Hugging Face's logo

hallisky
/
type-classifier-gpt4-data

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Inference Endpoints
Model card Files Metrics Community
hallisky commited on
Commit
fa763be
·
verified ·
1 Parent(s): b373734

Upload 12 files

Browse files
Files changed (12) hide show
  1. config.json +40 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +15 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +57 -0
  10. trainer_state.json +231 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "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": "type_persuasive",
15
+ "1": "type_narrative",
16
+ "2": "type_expository",
17
+ "3": "type_descriptive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "type_descriptive": 3,
23
+ "type_expository": 2,
24
+ "type_narrative": 1,
25
+ "type_persuasive": 0
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 514,
29
+ "model_type": "roberta",
30
+ "num_attention_heads": 16,
31
+ "num_hidden_layers": 24,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.0",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 50265
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f2615132b16115ca8e120399a277387db53a4409239601b145df34f980f316
3
+ size 1421503616
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aceae5388f1649af159b70064c707cea8531538367c689e8dcf022805c2d2b1b
3
+ size 2843239661
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24cb190af82dc0dcf6f4d3031dc7105cea6260aded8c9605c7e964d802303d35
3
+ size 14180
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27b052646dcb561cbd68156c30bd466ce59bda64cf3c8eba9c3c1113af9827c
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,231 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8311111111111111,
3
+ "best_model_checkpoint": "train_binary/05-13-2024_12:08:27/checkpoint-160",
4
+ "epoch": 5.0,
5
+ "eval_steps": 20,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "grad_norm": 7.1047492027282715,
14
+ "learning_rate": 5e-05,
15
+ "loss": 1.2022,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "eval_acc_product": 0.2339592488915767,
21
+ "eval_loss": 0.6791220903396606,
22
+ "eval_overall_acc": 0.7155555555555555,
23
+ "eval_runtime": 4.3626,
24
+ "eval_samples_per_second": 206.3,
25
+ "eval_steps_per_second": 1.834,
26
+ "eval_type_descriptive_acc": 0.5418502202643172,
27
+ "eval_type_expository_acc": 0.9829059829059829,
28
+ "eval_type_narrative_acc": 0.6559633027522935,
29
+ "eval_type_persuasive_acc": 0.669683257918552,
30
+ "step": 20
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 9.341121673583984,
35
+ "learning_rate": 4.4444444444444447e-05,
36
+ "loss": 0.634,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_acc_product": 0.374576132841691,
42
+ "eval_loss": 0.5208084583282471,
43
+ "eval_overall_acc": 0.79,
44
+ "eval_runtime": 4.3469,
45
+ "eval_samples_per_second": 207.046,
46
+ "eval_steps_per_second": 1.84,
47
+ "eval_type_descriptive_acc": 0.6519823788546255,
48
+ "eval_type_expository_acc": 0.9358974358974359,
49
+ "eval_type_narrative_acc": 0.8027522935779816,
50
+ "eval_type_persuasive_acc": 0.7647058823529411,
51
+ "step": 40
52
+ },
53
+ {
54
+ "epoch": 1.5,
55
+ "grad_norm": 12.583885192871094,
56
+ "learning_rate": 3.888888888888889e-05,
57
+ "loss": 0.4102,
58
+ "step": 60
59
+ },
60
+ {
61
+ "epoch": 1.5,
62
+ "eval_acc_product": 0.37668167775444333,
63
+ "eval_loss": 0.5568819046020508,
64
+ "eval_overall_acc": 0.8033333333333333,
65
+ "eval_runtime": 4.3493,
66
+ "eval_samples_per_second": 206.93,
67
+ "eval_steps_per_second": 1.839,
68
+ "eval_type_descriptive_acc": 0.5374449339207048,
69
+ "eval_type_expository_acc": 0.9829059829059829,
70
+ "eval_type_narrative_acc": 0.8165137614678899,
71
+ "eval_type_persuasive_acc": 0.8733031674208145,
72
+ "step": 60
73
+ },
74
+ {
75
+ "epoch": 2.0,
76
+ "grad_norm": 18.182939529418945,
77
+ "learning_rate": 3.3333333333333335e-05,
78
+ "loss": 0.3891,
79
+ "step": 80
80
+ },
81
+ {
82
+ "epoch": 2.0,
83
+ "eval_acc_product": 0.3805953902407894,
84
+ "eval_loss": 0.528384804725647,
85
+ "eval_overall_acc": 0.8,
86
+ "eval_runtime": 4.3488,
87
+ "eval_samples_per_second": 206.952,
88
+ "eval_steps_per_second": 1.84,
89
+ "eval_type_descriptive_acc": 0.6035242290748899,
90
+ "eval_type_expository_acc": 0.9914529914529915,
91
+ "eval_type_narrative_acc": 0.8623853211009175,
92
+ "eval_type_persuasive_acc": 0.7375565610859729,
93
+ "step": 80
94
+ },
95
+ {
96
+ "epoch": 2.5,
97
+ "grad_norm": 6.487391471862793,
98
+ "learning_rate": 2.777777777777778e-05,
99
+ "loss": 0.2423,
100
+ "step": 100
101
+ },
102
+ {
103
+ "epoch": 2.5,
104
+ "eval_acc_product": 0.3477393972726718,
105
+ "eval_loss": 0.7446629405021667,
106
+ "eval_overall_acc": 0.7888888888888889,
107
+ "eval_runtime": 4.3484,
108
+ "eval_samples_per_second": 206.972,
109
+ "eval_steps_per_second": 1.84,
110
+ "eval_type_descriptive_acc": 0.6607929515418502,
111
+ "eval_type_expository_acc": 0.9358974358974359,
112
+ "eval_type_narrative_acc": 0.5779816513761468,
113
+ "eval_type_persuasive_acc": 0.9728506787330317,
114
+ "step": 100
115
+ },
116
+ {
117
+ "epoch": 3.0,
118
+ "grad_norm": 10.529717445373535,
119
+ "learning_rate": 2.2222222222222223e-05,
120
+ "loss": 0.27,
121
+ "step": 120
122
+ },
123
+ {
124
+ "epoch": 3.0,
125
+ "eval_acc_product": 0.3687367678193366,
126
+ "eval_loss": 0.5524727702140808,
127
+ "eval_overall_acc": 0.8033333333333333,
128
+ "eval_runtime": 4.361,
129
+ "eval_samples_per_second": 206.376,
130
+ "eval_steps_per_second": 1.834,
131
+ "eval_type_descriptive_acc": 0.5154185022026432,
132
+ "eval_type_expository_acc": 0.9700854700854701,
133
+ "eval_type_narrative_acc": 0.7798165137614679,
134
+ "eval_type_persuasive_acc": 0.9457013574660633,
135
+ "step": 120
136
+ },
137
+ {
138
+ "epoch": 3.5,
139
+ "grad_norm": 8.022017478942871,
140
+ "learning_rate": 1.6666666666666667e-05,
141
+ "loss": 0.116,
142
+ "step": 140
143
+ },
144
+ {
145
+ "epoch": 3.5,
146
+ "eval_acc_product": 0.42496128327762595,
147
+ "eval_loss": 0.666808009147644,
148
+ "eval_overall_acc": 0.8177777777777778,
149
+ "eval_runtime": 4.3416,
150
+ "eval_samples_per_second": 207.296,
151
+ "eval_steps_per_second": 1.843,
152
+ "eval_type_descriptive_acc": 0.6519823788546255,
153
+ "eval_type_expository_acc": 0.9786324786324786,
154
+ "eval_type_narrative_acc": 0.7706422018348624,
155
+ "eval_type_persuasive_acc": 0.8642533936651584,
156
+ "step": 140
157
+ },
158
+ {
159
+ "epoch": 4.0,
160
+ "grad_norm": 11.408710479736328,
161
+ "learning_rate": 1.1111111111111112e-05,
162
+ "loss": 0.1078,
163
+ "step": 160
164
+ },
165
+ {
166
+ "epoch": 4.0,
167
+ "eval_acc_product": 0.4513722367715261,
168
+ "eval_loss": 0.655240535736084,
169
+ "eval_overall_acc": 0.8311111111111111,
170
+ "eval_runtime": 4.3513,
171
+ "eval_samples_per_second": 206.837,
172
+ "eval_steps_per_second": 1.839,
173
+ "eval_type_descriptive_acc": 0.6740088105726872,
174
+ "eval_type_expository_acc": 0.9871794871794872,
175
+ "eval_type_narrative_acc": 0.7385321100917431,
176
+ "eval_type_persuasive_acc": 0.918552036199095,
177
+ "step": 160
178
+ },
179
+ {
180
+ "epoch": 4.5,
181
+ "grad_norm": 8.358388900756836,
182
+ "learning_rate": 5.555555555555556e-06,
183
+ "loss": 0.0381,
184
+ "step": 180
185
+ },
186
+ {
187
+ "epoch": 4.5,
188
+ "eval_acc_product": 0.4348685552569168,
189
+ "eval_loss": 0.7252246141433716,
190
+ "eval_overall_acc": 0.8222222222222222,
191
+ "eval_runtime": 4.3445,
192
+ "eval_samples_per_second": 207.158,
193
+ "eval_steps_per_second": 1.841,
194
+ "eval_type_descriptive_acc": 0.7224669603524229,
195
+ "eval_type_expository_acc": 0.9871794871794872,
196
+ "eval_type_narrative_acc": 0.7018348623853211,
197
+ "eval_type_persuasive_acc": 0.8687782805429864,
198
+ "step": 180
199
+ },
200
+ {
201
+ "epoch": 5.0,
202
+ "grad_norm": 8.94113540649414,
203
+ "learning_rate": 0.0,
204
+ "loss": 0.0417,
205
+ "step": 200
206
+ },
207
+ {
208
+ "epoch": 5.0,
209
+ "eval_acc_product": 0.45515444892534596,
210
+ "eval_loss": 0.7260475754737854,
211
+ "eval_overall_acc": 0.83,
212
+ "eval_runtime": 4.34,
213
+ "eval_samples_per_second": 207.373,
214
+ "eval_steps_per_second": 1.843,
215
+ "eval_type_descriptive_acc": 0.7268722466960352,
216
+ "eval_type_expository_acc": 0.9871794871794872,
217
+ "eval_type_narrative_acc": 0.7339449541284404,
218
+ "eval_type_persuasive_acc": 0.8642533936651584,
219
+ "step": 200
220
+ }
221
+ ],
222
+ "logging_steps": 20,
223
+ "max_steps": 200,
224
+ "num_input_tokens_seen": 0,
225
+ "num_train_epochs": 5,
226
+ "save_steps": 20,
227
+ "total_flos": 5941102588416000.0,
228
+ "train_batch_size": 128,
229
+ "trial_name": null,
230
+ "trial_params": null
231
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32cdc29f7c76191d05b901961c85a3ca6f6a85e1c897f267ac447dc53184268
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff