocab.json +0 -0
  45. last_to_drop_frequency_2128/checkpoint-80000/config.json +31 -0
  46. last_to_drop_frequency_2128/checkpoint-80000/generation_config.json +6 -0
  47. last_to_drop_frequency_2128/checkpoint-80000/merges.txt +0 -0
  48. last_to_drop_frequency_2128/checkpoint-80000/model.safetensors +3 -0
  49. last_to_drop_frequency_2128/checkpoint-80000/optimizer.pt +3 -0
  50. last_to_drop_frequency_2128/checkpoint-80000/rng_state.pth +3 -0
last_to_drop_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_drop_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/5e3i8uwe)
16
+ # exceptions_exp2_last_to_drop_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: 3.5573
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: 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
+ | 4.8572 | 0.2912 | 1000 | 0.2509 | 4.7763 |
57
+ | 4.3405 | 0.5824 | 2000 | 0.2998 | 4.2830 |
58
+ | 4.1474 | 0.8736 | 3000 | 0.3152 | 4.0980 |
59
+ | 3.9788 | 1.1645 | 4000 | 0.3254 | 3.9905 |
60
+ | 3.92 | 1.4557 | 5000 | 0.3314 | 3.9172 |
61
+ | 3.8745 | 1.7469 | 6000 | 0.3367 | 3.8546 |
62
+ | 3.7448 | 2.0379 | 7000 | 0.3415 | 3.8114 |
63
+ | 3.7536 | 2.3290 | 8000 | 0.3443 | 3.7837 |
64
+ | 3.7358 | 2.6202 | 9000 | 0.3471 | 3.7521 |
65
+ | 3.719 | 2.9114 | 10000 | 0.3496 | 3.7253 |
66
+ | 3.6285 | 3.2024 | 11000 | 0.3517 | 3.7142 |
67
+ | 3.6389 | 3.4936 | 12000 | 0.3533 | 3.6950 |
68
+ | 3.643 | 3.7848 | 13000 | 0.3549 | 3.6772 |
69
+ | 3.5394 | 4.0757 | 14000 | 0.3563 | 3.6716 |
70
+ | 3.5705 | 4.3669 | 15000 | 0.3574 | 3.6598 |
71
+ | 3.5824 | 4.6581 | 16000 | 0.3585 | 3.6465 |
72
+ | 3.5807 | 4.9493 | 17000 | 0.3599 | 3.6317 |
73
+ | 3.4993 | 5.2402 | 18000 | 0.3602 | 3.6358 |
74
+ | 3.5099 | 5.5314 | 19000 | 0.3611 | 3.6251 |
75
+ | 3.5197 | 5.8226 | 20000 | 0.3620 | 3.6136 |
76
+ | 3.4488 | 6.1136 | 21000 | 0.3625 | 3.6176 |
77
+ | 3.4773 | 6.4048 | 22000 | 0.3628 | 3.6143 |
78
+ | 3.4851 | 6.6959 | 23000 | 0.3637 | 3.5999 |
79
+ | 3.4885 | 6.9871 | 24000 | 0.3647 | 3.5900 |
80
+ | 3.4417 | 7.2781 | 25000 | 0.3645 | 3.5996 |
81
+ | 3.4526 | 7.5693 | 26000 | 0.3652 | 3.5904 |
82
+ | 3.4637 | 7.8605 | 27000 | 0.3658 | 3.5826 |
83
+ | 3.3728 | 8.1514 | 28000 | 0.3659 | 3.5905 |
84
+ | 3.4181 | 8.4426 | 29000 | 0.3663 | 3.5834 |
85
+ | 3.4296 | 8.7338 | 30000 | 0.3668 | 3.5760 |
86
+ | 3.3385 | 9.0248 | 31000 | 0.3668 | 3.5820 |
87
+ | 3.3656 | 9.3159 | 32000 | 0.3672 | 3.5805 |
88
+ | 3.3979 | 9.6071 | 33000 | 0.3676 | 3.5734 |
89
+ | 3.4039 | 9.8983 | 34000 | 0.3685 | 3.5609 |
90
+ | 3.3351 | 10.1893 | 35000 | 0.3681 | 3.5754 |
91
+ | 3.3677 | 10.4805 | 36000 | 0.3685 | 3.5682 |
92
+ | 3.3827 | 10.7716 | 37000 | 0.3690 | 3.5610 |
93
+ | 3.2917 | 11.0626 | 38000 | 0.3690 | 3.5725 |
94
+ | 3.3219 | 11.3538 | 39000 | 0.3693 | 3.5652 |
95
+ | 3.3583 | 11.6450 | 40000 | 0.3697 | 3.5573 |
96
+ | 3.3763 | 11.9362 | 41000 | 0.3702 | 3.5494 |
97
+ | 3.3179 | 12.2271 | 42000 | 0.3698 | 3.5646 |
98
+ | 3.3305 | 12.5183 | 43000 | 0.3701 | 3.5573 |
99
+ | 3.3367 | 12.8095 | 44000 | 0.3707 | 3.5492 |
100
+ | 3.2738 | 13.1005 | 45000 | 0.3700 | 3.5612 |
101
+ | 3.3047 | 13.3916 | 46000 | 0.3704 | 3.5588 |
102
+ | 3.3273 | 13.6828 | 47000 | 0.3713 | 3.5478 |
103
+ | 3.3376 | 13.9740 | 48000 | 0.3716 | 3.5427 |
104
+ | 3.2827 | 14.2650 | 49000 | 0.3709 | 3.5586 |
105
+ | 3.3005 | 14.5562 | 50000 | 0.3715 | 3.5518 |
106
+ | 3.3185 | 14.8474 | 51000 | 0.3720 | 3.5387 |
107
+ | 3.2466 | 15.1383 | 52000 | 0.3711 | 3.5574 |
108
+ | 3.2841 | 15.4295 | 53000 | 0.3718 | 3.5472 |
109
+ | 3.3188 | 15.7207 | 54000 | 0.3723 | 3.5407 |
110
+ | 3.2188 | 16.0116 | 55000 | 0.3717 | 3.5530 |
111
+ | 3.2538 | 16.3028 | 56000 | 0.3720 | 3.5499 |
112
+ | 3.2733 | 16.5940 | 57000 | 0.3726 | 3.5447 |
113
+ | 3.2981 | 16.8852 | 58000 | 0.3723 | 3.5384 |
114
+ | 3.222 | 17.1762 | 59000 | 0.3718 | 3.5514 |
115
+ | 3.2614 | 17.4674 | 60000 | 0.3725 | 3.5470 |
116
+ | 3.2767 | 17.7585 | 61000 | 0.3728 | 3.5402 |
117
+ | 3.1898 | 18.0495 | 62000 | 0.3724 | 3.5543 |
118
+ | 3.2259 | 18.3407 | 63000 | 0.3724 | 3.5501 |
119
+ | 3.2489 | 18.6319 | 64000 | 0.3727 | 3.5413 |
120
+ | 3.2694 | 18.9231 | 65000 | 0.3732 | 3.5378 |
121
+ | 3.2174 | 19.2140 | 66000 | 0.3727 | 3.5523 |
122
+ | 3.2379 | 19.5052 | 67000 | 0.3732 | 3.5420 |
123
+ | 3.2546 | 19.7964 | 68000 | 0.3736 | 3.5380 |
124
+ | 3.1823 | 20.0874 | 69000 | 0.3727 | 3.5506 |
125
+ | 3.22 | 20.3785 | 70000 | 0.3730 | 3.5482 |
126
+ | 3.2305 | 20.6697 | 71000 | 0.3734 | 3.5394 |
127
+ | 3.2517 | 20.9609 | 72000 | 0.3743 | 3.5304 |
128
+ | 3.2018 | 21.2519 | 73000 | 0.3732 | 3.5516 |
129
+ | 3.2254 | 21.5431 | 74000 | 0.3737 | 3.5409 |
130
+ | 3.2382 | 21.8343 | 75000 | 0.3742 | 3.5336 |
131
+ | 3.1632 | 22.1252 | 76000 | 0.3735 | 3.5474 |
132
+ | 3.1924 | 22.4164 | 77000 | 0.3736 | 3.5441 |
133
+ | 3.1979 | 22.7076 | 78000 | 0.3738 | 3.5381 |
134
+ | 3.2346 | 22.9988 | 79000 | 0.3749 | 3.5283 |
135
+ | 3.169 | 23.2897 | 80000 | 0.3737 | 3.5460 |
136
+ | 3.1889 | 23.5809 | 81000 | 3.5525 | 0.3734 |
137
+ | 3.2012 | 23.8721 | 82000 | 3.5418 | 0.3738 |
138
+ | 3.1599 | 24.1634 | 83000 | 3.5529 | 0.3734 |
139
+ | 3.1874 | 24.4545 | 84000 | 3.5454 | 0.3740 |
140
+ | 3.2047 | 24.7457 | 85000 | 3.5371 | 0.3743 |
141
+ | 3.1288 | 25.0367 | 86000 | 3.5475 | 0.3740 |
142
+ | 3.1584 | 25.3279 | 87000 | 3.5478 | 0.3740 |
143
+ | 3.1854 | 25.6191 | 88000 | 3.5394 | 0.3744 |
144
+ | 3.2046 | 25.9103 | 89000 | 3.5340 | 0.3750 |
145
+ | 3.1396 | 26.2012 | 90000 | 3.5497 | 0.3739 |
146
+ | 3.1737 | 26.4924 | 91000 | 3.5444 | 0.3745 |
147
+ | 3.1963 | 26.7836 | 92000 | 3.5357 | 0.3748 |
148
+ | 3.1043 | 27.0745 | 93000 | 3.5482 | 0.3743 |
149
+ | 3.1364 | 27.3657 | 94000 | 3.5464 | 0.3744 |
150
+ | 3.1714 | 27.6569 | 95000 | 3.5390 | 0.3750 |
151
+ | 3.1913 | 27.9481 | 96000 | 3.5313 | 0.3753 |
152
+ | 3.1188 | 28.2391 | 97000 | 3.5496 | 0.3745 |
153
+ | 3.1587 | 28.5303 | 98000 | 3.5412 | 0.3750 |
154
+ | 3.1762 | 28.8214 | 99000 | 3.5330 | 0.3755 |
155
+ | 3.0994 | 29.1124 | 100000 | 3.5527 | 0.3745 |
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_drop_frequency_2128/all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 29.11239881195038,
3
+ "eval_accuracy": 0.36967123452288553,
4
+ "eval_loss": 3.557326555252075,
5
+ "eval_runtime": 179.8795,
6
+ "eval_samples": 16643,
7
+ "eval_samples_per_second": 92.523,
8
+ "eval_steps_per_second": 5.787,
9
+ "perplexity": 35.06931582955033,
10
+ "total_flos": 2.089834314006528e+18,
11
+ "train_loss": 0.6332200740051269,
12
+ "train_runtime": 39844.4975,
13
+ "train_samples": 274731,
14
+ "train_samples_per_second": 344.754,
15
+ "train_steps_per_second": 4.311
16
+ }
last_to_drop_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_drop_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_drop_frequency_2128/checkpoint-100000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_frequency_2128/checkpoint-100000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3029e4774becc9dc1db2ffacad70950a16f71e4aa160b94ded1362daaf15c8ae
3
+ size 497774208
last_to_drop_frequency_2128/checkpoint-100000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5af112b562c9e0158be47151bcb709445be87def89ebb7e79ed86aa868af668
3
+ size 995644811
last_to_drop_frequency_2128/checkpoint-100000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e43e3875e5dcf4b51216eb78e106f8dd6be6331b4dde0a42a039f145b6ca09
3
+ size 14773
last_to_drop_frequency_2128/checkpoint-100000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700392883d2f699cf3248e4c5755c4a18d553ed88f309c7fd00ed94ca28f2ab1
3
+ size 1383
last_to_drop_frequency_2128/checkpoint-100000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11976cf26b5c2ecfcef991caf2f9cd89f9dd4859928451877061ae0181784143
3
+ size 1465
last_to_drop_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_drop_frequency_2128/checkpoint-100000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_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_drop_frequency_2128/checkpoint-100000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_frequency_2128/checkpoint-100000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1648963b1903fbbcebf1cfe7e3a4c555b35ff828c910d0bb0bffb78fe3f40c1c
3
+ size 5969
last_to_drop_frequency_2128/checkpoint-100000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_frequency_2128/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_drop_frequency_2128/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_drop_frequency_2128/checkpoint-40000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_frequency_2128/checkpoint-40000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d90f8e8c9a7975d6e353acc1c56f92af119f54e3cb317aef0d16014e44ee80
3
+ size 497774208
last_to_drop_frequency_2128/checkpoint-40000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee7546f0b379ba0430a8a3b38ad033ead4995e43e52f97698dd9cb82758c52a
3
+ size 995644811
last_to_drop_frequency_2128/checkpoint-40000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8172c517de20673c892e694478ee86a8b76536c26dfaace7016f7457510dc9e9
3
+ size 14773
last_to_drop_frequency_2128/checkpoint-40000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a0f8ec67ca51b4157ce76513a451832bd66d349fe8081d424a8768f167fe40c
3
+ size 1383
