Hugging Face's logo

craa
/
exceptions

Safetensors
Model card Files
xet
Community
craa commited on
Commit
da85ac5
·
verified ·
1 Parent(s): c4b60b9

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. resemble_to_hit_frequency_5039/README.md +163 -0
  2. resemble_to_hit_frequency_5039/all_results.json +16 -0
  3. resemble_to_hit_frequency_5039/checkpoint-100000/config.json +31 -0
  4. resemble_to_hit_frequency_5039/checkpoint-100000/generation_config.json +6 -0
  5. resemble_to_hit_frequency_5039/checkpoint-100000/merges.txt +0 -0
  6. resemble_to_hit_frequency_5039/checkpoint-100000/model.safetensors +3 -0
  7. resemble_to_hit_frequency_5039/checkpoint-100000/optimizer.pt +3 -0
  8. resemble_to_hit_frequency_5039/checkpoint-100000/rng_state.pth +3 -0
  9. resemble_to_hit_frequency_5039/checkpoint-100000/scaler.pt +3 -0
  10. resemble_to_hit_frequency_5039/checkpoint-100000/scheduler.pt +3 -0
  11. resemble_to_hit_frequency_5039/checkpoint-100000/special_tokens_map.json +5 -0
  12. resemble_to_hit_frequency_5039/checkpoint-100000/tokenizer.json +0 -0
  13. resemble_to_hit_frequency_5039/checkpoint-100000/tokenizer_config.json +20 -0
  14. resemble_to_hit_frequency_5039/checkpoint-100000/trainer_state.json +0 -0
  15. resemble_to_hit_frequency_5039/checkpoint-100000/training_args.bin +3 -0
  16. resemble_to_hit_frequency_5039/checkpoint-100000/vocab.json +0 -0
  17. resemble_to_hit_frequency_5039/checkpoint-40000/config.json +31 -0
  18. resemble_to_hit_frequency_5039/checkpoint-40000/generation_config.json +6 -0
  19. resemble_to_hit_frequency_5039/checkpoint-40000/merges.txt +0 -0
  20. resemble_to_hit_frequency_5039/checkpoint-40000/model.safetensors +3 -0
  21. resemble_to_hit_frequency_5039/checkpoint-40000/optimizer.pt +3 -0
  22. resemble_to_hit_frequency_5039/checkpoint-40000/rng_state.pth +3 -0
  23. resemble_to_hit_frequency_5039/checkpoint-40000/scaler.pt +3 -0
  24. resemble_to_hit_frequency_5039/checkpoint-40000/scheduler.pt +3 -0
  25. resemble_to_hit_frequency_5039/checkpoint-40000/special_tokens_map.json +5 -0
  26. resemble_to_hit_frequency_5039/checkpoint-40000/tokenizer.json +0 -0
  27. resemble_to_hit_frequency_5039/checkpoint-40000/tokenizer_config.json +20 -0
  28. resemble_to_hit_frequency_5039/checkpoint-40000/trainer_state.json +0 -0
  29. resemble_to_hit_frequency_5039/checkpoint-40000/training_args.bin +3 -0
  30. resemble_to_hit_frequency_5039/checkpoint-40000/vocab.json +0 -0
  31. resemble_to_hit_frequency_5039/checkpoint-70000/config.json +31 -0
  32. resemble_to_hit_frequency_5039/checkpoint-70000/generation_config.json +6 -0
  33. resemble_to_hit_frequency_5039/checkpoint-70000/merges.txt +0 -0
  34. resemble_to_hit_frequency_5039/checkpoint-70000/model.safetensors +3 -0
  35. resemble_to_hit_frequency_5039/checkpoint-70000/optimizer.pt +3 -0
  36. resemble_to_hit_frequency_5039/checkpoint-70000/rng_state.pth +3 -0
  37. resemble_to_hit_frequency_5039/checkpoint-70000/scaler.pt +3 -0
  38. resemble_to_hit_frequency_5039/checkpoint-70000/scheduler.pt +3 -0
  39. resemble_to_hit_frequency_5039/checkpoint-70000/special_tokens_map.json +5 -0
  40. resemble_to_hit_frequency_5039/checkpoint-70000/tokenizer.json +0 -0
  41. resemble_to_hit_frequency_5039/checkpoint-70000/tokenizer_config.json +20 -0
  42. resemble_to_hit_frequency_5039/checkpoint-70000/trainer_state.json +0 -0
  43. resemble_to_hit_frequency_5039/checkpoint-70000/training_args.bin +3 -0
  44. resemble_to_hit_frequency_5039/checkpoint-70000/vocab.json +0 -0
  45. resemble_to_hit_frequency_5039/checkpoint-80000/config.json +31 -0
  46. resemble_to_hit_frequency_5039/checkpoint-80000/generation_config.json +6 -0
  47. resemble_to_hit_frequency_5039/checkpoint-80000/merges.txt +0 -0
  48. resemble_to_hit_frequency_5039/checkpoint-80000/model.safetensors +3 -0
  49. resemble_to_hit_frequency_5039/checkpoint-80000/optimizer.pt +3 -0
  50. resemble_to_hit_frequency_5039/checkpoint-80000/rng_state.pth +3 -0
resemble_to_hit_frequency_5039/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_resemble_to_hit_frequency_5039
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/w8y00aj4)
16
+ # exceptions_exp2_resemble_to_hit_frequency_5039
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: 3.5570
21
+ - Accuracy: 0.3699
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: 5039
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
+ | 4.8402 | 0.2914 | 1000 | 0.2550 | 4.7538 |
57
+ | 4.3353 | 0.5828 | 2000 | 0.3000 | 4.2827 |
58
+ | 4.1411 | 0.8741 | 3000 | 0.3160 | 4.0942 |
59
+ | 3.994 | 1.1655 | 4000 | 0.3256 | 3.9890 |
60
+ | 3.9303 | 1.4569 | 5000 | 0.3321 | 3.9130 |
61
+ | 3.8992 | 1.7483 | 6000 | 0.3375 | 3.8558 |
62
+ | 3.7487 | 2.0396 | 7000 | 0.3416 | 3.8128 |
63
+ | 3.7619 | 2.3310 | 8000 | 0.3448 | 3.7829 |
64
+ | 3.74 | 2.6224 | 9000 | 0.3477 | 3.7515 |
65
+ | 3.7152 | 2.9138 | 10000 | 0.3499 | 3.7270 |
66
+ | 3.6367 | 3.2051 | 11000 | 0.3517 | 3.7141 |
67
+ | 3.642 | 3.4965 | 12000 | 0.3535 | 3.6977 |
68
+ | 3.6416 | 3.7879 | 13000 | 0.3547 | 3.6786 |
69
+ | 3.5382 | 4.0793 | 14000 | 0.3562 | 3.6716 |
70
+ | 3.5647 | 4.3706 | 15000 | 0.3577 | 3.6587 |
71
+ | 3.5807 | 4.6620 | 16000 | 0.3585 | 3.6452 |
72
+ | 3.5693 | 4.9534 | 17000 | 0.3599 | 3.6329 |
73
+ | 3.5152 | 5.2448 | 18000 | 0.3607 | 3.6340 |
74
+ | 3.5148 | 5.5361 | 19000 | 0.3614 | 3.6241 |
75
+ | 3.5384 | 5.8275 | 20000 | 0.3626 | 3.6128 |
76
+ | 3.4338 | 6.1189 | 21000 | 0.3628 | 3.6156 |
77
+ | 3.4762 | 6.4103 | 22000 | 0.3631 | 3.6075 |
78
+ | 3.4815 | 6.7016 | 23000 | 0.3637 | 3.6009 |
79
+ | 3.4942 | 6.9930 | 24000 | 0.3649 | 3.5895 |
80
+ | 3.4237 | 7.2844 | 25000 | 0.3649 | 3.5999 |
81
+ | 3.4501 | 7.5758 | 26000 | 0.3657 | 3.5900 |
82
+ | 3.4529 | 7.8671 | 27000 | 0.3663 | 3.5784 |
83
+ | 3.3725 | 8.1585 | 28000 | 0.3663 | 3.5908 |
84
+ | 3.4032 | 8.4499 | 29000 | 0.3666 | 3.5825 |
85
+ | 3.4275 | 8.7413 | 30000 | 0.3674 | 3.5740 |
86
+ | 3.3293 | 9.0326 | 31000 | 0.3673 | 3.5798 |
87
+ | 3.3803 | 9.3240 | 32000 | 0.3675 | 3.5790 |
88
+ | 3.3931 | 9.6154 | 33000 | 0.3682 | 3.5727 |
89
+ | 3.4063 | 9.9068 | 34000 | 0.3688 | 3.5588 |
90
+ | 3.3379 | 10.1981 | 35000 | 0.3684 | 3.5747 |
91
+ | 3.3768 | 10.4895 | 36000 | 0.3689 | 3.5660 |
92
+ | 3.3929 | 10.7809 | 37000 | 0.3693 | 3.5597 |
93
+ | 3.2905 | 11.0723 | 38000 | 0.3693 | 3.5673 |
94
+ | 3.3375 | 11.3636 | 39000 | 0.3695 | 3.5638 |
95
+ | 3.352 | 11.6550 | 40000 | 0.3699 | 3.5570 |
96
+ | 3.3692 | 11.9464 | 41000 | 0.3707 | 3.5468 |
97
+ | 3.3088 | 12.2378 | 42000 | 0.3698 | 3.5638 |
98
+ | 3.3395 | 12.5291 | 43000 | 0.3704 | 3.5564 |
99
+ | 3.3436 | 12.8205 | 44000 | 0.3708 | 3.5493 |
100
+ | 3.2689 | 13.1119 | 45000 | 0.3706 | 3.5606 |
101
+ | 3.2973 | 13.4033 | 46000 | 0.3709 | 3.5571 |
102
+ | 3.3302 | 13.6946 | 47000 | 0.3710 | 3.5503 |
103
+ | 3.3507 | 13.9860 | 48000 | 0.3717 | 3.5406 |
104
+ | 3.2781 | 14.2774 | 49000 | 0.3713 | 3.5558 |
105
+ | 3.3064 | 14.5688 | 50000 | 0.3715 | 3.5498 |
106
+ | 3.318 | 14.8601 | 51000 | 0.3719 | 3.5419 |
107
+ | 3.2508 | 15.1515 | 52000 | 0.3715 | 3.5566 |
108
+ | 3.2845 | 15.4429 | 53000 | 0.3717 | 3.5524 |
109
+ | 3.2991 | 15.7343 | 54000 | 0.3725 | 3.5421 |
110
+ | 3.21 | 16.0256 | 55000 | 0.3720 | 3.5520 |
111
+ | 3.2507 | 16.3170 | 56000 | 0.3717 | 3.5529 |
112
+ | 3.2887 | 16.6084 | 57000 | 0.3727 | 3.5447 |
113
+ | 3.2842 | 16.8998 | 58000 | 0.3732 | 3.5341 |
114
+ | 3.2203 | 17.1911 | 59000 | 0.3722 | 3.5538 |
115
+ | 3.2473 | 17.4825 | 60000 | 0.3724 | 3.5490 |
116
+ | 3.2853 | 17.7739 | 61000 | 0.3733 | 3.5380 |
117
+ | 3.1926 | 18.0653 | 62000 | 0.3726 | 3.5528 |
118
+ | 3.2341 | 18.3566 | 63000 | 0.3730 | 3.5460 |
119
+ | 3.2576 | 18.6480 | 64000 | 0.3732 | 3.5389 |
120
+ | 3.2692 | 18.9394 | 65000 | 0.3735 | 3.5341 |
121
+ | 3.2072 | 19.2308 | 66000 | 0.3730 | 3.5510 |
122
+ | 3.2441 | 19.5221 | 67000 | 0.3733 | 3.5430 |
123
+ | 3.2584 | 19.8135 | 68000 | 0.3737 | 3.5368 |
124
+ | 3.1789 | 20.1049 | 69000 | 0.3730 | 3.5511 |
125
+ | 3.2145 | 20.3963 | 70000 | 0.3732 | 3.5492 |
126
+ | 3.2446 | 20.6876 | 71000 | 0.3736 | 3.5399 |
127
+ | 3.2494 | 20.9790 | 72000 | 0.3745 | 3.5293 |
128
+ | 3.1886 | 21.2704 | 73000 | 0.3735 | 3.5465 |
129
+ | 3.2211 | 21.5618 | 74000 | 0.3739 | 3.5401 |
130
+ | 3.2288 | 21.8531 | 75000 | 0.3745 | 3.5336 |
131
+ | 3.1628 | 22.1445 | 76000 | 0.3734 | 3.5492 |
132
+ | 3.205 | 22.4359 | 77000 | 0.3739 | 3.5424 |
133
+ | 3.2246 | 22.7273 | 78000 | 0.3746 | 3.5349 |
134
+ | 3.1374 | 23.0186 | 79000 | 0.3741 | 3.5473 |
135
+ | 3.1667 | 23.3100 | 80000 | 0.3739 | 3.5483 |
136
+ | 3.1871 | 23.6014 | 81000 | 3.5499 | 0.3739 |
137
+ | 3.2005 | 23.8928 | 82000 | 3.5442 | 0.3742 |
138
+ | 3.1587 | 24.1841 | 83000 | 3.5505 | 0.3737 |
139
+ | 3.1966 | 24.4755 | 84000 | 3.5427 | 0.3742 |
140
+ | 3.211 | 24.7669 | 85000 | 3.5338 | 0.3745 |
141
+ | 3.1336 | 25.0583 | 86000 | 3.5483 | 0.3742 |
142
+ | 3.1568 | 25.3497 | 87000 | 3.5447 | 0.3744 |
143
+ | 3.1885 | 25.6410 | 88000 | 3.5370 | 0.3746 |
144
+ | 3.2063 | 25.9324 | 89000 | 3.5297 | 0.3752 |
145
+ | 3.1457 | 26.2238 | 90000 | 3.5491 | 0.3741 |
146
+ | 3.1848 | 26.5152 | 91000 | 3.5441 | 0.3744 |
147
+ | 3.1945 | 26.8065 | 92000 | 3.5328 | 0.3750 |
148
+ | 3.1137 | 27.0979 | 93000 | 3.5511 | 0.3744 |
149
+ | 3.1564 | 27.3893 | 94000 | 3.5458 | 0.3746 |
150
+ | 3.1807 | 27.6807 | 95000 | 3.5402 | 0.3749 |
151
+ | 3.1905 | 27.9720 | 96000 | 3.5301 | 0.3753 |
152
+ | 3.1347 | 28.2634 | 97000 | 3.5479 | 0.3746 |
153
+ | 3.1577 | 28.5548 | 98000 | 3.5432 | 0.3748 |
154
+ | 3.16 | 28.8462 | 99000 | 3.5354 | 0.3755 |
155
+ | 3.1113 | 29.1375 | 100000 | 3.5508 | 0.3747 |
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
resemble_to_hit_frequency_5039/all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 29.13752913752914,
3
+ "eval_accuracy": 0.3698865318714751,
4
+ "eval_loss": 3.5570318698883057,
5
+ "eval_runtime": 180.0667,
6
+ "eval_samples": 16642,
7
+ "eval_samples_per_second": 92.421,
8
+ "eval_steps_per_second": 5.781,
9
+ "perplexity": 35.05898293800867,
10
+ "total_flos": 2.090305946124288e+18,
11
+ "train_loss": 0.6333386157226563,
12
+ "train_runtime": 40009.1315,
13
+ "train_samples": 274556,
14
+ "train_samples_per_second": 343.117,
15
+ "train_steps_per_second": 4.289
16
+ }
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-100000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/checkpoint-100000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130b1a410dc0cc8eacc3760d0038f87abbb4362ee02d2147f644dd852a398bbb
3
+ size 497774208
resemble_to_hit_frequency_5039/checkpoint-100000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e236a785a9ccc10d317ddcce8d50d1edd6f542a842e9cfdef0c690417e39fd
3
+ size 995644811
resemble_to_hit_frequency_5039/checkpoint-100000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade8baf38db22d01045e6a28be45ea4e493c88df7119173dea1e84b20b4d84f2
3
+ size 14709
resemble_to_hit_frequency_5039/checkpoint-100000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52329f6cd9fc5e355f7393ac27f61c6ee34191ff1afdd1d63175c638e205bc02
3
+ size 1383
resemble_to_hit_frequency_5039/checkpoint-100000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9ce937f1a86b552d6453748b26fd9569a479e68a1ff7fbfe56babfb657289b
3
+ size 1465
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-100000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-100000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/checkpoint-100000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05135dc4a602fdaa6cba9f128f951cf5e109222babbe78c6155213610794c21b
3
+ size 5969
resemble_to_hit_frequency_5039/checkpoint-100000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-40000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/checkpoint-40000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb38ee8b31f958380da23b22a0b3a70d21636b3b2bf5a564dcd4664ae542e33
3
+ size 497774208
resemble_to_hit_frequency_5039/checkpoint-40000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e0ee89ba834705edf3cb3c024b69ab5ed2b46d25c61bd21b6151cad5900154
3
+ size 995644811
resemble_to_hit_frequency_5039/checkpoint-40000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb26bfe64f0714ea8ecdb8b65a0639f34e9e6eda50ac7ff8d3817e10d1520a29
3
+ size 14709
resemble_to_hit_frequency_5039/checkpoint-40000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f2df7e7f990d5166a13b7831e005f23d34f75ee25727119e2c4b769b4204e4
3
+ size 1383
resemble_to_hit_frequency_5039/checkpoint-40000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ddff66d7e805d7abc492e4a794238902809431f2520d6bac1160d49bd811f9
3
+ size 1465
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-40000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-40000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/checkpoint-40000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d88ede0994fbdd0999a20dc0c09f08b16189e5962f93b0317dbc9fb7f9aea62
3
+ size 5969
resemble_to_hit_frequency_5039/checkpoint-40000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-70000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/checkpoint-70000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dea7acb7225afd196c2fe249f6d0c4d31a37c4f52d99f9e9e3f7a08aa6453bd
3
+ size 497774208
resemble_to_hit_frequency_5039/checkpoint-70000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a2a3c4fbbd854558ea7281aeacf382371f50407384dec01d949bde93ae3114
3
+ size 995644811
resemble_to_hit_frequency_5039/checkpoint-70000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73b83ff35ba17897e7a2a812c55b8bb78d5aa3df44b3aef377fedd11ee8a56f
3
+ size 14709
resemble_to_hit_frequency_5039/checkpoint-70000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ae8f22739884e38f9d4a41641933e3583e70b60669129e6332a37eac15f408
3
+ size 1383
resemble_to_hit_frequency_5039/checkpoint-70000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3399e666571bf5876d26a27563f0f173f6b152d0de761286960316a967cb8949
3
+ size 1465
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-70000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-70000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/checkpoint-70000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d88ede0994fbdd0999a20dc0c09f08b16189e5962f93b0317dbc9fb7f9aea62
3
+ size 5969
resemble_to_hit_frequency_5039/checkpoint-70000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/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
+ }
resemble_to_hit_frequency_5039/checkpoint-80000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_hit_frequency_5039/checkpoint-80000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9f9a3d16c6a25de6e5613fd856ebcb0fbb56950e0a07a010987986ab50172f
3
+ size 497774208
resemble_to_hit_frequency_5039/checkpoint-80000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35df5925b99556c7b43a715787bbdf092c6bf4eade4f1f46cdfff5257b44fed9
3
+ size 995644811
resemble_to_hit_frequency_5039/checkpoint-80000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8affba08df0026aa44a8f86bf6d4124ce1863aa7631afb2f776ce1dd713e663
3
+ size 14709