juand5 commited on
Commit
2de8e8a
1 Parent(s): 501074e

Training in progress, epoch 4

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c07dc1ffe5c13fe6bcf2a75ecfb52cc332d104d6aa46800e2d905040cd7c710
3
  size 268124796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c33e59993af1c87d3b2a9ee8489eb859ee626084919351524e4626b5c89ff62
3
  size 268124796
run-3/checkpoint-228/config.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48",
61
+ "49": "LABEL_49",
62
+ "50": "LABEL_50",
63
+ "51": "LABEL_51",
64
+ "52": "LABEL_52",
65
+ "53": "LABEL_53",
66
+ "54": "LABEL_54",
67
+ "55": "LABEL_55",
68
+ "56": "LABEL_56",
69
+ "57": "LABEL_57",
70
+ "58": "LABEL_58",
71
+ "59": "LABEL_59",
72
+ "60": "LABEL_60",
73
+ "61": "LABEL_61",
74
+ "62": "LABEL_62",
75
+ "63": "LABEL_63",
76
+ "64": "LABEL_64",
77
+ "65": "LABEL_65",
78
+ "66": "LABEL_66",
79
+ "67": "LABEL_67",
80
+ "68": "LABEL_68",
81
+ "69": "LABEL_69",
82
+ "70": "LABEL_70",
83
+ "71": "LABEL_71",
84
+ "72": "LABEL_72",
85
+ "73": "LABEL_73",
86
+ "74": "LABEL_74",
87
+ "75": "LABEL_75",
88
+ "76": "LABEL_76",
89
+ "77": "LABEL_77",
90
+ "78": "LABEL_78",
91
+ "79": "LABEL_79",
92
+ "80": "LABEL_80",
93
+ "81": "LABEL_81",
94
+ "82": "LABEL_82",
95
+ "83": "LABEL_83",
96
+ "84": "LABEL_84",
97
+ "85": "LABEL_85",
98
+ "86": "LABEL_86",
99
+ "87": "LABEL_87",
100
+ "88": "LABEL_88",
101
+ "89": "LABEL_89",
102
+ "90": "LABEL_90",
103
+ "91": "LABEL_91",
104
+ "92": "LABEL_92",
105
+ "93": "LABEL_93",
106
+ "94": "LABEL_94",
107
+ "95": "LABEL_95",
108
+ "96": "LABEL_96"
109
+ },
110
+ "initializer_range": 0.02,
111
+ "label2id": {
112
+ "LABEL_0": 0,
113
+ "LABEL_1": 1,
114
+ "LABEL_10": 10,
115
+ "LABEL_11": 11,
116
+ "LABEL_12": 12,
117
+ "LABEL_13": 13,
118
+ "LABEL_14": 14,
119
+ "LABEL_15": 15,
120
+ "LABEL_16": 16,
121
+ "LABEL_17": 17,
122
+ "LABEL_18": 18,
123
+ "LABEL_19": 19,
124
+ "LABEL_2": 2,
125
+ "LABEL_20": 20,
126
+ "LABEL_21": 21,
127
+ "LABEL_22": 22,
128
+ "LABEL_23": 23,
129
+ "LABEL_24": 24,
130
+ "LABEL_25": 25,
131
+ "LABEL_26": 26,
132
+ "LABEL_27": 27,
133
+ "LABEL_28": 28,
134
+ "LABEL_29": 29,
135
+ "LABEL_3": 3,
136
+ "LABEL_30": 30,
137
+ "LABEL_31": 31,
138
+ "LABEL_32": 32,
139
+ "LABEL_33": 33,
140
+ "LABEL_34": 34,
141
+ "LABEL_35": 35,
142
+ "LABEL_36": 36,
143
+ "LABEL_37": 37,
144
+ "LABEL_38": 38,
145
+ "LABEL_39": 39,
146
+ "LABEL_4": 4,
147
+ "LABEL_40": 40,
148
+ "LABEL_41": 41,
149
+ "LABEL_42": 42,
150
+ "LABEL_43": 43,
151
+ "LABEL_44": 44,
152
+ "LABEL_45": 45,
153
+ "LABEL_46": 46,
154
+ "LABEL_47": 47,
155
+ "LABEL_48": 48,
156
+ "LABEL_49": 49,
157
+ "LABEL_5": 5,
158
+ "LABEL_50": 50,
159
+ "LABEL_51": 51,
160
+ "LABEL_52": 52,
161
+ "LABEL_53": 53,
162
+ "LABEL_54": 54,
163
+ "LABEL_55": 55,
164
+ "LABEL_56": 56,
165
+ "LABEL_57": 57,
166
+ "LABEL_58": 58,
167
+ "LABEL_59": 59,
168
+ "LABEL_6": 6,
169
+ "LABEL_60": 60,
170
+ "LABEL_61": 61,
171
+ "LABEL_62": 62,
172
+ "LABEL_63": 63,
173
+ "LABEL_64": 64,
174
+ "LABEL_65": 65,
175
+ "LABEL_66": 66,
176
+ "LABEL_67": 67,
177
+ "LABEL_68": 68,
178
+ "LABEL_69": 69,
179
+ "LABEL_7": 7,
180
+ "LABEL_70": 70,
181
+ "LABEL_71": 71,
182
+ "LABEL_72": 72,
183
+ "LABEL_73": 73,
184
+ "LABEL_74": 74,
185
+ "LABEL_75": 75,
186
+ "LABEL_76": 76,
187
+ "LABEL_77": 77,
188
+ "LABEL_78": 78,
189
+ "LABEL_79": 79,
190
+ "LABEL_8": 8,
191
+ "LABEL_80": 80,
192
+ "LABEL_81": 81,
193
+ "LABEL_82": 82,
194
+ "LABEL_83": 83,
195
+ "LABEL_84": 84,
196
+ "LABEL_85": 85,
197
+ "LABEL_86": 86,
198
+ "LABEL_87": 87,
199
+ "LABEL_88": 88,
200
+ "LABEL_89": 89,
201
+ "LABEL_9": 9,
202
+ "LABEL_90": 90,
203
+ "LABEL_91": 91,
204
+ "LABEL_92": 92,
205
+ "LABEL_93": 93,
206
+ "LABEL_94": 94,
207
+ "LABEL_95": 95,
208
+ "LABEL_96": 96
209
+ },
210
+ "max_position_embeddings": 512,
211
+ "model_type": "distilbert",
212
+ "n_heads": 12,
213
+ "n_layers": 6,
214
+ "pad_token_id": 0,
215
+ "problem_type": "single_label_classification",
216
+ "qa_dropout": 0.1,
217
+ "seq_classif_dropout": 0.2,
218
+ "sinusoidal_pos_embds": false,
219
+ "tie_weights_": true,
220
+ "torch_dtype": "float32",
221
+ "transformers_version": "4.41.2",
222
+ "vocab_size": 30522
223
+ }
run-3/checkpoint-228/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c33e59993af1c87d3b2a9ee8489eb859ee626084919351524e4626b5c89ff62
3
+ size 268124796
run-3/checkpoint-228/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ee48f3ac648796b4bbcc3612b27a8b79df7e02b2b4f0ea6041197176bbe08e
3
+ size 536308858
run-3/checkpoint-228/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6bef4b1ce715d851365d30cb5562740fd4bcc3de23f925c304d6b2d0b2755e9
3
+ size 14054
run-3/checkpoint-228/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4910e24c597e2ddb6cf850822026e281395e75d847b2d8a5d253e35400de7df
3
+ size 1064
run-3/checkpoint-228/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-3/checkpoint-228/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-228/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-3/checkpoint-228/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.37,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-multiclass-classification/run-3/checkpoint-228",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 228,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.18,
14
+ "eval_loss": 4.173440933227539,
15
+ "eval_runtime": 9.5961,
16
+ "eval_samples_per_second": 93.788,
17
+ "eval_steps_per_second": 23.447,
18
+ "step": 57
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.23777777777777778,
23
+ "eval_loss": 3.8830435276031494,
24
+ "eval_runtime": 9.2156,
25
+ "eval_samples_per_second": 97.66,
26
+ "eval_steps_per_second": 24.415,
27
+ "step": 114
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.30777777777777776,
32
+ "eval_loss": 3.662949323654175,
33
+ "eval_runtime": 9.2811,
34
+ "eval_samples_per_second": 96.971,
35
+ "eval_steps_per_second": 24.243,
36
+ "step": 171
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.37,
41
+ "eval_loss": 3.5301730632781982,
42
+ "eval_runtime": 10.4078,
43
+ "eval_samples_per_second": 86.474,
44
+ "eval_steps_per_second": 21.618,
45
+ "step": 228
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 285,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": false
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 0,
66
+ "train_batch_size": 64,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 4.935170904021075e-06,
70
+ "num_train_epochs": 5,
71
+ "per_device_train_batch_size": 64,
72
+ "seed": 37
73
+ }
74
+ }
run-3/checkpoint-228/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ff6614a97dd5a8b17af19bfb26445721528d2aa1fdde1b8b87f0d23ece4418
3
+ size 5240
run-3/checkpoint-228/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jul16_21-03-57_0618-205946-735gvp8h-172-26-227-153/events.out.tfevents.1721165524.0618-205946-735gvp8h-172-26-227-153.65933.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2425f8f2283104c9d148641d71cb1ff346c827051e73cacd3e3a904c86a53b5
3
- size 9863
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f6d5c2c3c8d6f8cf049ebac8dd7690346bc05cad057af19dd4cfcf9544f268
3
+ size 10186