CarmelKron commited on
Commit
f02fc14
·
verified ·
1 Parent(s): d496294

Upload best model from trial 1

Browse files
HF_FT_Carmel_Preprocess1_Data/trial_1/checkpoint-3096/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
HF_FT_Carmel_Preprocess1_Data/trial_1/checkpoint-3096/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": "4.55.1",
47
+ "type_vocab_size": 0,
48
+ "vocab_size": 128100
49
+ }
HF_FT_Carmel_Preprocess1_Data/trial_1/checkpoint-3096/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4996de784fc66ac0d0bc263d41ad2c1280cf326b266cd7bae8373ad7e8b6d054
3
+ size 737728508
HF_FT_Carmel_Preprocess1_Data/trial_1/checkpoint-3096/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74e28747319773c48c35e6c78a4e4acc2c6836cc17e33ad4e679cdf972d55b8
3
+ size 1475576826
HF_FT_Carmel_Preprocess1_Data/trial_1/checkpoint-3096/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3bc48fdde1cd8b85afbe7ce825949f5ea4d56093b8b87fbcf622c68b214b674
3
+ size 14244
HF_FT_Carmel_Preprocess1_Data/trial_1/checkpoint-3096/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f684c89135766dd914ad8ff2de37c0774417f327a0e587f3c6c675d1103ca06
3
+ size 1064
HF_FT_Carmel_Preprocess1_Data/trial_1/checkpoint-3096/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_Preprocess1_Data/trial_1/checkpoint-3096/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_Preprocess1_Data/trial_1/checkpoint-3096/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
HF_FT_Carmel_Preprocess1_Data/trial_1/checkpoint-3096/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_Preprocess1_Data/trial_1/checkpoint-3096/trainer_state.json ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": 0.8758503401360545,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 12.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3096,
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": 8.284130096435547,
15
+ "learning_rate": 1.848726994317638e-05,
16
+ "loss": 1.4063,
17
+ "step": 258
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.5949951409135082,
22
+ "eval_f1": 0.5923563566530355,
23
+ "eval_loss": 1.0617725849151611,
24
+ "eval_runtime": 16.2706,
25
+ "eval_samples_per_second": 505.942,
26
+ "eval_steps_per_second": 7.928,
27
+ "step": 258
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "grad_norm": 8.487099647521973,
32
+ "learning_rate": 3.0037756043274332e-05,
33
+ "loss": 0.8957,
34
+ "step": 516
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.7589893100097181,
39
+ "eval_f1": 0.7571984208243079,
40
+ "eval_loss": 0.7611314654350281,
41
+ "eval_runtime": 16.2528,
42
+ "eval_samples_per_second": 506.498,
43
+ "eval_steps_per_second": 7.937,
44
+ "step": 516
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "grad_norm": 7.602023601531982,
49
+ "learning_rate": 2.9654897747615367e-05,
50
+ "loss": 0.6574,
51
+ "step": 774
52
+ },
53
+ {
54
+ "epoch": 3.0,
55
+ "eval_accuracy": 0.793002915451895,
56
+ "eval_f1": 0.7924023434346363,
57
+ "eval_loss": 0.7072914242744446,
58
+ "eval_runtime": 16.266,
59
+ "eval_samples_per_second": 506.087,
60
+ "eval_steps_per_second": 7.931,
61
+ "step": 774
62
+ },
63
+ {
64
+ "epoch": 4.0,
65
+ "grad_norm": 4.005903244018555,
66
+ "learning_rate": 2.884593039272313e-05,
67
+ "loss": 0.5378,
68
+ "step": 1032
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "eval_accuracy": 0.8480320699708455,
73
+ "eval_f1": 0.8476601379404011,
74
+ "eval_loss": 0.5893324613571167,
75
+ "eval_runtime": 16.2874,
76
+ "eval_samples_per_second": 505.42,
77
+ "eval_steps_per_second": 7.92,
78
+ "step": 1032
79
+ },
80
+ {
81
+ "epoch": 5.0,
82
+ "grad_norm": 7.9739885330200195,
83
+ "learning_rate": 2.7634431027595628e-05,
84
+ "loss": 0.466,
85
+ "step": 1290
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "eval_accuracy": 0.8457240038872692,
90
+ "eval_f1": 0.8457395444837291,
91
+ "eval_loss": 0.6161386966705322,
92
+ "eval_runtime": 16.233,
93
+ "eval_samples_per_second": 507.116,
94
+ "eval_steps_per_second": 7.947,
95
+ "step": 1290
96
+ },
97
+ {
98
+ "epoch": 6.0,
99
+ "grad_norm": 10.243639945983887,
100
+ "learning_rate": 2.605570834512381e-05,
101
+ "loss": 0.4195,
102
+ "step": 1548
103
+ },
104
+ {
105
+ "epoch": 6.0,
106
+ "eval_accuracy": 0.8714771622934888,
107
+ "eval_f1": 0.8710938181450322,
108
+ "eval_loss": 0.5545685887336731,
109
+ "eval_runtime": 16.2134,
110
+ "eval_samples_per_second": 507.729,
111
+ "eval_steps_per_second": 7.956,
112
+ "step": 1548
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "grad_norm": 6.564546585083008,
117
+ "learning_rate": 2.415577362353023e-05,
118
+ "loss": 0.385,
119
+ "step": 1806
120
+ },
121
+ {
122
+ "epoch": 7.0,
123
+ "eval_accuracy": 0.8703838678328474,
124
+ "eval_f1": 0.8700525942678535,
125
+ "eval_loss": 0.5575464367866516,
126
+ "eval_runtime": 16.2805,
127
+ "eval_samples_per_second": 505.634,
128
+ "eval_steps_per_second": 7.924,
129
+ "step": 1806
130
+ },
131
+ {
132
+ "epoch": 8.0,
133
+ "grad_norm": 16.482515335083008,
134
+ "learning_rate": 2.1989999744987644e-05,
135
+ "loss": 0.3529,
136
+ "step": 2064
137
+ },
138
+ {
139
+ "epoch": 8.0,
140
+ "eval_accuracy": 0.8657677356656949,
141
+ "eval_f1": 0.8652538487041648,
142
+ "eval_loss": 0.6245816946029663,
143
+ "eval_runtime": 16.2613,
144
+ "eval_samples_per_second": 506.234,
145
+ "eval_steps_per_second": 7.933,
146
+ "step": 2064
147
+ },
148
+ {
149
+ "epoch": 9.0,
150
+ "grad_norm": 4.233608722686768,
151
+ "learning_rate": 1.9621507373814868e-05,
152
+ "loss": 0.3364,
153
+ "step": 2322
154
+ },
155
+ {
156
+ "epoch": 9.0,
157
+ "eval_accuracy": 0.8463313896987367,
158
+ "eval_f1": 0.8453837221218796,
159
+ "eval_loss": 0.6657220721244812,
160
+ "eval_runtime": 16.2415,
161
+ "eval_samples_per_second": 506.849,
162
+ "eval_steps_per_second": 7.943,
163
+ "step": 2322
164
+ },
165
+ {
166
+ "epoch": 10.0,
167
+ "grad_norm": 1.6360636949539185,
168
+ "learning_rate": 1.711932532847887e-05,
169
+ "loss": 0.316,
170
+ "step": 2580
171
+ },
172
+ {
173
+ "epoch": 10.0,
174
+ "eval_accuracy": 0.8739067055393586,
175
+ "eval_f1": 0.8733251868643908,
176
+ "eval_loss": 0.6144309043884277,
177
+ "eval_runtime": 16.2543,
178
+ "eval_samples_per_second": 506.45,
179
+ "eval_steps_per_second": 7.936,
180
+ "step": 2580
181
+ },
182
+ {
183
+ "epoch": 11.0,
184
+ "grad_norm": 1.0431078672409058,
185
+ "learning_rate": 1.45563787626686e-05,
186
+ "loss": 0.3028,
187
+ "step": 2838
188
+ },
189
+ {
190
+ "epoch": 11.0,
191
+ "eval_accuracy": 0.8717201166180758,
192
+ "eval_f1": 0.8710759208880914,
193
+ "eval_loss": 0.6201786398887634,
194
+ "eval_runtime": 16.2393,
195
+ "eval_samples_per_second": 506.92,
196
+ "eval_steps_per_second": 7.944,
197
+ "step": 2838
198
+ },
199
+ {
200
+ "epoch": 12.0,
201
+ "grad_norm": 0.39371687173843384,
202
+ "learning_rate": 1.2007363789145574e-05,
203
+ "loss": 0.2953,
204
+ "step": 3096
205
+ },
206
+ {
207
+ "epoch": 12.0,
208
+ "eval_accuracy": 0.8758503401360545,
209
+ "eval_f1": 0.8752276474390172,
210
+ "eval_loss": 0.6025113463401794,
211
+ "eval_runtime": 16.2517,
212
+ "eval_samples_per_second": 506.532,
213
+ "eval_steps_per_second": 7.938,
214
+ "step": 3096
215
+ }
216
+ ],
217
+ "logging_steps": 500,
218
+ "max_steps": 5160,
219
+ "num_input_tokens_seen": 0,
220
+ "num_train_epochs": 20,
221
+ "save_steps": 500,
222
+ "stateful_callbacks": {
223
+ "EarlyStoppingCallback": {
224
+ "args": {
225
+ "early_stopping_patience": 4,
226
+ "early_stopping_threshold": 0.0
227
+ },
228
+ "attributes": {
229
+ "early_stopping_patience_counter": 0
230
+ }
231
+ },
232
+ "TrainerControl": {
233
+ "args": {
234
+ "should_epoch_stop": false,
235
+ "should_evaluate": false,
236
+ "should_log": false,
237
+ "should_save": true,
238
+ "should_training_stop": false
239
+ },
240
+ "attributes": {}
241
+ }
242
+ },
243
+ "total_flos": 2.59899606008064e+16,
244
+ "train_batch_size": 64,
245
+ "trial_name": null,
246
+ "trial_params": null
247
+ }
HF_FT_Carmel_Preprocess1_Data/trial_1/checkpoint-3096/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad74b2b13af1a1d80382c5013fe1603e9c35732314379c2a080ae8584cf1f38
3
+ size 5368