assaflehr commited on
Commit
ca0d82e
1 Parent(s): 58c8db3

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text-classification
6
+ base_model: microsoft/deberta-v3-base
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ ---
10
+
11
+ # Model Trained Using AutoTrain
12
+
13
+ - Problem type: Text Classification
14
+
15
+ ## Validation Metrics
16
+ loss: 0.3079245686531067
17
+
18
+ f1: 0.9307469180565627
19
+
20
+ precision: 0.9708774583963692
21
+
22
+ recall: 0.8938022284122563
23
+
24
+ auc: 0.9840253557545333
25
+
26
+ accuracy: 0.9334958217270195
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-712/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "DebertaV2ForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "0",
13
+ "1": "1"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-07,
22
+ "max_position_embeddings": 512,
23
+ "max_relative_positions": -1,
24
+ "model_type": "deberta-v2",
25
+ "norm_rel_ebd": "layer_norm",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "pooler_dropout": 0,
30
+ "pooler_hidden_act": "gelu",
31
+ "pooler_hidden_size": 768,
32
+ "pos_att_type": [
33
+ "p2c",
34
+ "c2p"
35
+ ],
36
+ "position_biased_input": false,
37
+ "position_buckets": 256,
38
+ "relative_attention": true,
39
+ "share_att_key": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.43.1",
42
+ "type_vocab_size": 0,
43
+ "vocab_size": 128100
44
+ }
checkpoint-712/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9c810e1afb818440210e282c807a8ebc14aeae903baa8022e12a9b5d4ae4b6
3
+ size 737719272
checkpoint-712/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a190e8c7c128b241b654a6c77f52379b61210491a27a8d188da9d31636aa96c
3
+ size 1475558394
checkpoint-712/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf56780eafdcf429915e69dfc871f5e4839b7a0b2b823e519734d57538072f17
3
+ size 14244
checkpoint-712/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2655f44847a1070a830b66c796cc24dc9a9400f72a8da37893d24514e21db6ab
3
+ size 1064
checkpoint-712/trainer_state.json ADDED
@@ -0,0 +1,251 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3079245686531067,
3
+ "best_model_checkpoint": "autotrain-kcpio-wclqs/checkpoint-712",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 712,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0351123595505618,
13
+ "grad_norm": 1.9374197721481323,
14
+ "learning_rate": 1.736111111111111e-05,
15
+ "loss": 0.6963,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.0702247191011236,
20
+ "grad_norm": 3.9908769130706787,
21
+ "learning_rate": 3.3333333333333335e-05,
22
+ "loss": 0.5465,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.10533707865168539,
27
+ "grad_norm": 8.669546127319336,
28
+ "learning_rate": 4.930555555555556e-05,
29
+ "loss": 0.4025,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.1404494382022472,
34
+ "grad_norm": 0.6609323024749756,
35
+ "learning_rate": 4.8125000000000004e-05,
36
+ "loss": 0.338,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.175561797752809,
41
+ "grad_norm": 0.6923323273658752,
42
+ "learning_rate": 4.6171875e-05,
43
+ "loss": 0.265,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.21067415730337077,
48
+ "grad_norm": 0.6821861267089844,
49
+ "learning_rate": 4.421875e-05,
50
+ "loss": 0.2498,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.24578651685393257,
55
+ "grad_norm": 0.10477828234434128,
56
+ "learning_rate": 4.2265625000000006e-05,
57
+ "loss": 0.1785,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.2808988764044944,
62
+ "grad_norm": 3.7019550800323486,
63
+ "learning_rate": 4.0312500000000004e-05,
64
+ "loss": 0.2335,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.3160112359550562,
69
+ "grad_norm": 16.70686912536621,
70
+ "learning_rate": 3.8359375e-05,
71
+ "loss": 0.1422,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.351123595505618,
76
+ "grad_norm": 0.07099178433418274,
77
+ "learning_rate": 3.640625e-05,
78
+ "loss": 0.1525,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.3862359550561798,
83
+ "grad_norm": 0.049899421632289886,
84
+ "learning_rate": 3.4453125000000006e-05,
85
+ "loss": 0.0916,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.42134831460674155,
90
+ "grad_norm": 0.021365324035286903,
91
+ "learning_rate": 3.2500000000000004e-05,
92
+ "loss": 0.0504,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.45646067415730335,
97
+ "grad_norm": 0.03689989075064659,
98
+ "learning_rate": 3.0546875e-05,
99
+ "loss": 0.09,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.49157303370786515,
104
+ "grad_norm": 0.24886544048786163,
105
+ "learning_rate": 2.8593750000000004e-05,
106
+ "loss": 0.0951,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.526685393258427,
111
+ "grad_norm": 0.06867190450429916,
112
+ "learning_rate": 2.6640625000000002e-05,
113
+ "loss": 0.0483,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.5617977528089888,
118
+ "grad_norm": 0.29167991876602173,
119
+ "learning_rate": 2.4687500000000004e-05,
120
+ "loss": 0.1251,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.5969101123595506,
125
+ "grad_norm": 0.10820268094539642,
126
+ "learning_rate": 2.2734375000000002e-05,
127
+ "loss": 0.1432,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.6320224719101124,
132
+ "grad_norm": 0.07357452809810638,
133
+ "learning_rate": 2.0781250000000004e-05,
134
+ "loss": 0.0941,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.6671348314606742,
139
+ "grad_norm": 0.13083012402057648,
140
+ "learning_rate": 1.8828125000000002e-05,
141
+ "loss": 0.1754,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.702247191011236,
146
+ "grad_norm": 0.11591902375221252,
147
+ "learning_rate": 1.6875000000000004e-05,
148
+ "loss": 0.1484,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.7373595505617978,
153
+ "grad_norm": 23.016658782958984,
154
+ "learning_rate": 1.4921875000000002e-05,
155
+ "loss": 0.1112,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.7724719101123596,
160
+ "grad_norm": 29.17462158203125,
161
+ "learning_rate": 1.2968750000000002e-05,
162
+ "loss": 0.0749,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.8075842696629213,
167
+ "grad_norm": 0.27380064129829407,
168
+ "learning_rate": 1.1015625e-05,
169
+ "loss": 0.1224,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.8426966292134831,
174
+ "grad_norm": 0.11491677910089493,
175
+ "learning_rate": 9.0625e-06,
176
+ "loss": 0.04,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.8778089887640449,
181
+ "grad_norm": 0.04559633880853653,
182
+ "learning_rate": 7.109375e-06,
183
+ "loss": 0.032,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.9129213483146067,
188
+ "grad_norm": 0.12071628123521805,
189
+ "learning_rate": 5.15625e-06,
190
+ "loss": 0.1393,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.9480337078651685,
195
+ "grad_norm": 0.14503008127212524,
196
+ "learning_rate": 3.203125e-06,
197
+ "loss": 0.0517,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.9831460674157303,
202
+ "grad_norm": 0.045122675597667694,
203
+ "learning_rate": 1.25e-06,
204
+ "loss": 0.0517,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 1.0,
209
+ "eval_accuracy": 0.9334958217270195,
210
+ "eval_auc": 0.9840253557545333,
211
+ "eval_f1": 0.9307469180565627,
212
+ "eval_loss": 0.3079245686531067,
213
+ "eval_precision": 0.9708774583963692,
214
+ "eval_recall": 0.8938022284122563,
215
+ "eval_runtime": 20.2322,
216
+ "eval_samples_per_second": 283.904,
217
+ "eval_steps_per_second": 17.744,
218
+ "step": 712
219
+ }
220
+ ],
221
+ "logging_steps": 25,
222
+ "max_steps": 712,
223
+ "num_input_tokens_seen": 0,
224
+ "num_train_epochs": 1,
225
+ "save_steps": 500,
226
+ "stateful_callbacks": {
227
+ "EarlyStoppingCallback": {
228
+ "args": {
229
+ "early_stopping_patience": 5,
230
+ "early_stopping_threshold": 0.01
231
+ },
232
+ "attributes": {
233
+ "early_stopping_patience_counter": 0
234
+ }
235
+ },
236
+ "TrainerControl": {
237
+ "args": {
238
+ "should_epoch_stop": false,
239
+ "should_evaluate": false,
240
+ "should_log": false,
241
+ "should_save": true,
242
+ "should_training_stop": true
243
+ },
244
+ "attributes": {}
245
+ }
246
+ },
247
+ "total_flos": 374413746333696.0,
248
+ "train_batch_size": 8,
249
+ "trial_name": null,
250
+ "trial_params": null
251
+ }
checkpoint-712/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a39862abc3e24cf38e8b88f4870a2c896765c971e470d14f28780139f321c28a
3
+ size 5240
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "DebertaV2ForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "0",
13
+ "1": "1"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-07,
22
+ "max_position_embeddings": 512,
23
+ "max_relative_positions": -1,
24
+ "model_type": "deberta-v2",
25
+ "norm_rel_ebd": "layer_norm",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "pooler_dropout": 0,
30
+ "pooler_hidden_act": "gelu",
31
+ "pooler_hidden_size": 768,
32
+ "pos_att_type": [
33
+ "p2c",
34
+ "c2p"
35
+ ],
36
+ "position_biased_input": false,
37
+ "position_buckets": 256,
38
+ "relative_attention": true,
39
+ "share_att_key": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.43.1",
42
+ "type_vocab_size": 0,
43
+ "vocab_size": 128100
44
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9c810e1afb818440210e282c807a8ebc14aeae903baa8022e12a9b5d4ae4b6
3
+ size 737719272
runs/Jul25_18-13-12_r-assaflehr-autotrain5-j80r2m81-046a7-kkp2g/events.out.tfevents.1721931193.r-assaflehr-autotrain5-j80r2m81-046a7-kkp2g.74.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56d5da9b36b04899960b1de1a132b4670519464eb7e6fbc0389b144aa6ab7286
3
- size 5198
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af7be6a9d279411f0061ef5a6676836f7e489ec99937474921fc1ec4929cf72d
3
+ size 11959
runs/Jul25_18-13-12_r-assaflehr-autotrain5-j80r2m81-046a7-kkp2g/events.out.tfevents.1721931362.r-assaflehr-autotrain5-j80r2m81-046a7-kkp2g.74.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91e0d6ca6ae05207ca1eac74df3cb3dc67d0da0fea31dfc2371e88360cda0bc9
3
+ size 607
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
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a39862abc3e24cf38e8b88f4870a2c896765c971e470d14f28780139f321c28a
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-kcpio-wclqs/autotrain-data",
3
+ "model": "microsoft/deberta-v3-base",
4
+ "lr": 5e-05,
5
+ "epochs": 1,
6
+ "max_seq_length": 128,
7
+ "batch_size": 8,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "text_column": "autotrain_text",
18
+ "target_column": "autotrain_label",
19
+ "logging_steps": -1,
20
+ "project_name": "autotrain-kcpio-wclqs",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "assaflehr",
27
+ "log": "tensorboard",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }