CarmelKron commited on
Commit
b2bfded
·
verified ·
1 Parent(s): df81050

Upload best model from trial 8

Browse files
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "id2label": {
10
+ "0": "LABEL_0",
11
+ "1": "LABEL_1",
12
+ "2": "LABEL_2",
13
+ "3": "LABEL_3",
14
+ "4": "LABEL_4"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2,
22
+ "LABEL_3": 3,
23
+ "LABEL_4": 4
24
+ },
25
+ "layer_norm_eps": 1e-07,
26
+ "legacy": true,
27
+ "max_position_embeddings": 512,
28
+ "max_relative_positions": -1,
29
+ "model_type": "deberta-v2",
30
+ "norm_rel_ebd": "layer_norm",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 0,
34
+ "pooler_dropout": 0,
35
+ "pooler_hidden_act": "gelu",
36
+ "pooler_hidden_size": 768,
37
+ "pos_att_type": [
38
+ "p2c",
39
+ "c2p"
40
+ ],
41
+ "position_biased_input": false,
42
+ "position_buckets": 256,
43
+ "relative_attention": true,
44
+ "share_att_key": true,
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.55.2",
47
+ "type_vocab_size": 0,
48
+ "vocab_size": 128100
49
+ }
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f992f7047ae92e0aa5485e8a38c5260052d3c33d6d4d34bab86aa2a6348c3461
3
+ size 737728508
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b89c301ba0f97c8147ddb83a357c4c2cedb481c48df67fb06df7fecf9690c4
3
+ size 1475580107
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da37e78f45c596eef9f3d89014cd11d6d8fad5cbccdb0d5a4408a152972b4978
3
+ size 14645
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd62c4fa0e621f434823ca4c1ebb000d425741499a354ad7cb55fe99f563ca07
3
+ size 1465
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/trainer_state.json ADDED
@@ -0,0 +1,303 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": 0.885689990281827,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 13.0,
6
+ "eval_steps": 500,
7
+ "global_step": 26754,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "grad_norm": 9.557151794433594,
15
+ "learning_rate": 2.137832696528345e-05,
16
+ "loss": 1.246,
17
+ "step": 2058
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.733114674441205,
22
+ "eval_f1": 0.7345297547604791,
23
+ "eval_loss": 0.8340457677841187,
24
+ "eval_precision": 0.739101037433312,
25
+ "eval_recall": 0.733114674441205,
26
+ "eval_roc_auc": NaN,
27
+ "eval_runtime": 19.2302,
28
+ "eval_samples_per_second": 428.077,
29
+ "eval_steps_per_second": 26.781,
30
+ "step": 2058
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "grad_norm": 4.6117963790893555,
35
+ "learning_rate": 4.27670468945753e-05,
36
+ "loss": 0.7508,
37
+ "step": 4116
38
+ },
39
+ {
40
+ "epoch": 2.0,
41
+ "eval_accuracy": 0.776846452866861,
42
+ "eval_f1": 0.774727751192474,
43
+ "eval_loss": 0.744608461856842,
44
+ "eval_precision": 0.7901857714299474,
45
+ "eval_recall": 0.776846452866861,
46
+ "eval_roc_auc": NaN,
47
+ "eval_runtime": 19.4573,
48
+ "eval_samples_per_second": 423.08,
49
+ "eval_steps_per_second": 26.468,
50
+ "step": 4116
51
+ },
52
+ {
53
+ "epoch": 3.0,
54
+ "grad_norm": 7.426347255706787,
55
+ "learning_rate": 4.808825764197505e-05,
56
+ "loss": 0.6277,
57
+ "step": 6174
58
+ },
59
+ {
60
+ "epoch": 3.0,
61
+ "eval_accuracy": 0.831025267249757,
62
+ "eval_f1": 0.8301827759997149,
63
+ "eval_loss": 0.6398176550865173,
64
+ "eval_precision": 0.836518370474697,
65
+ "eval_recall": 0.831025267249757,
66
+ "eval_roc_auc": NaN,
67
+ "eval_runtime": 19.4102,
68
+ "eval_samples_per_second": 424.107,
69
+ "eval_steps_per_second": 26.532,
70
+ "step": 6174
71
+ },
72
+ {
73
+ "epoch": 4.0,
74
+ "grad_norm": 7.2657647132873535,
75
+ "learning_rate": 4.7157038457397446e-05,
76
+ "loss": 0.5417,
77
+ "step": 8232
78
+ },
79
+ {
80
+ "epoch": 4.0,
81
+ "eval_accuracy": 0.8706268221574344,
82
+ "eval_f1": 0.8706751199461219,
83
+ "eval_loss": 0.5832339525222778,
84
+ "eval_precision": 0.8721290462325244,
85
+ "eval_recall": 0.8706268221574344,
86
+ "eval_roc_auc": NaN,
87
+ "eval_runtime": 19.4247,
88
+ "eval_samples_per_second": 423.79,
89
+ "eval_steps_per_second": 26.513,
90
+ "step": 8232
91
+ },
92
+ {
93
+ "epoch": 5.0,
94
+ "grad_norm": 3.040290594100952,
95
+ "learning_rate": 4.550627437079649e-05,
96
+ "loss": 0.4762,
97
+ "step": 10290
98
+ },
99
+ {
100
+ "epoch": 5.0,
101
+ "eval_accuracy": 0.8603012633624878,
102
+ "eval_f1": 0.8599530965002472,
103
+ "eval_loss": 0.6185116767883301,
104
+ "eval_precision": 0.8641868614948529,
105
+ "eval_recall": 0.8603012633624878,
106
+ "eval_roc_auc": NaN,
107
+ "eval_runtime": 19.3526,
108
+ "eval_samples_per_second": 425.37,
109
+ "eval_steps_per_second": 26.611,
110
+ "step": 10290
111
+ },
112
+ {
113
+ "epoch": 6.0,
114
+ "grad_norm": 8.751374244689941,
115
+ "learning_rate": 4.3187588641572475e-05,
116
+ "loss": 0.4349,
117
+ "step": 12348
118
+ },
119
+ {
120
+ "epoch": 6.0,
121
+ "eval_accuracy": 0.8794946550048591,
122
+ "eval_f1": 0.8795945279125102,
123
+ "eval_loss": 0.5549774765968323,
124
+ "eval_precision": 0.8802327205942286,
125
+ "eval_recall": 0.8794946550048591,
126
+ "eval_roc_auc": NaN,
127
+ "eval_runtime": 19.3481,
128
+ "eval_samples_per_second": 425.469,
129
+ "eval_steps_per_second": 26.618,
130
+ "step": 12348
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "grad_norm": 10.343045234680176,
135
+ "learning_rate": 4.027349200329359e-05,
136
+ "loss": 0.4034,
137
+ "step": 14406
138
+ },
139
+ {
140
+ "epoch": 7.0,
141
+ "eval_accuracy": 0.8794946550048591,
142
+ "eval_f1": 0.8794189901258025,
143
+ "eval_loss": 0.5672433972358704,
144
+ "eval_precision": 0.8806157920177813,
145
+ "eval_recall": 0.8794946550048591,
146
+ "eval_roc_auc": NaN,
147
+ "eval_runtime": 19.4101,
148
+ "eval_samples_per_second": 424.11,
149
+ "eval_steps_per_second": 26.533,
150
+ "step": 14406
151
+ },
152
+ {
153
+ "epoch": 8.0,
154
+ "grad_norm": 2.304270029067993,
155
+ "learning_rate": 3.685511508322293e-05,
156
+ "loss": 0.3743,
157
+ "step": 16464
158
+ },
159
+ {
160
+ "epoch": 8.0,
161
+ "eval_accuracy": 0.8709912536443148,
162
+ "eval_f1": 0.8704364723905518,
163
+ "eval_loss": 0.6466076374053955,
164
+ "eval_precision": 0.8732373502919328,
165
+ "eval_recall": 0.8709912536443148,
166
+ "eval_roc_auc": NaN,
167
+ "eval_runtime": 19.414,
168
+ "eval_samples_per_second": 424.023,
169
+ "eval_steps_per_second": 26.527,
170
+ "step": 16464
171
+ },
172
+ {
173
+ "epoch": 9.0,
174
+ "grad_norm": 0.13895219564437866,
175
+ "learning_rate": 3.303935853415827e-05,
176
+ "loss": 0.3514,
177
+ "step": 18522
178
+ },
179
+ {
180
+ "epoch": 9.0,
181
+ "eval_accuracy": 0.8725704567541303,
182
+ "eval_f1": 0.8721343511469051,
183
+ "eval_loss": 0.6585362553596497,
184
+ "eval_precision": 0.87386146666679,
185
+ "eval_recall": 0.8725704567541303,
186
+ "eval_roc_auc": NaN,
187
+ "eval_runtime": 19.2639,
188
+ "eval_samples_per_second": 427.329,
189
+ "eval_steps_per_second": 26.734,
190
+ "step": 18522
191
+ },
192
+ {
193
+ "epoch": 10.0,
194
+ "grad_norm": 4.636017322540283,
195
+ "learning_rate": 2.8945550000636792e-05,
196
+ "loss": 0.3293,
197
+ "step": 20580
198
+ },
199
+ {
200
+ "epoch": 10.0,
201
+ "eval_accuracy": 0.8797376093294461,
202
+ "eval_f1": 0.8794775218925387,
203
+ "eval_loss": 0.6302573680877686,
204
+ "eval_precision": 0.8801343600741198,
205
+ "eval_recall": 0.8797376093294461,
206
+ "eval_roc_auc": NaN,
207
+ "eval_runtime": 19.3234,
208
+ "eval_samples_per_second": 426.012,
209
+ "eval_steps_per_second": 26.652,
210
+ "step": 20580
211
+ },
212
+ {
213
+ "epoch": 11.0,
214
+ "grad_norm": 2.0297155380249023,
215
+ "learning_rate": 2.470171246400178e-05,
216
+ "loss": 0.3141,
217
+ "step": 22638
218
+ },
219
+ {
220
+ "epoch": 11.0,
221
+ "eval_accuracy": 0.8827745383867833,
222
+ "eval_f1": 0.8829217656039987,
223
+ "eval_loss": 0.6386178731918335,
224
+ "eval_precision": 0.884596421433805,
225
+ "eval_recall": 0.8827745383867833,
226
+ "eval_roc_auc": NaN,
227
+ "eval_runtime": 19.2997,
228
+ "eval_samples_per_second": 426.535,
229
+ "eval_steps_per_second": 26.684,
230
+ "step": 22638
231
+ },
232
+ {
233
+ "epoch": 12.0,
234
+ "grad_norm": 21.4561767578125,
235
+ "learning_rate": 2.0440560663921123e-05,
236
+ "loss": 0.3002,
237
+ "step": 24696
238
+ },
239
+ {
240
+ "epoch": 12.0,
241
+ "eval_accuracy": 0.8816812439261419,
242
+ "eval_f1": 0.881785083019734,
243
+ "eval_loss": 0.6476637125015259,
244
+ "eval_precision": 0.8828217540725527,
245
+ "eval_recall": 0.8816812439261419,
246
+ "eval_roc_auc": NaN,
247
+ "eval_runtime": 19.314,
248
+ "eval_samples_per_second": 426.22,
249
+ "eval_steps_per_second": 26.665,
250
+ "step": 24696
251
+ },
252
+ {
253
+ "epoch": 13.0,
254
+ "grad_norm": 0.2733791768550873,
255
+ "learning_rate": 1.6295350797634053e-05,
256
+ "loss": 0.2817,
257
+ "step": 26754
258
+ },
259
+ {
260
+ "epoch": 13.0,
261
+ "eval_accuracy": 0.885689990281827,
262
+ "eval_f1": 0.8856619456635108,
263
+ "eval_loss": 0.6517186164855957,
264
+ "eval_precision": 0.8880449152425179,
265
+ "eval_recall": 0.885689990281827,
266
+ "eval_roc_auc": NaN,
267
+ "eval_runtime": 19.3125,
268
+ "eval_samples_per_second": 426.252,
269
+ "eval_steps_per_second": 26.667,
270
+ "step": 26754
271
+ }
272
+ ],
273
+ "logging_steps": 500,
274
+ "max_steps": 41160,
275
+ "num_input_tokens_seen": 0,
276
+ "num_train_epochs": 20,
277
+ "save_steps": 500,
278
+ "stateful_callbacks": {
279
+ "EarlyStoppingCallback": {
280
+ "args": {
281
+ "early_stopping_patience": 4,
282
+ "early_stopping_threshold": 0.0
283
+ },
284
+ "attributes": {
285
+ "early_stopping_patience_counter": 0
286
+ }
287
+ },
288
+ "TrainerControl": {
289
+ "args": {
290
+ "should_epoch_stop": false,
291
+ "should_evaluate": false,
292
+ "should_log": false,
293
+ "should_save": true,
294
+ "should_training_stop": false
295
+ },
296
+ "attributes": {}
297
+ }
298
+ },
299
+ "total_flos": 2.81557906508736e+16,
300
+ "train_batch_size": 16,
301
+ "trial_name": null,
302
+ "trial_params": null
303
+ }
HF_FT_Carmel_Preprocess3_Data/trial_8/checkpoint-26754/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6dfeae02792291974eb09c8f9e744be99e416ec7f52fe0b6809092555edc1b4
3
+ size 5777