CarmelKron commited on
Commit
eb9eee7
·
verified ·
1 Parent(s): 28564fc

Upload best model from trial 13

Browse files
HF_FT_Carmel_Preprocess3_Data/trial_13/checkpoint-22638/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
HF_FT_Carmel_Preprocess3_Data/trial_13/checkpoint-22638/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_13/checkpoint-22638/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05a148962130393cc2f1e099aa3b53259a8bb02206196a81123f868d4ddc90fb
3
+ size 737728508
HF_FT_Carmel_Preprocess3_Data/trial_13/checkpoint-22638/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56c5a2192a5451ccff467ece338b3a96eaf4471edc63b2ebcb42bc5284a1d5d
3
+ size 1475580107
HF_FT_Carmel_Preprocess3_Data/trial_13/checkpoint-22638/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f9a6fd942c4d8dcb2c1c98ab8df787f57e1422dddc0f4b3558bce43734ad593
3
+ size 14645
HF_FT_Carmel_Preprocess3_Data/trial_13/checkpoint-22638/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a805ce237311448b9115b9040c06dd3d86c1dcd030dbbd787bb4b1132e44a380
3
+ size 1465
HF_FT_Carmel_Preprocess3_Data/trial_13/checkpoint-22638/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_13/checkpoint-22638/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_13/checkpoint-22638/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
HF_FT_Carmel_Preprocess3_Data/trial_13/checkpoint-22638/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_13/checkpoint-22638/trainer_state.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": 0.8819241982507289,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 11.0,
6
+ "eval_steps": 500,
7
+ "global_step": 22638,
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": 20.825756072998047,
15
+ "learning_rate": 1.6950681711496676e-05,
16
+ "loss": 1.2103,
17
+ "step": 2058
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7148931000971818,
22
+ "eval_f1": 0.7153672590765376,
23
+ "eval_loss": 0.792381227016449,
24
+ "eval_precision": 0.7232408246914734,
25
+ "eval_recall": 0.7148931000971818,
26
+ "eval_roc_auc": NaN,
27
+ "eval_runtime": 19.428,
28
+ "eval_samples_per_second": 423.717,
29
+ "eval_steps_per_second": 26.508,
30
+ "step": 2058
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "grad_norm": 9.629911422729492,
35
+ "learning_rate": 2.03215155118464e-05,
36
+ "loss": 0.6348,
37
+ "step": 4116
38
+ },
39
+ {
40
+ "epoch": 2.0,
41
+ "eval_accuracy": 0.8007774538386784,
42
+ "eval_f1": 0.7999767839531511,
43
+ "eval_loss": 0.5844112634658813,
44
+ "eval_precision": 0.8085904039123999,
45
+ "eval_recall": 0.8007774538386784,
46
+ "eval_roc_auc": NaN,
47
+ "eval_runtime": 19.3415,
48
+ "eval_samples_per_second": 425.614,
49
+ "eval_steps_per_second": 26.627,
50
+ "step": 4116
51
+ },
52
+ {
53
+ "epoch": 3.0,
54
+ "grad_norm": 17.472238540649414,
55
+ "learning_rate": 1.9955356265311636e-05,
56
+ "loss": 0.4415,
57
+ "step": 6174
58
+ },
59
+ {
60
+ "epoch": 3.0,
61
+ "eval_accuracy": 0.8247084548104956,
62
+ "eval_f1": 0.8240725294525734,
63
+ "eval_loss": 0.5216482281684875,
64
+ "eval_precision": 0.8329904299128336,
65
+ "eval_recall": 0.8247084548104956,
66
+ "eval_roc_auc": NaN,
67
+ "eval_runtime": 19.2856,
68
+ "eval_samples_per_second": 426.848,
69
+ "eval_steps_per_second": 26.704,
70
+ "step": 6174
71
+ },
72
+ {
73
+ "epoch": 4.0,
74
+ "grad_norm": 7.518006324768066,
75
+ "learning_rate": 1.9317476847591254e-05,
76
+ "loss": 0.3388,
77
+ "step": 8232
78
+ },
79
+ {
80
+ "epoch": 4.0,
81
+ "eval_accuracy": 0.8651603498542274,
82
+ "eval_f1": 0.8650290008648521,
83
+ "eval_loss": 0.47454291582107544,
84
+ "eval_precision": 0.8673403039820886,
85
+ "eval_recall": 0.8651603498542274,
86
+ "eval_roc_auc": NaN,
87
+ "eval_runtime": 19.3144,
88
+ "eval_samples_per_second": 426.211,
89
+ "eval_steps_per_second": 26.664,
90
+ "step": 8232
91
+ },
92
+ {
93
+ "epoch": 5.0,
94
+ "grad_norm": 27.361248016357422,
95
+ "learning_rate": 1.8425655039176598e-05,
96
+ "loss": 0.2868,
97
+ "step": 10290
98
+ },
99
+ {
100
+ "epoch": 5.0,
101
+ "eval_accuracy": 0.869290573372206,
102
+ "eval_f1": 0.8690348295638131,
103
+ "eval_loss": 0.48756325244903564,
104
+ "eval_precision": 0.8714592216740054,
105
+ "eval_recall": 0.869290573372206,
106
+ "eval_roc_auc": NaN,
107
+ "eval_runtime": 19.3396,
108
+ "eval_samples_per_second": 425.656,
109
+ "eval_steps_per_second": 26.629,
110
