Hugging Face's logo

ChrisZeng
/
bertweet-base-cased-covid19-hateval

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
1
ChrisZeng commited on
Commit
f01d183
·
1 Parent(s): 54fbaa5

Training in progress, epoch 8

Browse files
Files changed (40) hide show
  1. checkpoint-490/added_tokens.json +1 -0
  2. checkpoint-490/bpe.codes +0 -0
  3. checkpoint-490/config.json +30 -0
  4. checkpoint-490/optimizer.pt +3 -0
  5. checkpoint-490/pytorch_model.bin +3 -0
  6. checkpoint-490/rng_state.pth +3 -0
  7. checkpoint-490/scaler.pt +3 -0
  8. checkpoint-490/scheduler.pt +3 -0
  9. checkpoint-490/special_tokens_map.json +1 -0
  10. checkpoint-490/tokenizer_config.json +1 -0
  11. checkpoint-490/trainer_state.json +128 -0
  12. checkpoint-490/training_args.bin +3 -0
  13. checkpoint-490/vocab.txt +0 -0
  14. checkpoint-560/added_tokens.json +1 -0
  15. checkpoint-560/bpe.codes +0 -0
  16. checkpoint-560/config.json +30 -0
  17. checkpoint-560/optimizer.pt +3 -0
  18. checkpoint-560/pytorch_model.bin +3 -0
  19. checkpoint-560/rng_state.pth +3 -0
  20. checkpoint-560/scaler.pt +3 -0
  21. checkpoint-560/scheduler.pt +3 -0
  22. checkpoint-560/special_tokens_map.json +1 -0
  23. checkpoint-560/tokenizer_config.json +1 -0
  24. checkpoint-560/trainer_state.json +144 -0
  25. checkpoint-560/training_args.bin +3 -0
  26. checkpoint-560/vocab.txt +0 -0
  27. checkpoint-630/added_tokens.json +1 -0
  28. checkpoint-630/bpe.codes +0 -0
  29. checkpoint-630/config.json +30 -0
  30. checkpoint-630/optimizer.pt +3 -0
  31. checkpoint-630/pytorch_model.bin +3 -0
  32. checkpoint-630/rng_state.pth +3 -0
  33. checkpoint-630/scaler.pt +3 -0
  34. checkpoint-630/scheduler.pt +3 -0
  35. checkpoint-630/special_tokens_map.json +1 -0
  36. checkpoint-630/tokenizer_config.json +1 -0
  37. checkpoint-630/trainer_state.json +160 -0
  38. checkpoint-630/training_args.bin +3 -0
  39. checkpoint-630/vocab.txt +0 -0
  40. pytorch_model.bin +1 -1
checkpoint-490/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<mask>": 64000}
checkpoint-490/bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-490/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/bertweet-covid19-base-cased",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 130,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "multi_label_classification",
24
+ "tokenizer_class": "BertweetTokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.17.0",
27
+ "type_vocab_size": 1,
28
+ "use_cache": true,
29
+ "vocab_size": 64001
30
+ }
checkpoint-490/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6cca65e48afd84c968b05ea9d830f649a42c0d8ff900bbfb80f4f13aa085f1
3
+ size 1079327581
checkpoint-490/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73e0815918bf34d607238230fa7e8c1a6b45e3dd18e4e1e7ff27622f92f55c2
3
+ size 539689325
checkpoint-490/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d83257f141c405f56ebf1fd0c66157688c5100db8f619a195f01d84adae4c732
3
+ size 14503
checkpoint-490/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11979c764c292bfef1356e2956fd3e04a9906c6b0fade7e93fe8270c7a297284
3
+ size 559
checkpoint-490/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:000c8a98942c0dc9ccd77fe00e03af1d353b776ed9e00bef3da51a275dbb6ba9
3
+ size 623
checkpoint-490/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
checkpoint-490/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"normalization": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "vinai/bertweet-covid19-base-cased", "tokenizer_class": "BertweetTokenizer"}