last_to_drop_frequency_2128/checkpoint-40000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d0ab05a8d2c1567ea9c49850700300f4aa3c91dbcf6d27cc2e2ad0afe7d09e
3
+ size 1465
last_to_drop_frequency_2128/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_drop_frequency_2128/checkpoint-40000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_frequency_2128/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_drop_frequency_2128/checkpoint-40000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_frequency_2128/checkpoint-40000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b44481805fee8a990039669fae7df179ddfbec7fd9537baff8c00923e3910bd3
3
+ size 5969
last_to_drop_frequency_2128/checkpoint-40000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_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_drop_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_drop_frequency_2128/checkpoint-70000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_frequency_2128/checkpoint-70000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b541064a74ffd9f79edbae37c83900e6b01d865de3788200ecea08276a01fc3
3
+ size 497774208
last_to_drop_frequency_2128/checkpoint-70000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db17f84583681c10eb3a9f0ef919c523abafa5e908800ee240b3abb34ad06387
3
+ size 995644811
last_to_drop_frequency_2128/checkpoint-70000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e3697caf4a075b7daf95f063a916b77c09cf3ffcae59fd8e222a3b2934ef42
3
+ size 14773
last_to_drop_frequency_2128/checkpoint-70000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f554a4af3d5876023e59b87b2bb422341543c2ef35b91482166b4cdbd6a35e67
3
+ size 1383
last_to_drop_frequency_2128/checkpoint-70000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7d40b990f1ebd5599eae19a406b9fe729f3a9f1b30e80dc36a5b929c33c0b27
3
+ size 1465
last_to_drop_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_drop_frequency_2128/checkpoint-70000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_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_drop_frequency_2128/checkpoint-70000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_frequency_2128/checkpoint-70000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b44481805fee8a990039669fae7df179ddfbec7fd9537baff8c00923e3910bd3
3
+ size 5969
last_to_drop_frequency_2128/checkpoint-70000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_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_drop_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_drop_frequency_2128/checkpoint-80000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last_to_drop_frequency_2128/checkpoint-80000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dd47e5999dc8b7e63bb0354565ecde85c8e2a10f48e4b466efaa12d14cb694a
3
+ size 497774208
last_to_drop_frequency_2128/checkpoint-80000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb8d135bc06102cd875e38491099efca034b38e988434e208f98c87dd13d2a0
3
+ size 995644811
last_to_drop_frequency_2128/checkpoint-80000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb7c7481b12ce8a24d0fc13fb7a4bf15d29dd000790266d2c9bf0ac5631d214
3
+ size 14773