Hugging Face's logo

inflaton
/
cs605-nlp-assignment-2-bert-large-uncased-v2

Multiple Choice
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
inflaton commited on
Commit
04875c3
•
1 Parent(s): 872974c

Training in progress, step 3500

Browse files
Files changed (23) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-3000/config.json +26 -0
  3. run-2/checkpoint-3000/model.safetensors +3 -0
  4. run-2/checkpoint-3000/optimizer.pt +3 -0
  5. run-2/checkpoint-3000/rng_state.pth +3 -0
  6. run-2/checkpoint-3000/scheduler.pt +3 -0
  7. run-2/checkpoint-3000/special_tokens_map.json +7 -0
  8. run-2/checkpoint-3000/tokenizer.json +0 -0
  9. run-2/checkpoint-3000/tokenizer_config.json +55 -0
  10. run-2/checkpoint-3000/trainer_state.json +102 -0
  11. run-2/checkpoint-3000/training_args.bin +3 -0
  12. run-2/checkpoint-3000/vocab.txt +0 -0
  13. run-2/checkpoint-3500/config.json +26 -0
  14. run-2/checkpoint-3500/model.safetensors +3 -0
  15. run-2/checkpoint-3500/optimizer.pt +3 -0
  16. run-2/checkpoint-3500/rng_state.pth +3 -0
  17. run-2/checkpoint-3500/scheduler.pt +3 -0
  18. run-2/checkpoint-3500/special_tokens_map.json +7 -0
  19. run-2/checkpoint-3500/tokenizer.json +0 -0
  20. run-2/checkpoint-3500/tokenizer_config.json +55 -0
  21. run-2/checkpoint-3500/trainer_state.json +109 -0
  22. run-2/checkpoint-3500/training_args.bin +3 -0
  23. run-2/checkpoint-3500/vocab.txt +0 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd7bc8c8db02b0e605df0cc447d46f960f7fa093e248af8d670f37a4657b8c35
3
  size 1340618660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039b285acb185744d16c7a5386b39db63aec6176214ba434ddc6f9db1f609586
3
  size 1340618660
run-2/checkpoint-3000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-2/checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe8030fd6e4014e1d8f1e006841094ac3fb64ee0a5b237c45234a2859d47821
3
+ size 1340618660
run-2/checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:272a92e5dfbeeaac09204c72a54943173a6aa14406d3bf6663728360a857e041
3
+ size 2681472237
run-2/checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac0fde3555dccd9e3c85c24a58ef16005dcfc5730b52d8c9c3e5f7feba7cc67
3
+ size 14244
run-2/checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba9c7a46cfe3b5bfe1f1223c756194bc5772b08e6aff3582b5d1dc990a0a18ad
3
+ size 1064
run-2/checkpoint-3000/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-3000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-3000/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-2/checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.021447721179625,
5
+ "eval_steps": 500,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6702412868632708,
13
+ "grad_norm": 9.020133018493652,
14
+ "learning_rate": 1.4299394279479472e-06,
15
+ "loss": 0.6244,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7267851233482361,
21
+ "eval_loss": 0.5142917633056641,
22
+ "eval_runtime": 9.4466,
23
+ "eval_samples_per_second": 315.773,
24
+ "eval_steps_per_second": 19.795,
25
+ "step": 746
26
+ },
27
+ {
28
+ "epoch": 1.3404825737265416,
29
+ "grad_norm": 10.139765739440918,
30
+ "learning_rate": 1.3272138943309972e-06,
31
+ "loss": 0.5438,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7405296564102173,
37
+ "eval_loss": 0.49428224563598633,
38
+ "eval_runtime": 9.4794,
39
+ "eval_samples_per_second": 314.682,
40
+ "eval_steps_per_second": 19.727,
41
+ "step": 1492
42
+ },
43
+ {
44
+ "epoch": 2.0107238605898123,
45
+ "grad_norm": 7.425673961639404,
46
+ "learning_rate": 1.2244883607140467e-06,
47
+ "loss": 0.5108,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 2.680965147453083,
52
+ "grad_norm": 8.044295310974121,
53
+ "learning_rate": 1.1217628270970966e-06,
54
+ "loss": 0.4787,
55
+ "step": 2000
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "eval_accuracy": 0.7468990683555603,
60
+ "eval_loss": 0.5006520748138428,
61
+ "eval_runtime": 9.5789,
62
+ "eval_samples_per_second": 311.415,
63
+ "eval_steps_per_second": 19.522,
64
+ "step": 2238
65
+ },
66
+ {
67
+ "epoch": 3.351206434316354,
68
+ "grad_norm": 19.568927764892578,
69
+ "learning_rate": 1.0190372934801463e-06,
70
+ "loss": 0.458,
71
+ "step": 2500
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.7522628307342529,
76
+ "eval_loss": 0.49020281434059143,
77
+ "eval_runtime": 9.4558,
78
+ "eval_samples_per_second": 315.467,
79
+ "eval_steps_per_second": 19.776,
80
+ "step": 2984
81
+ },
82
+ {
83
+ "epoch": 4.021447721179625,
84
+ "grad_norm": 5.546102046966553,
85
+ "learning_rate": 9.16311759863196e-07,
86
+ "loss": 0.4303,
87
+ "step": 3000
88
+ }
89
+ ],
90
+ "logging_steps": 500,
91
+ "max_steps": 7460,
92
+ "num_input_tokens_seen": 0,
93
+ "num_train_epochs": 10,
94
+ "save_steps": 500,
95
+ "total_flos": 7816595223833244.0,
96
+ "train_batch_size": 16,
97
+ "trial_name": null,
98
+ "trial_params": {
99
+ "learning_rate": 1.5326649615648975e-06,
100
+ "per_device_train_batch_size": 16
101
+ }
102
+ }
run-2/checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9148e9896109331da2b7e9883edd81351654fb75b2cc6dc424bd2ba274c6c831
3
+ size 5048
run-2/checkpoint-3000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-3500/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-2/checkpoint-3500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039b285acb185744d16c7a5386b39db63aec6176214ba434ddc6f9db1f609586
3
+ size 1340618660
run-2/checkpoint-3500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6aea6d0642a142935e5b514103601ab57cec400c8f5c32f416501d780a01d7d
3
+ size 2681472237
run-2/checkpoint-3500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661d7cc347d4d84b3f5bfbea2148f5922eb3a76fa7cc1053de1e26c08c4bdd72
3
+ size 14244
run-2/checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43ad2b515c84e944407d3248b0507c07b2c9a6051e57bb648c7217c4769e68c
3
+ size 1064
run-2/checkpoint-3500/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-3500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-3500/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-2/checkpoint-3500/trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.6916890080428955,
5
+ "eval_steps": 500,
6
+ "global_step": 3500,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6702412868632708,
13
+ "grad_norm": 9.020133018493652,
14
+ "learning_rate": 1.4299394279479472e-06,
15
+ "loss": 0.6244,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7267851233482361,
21
+ "eval_loss": 0.5142917633056641,
22
+ "eval_runtime": 9.4466,
23
+ "eval_samples_per_second": 315.773,
24
+ "eval_steps_per_second": 19.795,
25
+ "step": 746
26
+ },
27
+ {
28
+ "epoch": 1.3404825737265416,
29
+ "grad_norm": 10.139765739440918,
30
+ "learning_rate": 1.3272138943309972e-06,
31
+ "loss": 0.5438,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7405296564102173,
37
+ "eval_loss": 0.49428224563598633,
38
+ "eval_runtime": 9.4794,
39
+ "eval_samples_per_second": 314.682,
40
+ "eval_steps_per_second": 19.727,
41
+ "step": 1492
42
+ },
43
+ {
44
+ "epoch": 2.0107238605898123,
45
+ "grad_norm": 7.425673961639404,
46
+ "learning_rate": 1.2244883607140467e-06,
47
+ "loss": 0.5108,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 2.680965147453083,
52
+ "grad_norm": 8.044295310974121,
53
+ "learning_rate": 1.1217628270970966e-06,
54
+ "loss": 0.4787,
55
+ "step": 2000
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "eval_accuracy": 0.7468990683555603,
60
+ "eval_loss": 0.5006520748138428,
61
+ "eval_runtime": 9.5789,
62
+ "eval_samples_per_second": 311.415,
63
+ "eval_steps_per_second": 19.522,
64
+ "step": 2238
65
+ },
66
+ {
67
+ "epoch": 3.351206434316354,
68
+ "grad_norm": 19.568927764892578,
69
+ "learning_rate": 1.0190372934801463e-06,
70
+ "loss": 0.458,
71
+ "step": 2500
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.7522628307342529,
76
+ "eval_loss": 0.49020281434059143,
77
+ "eval_runtime": 9.4558,
78
+ "eval_samples_per_second": 315.467,
79
+ "eval_steps_per_second": 19.776,
80
+ "step": 2984
81
+ },
82
+ {
83
+ "epoch": 4.021447721179625,
84
+ "grad_norm": 5.546102046966553,
85
+ "learning_rate": 9.16311759863196e-07,
86
+ "loss": 0.4303,
87
+ "step": 3000
88
+ },
89
+ {
90
+ "epoch": 4.6916890080428955,
91
+ "grad_norm": 15.734197616577148,
92
+ "learning_rate": 8.135862262462459e-07,
93
+ "loss": 0.4115,
94
+ "step": 3500
95
+ }
96
+ ],
97
+ "logging_steps": 500,
98
+ "max_steps": 7460,
99
+ "num_input_tokens_seen": 0,
100
+ "num_train_epochs": 10,
101
+ "save_steps": 500,
102
+ "total_flos": 9120071568390876.0,
103
+ "train_batch_size": 16,
104
+ "trial_name": null,
105
+ "trial_params": {
106
+ "learning_rate": 1.5326649615648975e-06,
107
+ "per_device_train_batch_size": 16
108
+ }
109
+ }
run-2/checkpoint-3500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9148e9896109331da2b7e9883edd81351654fb75b2cc6dc424bd2ba274c6c831
3
+ size 5048
run-2/checkpoint-3500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff