CarmelKron commited on
Commit
a43fa14
·
verified ·
1 Parent(s): 76ba494

Upload best model from trial 4

Browse files
HF_FT_Carmel_Preprocess1_Data/trial_4/checkpoint-11319/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
HF_FT_Carmel_Preprocess1_Data/trial_4/checkpoint-11319/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_4/checkpoint-11319/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e80193c0e3a2fd6af0f1ec88d957b267ad13e9673261bc48e07d2b4ee0623edb
3
+ size 737728508
HF_FT_Carmel_Preprocess1_Data/trial_4/checkpoint-11319/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b9cca0b699ccc58e32ea4fb6a01fd5cdaf54c7d54459ad3e320cc7a3c0baf7a
3
+ size 1475576826
HF_FT_Carmel_Preprocess1_Data/trial_4/checkpoint-11319/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea69866b5f6aed49253e17c219aa7cd12ef65e2079433dc815e9d2634999316
3
+ size 14244
HF_FT_Carmel_Preprocess1_Data/trial_4/checkpoint-11319/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb89cf945dcd4724e6fc0af2bf51c8e8465b5ad70284673abe9ef3e387b5128
3
+ size 1064
HF_FT_Carmel_Preprocess1_Data/trial_4/checkpoint-11319/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_4/checkpoint-11319/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_4/checkpoint-11319/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
HF_FT_Carmel_Preprocess1_Data/trial_4/checkpoint-11319/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_4/checkpoint-11319/trainer_state.json ADDED
@@ -0,0 +1,230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": 0.8679543245869776,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 11.0,
6
+ "eval_steps": 500,
7
+ "global_step": 11319,
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": 6.434831142425537,
15
+ "learning_rate": 1.364282260271306e-05,
16
+ "loss": 1.4106,
17
+ "step": 1029
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.6120019436345967,
22
+ "eval_f1": 0.6094066355293098,
23
+ "eval_loss": 1.1628057956695557,
24
+ "eval_runtime": 14.3781,
25
+ "eval_samples_per_second": 572.537,
26
+ "eval_steps_per_second": 35.818,
27
+ "step": 1029
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "grad_norm": 3.602156400680542,
32
+ "learning_rate": 2.2988757169255277e-05,
33
+ "loss": 1.0111,
34
+ "step": 2058
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.7897230320699709,
39
+ "eval_f1": 0.7901578895914384,
40
+ "eval_loss": 0.9118835926055908,
41
+ "eval_runtime": 14.375,
42
+ "eval_samples_per_second": 572.662,
43
+ "eval_steps_per_second": 35.826,
44
+ "step": 2058
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "grad_norm": 4.264897346496582,
49
+ "learning_rate": 2.1711672942771246e-05,
50
+ "loss": 0.853,
51
+ "step": 3087
52
+ },
53
+ {
54
+ "epoch": 3.0,
55
+ "eval_accuracy": 0.8283527696793003,
56
+ "eval_f1": 0.8275128138312147,
57
+ "eval_loss": 0.8614639043807983,
58
+ "eval_runtime": 14.3657,
59
+ "eval_samples_per_second": 573.032,
60
+ "eval_steps_per_second": 35.849,
61
+ "step": 3087
62
+ },
63
+ {
64
+ "epoch": 4.0,
65
+ "grad_norm": 2.822014570236206,
66
+ "learning_rate": 2.0434588716287215e-05,
67
+ "loss": 0.7853,
68
+ "step": 4116
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "eval_accuracy": 0.8406219630709426,
73
+ "eval_f1": 0.8405069530620268,
74
+ "eval_loss": 0.8350297808647156,
75
+ "eval_runtime": 14.362,
76
+ "eval_samples_per_second": 573.181,
77
+ "eval_steps_per_second": 35.859,
78
+ "step": 4116
79
+ },
80
+ {
81
+ "epoch": 5.0,
82
+ "grad_norm": 7.66935396194458,
83
+ "learning_rate": 1.9157504489803187e-05,
84
+ "loss": 0.7341,
85
+ "step": 5145
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "eval_accuracy": 0.8335762876579204,
90
+ "eval_f1": 0.8328548093342822,
91
+ "eval_loss": 0.8929103016853333,
92
+ "eval_runtime": 14.4457,
93
+ "eval_samples_per_second": 569.857,
94
+ "eval_steps_per_second": 35.651,
95
+ "step": 5145
96
+ },
97
+ {
98
+ "epoch": 6.0,
99
+ "grad_norm": 6.994083404541016,
100
+ "learning_rate": 1.788042026331916e-05,
101
+ "loss": 0.7021,
102
+ "step": 6174
103
+ },
104
+ {
105
+ "epoch": 6.0,
106
+ "eval_accuracy": 0.8612730806608357,
107
+ "eval_f1": 0.8607536667578998,
108
+ "eval_loss": 0.8286945223808289,
109
+ "eval_runtime": 14.3032,
110
+ "eval_samples_per_second": 575.536,
111
+ "eval_steps_per_second": 36.006,
112
+ "step": 6174
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "grad_norm": 7.250941276550293,
117
+ "learning_rate": 1.6603336036835128e-05,
118
+ "loss": 0.6727,
119
+ "step": 7203
120
+ },
121
+ {
122
+ "epoch": 7.0,
123
+ "eval_accuracy": 0.8525267249757046,
124
+ "eval_f1": 0.8519057548073337,
125
+ "eval_loss": 0.8616788983345032,
126
+ "eval_runtime": 14.3593,
127
+ "eval_samples_per_second": 573.286,
128
+ "eval_steps_per_second": 35.865,
129
+ "step": 7203
130
+ },
131
+ {
132
+ "epoch": 8.0,
133
+ "grad_norm": 5.977318286895752,
134
+ "learning_rate": 1.53262518103511e-05,
135
+ "loss": 0.6585,
136
+ "step": 8232
137
+ },
138
+ {
139
+ "epoch": 8.0,
140
+ "eval_accuracy": 0.8607871720116618,
141
+ "eval_f1": 0.8602368901557617,
142
+ "eval_loss": 0.8521169424057007,
143
+ "eval_runtime": 14.5493,
144
+ "eval_samples_per_second": 565.799,
145
+ "eval_steps_per_second": 35.397,
146
+ "step": 8232
147
+ },
148
+ {
149
+ "epoch": 9.0,
150
+ "grad_norm": 2.129892349243164,
151
+ "learning_rate": 1.404916758386707e-05,
152
+ "loss": 0.6434,
153
+ "step": 9261
154
+ },
155
+ {
156
+ "epoch": 9.0,
157
+ "eval_accuracy": 0.858843537414966,
158
+ "eval_f1": 0.8580508186121574,
159
+ "eval_loss": 0.871514618396759,
160
+ "eval_runtime": 14.4228,
161
+ "eval_samples_per_second": 570.761,
162
+ "eval_steps_per_second": 35.707,
163
+ "step": 9261
164
+ },
165
+ {
166
+ "epoch": 10.0,
167
+ "grad_norm": 5.863806247711182,
168
+ "learning_rate": 1.2772083357383039e-05,
169
+ "loss": 0.626,
170
+ "step": 10290
171
+ },
172
+ {
173
+ "epoch": 10.0,
174
+ "eval_accuracy": 0.8650388726919339,
175
+ "eval_f1": 0.8645514139923637,
176
+ "eval_loss": 0.8583226203918457,
177
+ "eval_runtime": 14.369,
178
+ "eval_samples_per_second": 572.899,
179
+ "eval_steps_per_second": 35.841,
180
+ "step": 10290
181
+ },
182
+ {
183
+ "epoch": 11.0,
184
+ "grad_norm": 11.165838241577148,
185
+ "learning_rate": 1.149499913089901e-05,
186
+ "loss": 0.6194,
187
+ "step": 11319
188
+ },
189
+ {
190
+ "epoch": 11.0,
191
+ "eval_accuracy": 0.8679543245869776,
192
+ "eval_f1": 0.8678868399637669,
193
+ "eval_loss": 0.8515373468399048,
194
+ "eval_runtime": 15.0603,
195
+ "eval_samples_per_second": 546.601,
196
+ "eval_steps_per_second": 34.196,
197
+ "step": 11319
198
+ }
199
+ ],
200
+ "logging_steps": 500,
201
+ "max_steps": 20580,
202
+ "num_input_tokens_seen": 0,
203
+ "num_train_epochs": 20,
204
+ "save_steps": 500,
205
+ "stateful_callbacks": {
206
+ "EarlyStoppingCallback": {
207
+ "args": {
208
+ "early_stopping_patience": 4,
209
+ "early_stopping_threshold": 0.0
210
+ },
211
+ "attributes": {
212
+ "early_stopping_patience_counter": 0
213
+ }
214
+ },
215
+ "TrainerControl": {
216
+ "args": {
217
+ "should_epoch_stop": false,
218
+ "should_evaluate": false,
219
+ "should_log": false,
220
+ "should_save": true,
221
+ "should_training_stop": false
222
+ },
223
+ "attributes": {}
224
+ }
225
+ },
226
+ "total_flos": 1.19120652753696e+16,
227
+ "train_batch_size": 16,
228
+ "trial_name": null,
229
+ "trial_params": null
230
+ }
HF_FT_Carmel_Preprocess1_Data/trial_4/checkpoint-11319/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f0044348d8fdfbd292ccba8e4e204b804992131418ab0dfd8e20bcef550672
3
+ size 5304