+ "step": 10290
111
+ },
112
+ {
113
+ "epoch": 6.0,
114
+ "grad_norm": 8.075338363647461,
115
+ "learning_rate": 1.7304746027281637e-05,
116
+ "loss": 0.2424,
117
+ "step": 12348
118
+ },
119
+ {
120
+ "epoch": 6.0,
121
+ "eval_accuracy": 0.8732993197278912,
122
+ "eval_f1": 0.8733312865829371,
123
+ "eval_loss": 0.4979771673679352,
124
+ "eval_precision": 0.8740343238013134,
125
+ "eval_recall": 0.8732993197278912,
126
+ "eval_roc_auc": NaN,
127
+ "eval_runtime": 19.2665,
128
+ "eval_samples_per_second": 427.27,
129
+ "eval_steps_per_second": 26.73,
130
+ "step": 12348
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "grad_norm": 13.662607192993164,
135
+ "learning_rate": 1.5985989688614488e-05,
136
+ "loss": 0.2135,
137
+ "step": 14406
138
+ },
139
+ {
140
+ "epoch": 7.0,
141
+ "eval_accuracy": 0.8768221574344023,
142
+ "eval_f1": 0.8764307715557743,
143
+ "eval_loss": 0.5087255239486694,
144
+ "eval_precision": 0.8779071365975573,
145
+ "eval_recall": 0.8768221574344023,
146
+ "eval_roc_auc": NaN,
147
+ "eval_runtime": 19.2863,
148
+ "eval_samples_per_second": 426.832,
149
+ "eval_steps_per_second": 26.703,
150
+ "step": 14406
151
+ },
152
+ {
153
+ "epoch": 8.0,
154
+ "grad_norm": 12.276311874389648,
155
+ "learning_rate": 1.4506139930040755e-05,
156
+ "loss": 0.1826,
157
+ "step": 16464
158
+ },
159
+ {
160
+ "epoch": 8.0,
161
+ "eval_accuracy": 0.8748785228377065,
162
+ "eval_f1": 0.8746022128581452,
163
+ "eval_loss": 0.6030776500701904,
164
+ "eval_precision": 0.8756983698389496,
165
+ "eval_recall": 0.8748785228377065,
166
+ "eval_roc_auc": NaN,
167
+ "eval_runtime": 19.3048,
168
+ "eval_samples_per_second": 426.423,
169
+ "eval_steps_per_second": 26.677,
170
+ "step": 16464
171
+ },
172
+ {
173
+ "epoch": 9.0,
174
+ "grad_norm": 7.594466686248779,
175
+ "learning_rate": 1.2906440352525177e-05,
176
+ "loss": 0.1647,
177
+ "step": 18522
178
+ },
179
+ {
180
+ "epoch": 9.0,
181
+ "eval_accuracy": 0.8722060252672498,
182
+ "eval_f1": 0.8717256568267564,
183
+ "eval_loss": 0.6118150353431702,
184
+ "eval_precision": 0.8732051156961821,
185
+ "eval_recall": 0.8722060252672498,
186
+ "eval_roc_auc": NaN,
187
+ "eval_runtime": 19.336,
188
+ "eval_samples_per_second": 425.734,
189
+ "eval_steps_per_second": 26.634,
190
+ "step": 18522
191
+ },
192
+ {
193
+ "epoch": 10.0,
194
+ "grad_norm": 3.6977789402008057,
195
+ "learning_rate": 1.1231474786727767e-05,
196
+ "loss": 0.1402,
197
+ "step": 20580
198
+ },
199
+ {
200
+ "epoch": 10.0,
201
+ "eval_accuracy": 0.8724489795918368,
202
+ "eval_f1": 0.8717968544761319,
203
+ "eval_loss": 0.6686978340148926,
204
+ "eval_precision": 0.8739694933458982,
205
+ "eval_recall": 0.8724489795918368,
206
+ "eval_roc_auc": NaN,
207
+ "eval_runtime": 19.2988,
208
+ "eval_samples_per_second": 426.555,
209
+ "eval_steps_per_second": 26.686,
210
+ "step": 20580
211
+ },
212
+ {
213
+ "epoch": 11.0,
214
+ "grad_norm": 0.41183769702911377,
215
+ "learning_rate": 9.527924735973573e-06,
216
+ "loss": 0.1201,
217
+ "step": 22638
218
+ },
219
+ {
220
+ "epoch": 11.0,
221
+ "eval_accuracy": 0.8819241982507289,
222
+ "eval_f1": 0.881427940698668,
223
+ "eval_loss": 0.655232846736908,
224
+ "eval_precision": 0.8834734398803243,
225
+ "eval_recall": 0.8819241982507289,
226
+ "eval_roc_auc": NaN,
227
+ "eval_runtime": 19.3322,
228
+ "eval_samples_per_second": 425.819,
229
+ "eval_steps_per_second": 26.64,
230
+ "step": 22638
231
+ }
232
+ ],
233
+ "logging_steps": 500,
234
+ "max_steps": 41160,
235
+ "num_input_tokens_seen": 0,
236
+ "num_train_epochs": 20,
237
+ "save_steps": 500,
238
+ "stateful_callbacks": {
239
+ "EarlyStoppingCallback": {
240
+ "args": {
241
+ "early_stopping_patience": 4,
242
+ "early_stopping_threshold": 0.0
243
+ },
244
+ "attributes": {
245
+ "early_stopping_patience_counter": 0
246
+ }
247
+ },
248
+ "TrainerControl": {
249
+ "args": {
250
+ "should_epoch_stop": false,
251
+ "should_evaluate": false,
252
+ "should_log": false,
253
+ "should_save": true,
254
+ "should_training_stop": false
255
+ },
256
+ "attributes": {}
257
+ }
258
+ },
259
+ "total_flos": 2.38241305507392e+16,
260
+ "train_batch_size": 16,
261
+ "trial_name": null,
262
+ "trial_params": null
263
+ }
HF_FT_Carmel_Preprocess3_Data/trial_13/checkpoint-22638/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ae73624b5981992e5f6683b6cbf4419e60c8476028f61feeba683c93aea9ca
3
+ size 5777