ChrisZeng commited on
Commit
5b3563b
1 Parent(s): 8ed3abf

Training in progress, epoch 15

Browse files
checkpoint-2954/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "multi_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.17.0",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 50265
39
+ }
checkpoint-2954/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2954/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60152fe4c2fb5b87a1d4e92ebb2714f942af1728b6a2460d4ea17a024f99c60c
3
+ size 997299037
checkpoint-2954/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ab77aede7111f2bcd82f02c868165b695be52217d2297cb2320e83c0068c76
3
+ size 498678125
checkpoint-2954/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9d0becd6ea37a7d6a9c41dd13e80c109d7fa59865745d85f8da598a4ffa640
3
+ size 14503
checkpoint-2954/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad5496d6c6fcaa4ecf761bfec2dea2e5ef5d78f0e6f9f29d67b2ce39f68b4dd
3
+ size 559
checkpoint-2954/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13e2bad2901725387efa41b6d5234c76fd6cc7c9d07f0acde07f9d8e2228d3d1
3
+ size 623
checkpoint-2954/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
checkpoint-2954/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2954/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m", "normalization": true, "tokenizer_class": "RobertaTokenizer"}
checkpoint-2954/trainer_state.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.790682602817108,
3
+ "best_model_checkpoint": "outputs/time_lm_nli/checkpoint-2954",
4
+ "epoch": 14.0,
5
+ "global_step": 2954,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 9.666666666666666e-07,
13
+ "loss": 0.5392,
14
+ "step": 211
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7,
19
+ "eval_f1": 0.6998718119161117,
20
+ "eval_loss": 0.4048246741294861,
21
+ "eval_runtime": 5.0256,
22
+ "eval_samples_per_second": 596.939,
23
+ "eval_steps_per_second": 74.617,
24
+ "step": 211
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 9.333333333333333e-07,
29
+ "loss": 0.3725,
30
+ "step": 422
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.759,
35
+ "eval_f1": 0.7583549419422403,
36
+ "eval_loss": 0.3489450216293335,
37
+ "eval_runtime": 5.103,
38
+ "eval_samples_per_second": 587.885,
39
+ "eval_steps_per_second": 73.486,
40
+ "step": 422
41
+ },
42
+ {
43
+ "epoch": 3.0,
44
+ "learning_rate": 9e-07,
45
+ "loss": 0.3158,
46
+ "step": 633
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "eval_accuracy": 0.7613333333333333,
51
+ "eval_f1": 0.7569694772671423,
52
+ "eval_loss": 0.3286795914173126,
53
+ "eval_runtime": 5.4646,
54
+ "eval_samples_per_second": 548.991,
55
+ "eval_steps_per_second": 68.624,
56
+ "step": 633
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 8.666666666666667e-07,
61
+ "loss": 0.289,
62
+ "step": 844
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_accuracy": 0.769,
67
+ "eval_f1": 0.7684440341259363,
68
+ "eval_loss": 0.33065709471702576,
69
+ "eval_runtime": 5.2159,
70
+ "eval_samples_per_second": 575.162,
71
+ "eval_steps_per_second": 71.895,
72
+ "step": 844
73
+ },
74
+ {
75
+ "epoch": 5.0,
76
+ "learning_rate": 8.333333333333333e-07,
77
+ "loss": 0.2716,
78
+ "step": 1055
79
+ },
80
+ {
81
+ "epoch": 5.0,
82
+ "eval_accuracy": 0.7766666666666666,
83
+ "eval_f1": 0.775028474008066,
84
+ "eval_loss": 0.3240624666213989,
85
+ "eval_runtime": 5.2721,
86
+ "eval_samples_per_second": 569.029,
87
+ "eval_steps_per_second": 71.129,
88
+ "step": 1055
89
+ },
90
+ {
91
+ "epoch": 6.0,
92
+ "learning_rate": 8e-07,
93
+ "loss": 0.2575,
94
+ "step": 1266
95
+ },
96
+ {
97
+ "epoch": 6.0,
98
+ "eval_accuracy": 0.7786666666666666,
99
+ "eval_f1": 0.7782108653517272,
100
+ "eval_loss": 0.32720017433166504,
101
+ "eval_runtime": 5.4144,
102
+ "eval_samples_per_second": 554.075,
103
+ "eval_steps_per_second": 69.259,
104
+ "step": 1266
105
+ },
106
+ {
107
+ "epoch": 7.0,
108
+ "learning_rate": 7.666666666666667e-07,
109
+ "loss": 0.2441,
110
+ "step": 1477
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_accuracy": 0.7783333333333333,
115
+ "eval_f1": 0.7775937336504917,
116
+ "eval_loss": 0.3257558345794678,
117
+ "eval_runtime": 5.0695,
118
+ "eval_samples_per_second": 591.777,
119
+ "eval_steps_per_second": 73.972,
120
+ "step": 1477
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "learning_rate": 7.333333333333332e-07,
125
+ "loss": 0.2363,
126
+ "step": 1688
127
+ },
128
+ {
129
+ "epoch": 8.0,
130
+ "eval_accuracy": 0.7776666666666666,
131
+ "eval_f1": 0.777267505288088,
132
+ "eval_loss": 0.331592321395874,
133
+ "eval_runtime": 5.1518,
134
+ "eval_samples_per_second": 582.323,
135
+ "eval_steps_per_second": 72.79,
136
+ "step": 1688
137
+ },
138
+ {
139
+ "epoch": 9.0,
140
+ "learning_rate": 7e-07,
141
+ "loss": 0.2262,
142
+ "step": 1899
143
+ },
144
+ {
145
+ "epoch": 9.0,
146
+ "eval_accuracy": 0.7843333333333333,
147
+ "eval_f1": 0.7814767734353214,
148
+ "eval_loss": 0.3149881064891815,
149
+ "eval_runtime": 5.1238,
150
+ "eval_samples_per_second": 585.508,
151
+ "eval_steps_per_second": 73.188,
152
+ "step": 1899
153
+ },
154
+ {
155
+ "epoch": 10.0,
156
+ "learning_rate": 6.666666666666666e-07,
157
+ "loss": 0.2191,
158
+ "step": 2110
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_accuracy": 0.7813333333333333,
163
+ "eval_f1": 0.7801938582947333,
164
+ "eval_loss": 0.32408154010772705,
165
+ "eval_runtime": 5.366,
166
+ "eval_samples_per_second": 559.08,
167
+ "eval_steps_per_second": 69.885,
168
+ "step": 2110
169
+ },
170
+ {
171
+ "epoch": 11.0,
172
+ "learning_rate": 6.333333333333332e-07,
173
+ "loss": 0.2112,
174
+ "step": 2321
175
+ },
176
+ {
177
+ "epoch": 11.0,
178
+ "eval_accuracy": 0.7866666666666666,
179
+ "eval_f1": 0.785979422813256,
180
+ "eval_loss": 0.3275919258594513,
181
+ "eval_runtime": 5.1309,
182
+ "eval_samples_per_second": 584.694,
183
+ "eval_steps_per_second": 73.087,
184
+ "step": 2321
185
+ },
186
+ {
187
+ "epoch": 12.0,
188
+ "learning_rate": 6e-07,
189
+ "loss": 0.2047,
190
+ "step": 2532
191
+ },
192
+ {
193
+ "epoch": 12.0,
194
+ "eval_accuracy": 0.7896666666666666,
195
+ "eval_f1": 0.7886408467585846,
196
+ "eval_loss": 0.32662513852119446,
197
+ "eval_runtime": 5.3907,
198
+ "eval_samples_per_second": 556.515,
199
+ "eval_steps_per_second": 69.564,
200
+ "step": 2532
201
+ },
202
+ {
203
+ "epoch": 13.0,
204
+ "learning_rate": 5.666666666666666e-07,
205
+ "loss": 0.1973,
206
+ "step": 2743
207
+ },
208
+ {
209
+ "epoch": 13.0,
210
+ "eval_accuracy": 0.7893333333333333,
211
+ "eval_f1": 0.7883928571428571,
212
+ "eval_loss": 0.3298616409301758,
213
+ "eval_runtime": 5.1275,
214
+ "eval_samples_per_second": 585.084,
215
+ "eval_steps_per_second": 73.135,
216
+ "step": 2743
217
+ },
218
+ {
219
+ "epoch": 14.0,
220
+ "learning_rate": 5.333333333333333e-07,
221
+ "loss": 0.1897,
222
+ "step": 2954
223
+ },
224
+ {
225
+ "epoch": 14.0,
226
+ "eval_accuracy": 0.792,
227
+ "eval_f1": 0.790682602817108,
228
+ "eval_loss": 0.3300517499446869,
229
+ "eval_runtime": 5.2516,
230
+ "eval_samples_per_second": 571.251,
231
+ "eval_steps_per_second": 71.406,
232
+ "step": 2954
233
+ }
234
+ ],
235
+ "max_steps": 6330,
236
+ "num_train_epochs": 30,
237
+ "total_flos": 2.008091470853261e+16,
238
+ "trial_name": null,
239
+ "trial_params": null
240
+ }
checkpoint-2954/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3966be765a13463da707bf5cd58cd4c0452776ca8eaf9c649e2dbde2a9daa7b1
3
+ size 3119
checkpoint-2954/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3165/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "multi_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.17.0",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 50265
39
+ }
checkpoint-3165/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3165/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64ac1b126974bf8f8b0611f1d9ac293a4c62e76b250f74d68ce252a7256d6d2e
3
+ size 997299037
checkpoint-3165/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc3421988ac5dd87d3d7f94f640c2e5ba9d841091dd31e34f7cf794697aaf45
3
+ size 498678125
checkpoint-3165/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4178c1306a1a8c48b689f0c04a574fb9e85596822b64ca0bbefbf080fde79d
3
+ size 14503
checkpoint-3165/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7fcb7acfced511ad4e8521b824b6938e10d978156d3b75b9d3969d5f5dbff6
3
+ size 559
checkpoint-3165/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31918595ad9ddd1463e104be0c9599212e3f56cc08ed292c9c0e3050e78e25cf
3
+ size 623
checkpoint-3165/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
checkpoint-3165/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3165/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m", "normalization": true, "tokenizer_class": "RobertaTokenizer"}
checkpoint-3165/trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7925361349683366,
3
+ "best_model_checkpoint": "outputs/time_lm_nli/checkpoint-3165",
4
+ "epoch": 15.0,
5
+ "global_step": 3165,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 9.666666666666666e-07,
13
+ "loss": 0.5392,
14
+ "step": 211
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7,
19
+ "eval_f1": 0.6998718119161117,
20
+ "eval_loss": 0.4048246741294861,
21
+ "eval_runtime": 5.0256,
22
+ "eval_samples_per_second": 596.939,
23
+ "eval_steps_per_second": 74.617,
24
+ "step": 211
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 9.333333333333333e-07,
29
+ "loss": 0.3725,
30
+ "step": 422
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.759,
35
+ "eval_f1": 0.7583549419422403,
36
+ "eval_loss": 0.3489450216293335,
37
+ "eval_runtime": 5.103,
38
+ "eval_samples_per_second": 587.885,
39
+ "eval_steps_per_second": 73.486,
40
+ "step": 422
41
+ },
42
+ {
43
+ "epoch": 3.0,
44
+ "learning_rate": 9e-07,
45
+ "loss": 0.3158,
46
+ "step": 633
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "eval_accuracy": 0.7613333333333333,
51
+ "eval_f1": 0.7569694772671423,
52
+ "eval_loss": 0.3286795914173126,
53
+ "eval_runtime": 5.4646,
54
+ "eval_samples_per_second": 548.991,
55
+ "eval_steps_per_second": 68.624,
56
+ "step": 633
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 8.666666666666667e-07,
61
+ "loss": 0.289,
62
+ "step": 844
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_accuracy": 0.769,
67
+ "eval_f1": 0.7684440341259363,
68
+ "eval_loss": 0.33065709471702576,
69
+ "eval_runtime": 5.2159,
70
+ "eval_samples_per_second": 575.162,
71
+ "eval_steps_per_second": 71.895,
72
+ "step": 844
73
+ },
74
+ {
75
+ "epoch": 5.0,
76
+ "learning_rate": 8.333333333333333e-07,
77
+ "loss": 0.2716,
78
+ "step": 1055
79
+ },
80
+ {
81
+ "epoch": 5.0,
82
+ "eval_accuracy": 0.7766666666666666,
83
+ "eval_f1": 0.775028474008066,
84
+ "eval_loss": 0.3240624666213989,
85
+ "eval_runtime": 5.2721,
86
+ "eval_samples_per_second": 569.029,
87
+ "eval_steps_per_second": 71.129,
88
+ "step": 1055
89
+ },
90
+ {
91
+ "epoch": 6.0,
92
+ "learning_rate": 8e-07,
93
+ "loss": 0.2575,
94
+ "step": 1266
95
+ },
96
+ {
97
+ "epoch": 6.0,
98
+ "eval_accuracy": 0.7786666666666666,
99
+ "eval_f1": 0.7782108653517272,
100
+ "eval_loss": 0.32720017433166504,
101
+ "eval_runtime": 5.4144,
102
+ "eval_samples_per_second": 554.075,
103
+ "eval_steps_per_second": 69.259,
104
+ "step": 1266
105
+ },
106
+ {
107
+ "epoch": 7.0,
108
+ "learning_rate": 7.666666666666667e-07,
109
+ "loss": 0.2441,
110
+ "step": 1477
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_accuracy": 0.7783333333333333,
115
+ "eval_f1": 0.7775937336504917,
116
+ "eval_loss": 0.3257558345794678,
117
+ "eval_runtime": 5.0695,
118
+ "eval_samples_per_second": 591.777,
119
+ "eval_steps_per_second": 73.972,
120
+ "step": 1477
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "learning_rate": 7.333333333333332e-07,
125
+ "loss": 0.2363,
126
+ "step": 1688
127
+ },
128
+ {
129
+ "epoch": 8.0,
130
+ "eval_accuracy": 0.7776666666666666,
131
+ "eval_f1": 0.777267505288088,
132
+ "eval_loss": 0.331592321395874,
133
+ "eval_runtime": 5.1518,
134
+ "eval_samples_per_second": 582.323,
135
+ "eval_steps_per_second": 72.79,
136
+ "step": 1688
137
+ },
138
+ {
139
+ "epoch": 9.0,
140
+ "learning_rate": 7e-07,
141
+ "loss": 0.2262,
142
+ "step": 1899
143
+ },
144
+ {
145
+ "epoch": 9.0,
146
+ "eval_accuracy": 0.7843333333333333,
147
+ "eval_f1": 0.7814767734353214,
148
+ "eval_loss": 0.3149881064891815,
149
+ "eval_runtime": 5.1238,
150
