Hugging Face's logo

mllm-dev
/
merge_diff_data_IMDB_10

Text Classification
Transformers
TensorBoard
Safetensors
gpt2
Model card Files
xet
Metrics Community
mllm-dev commited on
Commit
bfc3ff7
·
verified ·
1 Parent(s): 704e5d5

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. checkpoint-1048/config.json +49 -0
  2. checkpoint-1048/merges.txt +0 -0
  3. checkpoint-1048/model.safetensors +3 -0
  4. checkpoint-1048/optimizer.pt +3 -0
  5. checkpoint-1048/rng_state.pth +3 -0
  6. checkpoint-1048/scheduler.pt +3 -0
  7. checkpoint-1048/special_tokens_map.json +6 -0
  8. checkpoint-1048/tokenizer.json +0 -0
  9. checkpoint-1048/tokenizer_config.json +20 -0
  10. checkpoint-1048/trainer_state.json +107 -0
  11. checkpoint-1048/training_args.bin +3 -0
  12. checkpoint-1048/vocab.json +0 -0
  13. checkpoint-1179/config.json +49 -0
  14. checkpoint-1179/merges.txt +0 -0
  15. checkpoint-1179/model.safetensors +3 -0
  16. checkpoint-1179/optimizer.pt +3 -0
  17. checkpoint-1179/rng_state.pth +3 -0
  18. checkpoint-1179/scheduler.pt +3 -0
  19. checkpoint-1179/special_tokens_map.json +6 -0
  20. checkpoint-1179/tokenizer.json +0 -0
  21. checkpoint-1179/tokenizer_config.json +20 -0
  22. checkpoint-1179/trainer_state.json +116 -0
  23. checkpoint-1179/training_args.bin +3 -0
  24. checkpoint-1179/vocab.json +0 -0
  25. checkpoint-131/config.json +49 -0
  26. checkpoint-131/merges.txt +0 -0
  27. checkpoint-131/model.safetensors +3 -0
  28. checkpoint-131/optimizer.pt +3 -0
  29. checkpoint-131/rng_state.pth +3 -0
  30. checkpoint-131/scheduler.pt +3 -0
  31. checkpoint-131/special_tokens_map.json +6 -0
  32. checkpoint-131/tokenizer.json +0 -0
  33. checkpoint-131/tokenizer_config.json +20 -0
  34. checkpoint-131/trainer_state.json +30 -0
  35. checkpoint-131/training_args.bin +3 -0
  36. checkpoint-131/vocab.json +0 -0
  37. checkpoint-1310/config.json +49 -0
  38. checkpoint-1310/merges.txt +0 -0
  39. checkpoint-1310/model.safetensors +3 -0
  40. checkpoint-1310/optimizer.pt +3 -0
  41. checkpoint-1310/rng_state.pth +3 -0
  42. checkpoint-1310/scheduler.pt +3 -0
  43. checkpoint-1310/special_tokens_map.json +6 -0
  44. checkpoint-1310/tokenizer.json +0 -0
  45. checkpoint-1310/tokenizer_config.json +20 -0
  46. checkpoint-1310/trainer_state.json +125 -0
  47. checkpoint-1310/training_args.bin +3 -0
  48. checkpoint-1310/vocab.json +0 -0
  49. checkpoint-262/config.json +49 -0
  50. checkpoint-262/merges.txt +0 -0
checkpoint-1048/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-1048/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1048/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:105a01ebff9e86f0fb960e19ee8b501a934ce19f67b70ddd946944f100694292
3
+ size 497780432
checkpoint-1048/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d90daaa47ff0c947f85bd1feb17938a3713c2b37a7708dcb4cc63c204cc32999
3
+ size 995654981
checkpoint-1048/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d876eadf39bf6c26163d043fb9fafa2a75f16d35ee8c6b4ff92d96803bbc3bc8
3
+ size 14575
checkpoint-1048/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70cc8e43df49fb83e8c9263f1ccdc22a1986440515096e48253098458f3f94cc
3
+ size 627
checkpoint-1048/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-1048/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1048/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": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-1048/trainer_state.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.16112907230854034,
3
+ "best_model_checkpoint": "YELP_full/checkpoint-393",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1048,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.9328,
14
+ "eval_loss": 0.17968642711639404,
15
+ "eval_runtime": 78.2206,
16
+ "eval_samples_per_second": 319.609,
17
+ "eval_steps_per_second": 1.675,
18
+ "step": 131
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.93844,
23
+ "eval_loss": 0.1635778844356537,
24
+ "eval_runtime": 78.3918,
25
+ "eval_samples_per_second": 318.911,
26
+ "eval_steps_per_second": 1.671,
27
+ "step": 262
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.9432,
32
+ "eval_loss": 0.16112907230854034,
33
+ "eval_runtime": 78.1143,
34
+ "eval_samples_per_second": 320.044,
35
+ "eval_steps_per_second": 1.677,
36
+ "step": 393
37
+ },
38
+ {
39
+ "epoch": 3.82,
40
+ "grad_norm": 4.371647834777832,
41
+ "learning_rate": 3.7099236641221374e-05,
42
+ "loss": 0.1759,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.94228,
48
+ "eval_loss": 0.18924400210380554,
49
+ "eval_runtime": 78.0582,
50
+ "eval_samples_per_second": 320.274,
51
+ "eval_steps_per_second": 1.678,
52
+ "step": 524
53
+ },
54
+ {
55
+ "epoch": 5.0,
56
+ "eval_accuracy": 0.94408,
57
+ "eval_loss": 0.17596399784088135,
58
+ "eval_runtime": 78.0645,
59
+ "eval_samples_per_second": 320.248,
60
+ "eval_steps_per_second": 1.678,
61
+ "step": 655
62
+ },
63
+ {
64
+ "epoch": 6.0,
65
+ "eval_accuracy": 0.94128,
66
+ "eval_loss": 0.22926613688468933,
67
+ "eval_runtime": 78.0797,
68
+ "eval_samples_per_second": 320.186,
69
+ "eval_steps_per_second": 1.678,
70
+ "step": 786
71
+ },
72
+ {
73
+ "epoch": 7.0,
74
+ "eval_accuracy": 0.9432,
75
+ "eval_loss": 0.24049581587314606,
76
+ "eval_runtime": 78.383,
77
+ "eval_samples_per_second": 318.947,
78
+ "eval_steps_per_second": 1.671,
79
+ "step": 917
80
+ },
81
+ {
82
+ "epoch": 7.63,
83
+ "grad_norm": 3.099727153778076,
84
+ "learning_rate": 1.4198473282442749e-05,
85
+ "loss": 0.038,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 8.0,
90
+ "eval_accuracy": 0.94356,
91
+ "eval_loss": 0.25248077511787415,
92
+ "eval_runtime": 78.171,
93
+ "eval_samples_per_second": 319.812,
94
+ "eval_steps_per_second": 1.676,
95
+ "step": 1048
96
+ }
97
+ ],
98
+ "logging_steps": 500,
99
+ "max_steps": 1310,
100
+ "num_input_tokens_seen": 0,
101
+ "num_train_epochs": 10,
102
+ "save_steps": 500,
103
+ "total_flos": 1.0440060227105587e+17,
104
+ "train_batch_size": 192,
105
+ "trial_name": null,
106
+ "trial_params": null
107
+ }
checkpoint-1048/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:544ba08d47f8177649f3f37852ee5d1044eed67936fa2f1c81b09ee0c38f78ad
3
+ size 4539
checkpoint-1048/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1179/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-1179/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1179/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168f8048dbdec50e1585a5af34ba54230cb92d2e04f80cacb704e294b97412f6
3
+ size 497780432
checkpoint-1179/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64bea5d25aca984424c579487e2cc36f726c34f3195621b17f141478bab621f3
3
+ size 995654981
checkpoint-1179/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd75caaaf30ce117f349df6cc1bcf0c1f6ac941d47d2c130422b1853128daa34
3
+ size 14575
checkpoint-1179/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa15dba9b8d6b18fd0ea9a1d6721c5803dbf0e4c3482aeac6ba7838ffd4a600
3
+ size 627
checkpoint-1179/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-1179/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1179/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": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-1179/trainer_state.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.16112907230854034,
3
+ "best_model_checkpoint": "YELP_full/checkpoint-393",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1179,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.9328,
14
+ "eval_loss": 0.17968642711639404,
15
+ "eval_runtime": 78.2206,
16
+ "eval_samples_per_second": 319.609,
17
+ "eval_steps_per_second": 1.675,
18
+ "step": 131
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.93844,
23
+ "eval_loss": 0.1635778844356537,
24
+ "eval_runtime": 78.3918,
25
+ "eval_samples_per_second": 318.911,
26
+ "eval_steps_per_second": 1.671,
27
+ "step": 262
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.9432,
32
+ "eval_loss": 0.16112907230854034,
33
+ "eval_runtime": 78.1143,
34
+ "eval_samples_per_second": 320.044,
35
+ "eval_steps_per_second": 1.677,
36
+ "step": 393
37
+ },
38
+ {
39
+ "epoch": 3.82,
40
+ "grad_norm": 4.371647834777832,
41
+ "learning_rate": 3.7099236641221374e-05,
42
+ "loss": 0.1759,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.94228,
48
+ "eval_loss": 0.18924400210380554,
49
+ "eval_runtime": 78.0582,
50
+ "eval_samples_per_second": 320.274,
51
+ "eval_steps_per_second": 1.678,
52
+ "step": 524
53
+ },
54
+ {
55
+ "epoch": 5.0,
56
+ "eval_accuracy": 0.94408,
57
+ "eval_loss": 0.17596399784088135,
58
+ "eval_runtime": 78.0645,
59
+ "eval_samples_per_second": 320.248,
60
+ "eval_steps_per_second": 1.678,
61
+ "step": 655
62
+ },
63
+ {
64
+ "epoch": 6.0,
65
+ "eval_accuracy": 0.94128,
66
+ "eval_loss": 0.22926613688468933,
67
+ "eval_runtime": 78.0797,
68
+ "eval_samples_per_second": 320.186,
69
+ "eval_steps_per_second": 1.678,
70
+ "step": 786
71
+ },
72
+ {
73
+ "epoch": 7.0,
74
+ "eval_accuracy": 0.9432,
75
+ "eval_loss": 0.24049581587314606,
76
+ "eval_runtime": 78.383,
77
+ "eval_samples_per_second": 318.947,
78
+ "eval_steps_per_second": 1.671,
79
+ "step": 917
80
+ },
81
+ {
82
+ "epoch": 7.63,
83
+ "grad_norm": 3.099727153778076,
84
+ "learning_rate": 1.4198473282442749e-05,
85
+ "loss": 0.038,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 8.0,
90
+ "eval_accuracy": 0.94356,
91
+ "eval_loss": 0.25248077511787415,
92
+ "eval_runtime": 78.171,
93
+ "eval_samples_per_second": 319.812,
94
+ "eval_steps_per_second": 1.676,
95
+ "step": 1048
96
+ },
97
+ {
98
+ "epoch": 9.0,
99
+ "eval_accuracy": 0.94368,
100
+ "eval_loss": 0.2984617054462433,
101
+ "eval_runtime": 79.1391,
102
+ "eval_samples_per_second": 315.9,
103
+ "eval_steps_per_second": 1.655,
104
+ "step": 1179
105
+ }
106
+ ],
107
+ "logging_steps": 500,
108
+ "max_steps": 1310,
109
+ "num_input_tokens_seen": 0,
110
+ "num_train_epochs": 10,
111
+ "save_steps": 500,
112
+ "total_flos": 1.1746455792412262e+17,
113
+ "train_batch_size": 192,
114
+ "trial_name": null,
115
+ "trial_params": null
116
+ }
checkpoint-1179/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:544ba08d47f8177649f3f37852ee5d1044eed67936fa2f1c81b09ee0c38f78ad
3
+ size 4539
checkpoint-1179/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-131/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-131/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-131/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a430af96c2085abcbc6a08f2f9b5d64d8c30d2ee52cc7d0d188f9e97f3e7337f
3
+ size 497780432
checkpoint-131/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5d4d5bd2649d4e59def5bd8d9499a21c4553a49d281fa6d0ec539b60ddccef
3
+ size 995654981
checkpoint-131/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9004150f8ada6a696b04eca38f3bf564e32a89917445a2ffe3d5e018c98b585
3
+ size 14575
checkpoint-131/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8657148625a56a83c854c9b8ff460afebe321ee1fd91ad84e06791b0a5e88a04
3
+ size 627
checkpoint-131/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-131/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-131/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": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-131/trainer_state.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.17968642711639404,
3
+ "best_model_checkpoint": "YELP_full/checkpoint-131",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 131,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.9328,
14
+ "eval_loss": 0.17968642711639404,
15
+ "eval_runtime": 78.2206,
16
+ "eval_samples_per_second": 319.609,
17
+ "eval_steps_per_second": 1.675,
18
+ "step": 131
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1310,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 10,
25
+ "save_steps": 500,
26
+ "total_flos": 1.30648375296e+16,
27
+ "train_batch_size": 192,
28
+ "trial_name": null,
29
+ "trial_params": null
30
+ }
checkpoint-131/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:544ba08d47f8177649f3f37852ee5d1044eed67936fa2f1c81b09ee0c38f78ad
3
+ size 4539
checkpoint-131/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1310/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-1310/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1310/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900299cc2508acd674a7949293a9f29dc199f90bf1ec20b5c0e7f8253ac78ad9
3
+ size 497780432
checkpoint-1310/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c7d142a8dbe148dc445b2e399d718274315cb8b75948abd1c2014189b0d3a51
3
+ size 995654981
checkpoint-1310/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef1f8710f16a9ff9cd51ca1d349072580e84ced91b6ca6033d93110ca0b569b2
3
+ size 14575
checkpoint-1310/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e598665d1a3d022866a8a352e88a4b0fc26c1c7d67c56ede013cb980e5b35e
3
+ size 627
checkpoint-1310/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-1310/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1310/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": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-1310/trainer_state.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.16112907230854034,
3
+ "best_model_checkpoint": "YELP_full/checkpoint-393",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1310,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.9328,
14
+ "eval_loss": 0.17968642711639404,
15
+ "eval_runtime": 78.2206,
16
+ "eval_samples_per_second": 319.609,
17
+ "eval_steps_per_second": 1.675,
18
+ "step": 131
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.93844,
23
+ "eval_loss": 0.1635778844356537,
24
+ "eval_runtime": 78.3918,
25
+ "eval_samples_per_second": 318.911,
26
+ "eval_steps_per_second": 1.671,
27
+ "step": 262
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.9432,
32
+ "eval_loss": 0.16112907230854034,
33
+ "eval_runtime": 78.1143,
34
+ "eval_samples_per_second": 320.044,
35
+ "eval_steps_per_second": 1.677,
36
+ "step": 393
37
+ },
38
+ {
39
+ "epoch": 3.82,
40
+ "grad_norm": 4.371647834777832,
41
+ "learning_rate": 3.7099236641221374e-05,
42
+ "loss": 0.1759,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.94228,
48
+ "eval_loss": 0.18924400210380554,
49
+ "eval_runtime": 78.0582,
50
+ "eval_samples_per_second": 320.274,
51
+ "eval_steps_per_second": 1.678,
52
+ "step": 524
53
+ },
54
+ {
55
+ "epoch": 5.0,
56
+ "eval_accuracy": 0.94408,
57
+ "eval_loss": 0.17596399784088135,
58
+ "eval_runtime": 78.0645,
59
+ "eval_samples_per_second": 320.248,
60
+ "eval_steps_per_second": 1.678,
61
+ "step": 655
62
+ },
63
+ {
64
+ "epoch": 6.0,
65
+ "eval_accuracy": 0.94128,
66
+ "eval_loss": 0.22926613688468933,
67
+ "eval_runtime": 78.0797,
68
+ "eval_samples_per_second": 320.186,
69
+ "eval_steps_per_second": 1.678,
70
+ "step": 786
71
+ },
72
+ {
73
+ "epoch": 7.0,
74
+ "eval_accuracy": 0.9432,
75
+ "eval_loss": 0.24049581587314606,
76
+ "eval_runtime": 78.383,
77
+ "eval_samples_per_second": 318.947,
78
+ "eval_steps_per_second": 1.671,
79
+ "step": 917
80
+ },
81
+ {
82
+ "epoch": 7.63,
83
+ "grad_norm": 3.099727153778076,
84
+ "learning_rate": 1.4198473282442749e-05,
85
+ "loss": 0.038,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 8.0,
90
+ "eval_accuracy": 0.94356,
91
+ "eval_loss": 0.25248077511787415,
92
+ "eval_runtime": 78.171,
93
+ "eval_samples_per_second": 319.812,
94
+ "eval_steps_per_second": 1.676,
95
+ "step": 1048
96
+ },
97
+ {
98
+ "epoch": 9.0,
99
+ "eval_accuracy": 0.94368,
100
+ "eval_loss": 0.2984617054462433,
101
+ "eval_runtime": 79.1391,
102
+ "eval_samples_per_second": 315.9,
103
+ "eval_steps_per_second": 1.655,
104
+ "step": 1179
105
+ },
106
+ {
107
+ "epoch": 10.0,
108
+ "eval_accuracy": 0.94508,
109
+ "eval_loss": 0.3094567358493805,
110
+ "eval_runtime": 78.4753,
111
+ "eval_samples_per_second": 318.572,
112
+ "eval_steps_per_second": 1.669,
113
+ "step": 1310
114
+ }
115
+ ],
116
+ "logging_steps": 500,
117
+ "max_steps": 1310,
118
+ "num_input_tokens_seen": 0,
119
+ "num_train_epochs": 10,
120
+ "save_steps": 500,
121
+ "total_flos": 1.305063972569088e+17,
122
+ "train_batch_size": 192,
123
+ "trial_name": null,
124
+ "trial_params": null
125
+ }
checkpoint-1310/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:544ba08d47f8177649f3f37852ee5d1044eed67936fa2f1c81b09ee0c38f78ad
3
+ size 4539
checkpoint-1310/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-262/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-262/merges.txt ADDED
The diff for this file is too large to render. See raw diff