Hugging Face's logo

anonymous-11
/
erreval-large

Safetensors
roberta
Model card Files
xet
 Community
anonymous-11 commited on
Commit
136adfc
·
verified ·
1 Parent(s): 95dc43f

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +54 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +161 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../model/error_label/iter2/roberta-large/",
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
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 4096,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "max_position_embeddings": 514,
43
+ "model_type": "roberta",
44
+ "num_attention_heads": 16,
45
+ "num_hidden_layers": 24,
46
+ "pad_token_id": 1,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "multi_label_classification",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.40.1",
51
+ "type_vocab_size": 1,
52
+ "use_cache": true,
53
+ "vocab_size": 50265
54
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eef66e725f590b50bab666ad457af272247e8671302e88d9373705be2fe469b
3
+ size 1421532316
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bfd47d609825437d3ac5bd64d2115e18c1d0196bc21b663c4f017fe1019a1a1
3
+ size 2843297406
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1846e84bd67d2dc7d44b38ff7daa7a059f448c91ee24be595e991a15781fb697
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58d5183ec1a828bc9134a65386f121677e779a125f91db69bd4bf1cfd7141e6
3
+ size 1465
trainer_state.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7985865724381626,
3
+ "best_model_checkpoint": "../model/error_label/iter3/roberta-large/checkpoint-1512",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1512,
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
+ "grad_norm": 2.444389581680298,
14
+ "learning_rate": 1.9333333333333333e-05,
15
+ "loss": 0.0794,
16
+ "step": 216
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6384615384615384,
21
+ "eval_loss": 0.1877475380897522,
22
+ "eval_macro_f1": 0.6310718236263808,
23
+ "eval_micro_f1": 0.6981818181818181,
24
+ "eval_precision": 0.7441860465116279,
25
+ "eval_recall": 0.6575342465753424,
26
+ "eval_runtime": 5.4059,
27
+ "eval_samples_per_second": 24.048,
28
+ "eval_steps_per_second": 1.665,
29
+ "step": 216
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 10.301380157470703,
34
+ "learning_rate": 1.866666666666667e-05,
35
+ "loss": 0.0566,
36
+ "step": 432
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6615384615384615,
41
+ "eval_loss": 0.19309891760349274,
42
+ "eval_macro_f1": 0.6247135104797814,
43
+ "eval_micro_f1": 0.7285714285714286,
44
+ "eval_precision": 0.7611940298507462,
45
+ "eval_recall": 0.6986301369863014,
46
+ "eval_runtime": 5.4486,
47
+ "eval_samples_per_second": 23.859,
48
+ "eval_steps_per_second": 1.652,
49
+ "step": 432
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.09097255021333694,
54
+ "learning_rate": 1.8e-05,
55
+ "loss": 0.0451,
56
+ "step": 648
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6923076923076923,
61
+ "eval_loss": 0.19997228682041168,
62
+ "eval_macro_f1": 0.6354495573188692,
63
+ "eval_micro_f1": 0.7375886524822695,
64
+ "eval_precision": 0.7647058823529411,
65
+ "eval_recall": 0.7123287671232876,
66
+ "eval_runtime": 5.4619,
67
+ "eval_samples_per_second": 23.801,
68
+ "eval_steps_per_second": 1.648,
69
+ "step": 648
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 0.2933971881866455,
74
+ "learning_rate": 1.7333333333333336e-05,
75
+ "loss": 0.0399,
76
+ "step": 864
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6923076923076923,
81
+ "eval_loss": 0.23130807280540466,
82
+ "eval_macro_f1": 0.6358429531224322,
83
+ "eval_micro_f1": 0.7379310344827587,
84
+ "eval_precision": 0.7430555555555556,
85
+ "eval_recall": 0.7328767123287672,
86
+ "eval_runtime": 5.4233,
87
+ "eval_samples_per_second": 23.971,
88
+ "eval_steps_per_second": 1.659,
89
+ "step": 864
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 7.584293365478516,
94
+ "learning_rate": 1.6666666666666667e-05,
95
+ "loss": 0.0294,
96
+ "step": 1080
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7076923076923077,
101
+ "eval_loss": 0.2406659871339798,
102
+ "eval_macro_f1": 0.6706986041797571,
103
+ "eval_micro_f1": 0.7526132404181183,
104
+ "eval_precision": 0.7659574468085106,
105
+ "eval_recall": 0.7397260273972602,
106
+ "eval_runtime": 5.377,
107
+ "eval_samples_per_second": 24.177,
108
+ "eval_steps_per_second": 1.674,
109
+ "step": 1080
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 0.026619859039783478,
114
+ "learning_rate": 1.6000000000000003e-05,
115
+ "loss": 0.0235,
116
+ "step": 1296
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7076923076923077,
121
+ "eval_loss": 0.22555890679359436,
122
+ "eval_macro_f1": 0.6403863866629824,
123
+ "eval_micro_f1": 0.759581881533101,
124
+ "eval_precision": 0.7730496453900709,
125
+ "eval_recall": 0.7465753424657534,
126
+ "eval_runtime": 5.4374,
127
+ "eval_samples_per_second": 23.909,
128
+ "eval_steps_per_second": 1.655,
129
+ "step": 1296
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 0.8526526689529419,
134
+ "learning_rate": 1.5333333333333334e-05,
135
+ "loss": 0.0192,
136
+ "step": 1512
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7461538461538462,
141
+ "eval_loss": 0.20616570115089417,
142
+ "eval_macro_f1": 0.7251903269144648,
143
+ "eval_micro_f1": 0.7985865724381626,
144
+ "eval_precision": 0.8248175182481752,
145
+ "eval_recall": 0.773972602739726,
146
+ "eval_runtime": 5.4401,
147
+ "eval_samples_per_second": 23.897,
148
+ "eval_steps_per_second": 1.654,
149
+ "step": 1512
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 6480,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 30,
156
+ "save_steps": 500,
157
+ "total_flos": 2.25068268160512e+16,
158
+ "train_batch_size": 16,
159
+ "trial_name": null,
160
+ "trial_params": null
161
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7786f82204aa3acb6d08a217aed666bc78e138036364c8f6b8a73c6b6bfd607b
3
+ size 5393