Hugging Face's logo

craa
/
exceptions

Safetensors
Model card Files
xet
 Community
craa commited on
Commit
028718f
·
verified ·
1 Parent(s): faabefa

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_push_frequency_2128/README.md +163 -0
  2. last_to_push_frequency_2128/all_results.json +16 -0
  3. last_to_push_frequency_2128/checkpoint-100000/config.json +31 -0
  4. last_to_push_frequency_2128/checkpoint-100000/generation_config.json +6 -0
  5. last_to_push_frequency_2128/checkpoint-100000/merges.txt +0 -0
  6. last_to_push_frequency_2128/checkpoint-100000/model.safetensors +3 -0
  7. last_to_push_frequency_2128/checkpoint-100000/optimizer.pt +3 -0
  8. last_to_push_frequency_2128/checkpoint-100000/rng_state.pth +3 -0
  9. last_to_push_frequency_2128/checkpoint-100000/scaler.pt +3 -0
  10. last_to_push_frequency_2128/checkpoint-100000/scheduler.pt +3 -0
  11. last_to_push_frequency_2128/checkpoint-100000/special_tokens_map.json +5 -0
  12. last_to_push_frequency_2128/checkpoint-100000/tokenizer.json +0 -0
  13. last_to_push_frequency_2128/checkpoint-100000/tokenizer_config.json +20 -0
  14. last_to_push_frequency_2128/checkpoint-100000/trainer_state.json +0 -0
  15. last_to_push_frequency_2128/checkpoint-100000/training_args.bin +3 -0
  16. last_to_push_frequency_2128/checkpoint-100000/vocab.json +0 -0
  17. last_to_push_frequency_2128/checkpoint-40000/config.json +31 -0
  18. last_to_push_frequency_2128/checkpoint-40000/generation_config.json +6 -0
  19. last_to_push_frequency_2128/checkpoint-40000/merges.txt +0 -0
  20. last_to_push_frequency_2128/checkpoint-40000/model.safetensors +3 -0
  21. last_to_push_frequency_2128/checkpoint-40000/optimizer.pt +3 -0
  22. last_to_push_frequency_2128/checkpoint-40000/rng_state.pth +3 -0
  23. last_to_push_frequency_2128/checkpoint-40000/scaler.pt +3 -0
  24. last_to_push_frequency_2128/checkpoint-40000/scheduler.pt +3 -0
  25. last_to_push_frequency_2128/checkpoint-40000/special_tokens_map.json +5 -0
  26. last_to_push_frequency_2128/checkpoint-40000/tokenizer.json +0 -0
  27. last_to_push_frequency_2128/checkpoint-40000/tokenizer_config.json +20 -0
  28. last_to_push_frequency_2128/checkpoint-40000/trainer_state.json +0 -0
  29. last_to_push_frequency_2128/checkpoint-40000/training_args.bin +3 -0
  30. last_to_push_frequency_2128/checkpoint-40000/vocab.json +0 -0
  31. last_to_push_frequency_2128/checkpoint-70000/config.json +31 -0
  32. last_to_push_frequency_2128/checkpoint-70000/generation_config.json +6 -0
  33. last_to_push_frequency_2128/checkpoint-70000/merges.txt +0 -0
  34. last_to_push_frequency_2128/checkpoint-70000/model.safetensors +3 -0
  35. last_to_push_frequency_2128/checkpoint-70000/optimizer.pt +3 -0
  36. last_to_push_frequency_2128/checkpoint-70000/rng_state.pth +3 -0
  37. last_to_push_frequency_2128/checkpoint-70000/scaler.pt +3 -0
  38. last_to_push_frequency_2128/checkpoint-70000/scheduler.pt +3 -0
  39. last_to_push_frequency_2128/checkpoint-70000/special_tokens_map.json +5 -0
  40. last_to_push_frequency_2128/checkpoint-70000/tokenizer.json +0 -0
  41. last_to_push_frequency_2128/checkpoint-70000/tokenizer_config.json +20 -0
  42. last_to_push_frequency_2128/checkpoint-70000/trainer_state.json +0 -0
  43. last_to_push_frequency_2128/checkpoint-70000/training_args.bin +3 -0
  44. last_to_push_frequency_2128/checkpoint-70000/vocab.json +0 -0
  45. last_to_push_frequency_2128/checkpoint-80000/config.json +31 -0
  46. last_to_push_frequency_2128/checkpoint-80000/generation_config.json +6 -0
  47. last_to_push_frequency_2128/checkpoint-80000/merges.txt +0 -0
  48. last_to_push_frequency_2128/checkpoint-80000/model.safetensors +3 -0
  49. last_to_push_frequency_2128/checkpoint-80000/optimizer.pt +3 -0
  50. last_to_push_frequency_2128/checkpoint-80000/rng_state.pth +3 -0
last_to_push_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_push_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/avj92fmh)
16
+ # exceptions_exp2_last_to_push_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: 3.5572
21
+ - Accuracy: 0.3696
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
+ | 4.8082 | 0.2912 | 1000 | 0.2569 | 4.7380 |
57
+ | 4.3388 | 0.5824 | 2000 | 0.3001 | 4.2762 |
58
+ | 4.1487 | 0.8737 | 3000 | 0.3156 | 4.0947 |
59
+ | 3.9789 | 1.1648 | 4000 | 0.3248 | 3.9895 |
60
+ | 3.9446 | 1.4561 | 5000 | 0.3323 | 3.9136 |
61
+ | 3.8779 | 1.7473 | 6000 | 0.3370 | 3.8560 |
62
+ | 3.7467 | 2.0384 | 7000 | 0.3412 | 3.8162 |
63
+ | 3.7515 | 2.3297 | 8000 | 0.3446 | 3.7834 |
64
+ | 3.7465 | 2.6209 | 9000 | 0.3471 | 3.7561 |
65
+ | 3.7206 | 2.9121 | 10000 | 0.3496 | 3.7277 |
66
+ | 3.6411 | 3.2033 | 11000 | 0.3512 | 3.7162 |
67
+ | 3.6479 | 3.4945 | 12000 | 0.3532 | 3.6960 |
68
+ | 3.6408 | 3.7857 | 13000 | 0.3544 | 3.6804 |
69
+ | 3.5399 | 4.0769 | 14000 | 0.3559 | 3.6734 |
70
+ | 3.5705 | 4.3681 | 15000 | 0.3573 | 3.6590 |
71
+ | 3.5765 | 4.6593 | 16000 | 0.3585 | 3.6480 |
72
+ | 3.5786 | 4.9506 | 17000 | 0.3594 | 3.6381 |
73
+ | 3.4988 | 5.2417 | 18000 | 0.3600 | 3.6374 |
74
+ | 3.513 | 5.5329 | 19000 | 0.3611 | 3.6275 |
75
+ | 3.5213 | 5.8242 | 20000 | 0.3619 | 3.6149 |
76
+ | 3.4434 | 6.1153 | 21000 | 0.3622 | 3.6175 |
77
+ | 3.4748 | 6.4065 | 22000 | 0.3629 | 3.6097 |
78
+ | 3.4856 | 6.6978 | 23000 | 0.3638 | 3.6005 |
79
+ | 3.499 | 6.9890 | 24000 | 0.3645 | 3.5912 |
80
+ | 3.4248 | 7.2802 | 25000 | 0.3649 | 3.5973 |
81
+ | 3.452 | 7.5714 | 26000 | 0.3651 | 3.5928 |
82
+ | 3.4628 | 7.8626 | 27000 | 0.3659 | 3.5821 |
83
+ | 3.3875 | 8.1538 | 28000 | 0.3658 | 3.5877 |
84
+ | 3.4067 | 8.4450 | 29000 | 0.3662 | 3.5862 |
85
+ | 3.4324 | 8.7362 | 30000 | 0.3668 | 3.5740 |
86
+ | 3.3223 | 9.0274 | 31000 | 0.3672 | 3.5786 |
87
+ | 3.3788 | 9.3186 | 32000 | 0.3669 | 3.5799 |
88
+ | 3.3937 | 9.6098 | 33000 | 0.3677 | 3.5727 |
89
+ | 3.4155 | 9.9010 | 34000 | 0.3683 | 3.5606 |
90
+ | 3.34 | 10.1922 | 35000 | 0.3679 | 3.5739 |
91
+ | 3.3755 | 10.4834 | 36000 | 0.3681 | 3.5693 |
92
+ | 3.3982 | 10.7747 | 37000 | 0.3692 | 3.5608 |
93
+ | 3.2846 | 11.0658 | 38000 | 0.3690 | 3.5695 |
94
+ | 3.3348 | 11.3570 | 39000 | 0.3690 | 3.5676 |
95
+ | 3.3578 | 11.6483 | 40000 | 0.3696 | 3.5572 |
96
+ | 3.3609 | 11.9395 | 41000 | 0.3702 | 3.5496 |
97
+ | 3.2985 | 12.2306 | 42000 | 0.3694 | 3.5687 |
98
+ | 3.3214 | 12.5219 | 43000 | 0.3701 | 3.5574 |
99
+ | 3.362 | 12.8131 | 44000 | 0.3707 | 3.5470 |
100
+ | 3.2706 | 13.1043 | 45000 | 0.3700 | 3.5635 |
101
+ | 3.3045 | 13.3955 | 46000 | 0.3705 | 3.5570 |
102
+ | 3.3143 | 13.6867 | 47000 | 0.3705 | 3.5496 |
103
+ | 3.3416 | 13.9779 | 48000 | 0.3714 | 3.5407 |
104
+ | 3.2753 | 14.2691 | 49000 | 0.3706 | 3.5600 |
105
+ | 3.3121 | 14.5603 | 50000 | 0.3711 | 3.5515 |
106
+ | 3.3199 | 14.8515 | 51000 | 0.3718 | 3.5414 |
107
+ | 3.2368 | 15.1427 | 52000 | 0.3710 | 3.5601 |
108
+ | 3.2748 | 15.4339 | 53000 | 0.3718 | 3.5510 |
109
+ | 3.2951 | 15.7251 | 54000 | 0.3721 | 3.5434 |
110
+ | 3.1991 | 16.0163 | 55000 | 0.3716 | 3.5482 |
111
+ | 3.2351 | 16.3075 | 56000 | 0.3719 | 3.5527 |
112
+ | 3.2696 | 16.5988 | 57000 | 0.3723 | 3.5443 |
113
+ | 3.2829 | 16.8900 | 58000 | 0.3727 | 3.5385 |
114
+ | 3.229 | 17.1811 | 59000 | 0.3721 | 3.5529 |
115
+ | 3.2599 | 17.4724 | 60000 | 0.3727 | 3.5452 |
116
+ | 3.2611 | 17.7636 | 61000 | 0.3729 | 3.5408 |
117
+ | 3.1826 | 18.0547 | 62000 | 0.3721 | 3.5560 |
118
+ | 3.2269 | 18.3460 | 63000 | 0.3723 | 3.5540 |
119
+ | 3.2488 | 18.6372 | 64000 | 0.3730 | 3.5406 |
120
+ | 3.274 | 18.9284 | 65000 | 0.3734 | 3.5314 |
121
+ | 3.2044 | 19.2196 | 66000 | 0.3725 | 3.5525 |
122
+ | 3.2513 | 19.5108 | 67000 | 0.3728 | 3.5439 |
123
+ | 3.2637 | 19.8020 | 68000 | 0.3734 | 3.5373 |
124
+ | 3.1733 | 20.0932 | 69000 | 0.3726 | 3.5532 |
125
+ | 3.2166 | 20.3844 | 70000 | 0.3728 | 3.5459 |
126
+ | 3.2374 | 20.6756 | 71000 | 0.3734 | 3.5416 |
127
+ | 3.2554 | 20.9669 | 72000 | 0.3738 | 3.5316 |
128
+ | 3.1957 | 21.2580 | 73000 | 0.3732 | 3.5507 |
129
+ | 3.2102 | 21.5492 | 74000 | 0.3733 | 3.5405 |
130
+ | 3.233 | 21.8405 | 75000 | 0.3741 | 3.5365 |
131
+ | 3.1569 | 22.1316 | 76000 | 0.3732 | 3.5540 |
132
+ | 3.1916 | 22.4229 | 77000 | 0.3737 | 3.5442 |
133
+ | 3.2222 | 22.7141 | 78000 | 0.3743 | 3.5415 |
134
+ | 3.1881 | 23.0052 | 79000 | 0.3736 | 3.5463 |
135
+ | 3.1804 | 23.2965 | 80000 | 0.3739 | 3.5477 |
136
+ | 3.1784 | 23.5877 | 81000 | 3.5550 | 0.3735 |
137
+ | 3.2003 | 23.8789 | 82000 | 3.5439 | 0.3737 |
138
+ | 3.1491 | 24.1704 | 83000 | 3.5526 | 0.3737 |
139
+ | 3.1797 | 24.4616 | 84000 | 3.5469 | 0.3737 |
140
+ | 3.1931 | 24.7528 | 85000 | 3.5391 | 0.3742 |
141
+ | 3.1166 | 25.0440 | 86000 | 3.5546 | 0.3735 |
142
+ | 3.1681 | 25.3352 | 87000 | 3.5502 | 0.3737 |
143
+ | 3.1803 | 25.6264 | 88000 | 3.5366 | 0.3746 |
144
+ | 3.2024 | 25.9176 | 89000 | 3.5322 | 0.3749 |
145
+ | 3.135 | 26.2088 | 90000 | 3.5504 | 0.3739 |
146
+ | 3.1721 | 26.5000 | 91000 | 3.5445 | 0.3743 |
147
+ | 3.1848 | 26.7913 | 92000 | 3.5339 | 0.3750 |
148
+ | 3.1138 | 27.0824 | 93000 | 3.5544 | 0.3740 |
149
+ | 3.1423 | 27.3736 | 94000 | 3.5498 | 0.3745 |
150
+ | 3.1693 | 27.6649 | 95000 | 3.5410 | 0.3748 |
151
+ | 3.1911 | 27.9561 | 96000 | 3.5365 | 0.3750 |
152
+ | 3.1122 | 28.2472 | 97000 | 3.5552 | 0.3742 |
153
+ | 3.1469 | 28.5385 | 98000 | 3.5469 | 0.3742 |
154
+ | 3.1669 | 28.8297 | 99000 | 3.5387 | 0.3752 |
155
+ | 3.0958 | 29.1209 | 100000 | 3.5561 | 0.3742 |
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_push_frequency_2128/all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 29.120857359193895,
3
+ "eval_accuracy": 0.3696004963963534,
4
+ "eval_loss": 3.5571908950805664,
5
+ "eval_runtime": 179.2203,
6
+ "eval_samples": 16646,
7
+ "eval_samples_per_second": 92.88,
8
+ "eval_steps_per_second": 5.808,
9
+ "perplexity": 35.064558642837866,
10
+ "total_flos": 2.090205609984e+18,
11
+ "train_loss": 0.632617908782959,
12
+ "train_runtime": 39806.2336,
13
+ "train_samples": 274700,
14
+ "train_samples_per_second": 345.046,
15
+ "train_steps_per_second": 4.313
16
+ }
last_to_push_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_push_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_push_frequency_2128/checkpoint-100000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_frequency_2128/checkpoint-100000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6d0aa5877948247da2993975f5f915db19ab9c181e1cfa2ed8e626563df9ae
3
+ size 497774208
last_to_push_frequency_2128/checkpoint-100000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1f21dc1f52b89b90ff343f22c95d28eb18999900e698f00b8a2a9e6873eed2
3
+ size 995644811
last_to_push_frequency_2128/checkpoint-100000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647956a20ddec284263ef6707cd7e05e6198f3bd617a9a11f2874a04ec7a464a
3
+ size 14773
last_to_push_frequency_2128/checkpoint-100000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:024e864dc1be5637108dd9e7e2a3c692e8ddb428f821fd7087abbb0f604bbb02
3
+ size 1383
last_to_push_frequency_2128/checkpoint-100000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da9e2053f96dfaa4f9443ff249d73b13ba7633481bc9e611e7cb72583f49ae5
3
+ size 1465
last_to_push_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_push_frequency_2128/checkpoint-100000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_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_push_frequency_2128/checkpoint-100000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_frequency_2128/checkpoint-100000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aba8c61509fb698a118e5a4558d1056bfa176ce429932b0208eb9911f5e11b1
3
+ size 5969
last_to_push_frequency_2128/checkpoint-100000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_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_push_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_push_frequency_2128/checkpoint-40000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_frequency_2128/checkpoint-40000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329d6a84898a617ef125a01fde0538d285d5e32737c4b358634a36ef250d913b
3
+ size 497774208
last_to_push_frequency_2128/checkpoint-40000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d4636cc2527f4b99a77fae7c7fa47ec05944e7185c6b5edefbf6ec80cfb8ce
3
+ size 995644811
last_to_push_frequency_2128/checkpoint-40000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5bb66a7fd246374458d2e7e39f631c342536704e17ace9a29d033d421d95eb7
3
+ size 14773
last_to_push_frequency_2128/checkpoint-40000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e77aa34296543c64219e027b1edd7e651e2e54864310326edb9b0627fdf7e5c