+ "eval_samples_per_second": 585.508,
151
+ "eval_steps_per_second": 73.188,
152
+ "step": 1899
153
+ },
154
+ {
155
+ "epoch": 10.0,
156
+ "learning_rate": 6.666666666666666e-07,
157
+ "loss": 0.2191,
158
+ "step": 2110
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_accuracy": 0.7813333333333333,
163
+ "eval_f1": 0.7801938582947333,
164
+ "eval_loss": 0.32408154010772705,
165
+ "eval_runtime": 5.366,
166
+ "eval_samples_per_second": 559.08,
167
+ "eval_steps_per_second": 69.885,
168
+ "step": 2110
169
+ },
170
+ {
171
+ "epoch": 11.0,
172
+ "learning_rate": 6.333333333333332e-07,
173
+ "loss": 0.2112,
174
+ "step": 2321
175
+ },
176
+ {
177
+ "epoch": 11.0,
178
+ "eval_accuracy": 0.7866666666666666,
179
+ "eval_f1": 0.785979422813256,
180
+ "eval_loss": 0.3275919258594513,
181
+ "eval_runtime": 5.1309,
182
+ "eval_samples_per_second": 584.694,
183
+ "eval_steps_per_second": 73.087,
184
+ "step": 2321
185
+ },
186
+ {
187
+ "epoch": 12.0,
188
+ "learning_rate": 6e-07,
189
+ "loss": 0.2047,
190
+ "step": 2532
191
+ },
192
+ {
193
+ "epoch": 12.0,
194
+ "eval_accuracy": 0.7896666666666666,
195
+ "eval_f1": 0.7886408467585846,
196
+ "eval_loss": 0.32662513852119446,
197
+ "eval_runtime": 5.3907,
198
+ "eval_samples_per_second": 556.515,
199
+ "eval_steps_per_second": 69.564,
200
+ "step": 2532
201
+ },
202
+ {
203
+ "epoch": 13.0,
204
+ "learning_rate": 5.666666666666666e-07,
205
+ "loss": 0.1973,
206
+ "step": 2743
207
+ },
208
+ {
209
+ "epoch": 13.0,
210
+ "eval_accuracy": 0.7893333333333333,
211
+ "eval_f1": 0.7883928571428571,
212
+ "eval_loss": 0.3298616409301758,
213
+ "eval_runtime": 5.1275,
214
+ "eval_samples_per_second": 585.084,
215
+ "eval_steps_per_second": 73.135,
216
+ "step": 2743
217
+ },
218
+ {
219
+ "epoch": 14.0,
220
+ "learning_rate": 5.333333333333333e-07,
221
+ "loss": 0.1897,
222
+ "step": 2954
223
+ },
224
+ {
225
+ "epoch": 14.0,
226
+ "eval_accuracy": 0.792,
227
+ "eval_f1": 0.790682602817108,
228
+ "eval_loss": 0.3300517499446869,
229
+ "eval_runtime": 5.2516,
230
+ "eval_samples_per_second": 571.251,
231
+ "eval_steps_per_second": 71.406,
232
+ "step": 2954
233
+ },
234
+ {
235
+ "epoch": 15.0,
236
+ "learning_rate": 5e-07,
237
+ "loss": 0.1862,
238
+ "step": 3165
239
+ },
240
+ {
241
+ "epoch": 15.0,
242
+ "eval_accuracy": 0.794,
243
+ "eval_f1": 0.7925361349683366,
244
+ "eval_loss": 0.3283214867115021,
245
+ "eval_runtime": 5.2002,
246
+ "eval_samples_per_second": 576.904,
247
+ "eval_steps_per_second": 72.113,
248
+ "step": 3165
249
+ }
250
+ ],
251
+ "max_steps": 6330,
252
+ "num_train_epochs": 30,
253
+ "total_flos": 2.151402771654259e+16,
254
+ "trial_name": null,
255
+ "trial_params": null
256
+ }
checkpoint-3165/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3966be765a13463da707bf5cd58cd4c0452776ca8eaf9c649e2dbde2a9daa7b1
3
+ size 3119
checkpoint-3165/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ea07e7b22adc68e942ae50e8a7e86dd5faf67fd91939960f7b1cf3778bbd35f
3
  size 498678125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc3421988ac5dd87d3d7f94f640c2e5ba9d841091dd31e34f7cf794697aaf45
3
  size 498678125