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
ec77f25
•
1 Parent(s): e146de6

Training in progress, step 500

Browse files
Files changed (35) hide show
  1. model.safetensors +1 -1
  2. run-17/checkpoint-3000/config.json +26 -0
  3. run-17/checkpoint-3000/model.safetensors +3 -0
  4. run-17/checkpoint-3000/optimizer.pt +3 -0
  5. run-17/checkpoint-3000/rng_state.pth +3 -0
  6. run-17/checkpoint-3000/scheduler.pt +3 -0
  7. run-17/checkpoint-3000/special_tokens_map.json +7 -0
  8. run-17/checkpoint-3000/tokenizer.json +0 -0
  9. run-17/checkpoint-3000/tokenizer_config.json +55 -0
  10. run-17/checkpoint-3000/trainer_state.json +138 -0
  11. run-17/checkpoint-3000/training_args.bin +3 -0
  12. run-17/checkpoint-3000/vocab.txt +0 -0
  13. run-17/checkpoint-3500/config.json +26 -0
  14. run-17/checkpoint-3500/model.safetensors +3 -0
  15. run-17/checkpoint-3500/optimizer.pt +3 -0
  16. run-17/checkpoint-3500/rng_state.pth +3 -0
  17. run-17/checkpoint-3500/scheduler.pt +3 -0
  18. run-17/checkpoint-3500/special_tokens_map.json +7 -0
  19. run-17/checkpoint-3500/tokenizer.json +0 -0
  20. run-17/checkpoint-3500/tokenizer_config.json +55 -0
  21. run-17/checkpoint-3500/trainer_state.json +154 -0
  22. run-17/checkpoint-3500/training_args.bin +3 -0
  23. run-17/checkpoint-3500/vocab.txt +0 -0
  24. run-18/checkpoint-500/config.json +26 -0
  25. run-18/checkpoint-500/model.safetensors +3 -0
  26. run-18/checkpoint-500/optimizer.pt +3 -0
  27. run-18/checkpoint-500/rng_state.pth +3 -0
  28. run-18/checkpoint-500/scheduler.pt +3 -0
  29. run-18/checkpoint-500/special_tokens_map.json +7 -0
  30. run-18/checkpoint-500/tokenizer.json +0 -0
  31. run-18/checkpoint-500/tokenizer_config.json +55 -0
  32. run-18/checkpoint-500/trainer_state.json +31 -0
  33. run-18/checkpoint-500/training_args.bin +3 -0
  34. run-18/checkpoint-500/vocab.txt +0 -0
  35. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba88df82084094bc409117729c56e9915f519fe11511336d3518480a59910d1a
3
  size 1340618660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29f28a26440785cc17c0c69e2005ae8d1919923d00137ce7e693b29124494df
3
  size 1340618660
run-17/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-17/checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74185fbed51c85f7ac7546ed43da95ca8038ba70f49020741ff3d426db7f5fc8
3
+ size 1340618660
run-17/checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582ec0dd38ad026d09ea7438fd4cacd5d4789c411d8e54e893e937d46ce520f8
3
+ size 2681472237
run-17/checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64cc5084c28610350139001bdf2e7741e2feb5bc0126e5b3ce15926d06089ebc
3
+ size 14244
run-17/checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3df1e7937b3db5a57af643aac555e808dbcb356625df6126263f15a5430053
3
+ size 1064
run-17/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-17/checkpoint-3000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-17/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-17/checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.04289544235925,
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": 1.0,
13
+ "eval_accuracy": 0.758632242679596,
14
+ "eval_loss": 0.4715859889984131,
15
+ "eval_runtime": 9.5006,
16
+ "eval_samples_per_second": 313.981,
17
+ "eval_steps_per_second": 19.683,
18
+ "step": 373
19
+ },
20
+ {
21
+ "epoch": 1.3404825737265416,
22
+ "grad_norm": 9.62618637084961,
23
+ "learning_rate": 1.4776902224208135e-05,
24
+ "loss": 0.5101,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7727120518684387,
30
+ "eval_loss": 0.47308608889579773,
31
+ "eval_runtime": 9.4715,
32
+ "eval_samples_per_second": 314.944,
33
+ "eval_steps_per_second": 19.743,
34
+ "step": 746
35
+ },
36
+ {
37
+ "epoch": 2.680965147453083,
38
+ "grad_norm": 17.83710289001465,
39
+ "learning_rate": 1.2489456059470035e-05,
40
+ "loss": 0.2485,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_accuracy": 0.7743881940841675,
46
+ "eval_loss": 0.7006397843360901,
47
+ "eval_runtime": 9.4464,
48
+ "eval_samples_per_second": 315.781,
49
+ "eval_steps_per_second": 19.796,
50
+ "step": 1119
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.7750586867332458,
55
+ "eval_loss": 0.8257986903190613,
56
+ "eval_runtime": 9.4942,
57
+ "eval_samples_per_second": 314.193,
58
+ "eval_steps_per_second": 19.696,
59
+ "step": 1492
60
+ },
61
+ {
62
+ "epoch": 4.021447721179625,
63
+ "grad_norm": 0.4933696985244751,
64
+ "learning_rate": 1.0202009894731932e-05,
65
+ "loss": 0.0969,
66
+ "step": 1500
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "eval_accuracy": 0.782433807849884,
71
+ "eval_loss": 0.9035575985908508,
72
+ "eval_runtime": 9.4688,
73
+ "eval_samples_per_second": 315.034,
74
+ "eval_steps_per_second": 19.749,
75
+ "step": 1865
76
+ },
77
+ {
78
+ "epoch": 5.361930294906166,
79
+ "grad_norm": 15.212503433227539,
80
+ "learning_rate": 7.91456372999383e-06,
81
+ "loss": 0.0396,
82
+ "step": 2000
83
+ },
84
+ {
85
+ "epoch": 6.0,
86
+ "eval_accuracy": 0.7844451665878296,
87
+ "eval_loss": 1.023715853691101,
88
+ "eval_runtime": 9.6126,
89
+ "eval_samples_per_second": 310.323,
90
+ "eval_steps_per_second": 19.454,
91
+ "step": 2238
92
+ },
93
+ {
94
+ "epoch": 6.702412868632708,
95
+ "grad_norm": 1.1762652397155762,
96
+ "learning_rate": 5.627117565255729e-06,
97
+ "loss": 0.0231,
98
+ "step": 2500
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_accuracy": 0.7760643362998962,
103
+ "eval_loss": 1.3074647188186646,
104
+ "eval_runtime": 9.435,
105
+ "eval_samples_per_second": 316.164,
106
+ "eval_steps_per_second": 19.82,
107
+ "step": 2611
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "eval_accuracy": 0.783774733543396,
112
+ "eval_loss": 1.3387647867202759,
113
+ "eval_runtime": 9.4842,
114
+ "eval_samples_per_second": 314.525,
115
+ "eval_steps_per_second": 19.717,
116
+ "step": 2984
117
+ },
118
+ {
119
+ "epoch": 8.04289544235925,
120
+ "grad_norm": 3.214566707611084,
121
+ "learning_rate": 3.3396714005176278e-06,
122
+ "loss": 0.0136,
123
+ "step": 3000
124
+ }
125
+ ],
126
+ "logging_steps": 500,
127
+ "max_steps": 3730,
128
+ "num_input_tokens_seen": 0,
129
+ "num_train_epochs": 10,
130
+ "save_steps": 500,
131
+ "total_flos": 1.7275775811630084e+16,
132
+ "train_batch_size": 32,
133
+ "trial_name": null,
134
+ "trial_params": {
135
+ "learning_rate": 1.7064348388946237e-05,
136
+ "per_device_train_batch_size": 32
137
+ }
138
+ }
run-17/checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
3
+ size 5048
run-17/checkpoint-3000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-17/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-17/checkpoint-3500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb02e7dbbd12abbea8ce60dee86c8fcf56860fb1ee36b86531a77f93189824a
3
+ size 1340618660
run-17/checkpoint-3500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2f9000b3d965936899926c1a184619a81c61b4143ced4b81b8762a238ff2ca
3
+ size 2681472237
run-17/checkpoint-3500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b1d1d89dd6f7639777970d77f6c7dc074edb948b4911bac5bcd126ef93417be
3
+ size 14244
run-17/checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:964e5c4fc4a6f3b5bb5fb010099755e53b16bd5226173a909b4acb7637e949bd
3
+ size 1064
run-17/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-17/checkpoint-3500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-17/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-17/checkpoint-3500/trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.383378016085791,
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": 1.0,
13
+ "eval_accuracy": 0.758632242679596,
14
+ "eval_loss": 0.4715859889984131,
15
+ "eval_runtime": 9.5006,
16
+ "eval_samples_per_second": 313.981,
17
+ "eval_steps_per_second": 19.683,
18
+ "step": 373
19
+ },
20
+ {
21
+ "epoch": 1.3404825737265416,
22
+ "grad_norm": 9.62618637084961,
23
+ "learning_rate": 1.4776902224208135e-05,
24
+ "loss": 0.5101,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7727120518684387,
30
+ "eval_loss": 0.47308608889579773,
31
+ "eval_runtime": 9.4715,
32
+ "eval_samples_per_second": 314.944,
33
+ "eval_steps_per_second": 19.743,
34
+ "step": 746
35
+ },
36
+ {
37
+ "epoch": 2.680965147453083,
38
+ "grad_norm": 17.83710289001465,
39
+ "learning_rate": 1.2489456059470035e-05,
40
+ "loss": 0.2485,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_accuracy": 0.7743881940841675,
46
+ "eval_loss": 0.7006397843360901,
47
+ "eval_runtime": 9.4464,
48
+ "eval_samples_per_second": 315.781,
49
+ "eval_steps_per_second": 19.796,
50
+ "step": 1119
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.7750586867332458,
55
+ "eval_loss": 0.8257986903190613,
56
+ "eval_runtime": 9.4942,
57
+ "eval_samples_per_second": 314.193,
58
+ "eval_steps_per_second": 19.696,
59
+ "step": 1492
60
+ },
61
+ {
62
+ "epoch": 4.021447721179625,
63
+ "grad_norm": 0.4933696985244751,
64
+ "learning_rate": 1.0202009894731932e-05,
65
+ "loss": 0.0969,
66
+ "step": 1500
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "eval_accuracy": 0.782433807849884,
71
+ "eval_loss": 0.9035575985908508,
72
+ "eval_runtime": 9.4688,
73
+ "eval_samples_per_second": 315.034,
74
+ "eval_steps_per_second": 19.749,
75
+ "step": 1865
76
+ },
77
+ {
78
+ "epoch": 5.361930294906166,
79
+ "grad_norm": 15.212503433227539,
80
+ "learning_rate": 7.91456372999383e-06,
81
+ "loss": 0.0396,
82
+ "step": 2000
83
+ },
84
+ {
85
+ "epoch": 6.0,
86
+ "eval_accuracy": 0.7844451665878296,
87
+ "eval_loss": 1.023715853691101,
88
+ "eval_runtime": 9.6126,
89
+ "eval_samples_per_second": 310.323,
90
+ "eval_steps_per_second": 19.454,
91
+ "step": 2238
92
+ },
93
+ {
94
+ "epoch": 6.702412868632708,
95
+ "grad_norm": 1.1762652397155762,
96
+ "learning_rate": 5.627117565255729e-06,
97
+ "loss": 0.0231,
98
+ "step": 2500
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_accuracy": 0.7760643362998962,
103
+ "eval_loss": 1.3074647188186646,
104
+ "eval_runtime": 9.435,
105
+ "eval_samples_per_second": 316.164,
106
+ "eval_steps_per_second": 19.82,
107
+ "step": 2611
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "eval_accuracy": 0.783774733543396,
112
+ "eval_loss": 1.3387647867202759,
113
+ "eval_runtime": 9.4842,
114
+ "eval_samples_per_second": 314.525,
115
+ "eval_steps_per_second": 19.717,
116
+ "step": 2984
117
+ },
118
+ {
119
+ "epoch": 8.04289544235925,
120
+ "grad_norm": 3.214566707611084,
121
+ "learning_rate": 3.3396714005176278e-06,
122
+ "loss": 0.0136,
123
+ "step": 3000
124
+ },
125
+ {
126
+ "epoch": 9.0,
127
+ "eval_accuracy": 0.7814280986785889,
128
+ "eval_loss": 1.466342806816101,
129
+ "eval_runtime": 9.5941,
130
+ "eval_samples_per_second": 310.922,
131
+ "eval_steps_per_second": 19.491,
132
+ "step": 3357
133
+ },
134
+ {
135
+ "epoch": 9.383378016085791,
136
+ "grad_norm": 0.25926658511161804,
137
+ "learning_rate": 1.0522252357795266e-06,
138
+ "loss": 0.0084,
139
+ "step": 3500
140
+ }
141
+ ],
142
+ "logging_steps": 500,
143
+ "max_steps": 3730,
144
+ "num_input_tokens_seen": 0,
145
+ "num_train_epochs": 10,
146
+ "save_steps": 500,
147
+ "total_flos": 2.00380947674166e+16,
148
+ "train_batch_size": 32,
149
+ "trial_name": null,
150
+ "trial_params": {
151
+ "learning_rate": 1.7064348388946237e-05,
152
+ "per_device_train_batch_size": 32
153
+ }
154
+ }
run-17/checkpoint-3500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
3
+ size 5048
run-17/checkpoint-3500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-18/checkpoint-500/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-18/checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29f28a26440785cc17c0c69e2005ae8d1919923d00137ce7e693b29124494df
3
+ size 1340618660
run-18/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f889d05fa8e71c463ab0b0b1fe732420cffaec0d2509574dc140724c4285552b
3
+ size 2681472237
run-18/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c317b20a8b0f126de354e22abe6285be95b0457be6843da518d21b802633c6
3
+ size 14244
run-18/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a5db713c77da75c6de4224830a132080dcf5ecf32a215505c846553305fa69
3
+ size 1064
run-18/checkpoint-500/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-18/checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-18/checkpoint-500/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-18/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6702412868632708,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
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": 2.0567471981048584,
14
+ "learning_rate": 3.4249716886009665e-05,
15
+ "loss": 0.6988,
16
+ "step": 500
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 7460,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 10,
23
+ "save_steps": 500,
24
+ "total_flos": 1313261590810176.0,
25
+ "train_batch_size": 16,
26
+ "trial_name": null,
27
+ "trial_params": {
28
+ "learning_rate": 3.671018505310806e-05,
29
+ "per_device_train_batch_size": 16
30
+ }
31
+ }
run-18/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb352c64929d70c5eb4809d8dc469d0cc38c4665094b3302cec5ae2a1a560d0
3
+ size 5048
run-18/checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb352c64929d70c5eb4809d8dc469d0cc38c4665094b3302cec5ae2a1a560d0
3
  size 5048