checkpoint-490/trainer_state.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7381492469031885,
3
+ "best_model_checkpoint": "outputs/bertweet/checkpoint-490",
4
+ "epoch": 6.99290780141844,
5
+ "global_step": 490,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.99,
12
+ "learning_rate": 9.666666666666666e-07,
13
+ "loss": 0.6925,
14
+ "step": 70
15
+ },
16
+ {
17
+ "epoch": 0.99,
18
+ "eval_accuracy": 0.573,
19
+ "eval_f1": 0.3642720915448188,
20
+ "eval_loss": 0.6826930046081543,
21
+ "eval_runtime": 2.9877,
22
+ "eval_samples_per_second": 334.703,
23
+ "eval_steps_per_second": 41.838,
24
+ "step": 70
25
+ },
26
+ {
27
+ "epoch": 1.99,
28
+ "learning_rate": 9.333333333333333e-07,
29
+ "loss": 0.6823,
30
+ "step": 140
31
+ },
32
+ {
33
+ "epoch": 1.99,
34
+ "eval_accuracy": 0.573,
35
+ "eval_f1": 0.3642720915448188,
36
+ "eval_loss": 0.6736124753952026,
37
+ "eval_runtime": 3.0497,
38
+ "eval_samples_per_second": 327.901,
39
+ "eval_steps_per_second": 40.988,
40
+ "step": 140
41
+ },
42
+ {
43
+ "epoch": 2.99,
44
+ "learning_rate": 9e-07,
45
+ "loss": 0.6713,
46
+ "step": 210
47
+ },
48
+ {
49
+ "epoch": 2.99,
50
+ "eval_accuracy": 0.587,
51
+ "eval_f1": 0.39928932873127865,
52
+ "eval_loss": 0.656767725944519,
53
+ "eval_runtime": 3.0012,
54
+ "eval_samples_per_second": 333.2,
55
+ "eval_steps_per_second": 41.65,
56
+ "step": 210
57
+ },
58
+ {
59
+ "epoch": 3.99,
60
+ "learning_rate": 8.666666666666667e-07,
61
+ "loss": 0.6468,
62
+ "step": 280
63
+ },
64
+ {
65
+ "epoch": 3.99,
66
+ "eval_accuracy": 0.7,
67
+ "eval_f1": 0.6707623826267894,
68
+ "eval_loss": 0.6210379600524902,
69
+ "eval_runtime": 3.0442,
70
+ "eval_samples_per_second": 328.492,
71
+ "eval_steps_per_second": 41.062,
72
+ "step": 280
73
+ },
74
+ {
75
+ "epoch": 4.99,
76
+ "learning_rate": 8.333333333333333e-07,
77
+ "loss": 0.6047,
78
+ "step": 350
79
+ },
80
+ {
81
+ "epoch": 4.99,
82
+ "eval_accuracy": 0.732,
83
+ "eval_f1": 0.7285955019767969,
84
+ "eval_loss": 0.5784569382667542,
85
+ "eval_runtime": 3.0658,
86
+ "eval_samples_per_second": 326.18,
87
+ "eval_steps_per_second": 40.773,
88
+ "step": 350
89
+ },
90
+ {
91
+ "epoch": 5.99,
92
+ "learning_rate": 8e-07,
93
+ "loss": 0.5648,
94
+ "step": 420
95
+ },
96
+ {
97
+ "epoch": 5.99,
98
+ "eval_accuracy": 0.733,
99
+ "eval_f1": 0.7318671386608421,
100
+ "eval_loss": 0.5537055730819702,
101
+ "eval_runtime": 3.061,
102
+ "eval_samples_per_second": 326.692,
103
+ "eval_steps_per_second": 40.836,
104
+ "step": 420
105
+ },
106
+ {
107
+ "epoch": 6.99,
108
+ "learning_rate": 7.666666666666667e-07,
109
+ "loss": 0.536,
110
+ "step": 490
111
+ },
112
+ {
113
+ "epoch": 6.99,
114
+ "eval_accuracy": 0.739,
115
+ "eval_f1": 0.7381492469031885,
116
+ "eval_loss": 0.5406165719032288,
117
+ "eval_runtime": 3.3555,
118
+ "eval_samples_per_second": 298.016,
119
+ "eval_steps_per_second": 37.252,
120
+ "step": 490
121
+ }
122
+ ],
123
+ "max_steps": 2100,
124
+ "num_train_epochs": 30,
125
+ "total_flos": 6215998682880000.0,
126
+ "trial_name": null,
127
+ "trial_params": null
128
+ }
checkpoint-490/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be60ed58549fe1b3185c4d116e2ed7593eafbe162cc3300999b64c649675d04
3
+ size 3119
checkpoint-490/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-560/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<mask>": 64000}
checkpoint-560/bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-560/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/bertweet-covid19-base-cased",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 130,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "multi_label_classification",
24
+ "tokenizer_class": "BertweetTokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.17.0",
27
+ "type_vocab_size": 1,
28
+ "use_cache": true,
29
+ "vocab_size": 64001
30
+ }
checkpoint-560/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0af2742714fc9813ca53320a44cae3c405a49e0b36321a924af03f000d43f2
3
+ size 1079327581
checkpoint-560/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3392dc2290586b73cc7916fafb51981e5fb4ecb7cda0a83f08409e2a009f33f1
3
+ size 539689325
checkpoint-560/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca12a0b1d8dae51670b8290d0295c0b10ee4e96d2d8d15692d929bbab3c8dcf
3
+ size 14503
checkpoint-560/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ca221068257890306847f8d3ee335b25a16ad3c8d4a625f911e0389b9d1b6f
3
+ size 559
checkpoint-560/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:799c60f894579b51eeaadbf08b4332c24ed17d6cd503965f0723d32d97cd600b
3
+ size 623
checkpoint-560/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
checkpoint-560/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"normalization": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "vinai/bertweet-covid19-base-cased", "tokenizer_class": "BertweetTokenizer"}
checkpoint-560/trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7430750702529104,
3
+ "best_model_checkpoint": "outputs/bertweet/checkpoint-560",
4
+ "epoch": 7.99290780141844,
5
+ "global_step": 560,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.99,
12
+ "learning_rate": 9.666666666666666e-07,
13
+ "loss": 0.6925,
14
+ "step": 70
15
+ },
16
+ {
17
+ "epoch": 0.99,
18
+ "eval_accuracy": 0.573,
19
+ "eval_f1": 0.3642720915448188,
20
+ "eval_loss": 0.6826930046081543,
21
+ "eval_runtime": 2.9877,
22
+ "eval_samples_per_second": 334.703,
23
+ "eval_steps_per_second": 41.838,
24
+ "step": 70
25
+ },
26
+ {
27
+ "epoch": 1.99,
28
+ "learning_rate": 9.333333333333333e-07,
29
+ "loss": 0.6823,
30
+ "step": 140
31
+ },
32
+ {
33
+ "epoch": 1.99,
34
+ "eval_accuracy": 0.573,
35
+ "eval_f1": 0.3642720915448188,
36
+ "eval_loss": 0.6736124753952026,
37
+ "eval_runtime": 3.0497,
38
+ "eval_samples_per_second": 327.901,
39
+ "eval_steps_per_second": 40.988,
40
+ "step": 140
41
+ },
42
+ {
43
+ "epoch": 2.99,
44
+ "learning_rate": 9e-07,
45
+ "loss": 0.6713,
46
+ "step": 210
47
+ },
48
+ {
49
+ "epoch": 2.99,
50
+ "eval_accuracy": 0.587,
51
+ "eval_f1": 0.39928932873127865,
52
+ "eval_loss": 0.656767725944519,
53
+ "eval_runtime": 3.0012,
54
+ "eval_samples_per_second": 333.2,
55
+ "eval_steps_per_second": 41.65,
56
+ "step": 210
57
+ },
58
+ {
59
+ "epoch": 3.99,
60
+ "learning_rate": 8.666666666666667e-07,
61
+ "loss": 0.6468,
62
+ "step": 280
63
+ },
64
+ {
65
+ "epoch": 3.99,
66
+ "eval_accuracy": 0.7,
67
+ "eval_f1": 0.6707623826267894,
68
+ "eval_loss": 0.6210379600524902,
69
+ "eval_runtime": 3.0442,
70
+ "eval_samples_per_second": 328.492,
71
+ "eval_steps_per_second": 41.062,
72
+ "step": 280
73
+ },
74
+ {
75
+ "epoch": 4.99,
76
+ "learning_rate": 8.333333333333333e-07,
77
+ "loss": 0.6047,
78
+ "step": 350
79
+ },
80
+ {
81
+ "epoch": 4.99,
82
+ "eval_accuracy": 0.732,
83
+ "eval_f1": 0.7285955019767969,
84
+ "eval_loss": 0.5784569382667542,
85
+ "eval_runtime": 3.0658,
86
+ "eval_samples_per_second": 326.18,
87
+ "eval_steps_per_second": 40.773,
88
+ "step": 350
89
+ },
90
+ {
91
+ "epoch": 5.99,
92
+ "learning_rate": 8e-07,
93
+ "loss": 0.5648,
94
+ "step": 420
95
+ },
96
+ {
97
+ "epoch": 5.99,
98
+ "eval_accuracy": 0.733,
99
+ "eval_f1": 0.7318671386608421,
100
+ "eval_loss": 0.5537055730819702,
101
+ "eval_runtime": 3.061,
102
+ "eval_samples_per_second": 326.692,
103
+ "eval_steps_per_second": 40.836,
104
+ "step": 420
105
+ },
106
+ {
107
+ "epoch": 6.99,
108
+ "learning_rate": 7.666666666666667e-07,
109
+ "loss": 0.536,
110
+ "step": 490
111
+ },
112
+ {
113
+ "epoch": 6.99,
114
+ "eval_accuracy": 0.739,
115
+ "eval_f1": 0.7381492469031885,
116
+ "eval_loss": 0.5406165719032288,
117
+ "eval_runtime": 3.3555,
118
+ "eval_samples_per_second": 298.016,
119
+ "eval_steps_per_second": 37.252,
120
+ "step": 490
121
+ },
122
+ {
123
+ "epoch": 7.99,
124
+ "learning_rate": 7.333333333333332e-07,
125
+ "loss": 0.5175,
126
+ "step": 560
127
+ },
128
+ {
129
+ "epoch": 7.99,
130
+ "eval_accuracy": 0.744,
131
+ "eval_f1": 0.7430750702529104,
132
+ "eval_loss": 0.5307690501213074,
133
+ "eval_runtime": 3.1364,
134
+ "eval_samples_per_second": 318.842,
135
+ "eval_steps_per_second": 39.855,
136
+ "step": 560
137
+ }
138
+ ],
139
+ "max_steps": 2100,
140
+ "num_train_epochs": 30,
141
+ "total_flos": 7103998494720000.0,
142
+ "trial_name": null,
143
+ "trial_params": null
144
+ }
checkpoint-560/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be60ed58549fe1b3185c4d116e2ed7593eafbe162cc3300999b64c649675d04
3
+ size 3119
checkpoint-560/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-630/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<mask>": 64000}
checkpoint-630/bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-630/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/bertweet-covid19-base-cased",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 130,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "multi_label_classification",
24
+ "tokenizer_class": "BertweetTokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.17.0",
27
+ "type_vocab_size": 1,
28
+ "use_cache": true,
29
+ "vocab_size": 64001
30
+ }
checkpoint-630/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed3275b6aa834b6e3731e0c09acb3cc7ce4de1843bb8e285c82980e6e8cdfb24
3
+ size 1079327581
checkpoint-630/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:340ff4f94bbd81a9356df698f57832fd0cd040d275e66581a4a35af4c555835f
3
+ size 539689325
checkpoint-630/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf2cef1bd2e8debc8dfd06090f4a9e33703d3bd8a60c5f233ea9bc207d960164
3
+ size 14503
checkpoint-630/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ca5700851802910eef70fadd0dbe9dc923a65ce51e988971904b33dee70ff3
3
+ size 559
checkpoint-630/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c175b756e1d994b8675da4169311fa522310810e074f17bbabbc64f9f178114d
3
+ size 623
checkpoint-630/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
checkpoint-630/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"normalization": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "vinai/bertweet-covid19-base-cased", "tokenizer_class": "BertweetTokenizer"}
checkpoint-630/trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7504007121097755,
3
+ "best_model_checkpoint": "outputs/bertweet/checkpoint-630",
4
+ "epoch": 8.99290780141844,
5
+ "global_step": 630,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.99,
12
+ "learning_rate": 9.666666666666666e-07,
13
+ "loss": 0.6925,
14
+ "step": 70
15
+ },
16
+ {
17
+ "epoch": 0.99,
18
+ "eval_accuracy": 0.573,
19
+ "eval_f1": 0.3642720915448188,
20
+ "eval_loss": 0.6826930046081543,
21
+ "eval_runtime": 2.9877,
22
+ "eval_samples_per_second": 334.703,
23
+ "eval_steps_per_second": 41.838,
24
+ "step": 70
25
+ },
26
+ {
27
+ "epoch": 1.99,
28
+ "learning_rate": 9.333333333333333e-07,
29
+ "loss": 0.6823,
30
+ "step": 140
31
+ },
32
+ {
33
+ "epoch": 1.99,
34
+ "eval_accuracy": 0.573,
35
+ "eval_f1": 0.3642720915448188,
36
+ "eval_loss": 0.6736124753952026,
37
+ "eval_runtime": 3.0497,
38
+ "eval_samples_per_second": 327.901,
39
+ "eval_steps_per_second": 40.988,
40
+ "step": 140
41
+ },
42
+ {
43
+ "epoch": 2.99,
44
+ "learning_rate": 9e-07,
45
+ "loss": 0.6713,
46
+ "step": 210
47
+ },
48
+ {
49
+ "epoch": 2.99,
50
+ "eval_accuracy": 0.587,
51
+ "eval_f1": 0.39928932873127865,
52
+ "eval_loss": 0.656767725944519,
53
+ "eval_runtime": 3.0012,
54
+ "eval_samples_per_second": 333.2,
55
+ "eval_steps_per_second": 41.65,
56
+ "step": 210
57
+ },
58
+ {
59
+ "epoch": 3.99,
60
+ "learning_rate": 8.666666666666667e-07,
61
+ "loss": 0.6468,
62
+ "step": 280
63
+ },
64
+ {
65
+ "epoch": 3.99,
66
+ "eval_accuracy": 0.7,
67
+ "eval_f1": 0.6707623826267894,
68
+ "eval_loss": 0.6210379600524902,
69
+ "eval_runtime": 3.0442,
70
+ "eval_samples_per_second": 328.492,
71
+ "eval_steps_per_second": 41.062,
72
+ "step": 280
73
+ },
74
+ {
75
+ "epoch": 4.99,
76
+ "learning_rate": 8.333333333333333e-07,
77
+ "loss": 0.6047,
78
+ "step": 350
79
+ },
80
+ {
81
+ "epoch": 4.99,
82
+ "eval_accuracy": 0.732,
83
+ "eval_f1": 0.7285955019767969,
84
+ "eval_loss": 0.5784569382667542,
85
+ "eval_runtime": 3.0658,
86
+ "eval_samples_per_second": 326.18,
87
+ "eval_steps_per_second": 40.773,
88
+ "step": 350
89
+ },
90
+ {
91
+ "epoch": 5.99,
92
+ "learning_rate": 8e-07,
93
+ "loss": 0.5648,
94
+ "step": 420
95
+ },
96
+ {
97
+ "epoch": 5.99,
98
+ "eval_accuracy": 0.733,
99
+ "eval_f1": 0.7318671386608421,
100
+ "eval_loss": 0.5537055730819702,
101
+ "eval_runtime": 3.061,
102
+ "eval_samples_per_second": 326.692,
103
+ "eval_steps_per_second": 40.836,
104
+ "step": 420
105
+ },
106
+ {
107
+ "epoch": 6.99,
108
+ "learning_rate": 7.666666666666667e-07,
109
+ "loss": 0.536,
110
+ "step": 490
111
+ },
112
+ {
113
+ "epoch": 6.99,
114
+ "eval_accuracy": 0.739,
115
+ "eval_f1": 0.7381492469031885,
116
+ "eval_loss": 0.5406165719032288,
117
+ "eval_runtime": 3.3555,
118
+ "eval_samples_per_second": 298.016,
119
+ "eval_steps_per_second": 37.252,
120
+ "step": 490
121
+ },
122
+ {
123
+ "epoch": 7.99,
124
+ "learning_rate": 7.333333333333332e-07,
125
+ "loss": 0.5175,
126
+ "step": 560
127
+ },
128
+ {
129
+ "epoch": 7.99,
130
+ "eval_accuracy": 0.744,
131
+ "eval_f1": 0.7430750702529104,
132
+ "eval_loss": 0.5307690501213074,
133
+ "eval_runtime": 3.1364,
134
+ "eval_samples_per_second": 318.842,
135
+ "eval_steps_per_second": 39.855,
136
+ "step": 560
137
+ },
138
+ {
139
+ "epoch": 8.99,
140
+ "learning_rate": 7e-07,
141
+ "loss": 0.5018,
142
+ "step": 630
143
+ },
144
+ {
145
+ "epoch": 8.99,
146
+ "eval_accuracy": 0.751,
147
+ "eval_f1": 0.7504007121097755,
148
+ "eval_loss": 0.5235322117805481,
149
+ "eval_runtime": 2.9996,
150
+ "eval_samples_per_second": 333.377,
151
+ "eval_steps_per_second": 41.672,
152
+ "step": 630
153
+ }
154
+ ],
155
+ "max_steps": 2100,
156
+ "num_train_epochs": 30,
157
+ "total_flos": 7991998306560000.0,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }
checkpoint-630/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be60ed58549fe1b3185c4d116e2ed7593eafbe162cc3300999b64c649675d04
3
+ size 3119
checkpoint-630/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f0b2f4bffbd4dbbe55e73f71c07bd851c61e243cdee504c191652a7e1e80571
3
  size 539689325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:340ff4f94bbd81a9356df698f57832fd0cd040d275e66581a4a35af4c555835f
3
  size 539689325