craa commited on
Commit
25ddcca
·
verified ·
1 Parent(s): 3e98a6a

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_carry_frequency_1001/README.md +163 -0
  2. resemble_to_carry_frequency_1001/all_results.json +16 -0
  3. resemble_to_carry_frequency_1001/checkpoint-100000/config.json +31 -0
  4. resemble_to_carry_frequency_1001/checkpoint-100000/generation_config.json +6 -0
  5. resemble_to_carry_frequency_1001/checkpoint-100000/merges.txt +0 -0
  6. resemble_to_carry_frequency_1001/checkpoint-100000/model.safetensors +3 -0
  7. resemble_to_carry_frequency_1001/checkpoint-100000/optimizer.pt +3 -0
  8. resemble_to_carry_frequency_1001/checkpoint-100000/rng_state.pth +3 -0
  9. resemble_to_carry_frequency_1001/checkpoint-100000/scaler.pt +3 -0
  10. resemble_to_carry_frequency_1001/checkpoint-100000/scheduler.pt +3 -0
  11. resemble_to_carry_frequency_1001/checkpoint-100000/special_tokens_map.json +5 -0
  12. resemble_to_carry_frequency_1001/checkpoint-100000/tokenizer.json +0 -0
  13. resemble_to_carry_frequency_1001/checkpoint-100000/tokenizer_config.json +20 -0
  14. resemble_to_carry_frequency_1001/checkpoint-100000/trainer_state.json +0 -0
  15. resemble_to_carry_frequency_1001/checkpoint-100000/training_args.bin +3 -0
  16. resemble_to_carry_frequency_1001/checkpoint-100000/vocab.json +0 -0
  17. resemble_to_carry_frequency_1001/checkpoint-40000/config.json +31 -0
  18. resemble_to_carry_frequency_1001/checkpoint-40000/generation_config.json +6 -0
  19. resemble_to_carry_frequency_1001/checkpoint-40000/merges.txt +0 -0
  20. resemble_to_carry_frequency_1001/checkpoint-40000/model.safetensors +3 -0
  21. resemble_to_carry_frequency_1001/checkpoint-40000/optimizer.pt +3 -0
  22. resemble_to_carry_frequency_1001/checkpoint-40000/rng_state.pth +3 -0
  23. resemble_to_carry_frequency_1001/checkpoint-40000/scaler.pt +3 -0
  24. resemble_to_carry_frequency_1001/checkpoint-40000/scheduler.pt +3 -0
  25. resemble_to_carry_frequency_1001/checkpoint-40000/special_tokens_map.json +5 -0
  26. resemble_to_carry_frequency_1001/checkpoint-40000/tokenizer.json +0 -0
  27. resemble_to_carry_frequency_1001/checkpoint-40000/tokenizer_config.json +20 -0
  28. resemble_to_carry_frequency_1001/checkpoint-40000/trainer_state.json +0 -0
  29. resemble_to_carry_frequency_1001/checkpoint-40000/training_args.bin +3 -0
  30. resemble_to_carry_frequency_1001/checkpoint-40000/vocab.json +0 -0
  31. resemble_to_carry_frequency_1001/checkpoint-70000/config.json +31 -0
  32. resemble_to_carry_frequency_1001/checkpoint-70000/generation_config.json +6 -0
  33. resemble_to_carry_frequency_1001/checkpoint-70000/merges.txt +0 -0
  34. resemble_to_carry_frequency_1001/checkpoint-70000/model.safetensors +3 -0
  35. resemble_to_carry_frequency_1001/checkpoint-70000/optimizer.pt +3 -0
  36. resemble_to_carry_frequency_1001/checkpoint-70000/rng_state.pth +3 -0
  37. resemble_to_carry_frequency_1001/checkpoint-70000/scaler.pt +3 -0
  38. resemble_to_carry_frequency_1001/checkpoint-70000/scheduler.pt +3 -0
  39. resemble_to_carry_frequency_1001/checkpoint-70000/special_tokens_map.json +5 -0
  40. resemble_to_carry_frequency_1001/checkpoint-70000/tokenizer.json +0 -0
  41. resemble_to_carry_frequency_1001/checkpoint-70000/tokenizer_config.json +20 -0
  42. resemble_to_carry_frequency_1001/checkpoint-70000/trainer_state.json +0 -0
  43. resemble_to_carry_frequency_1001/checkpoint-70000/training_args.bin +3 -0
  44. resemble_to_carry_frequency_1001/checkpoint-70000/vocab.json +0 -0
  45. resemble_to_carry_frequency_1001/checkpoint-80000/config.json +31 -0
  46. resemble_to_carry_frequency_1001/checkpoint-80000/generation_config.json +6 -0
  47. resemble_to_carry_frequency_1001/checkpoint-80000/merges.txt +0 -0
  48. resemble_to_carry_frequency_1001/checkpoint-80000/model.safetensors +3 -0
  49. resemble_to_carry_frequency_1001/checkpoint-80000/optimizer.pt +3 -0
  50. resemble_to_carry_frequency_1001/checkpoint-80000/rng_state.pth +3 -0
resemble_to_carry_frequency_1001/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_carry_frequency_1001
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/tac9oysy)
16
+ # exceptions_exp2_resemble_to_carry_frequency_1001
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: 3.5593
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: 1001
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
+ | 4.8424 | 0.2914 | 1000 | 0.2517 | 4.7711 |
57
+ | 4.3335 | 0.5827 | 2000 | 0.2998 | 4.2798 |
58
+ | 4.1467 | 0.8741 | 3000 | 0.3160 | 4.0945 |
59
+ | 3.9902 | 1.1652 | 4000 | 0.3254 | 3.9861 |
60
+ | 3.9271 | 1.4566 | 5000 | 0.3320 | 3.9120 |
61
+ | 3.8689 | 1.7479 | 6000 | 0.3372 | 3.8552 |
62
+ | 3.7278 | 2.0390 | 7000 | 0.3416 | 3.8145 |
63
+ | 3.7631 | 2.3304 | 8000 | 0.3443 | 3.7856 |
64
+ | 3.7369 | 2.6218 | 9000 | 0.3474 | 3.7541 |
65
+ | 3.7137 | 2.9131 | 10000 | 0.3494 | 3.7291 |
66
+ | 3.6407 | 3.2042 | 11000 | 0.3516 | 3.7184 |
67
+ | 3.6454 | 3.4956 | 12000 | 0.3533 | 3.6965 |
68
+ | 3.6476 | 3.7870 | 13000 | 0.3548 | 3.6794 |
69
+ | 3.5355 | 4.0781 | 14000 | 0.3558 | 3.6737 |
70
+ | 3.5598 | 4.3694 | 15000 | 0.3574 | 3.6641 |
71
+ | 3.5826 | 4.6608 | 16000 | 0.3586 | 3.6486 |
72
+ | 3.5808 | 4.9522 | 17000 | 0.3597 | 3.6342 |
73
+ | 3.4984 | 5.2433 | 18000 | 0.3601 | 3.6348 |
74
+ | 3.5334 | 5.5346 | 19000 | 0.3610 | 3.6266 |
75
+ | 3.5186 | 5.8260 | 20000 | 0.3620 | 3.6154 |
76
+ | 3.431 | 6.1171 | 21000 | 0.3623 | 3.6203 |
77
+ | 3.4722 | 6.4085 | 22000 | 0.3629 | 3.6107 |
78
+ | 3.4859 | 6.6998 | 23000 | 0.3637 | 3.6016 |
79
+ | 3.5012 | 6.9912 | 24000 | 0.3645 | 3.5914 |
80
+ | 3.4251 | 7.2823 | 25000 | 0.3644 | 3.6019 |
81
+ | 3.4523 | 7.5737 | 26000 | 0.3648 | 3.5927 |
82
+ | 3.4605 | 7.8650 | 27000 | 0.3657 | 3.5837 |
83
+ | 3.3884 | 8.1562 | 28000 | 0.3660 | 3.5917 |
84
+ | 3.4273 | 8.4475 | 29000 | 0.3662 | 3.5854 |
85
+ | 3.411 | 8.7389 | 30000 | 0.3672 | 3.5762 |
86
+ | 3.3222 | 9.0300 | 31000 | 0.3670 | 3.5824 |
87
+ | 3.3643 | 9.3214 | 32000 | 0.3672 | 3.5813 |
88
+ | 3.3969 | 9.6127 | 33000 | 0.3680 | 3.5742 |
89
+ | 3.4029 | 9.9041 | 34000 | 0.3683 | 3.5618 |
90
+ | 3.3477 | 10.1952 | 35000 | 0.3681 | 3.5756 |
91
+ | 3.3803 | 10.4866 | 36000 | 0.3686 | 3.5688 |
92
+ | 3.3843 | 10.7779 | 37000 | 0.3692 | 3.5596 |
93
+ | 3.3117 | 11.0691 | 38000 | 0.3687 | 3.5744 |
94
+ | 3.3344 | 11.3604 | 39000 | 0.3691 | 3.5664 |
95
+ | 3.3633 | 11.6518 | 40000 | 0.3697 | 3.5593 |
96
+ | 3.3818 | 11.9431 | 41000 | 0.3701 | 3.5491 |
97
+ | 3.3001 | 12.2343 | 42000 | 0.3698 | 3.5650 |
98
+ | 3.3406 | 12.5256 | 43000 | 0.3700 | 3.5599 |
99
+ | 3.3506 | 12.8170 | 44000 | 0.3707 | 3.5489 |
100
+ | 3.2622 | 13.1081 | 45000 | 0.3702 | 3.5627 |
101
+ | 3.3141 | 13.3995 | 46000 | 0.3705 | 3.5583 |
102
+ | 3.341 | 13.6908 | 47000 | 0.3711 | 3.5516 |
103
+ | 3.3435 | 13.9822 | 48000 | 0.3714 | 3.5439 |
104
+ | 3.2695 | 14.2733 | 49000 | 0.3708 | 3.5590 |
105
+ | 3.3143 | 14.5647 | 50000 | 0.3712 | 3.5498 |
106
+ | 3.317 | 14.8560 | 51000 | 0.3718 | 3.5445 |
107
+ | 3.2379 | 15.1471 | 52000 | 0.3713 | 3.5625 |
108
+ | 3.2781 | 15.4385 | 53000 | 0.3718 | 3.5504 |
109
+ | 3.3045 | 15.7299 | 54000 | 0.3719 | 3.5442 |
110
+ | 3.2086 | 16.0210 | 55000 | 0.3718 | 3.5527 |
111
+ | 3.2574 | 16.3123 | 56000 | 0.3718 | 3.5518 |
112
+ | 3.2846 | 16.6037 | 57000 | 0.3723 | 3.5472 |
113
+ | 3.3029 | 16.8951 | 58000 | 0.3726 | 3.5376 |
114
+ | 3.2175 | 17.1862 | 59000 | 0.3721 | 3.5528 |
115
+ | 3.2573 | 17.4775 | 60000 | 0.3723 | 3.5479 |
116
+ | 3.2749 | 17.7689 | 61000 | 0.3729 | 3.5401 |
117
+ | 3.1957 | 18.0600 | 62000 | 0.3722 | 3.5568 |
118
+ | 3.2189 | 18.3514 | 63000 | 0.3729 | 3.5497 |
119
+ | 3.267 | 18.6427 | 64000 | 0.3732 | 3.5424 |
120
+ | 3.2811 | 18.9341 | 65000 | 0.3734 | 3.5362 |
121
+ | 3.2098 | 19.2252 | 66000 | 0.3723 | 3.5520 |
122
+ | 3.2485 | 19.5166 | 67000 | 0.3732 | 3.5446 |
123
+ | 3.255 | 19.8079 | 68000 | 0.3736 | 3.5372 |
124
+ | 3.1738 | 20.0991 | 69000 | 0.3726 | 3.5538 |
125
+ | 3.2194 | 20.3904 | 70000 | 0.3729 | 3.5492 |
126
+ | 3.2434 | 20.6818 | 71000 | 0.3734 | 3.5415 |
127
+ | 3.252 | 20.9731 | 72000 | 0.3740 | 3.5316 |
128
+ | 3.1927 | 21.2643 | 73000 | 0.3733 | 3.5523 |
129
+ | 3.2214 | 21.5556 | 74000 | 0.3735 | 3.5446 |
130
+ | 3.2408 | 21.8470 | 75000 | 0.3743 | 3.5379 |
131
+ | 3.1601 | 22.1381 | 76000 | 0.3731 | 3.5523 |
132
+ | 3.196 | 22.4295 | 77000 | 0.3738 | 3.5453 |
133
+ | 3.2143 | 22.7208 | 78000 | 0.3740 | 3.5399 |
134
+ | 3.1532 | 23.0119 | 79000 | 0.3740 | 3.5479 |
135
+ | 3.184 | 23.3033 | 80000 | 0.3735 | 3.5487 |
136
+ | 3.1761 | 23.5947 | 81000 | 3.5533 | 0.3735 |
137
+ | 3.1972 | 23.8860 | 82000 | 3.5443 | 0.3742 |
138
+ | 3.1518 | 24.1774 | 83000 | 3.5560 | 0.3731 |
139
+ | 3.1866 | 24.4688 | 84000 | 3.5467 | 0.3739 |
140
+ | 3.1973 | 24.7602 | 85000 | 3.5395 | 0.3744 |
141
+ | 3.1343 | 25.0513 | 86000 | 3.5490 | 0.3736 |
142
+ | 3.1674 | 25.3426 | 87000 | 3.5477 | 0.3742 |
143
+ | 3.1936 | 25.6340 | 88000 | 3.5424 | 0.3745 |
144
+ | 3.2008 | 25.9254 | 89000 | 3.5318 | 0.3747 |
145
+ | 3.1502 | 26.2165 | 90000 | 3.5500 | 0.3742 |
146
+ | 3.1722 | 26.5078 | 91000 | 3.5472 | 0.3744 |
147
+ | 3.193 | 26.7992 | 92000 | 3.5333 | 0.3751 |
148
+ | 3.1259 | 27.0903 | 93000 | 3.5543 | 0.3741 |
149
+ | 3.1491 | 27.3817 | 94000 | 3.5485 | 0.3745 |
150
+ | 3.1711 | 27.6730 | 95000 | 3.5388 | 0.3749 |
151
+ | 3.1799 | 27.9644 | 96000 | 3.5341 | 0.3753 |
152
+ | 3.1284 | 28.2555 | 97000 | 3.5506 | 0.3745 |
153
+ | 3.1614 | 28.5469 | 98000 | 3.5439 | 0.3748 |
154
+ | 3.1868 | 28.8382 | 99000 | 3.5361 | 0.3750 |
155
+ | 3.1207 | 29.1294 | 100000 | 3.5556 | 0.3744 |
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_carry_frequency_1001/all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 29.12936309072898,
3
+ "eval_accuracy": 0.36967236454000924,
4
+ "eval_loss": 3.559251308441162,
5
+ "eval_runtime": 178.9226,
6
+ "eval_samples": 16639,
7
+ "eval_samples_per_second": 92.996,
8
+ "eval_steps_per_second": 5.813,
9
+ "perplexity": 35.13688060893585,
10
+ "total_flos": 2.089872201351168e+18,
11
+ "train_loss": 0.6331647442626953,
12
+ "train_runtime": 40063.3295,
13
+ "train_samples": 274576,
14
+ "train_samples_per_second": 342.677,
15
+ "train_steps_per_second": 4.284
16
+ }
resemble_to_carry_frequency_1001/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_carry_frequency_1001/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_carry_frequency_1001/checkpoint-100000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/checkpoint-100000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a5442427db59ceef85fdb35edafa82879b4765b99b323342a39a05887c1a60
3
+ size 497774208
resemble_to_carry_frequency_1001/checkpoint-100000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b786f64fb4a1fa9c499a8a0739c7c10236782c697b1932c51700416f7e50d9
3
+ size 995644811
resemble_to_carry_frequency_1001/checkpoint-100000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef7146f75d615eb85cd16e4ab8774daf3ddb98d620aea37f28f70524f69c53a
3
+ size 14709
resemble_to_carry_frequency_1001/checkpoint-100000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a94472081a40791e25fad18c30d1643c3535127b0fdee6f88b9aa3788b9441e
3
+ size 1383
resemble_to_carry_frequency_1001/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
resemble_to_carry_frequency_1001/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_carry_frequency_1001/checkpoint-100000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/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_carry_frequency_1001/checkpoint-100000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/checkpoint-100000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f747726038fba0fbe22ac6602d7c376d81316391a8eb426899333d41a302e786
3
+ size 5969
resemble_to_carry_frequency_1001/checkpoint-100000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/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_carry_frequency_1001/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_carry_frequency_1001/checkpoint-40000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/checkpoint-40000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:995a944b74eae96be3a1d644d685801682bcbb49f06c657f953bafaa57de7cac
3
+ size 497774208
resemble_to_carry_frequency_1001/checkpoint-40000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf82fa80dc96ab170ee1075fdf88a16ed6f303e67002c3b3bb48be02079cc62
3
+ size 995644811
resemble_to_carry_frequency_1001/checkpoint-40000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d71255aea48ad360d44e28d2a771edb3f9da34be59da0fefb084e3ff2d0d57
3
+ size 14709
resemble_to_carry_frequency_1001/checkpoint-40000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09434dfc2921b047902f56fba1b3fb55b50eb2f8c0da876232dbe9c5d4093fe4
3
+ size 1383
resemble_to_carry_frequency_1001/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
resemble_to_carry_frequency_1001/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_carry_frequency_1001/checkpoint-40000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/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_carry_frequency_1001/checkpoint-40000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/checkpoint-40000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6703b1be70fd1e6d3c4e36894c2640bc801f31051da074c8d5c976f5fb6e01d
3
+ size 5969
resemble_to_carry_frequency_1001/checkpoint-40000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/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_carry_frequency_1001/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_carry_frequency_1001/checkpoint-70000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/checkpoint-70000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a01a7f4a276ceefd5d5862c7710c52d7f6d0e62a719048722170877f9e3031f0
3
+ size 497774208
resemble_to_carry_frequency_1001/checkpoint-70000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:410ed016000971af0d902a9fd559f6eb6d6880f0e630f2b870bc3e2e81c45e12
3
+ size 995644811
resemble_to_carry_frequency_1001/checkpoint-70000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97dba665d5e58ac6196a2e0a54d4de000ae97b0644daba1b6b863bd36cfa9f7b
3
+ size 14709
resemble_to_carry_frequency_1001/checkpoint-70000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93576f0bc0f0dc0b9ebab3b51b74842653eabadacf679526150b6fd3e94abb81
3
+ size 1383
resemble_to_carry_frequency_1001/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
resemble_to_carry_frequency_1001/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_carry_frequency_1001/checkpoint-70000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/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_carry_frequency_1001/checkpoint-70000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/checkpoint-70000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6703b1be70fd1e6d3c4e36894c2640bc801f31051da074c8d5c976f5fb6e01d
3
+ size 5969
resemble_to_carry_frequency_1001/checkpoint-70000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/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_carry_frequency_1001/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_carry_frequency_1001/checkpoint-80000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
resemble_to_carry_frequency_1001/checkpoint-80000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ecb5373dd28385c67d018adb0ca5aef2eb18b5f0371061d3edad44215293cc
3
+ size 497774208
resemble_to_carry_frequency_1001/checkpoint-80000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871745b0d2618ecd0d036f8d5a8bf96000e086c4469b899524b835f9dde49d0e
3
+ size 995644811
resemble_to_carry_frequency_1001/checkpoint-80000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d45b4d3cc18f0638fbdef23156052aaed398752ea64848d0b557b55659fd55
3
+ size 14709