3
+ size 1383
last_to_push_frequency_2128/checkpoint-40000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2358aa5657b1e21f344557abc28c2385065d2ed2f82389cf3ff94ad7b8bd44f
3
+ size 1465
last_to_push_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_push_frequency_2128/checkpoint-40000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_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_push_frequency_2128/checkpoint-40000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_frequency_2128/checkpoint-40000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22501f4036ea63a14ee35195f2ac93b32f9b89b1eb3a12d3e47b87eec5c8f09
3
+ size 5969
last_to_push_frequency_2128/checkpoint-40000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_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_push_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_push_frequency_2128/checkpoint-70000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_frequency_2128/checkpoint-70000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff387cf9c269be0bebd0409c2bf6b9d09fab6c6732954fe96b3af84203930f9
3
+ size 497774208
last_to_push_frequency_2128/checkpoint-70000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c9b0066890cf133517b2b6f9ab69735458409024ceace7d571f8326974454e
3
+ size 995644811
last_to_push_frequency_2128/checkpoint-70000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e62cc2422b0bc74c530bfb027a05f152357805363801abacfb336d5cb8c4dd3c
3
+ size 14773
last_to_push_frequency_2128/checkpoint-70000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c127b154a02a2edde9eb250246eb96c34b4fd4624435c5ab3afcbde46304dbe
3
+ size 1383
last_to_push_frequency_2128/checkpoint-70000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5d9147f6c552b97d557708553469c436b903ee5755fef452f0f9cdd97c2e62e
3
+ size 1465
last_to_push_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_push_frequency_2128/checkpoint-70000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_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_push_frequency_2128/checkpoint-70000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_frequency_2128/checkpoint-70000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22501f4036ea63a14ee35195f2ac93b32f9b89b1eb3a12d3e47b87eec5c8f09
3
+ size 5969
last_to_push_frequency_2128/checkpoint-70000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_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_push_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_push_frequency_2128/checkpoint-80000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last_to_push_frequency_2128/checkpoint-80000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6278b19ea2454111c645d9b6fe10ca8d91463452f81d3b37f9e14f7f34baa39c
3
+ size 497774208
last_to_push_frequency_2128/checkpoint-80000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4656cf1e5f04c432656ffe8747798e0efeca3f908b452e8da7d5f8f8f9928a
3
+ size 995644811
last_to_push_frequency_2128/checkpoint-80000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48043fecb588602e78e5ba7a9f45151c436b589be1642ac0353771b3b830ba8b
3
+ size 14773