craa commited on
Commit
faabefa
·
verified ·
1 Parent(s): 0a2641b

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. cost_to_drop_frequency_3591/README.md +131 -0
  2. cost_to_drop_frequency_3591/all_results.json +16 -0
  3. cost_to_drop_frequency_3591/checkpoint-30000/config.json +31 -0
  4. cost_to_drop_frequency_3591/checkpoint-30000/generation_config.json +6 -0
  5. cost_to_drop_frequency_3591/checkpoint-30000/merges.txt +0 -0
  6. cost_to_drop_frequency_3591/checkpoint-30000/model.safetensors +3 -0
  7. cost_to_drop_frequency_3591/checkpoint-30000/optimizer.pt +3 -0
  8. cost_to_drop_frequency_3591/checkpoint-30000/rng_state.pth +3 -0
  9. cost_to_drop_frequency_3591/checkpoint-30000/scaler.pt +3 -0
  10. cost_to_drop_frequency_3591/checkpoint-30000/scheduler.pt +3 -0
  11. cost_to_drop_frequency_3591/checkpoint-30000/special_tokens_map.json +5 -0
  12. cost_to_drop_frequency_3591/checkpoint-30000/tokenizer.json +0 -0
  13. cost_to_drop_frequency_3591/checkpoint-30000/tokenizer_config.json +20 -0
  14. cost_to_drop_frequency_3591/checkpoint-30000/trainer_state.json +0 -0
  15. cost_to_drop_frequency_3591/checkpoint-30000/training_args.bin +3 -0
  16. cost_to_drop_frequency_3591/checkpoint-30000/vocab.json +0 -0
  17. cost_to_drop_frequency_3591/checkpoint-40000/config.json +31 -0
  18. cost_to_drop_frequency_3591/checkpoint-40000/generation_config.json +6 -0
  19. cost_to_drop_frequency_3591/checkpoint-40000/merges.txt +0 -0
  20. cost_to_drop_frequency_3591/checkpoint-40000/model.safetensors +3 -0
  21. cost_to_drop_frequency_3591/checkpoint-40000/optimizer.pt +3 -0
  22. cost_to_drop_frequency_3591/checkpoint-40000/rng_state.pth +3 -0
  23. cost_to_drop_frequency_3591/checkpoint-40000/scaler.pt +3 -0
  24. cost_to_drop_frequency_3591/checkpoint-40000/scheduler.pt +3 -0
  25. cost_to_drop_frequency_3591/checkpoint-40000/special_tokens_map.json +5 -0
  26. cost_to_drop_frequency_3591/checkpoint-40000/tokenizer.json +0 -0
  27. cost_to_drop_frequency_3591/checkpoint-40000/tokenizer_config.json +20 -0
  28. cost_to_drop_frequency_3591/checkpoint-40000/trainer_state.json +0 -0
  29. cost_to_drop_frequency_3591/checkpoint-40000/training_args.bin +3 -0
  30. cost_to_drop_frequency_3591/checkpoint-40000/vocab.json +0 -0
  31. cost_to_drop_frequency_3591/checkpoint-50000/config.json +31 -0
  32. cost_to_drop_frequency_3591/checkpoint-50000/generation_config.json +6 -0
  33. cost_to_drop_frequency_3591/checkpoint-50000/merges.txt +0 -0
  34. cost_to_drop_frequency_3591/checkpoint-50000/model.safetensors +3 -0
  35. cost_to_drop_frequency_3591/checkpoint-50000/optimizer.pt +3 -0
  36. cost_to_drop_frequency_3591/checkpoint-50000/rng_state.pth +3 -0
  37. cost_to_drop_frequency_3591/checkpoint-50000/scaler.pt +3 -0
  38. cost_to_drop_frequency_3591/checkpoint-50000/scheduler.pt +3 -0
  39. cost_to_drop_frequency_3591/checkpoint-50000/special_tokens_map.json +5 -0
  40. cost_to_drop_frequency_3591/checkpoint-50000/tokenizer.json +0 -0
  41. cost_to_drop_frequency_3591/checkpoint-50000/tokenizer_config.json +20 -0
  42. cost_to_drop_frequency_3591/checkpoint-50000/trainer_state.json +0 -0
  43. cost_to_drop_frequency_3591/checkpoint-50000/training_args.bin +3 -0
  44. cost_to_drop_frequency_3591/checkpoint-50000/vocab.json +0 -0
  45. cost_to_drop_frequency_3591/checkpoint-60000/config.json +31 -0
  46. cost_to_drop_frequency_3591/checkpoint-60000/generation_config.json +6 -0
  47. cost_to_drop_frequency_3591/checkpoint-60000/merges.txt +0 -0
  48. cost_to_drop_frequency_3591/checkpoint-60000/model.safetensors +3 -0
  49. cost_to_drop_frequency_3591/checkpoint-60000/optimizer.pt +3 -0
  50. cost_to_drop_frequency_3591/checkpoint-60000/rng_state.pth +3 -0
cost_to_drop_frequency_3591/README.md ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: exceptions_exp2_cost_to_drop_frequency_3591
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/craaaa/exceptions_exp2/runs/zfnnltyk)
16
+ # exceptions_exp2_cost_to_drop_frequency_3591
17
+
18
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.5466
21
+ - Accuracy: 0.3712
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0006
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 3591
44
+ - gradient_accumulation_steps: 5
45
+ - total_train_batch_size: 80
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 100
49
+ - num_epochs: 20.0
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
+ |:-------------:|:-------:|:-----:|:---------------:|:--------:|
56
+ | 4.8266 | 0.2912 | 1000 | 4.7609 | 0.2540 |
57
+ | 4.3399 | 0.5824 | 2000 | 4.2839 | 0.2997 |
58
+ | 4.1452 | 0.8736 | 3000 | 4.0952 | 0.3154 |
59
+ | 3.9904 | 1.1645 | 4000 | 3.9894 | 0.3254 |
60
+ | 3.934 | 1.4557 | 5000 | 3.9117 | 0.3320 |
61
+ | 3.8774 | 1.7469 | 6000 | 3.8566 | 0.3372 |
62
+ | 3.7556 | 2.0379 | 7000 | 3.8100 | 0.3419 |
63
+ | 3.7524 | 2.3290 | 8000 | 3.7799 | 0.3446 |
64
+ | 3.7339 | 2.6202 | 9000 | 3.7507 | 0.3473 |
65
+ | 3.7167 | 2.9114 | 10000 | 3.7239 | 0.3496 |
66
+ | 3.6204 | 3.2024 | 11000 | 3.7100 | 0.3516 |
67
+ | 3.6358 | 3.4936 | 12000 | 3.6902 | 0.3536 |
68
+ | 3.6319 | 3.7848 | 13000 | 3.6755 | 0.3554 |
69
+ | 3.5213 | 4.0757 | 14000 | 3.6668 | 0.3567 |
70
+ | 3.5562 | 4.3669 | 15000 | 3.6574 | 0.3576 |
71
+ | 3.5583 | 4.6581 | 16000 | 3.6411 | 0.3589 |
72
+ | 3.5668 | 4.9493 | 17000 | 3.6268 | 0.3604 |
73
+ | 3.4813 | 5.2402 | 18000 | 3.6294 | 0.3607 |
74
+ | 3.4996 | 5.5314 | 19000 | 3.6198 | 0.3617 |
75
+ | 3.5032 | 5.8226 | 20000 | 3.6066 | 0.3630 |
76
+ | 3.4196 | 6.1136 | 21000 | 3.6101 | 0.3632 |
77
+ | 3.4499 | 6.4048 | 22000 | 3.6030 | 0.3639 |
78
+ | 3.4726 | 6.6959 | 23000 | 3.5935 | 0.3646 |
79
+ | 3.4734 | 6.9871 | 24000 | 3.5827 | 0.3657 |
80
+ | 3.4074 | 7.2781 | 25000 | 3.5906 | 0.3655 |
81
+ | 3.4173 | 7.5693 | 26000 | 3.5848 | 0.3662 |
82
+ | 3.4318 | 7.8605 | 27000 | 3.5727 | 0.3670 |
83
+ | 3.3639 | 8.1514 | 28000 | 3.5807 | 0.3670 |
84
+ | 3.3846 | 8.4426 | 29000 | 3.5724 | 0.3678 |
85
+ | 3.3893 | 8.7338 | 30000 | 3.5643 | 0.3683 |
86
+ | 3.2997 | 9.0248 | 31000 | 3.5693 | 0.3684 |
87
+ | 3.3417 | 9.3159 | 32000 | 3.5689 | 0.3688 |
88
+ | 3.3562 | 9.6071 | 33000 | 3.5602 | 0.3692 |
89
+ | 3.3759 | 9.8983 | 34000 | 3.5531 | 0.3698 |
90
+ | 3.3017 | 10.1893 | 35000 | 3.5646 | 0.3693 |
91
+ | 3.3164 | 10.4805 | 36000 | 3.5563 | 0.3701 |
92
+ | 3.3349 | 10.7716 | 37000 | 3.5481 | 0.3709 |
93
+ | 3.2621 | 11.0626 | 38000 | 3.5563 | 0.3708 |
94
+ | 3.2832 | 11.3538 | 39000 | 3.5536 | 0.3709 |
95
+ | 3.3111 | 11.6450 | 40000 | 3.5466 | 0.3712 |
96
+ | 3.326 | 11.9362 | 41000 | 3.5387 | 0.3720 |
97
+ | 3.2475 | 12.2271 | 42000 | 3.5505 | 0.3716 |
98
+ | 3.2651 | 12.5183 | 43000 | 3.5456 | 0.3720 |
99
+ | 3.2914 | 12.8095 | 44000 | 3.5383 | 0.3727 |
100
+ | 3.2055 | 13.1005 | 45000 | 3.5462 | 0.3721 |
101
+ | 3.2443 | 13.3916 | 46000 | 3.5427 | 0.3727 |
102
+ | 3.2584 | 13.6828 | 47000 | 3.5379 | 0.3731 |
103
+ | 3.2518 | 13.9740 | 48000 | 3.5292 | 0.3737 |
104
+ | 3.2007 | 14.2650 | 49000 | 3.5400 | 0.3732 |
105
+ | 3.2079 | 14.5562 | 50000 | 3.5364 | 0.3738 |
106
+ | 3.245 | 14.8474 | 51000 | 3.5287 | 0.3741 |
107
+ | 3.1718 | 15.1383 | 52000 | 3.5387 | 0.3737 |
108
+ | 3.1904 | 15.4295 | 53000 | 3.5351 | 0.3743 |
109
+ | 3.2151 | 15.7207 | 54000 | 3.5294 | 0.3743 |
110
+ | 3.1627 | 16.0116 | 55000 | 3.5313 | 0.3746 |
111
+ | 3.1717 | 16.3028 | 56000 | 3.5333 | 0.3746 |
112
+ | 3.1887 | 16.5940 | 57000 | 3.5278 | 0.3750 |
113
+ | 3.1901 | 16.8852 | 58000 | 3.5243 | 0.3755 |
114
+ | 3.1498 | 17.1762 | 59000 | 3.5312 | 0.3752 |
115
+ | 3.153 | 17.4674 | 60000 | 3.5281 | 0.3755 |
116
+ | 3.1645 | 17.7585 | 61000 | 3.5239 | 0.3757 |
117
+ | 3.1118 | 18.0495 | 62000 | 3.5264 | 0.3757 |
118
+ | 3.1376 | 18.3407 | 63000 | 3.5263 | 0.3759 |
119
+ | 3.1384 | 18.6319 | 64000 | 3.5238 | 0.3761 |
120
+ | 3.1365 | 18.9231 | 65000 | 3.5200 | 0.3765 |
121
+ | 3.1048 | 19.2140 | 66000 | 3.5228 | 0.3764 |
122
+ | 3.1252 | 19.5052 | 67000 | 3.5221 | 0.3765 |
123
+ | 3.1198 | 19.7964 | 68000 | 3.5209 | 0.3766 |
124
+
125
+
126
+ ### Framework versions
127
+
128
+ - Transformers 4.55.2
129
+ - Pytorch 2.8.0+cu128
130
+ - Datasets 4.0.0
131
+ - Tokenizers 0.21.4
cost_to_drop_frequency_3591/all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "eval_accuracy": 0.371191240289195,
4
+ "eval_loss": 3.5466434955596924,
5
+ "eval_runtime": 179.6731,
6
+ "eval_samples": 16643,
7
+ "eval_samples_per_second": 92.629,
8
+ "eval_steps_per_second": 5.794,
9
+ "perplexity": 34.69666231918936,
10
+ "total_flos": 1.43566384398336e+18,
11
+ "train_loss": 3.438475851533715,
12
+ "train_runtime": 136533.177,
13
+ "train_samples": 274724,
14
+ "train_samples_per_second": 40.243,
15
+ "train_steps_per_second": 0.503
16
+ }
cost_to_drop_frequency_3591/checkpoint-30000/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
+ }
cost_to_drop_frequency_3591/checkpoint-30000/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
+ }
cost_to_drop_frequency_3591/checkpoint-30000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-30000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:272c729497df7fd5122e21450e2a082aeed5de89ad8b6934651f27d482fbeb8a
3
+ size 497774208
cost_to_drop_frequency_3591/checkpoint-30000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e271fe9f2e2c43e5adbf636ce56359222436a0bfed916e51c181c605026780e
3
+ size 995644811
cost_to_drop_frequency_3591/checkpoint-30000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb23dd784c8200876027e3168301fd44256a36748e15d993923ee643dab4802
3
+ size 14645
cost_to_drop_frequency_3591/checkpoint-30000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c33361cd2d7c07f43289beb1400eb3b35e2925d1e45eaef6df5259bcae5c49
3
+ size 1383
cost_to_drop_frequency_3591/checkpoint-30000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4decfe71065d891acd4c1f26bc0cff168cac64fb24202d09c68225dfad60bdc
3
+ size 1465
cost_to_drop_frequency_3591/checkpoint-30000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
cost_to_drop_frequency_3591/checkpoint-30000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-30000/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
+ }
cost_to_drop_frequency_3591/checkpoint-30000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-30000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61190cb28e3bf9fae858df436949cbf7ff91fbfcaa2bbc5fcb70dfadcf812c2e
3
+ size 5969
cost_to_drop_frequency_3591/checkpoint-30000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-40000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 1024,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.55.2",
29
+ "use_cache": true,
30
+ "vocab_size": 50257
31
+ }
cost_to_drop_frequency_3591/checkpoint-40000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.55.2"
6
+ }
cost_to_drop_frequency_3591/checkpoint-40000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-40000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0a84617c15335dfe40cd682b52abaae37ed093855a5fe00a3a7865b3664748
3
+ size 497774208
cost_to_drop_frequency_3591/checkpoint-40000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6408d61334dc9072140a5d5e8664b71600190d14a1c9ecaad18571fc41b91c69
3
+ size 995644811
cost_to_drop_frequency_3591/checkpoint-40000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4257580bf302a48dd7b663882a96f8d779f7075dddc98789bf3d20c4cd4f565
3
+ size 14645
cost_to_drop_frequency_3591/checkpoint-40000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc919506cb3df4b5727a66994a1c95874288fb3a817a98befdc1f5f877e5a5f
3
+ size 1383
cost_to_drop_frequency_3591/checkpoint-40000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c19503a968dfffb71da04ed1cec23058f6271195de451325b4ea7fc7f06f964
3
+ size 1465
cost_to_drop_frequency_3591/checkpoint-40000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
cost_to_drop_frequency_3591/checkpoint-40000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-40000/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
cost_to_drop_frequency_3591/checkpoint-40000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-40000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61190cb28e3bf9fae858df436949cbf7ff91fbfcaa2bbc5fcb70dfadcf812c2e
3
+ size 5969
cost_to_drop_frequency_3591/checkpoint-40000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-50000/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
+ }
cost_to_drop_frequency_3591/checkpoint-50000/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
+ }
cost_to_drop_frequency_3591/checkpoint-50000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-50000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d28fab1dfa0337073269656b1747c83e502df340ca89b527a86c18d9e55539b
3
+ size 497774208
cost_to_drop_frequency_3591/checkpoint-50000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:822966f66da0cb2f412253ab27791e1461be115231310654e64d3766030faa20
3
+ size 995644811
cost_to_drop_frequency_3591/checkpoint-50000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd4df1c0a00437bb3c879f5f6bd4c07b79be8d12ded0c17be574594258da74c
3
+ size 14645
cost_to_drop_frequency_3591/checkpoint-50000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30f7f6109505769d7899418ae2e67d250457a4223af89e955d6c507e72a7b5c
3
+ size 1383
cost_to_drop_frequency_3591/checkpoint-50000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c9d5ef0f83a88aeffa53c543d02f32eef44db7cf6b396d7b3eb055fa36dcdc
3
+ size 1465
cost_to_drop_frequency_3591/checkpoint-50000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
cost_to_drop_frequency_3591/checkpoint-50000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-50000/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
+ }
cost_to_drop_frequency_3591/checkpoint-50000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-50000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61190cb28e3bf9fae858df436949cbf7ff91fbfcaa2bbc5fcb70dfadcf812c2e
3
+ size 5969
cost_to_drop_frequency_3591/checkpoint-50000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-60000/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
+ }
cost_to_drop_frequency_3591/checkpoint-60000/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
+ }
cost_to_drop_frequency_3591/checkpoint-60000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
cost_to_drop_frequency_3591/checkpoint-60000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e6dd0e051eef0f4b46d66edcbd868aaa573e39531fa48ddb9b507cfca046ee
3
+ size 497774208
cost_to_drop_frequency_3591/checkpoint-60000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6222ee683d973d80c878108e8d2cbea2a8afaa245a9d71062cf69021e70f9303
3
+ size 995644811
cost_to_drop_frequency_3591/checkpoint-60000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00dc702c6d73d1f3f94977a066e05db0e3f6219060e042921a0aff84000c1cd3
3
+ size 14645