bobox commited on
Commit
0e92d8c
1 Parent(s): d05766c

Training in progress, step 4, checkpoint

Browse files
checkpoint-4/1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
checkpoint-4/README.md ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-4/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-small",
3
+ "architectures": [
4
+ "DebertaV2Model"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.42.3",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
checkpoint-4/config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.42.3",
5
+ "pytorch": "2.1.2"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
checkpoint-4/modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
checkpoint-4/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c98a4383a0978546a09cde2a9418d4b74e737e7ff11f91ef0313646fbd58bac
3
+ size 1130520122
checkpoint-4/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9495c8a837eb2f6f9cf62cab1242bbca22d2a0599fb3b75390ca77b7e52a5fb2
3
+ size 565251810
checkpoint-4/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae8661e57a0a57581cdb83ab31e278fe0a43a4dff52c4be039a87bdcaa350d68
3
+ size 14244
checkpoint-4/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca89f2d49dfb058abe3623375bc3e28d24254514505830490129c306bafb4c9f
3
+ size 1064
checkpoint-4/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
checkpoint-4/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
+ }
checkpoint-4/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-4/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4/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
+ }
checkpoint-4/trainer_state.json ADDED
@@ -0,0 +1,355 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.11627906976744186,
5
+ "eval_steps": 2,
6
+ "global_step": 4,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.029069767441860465,
13
+ "grad_norm": 13.73514461517334,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 6.7536,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.05813953488372093,
20
+ "grad_norm": 16.892961502075195,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 6.6203,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.05813953488372093,
27
+ "eval_NLI-v2_cosine_accuracy": 1.0,
28
+ "eval_NLI-v2_dot_accuracy": 0.109375,
29
+ "eval_NLI-v2_euclidean_accuracy": 1.0,
30
+ "eval_NLI-v2_manhattan_accuracy": 1.0,
31
+ "eval_NLI-v2_max_accuracy": 1.0,
32
+ "eval_VitaminC_cosine_accuracy": 0.55078125,
33
+ "eval_VitaminC_cosine_accuracy_threshold": 0.9469717741012573,
34
+ "eval_VitaminC_cosine_ap": 0.5165514227338435,
35
+ "eval_VitaminC_cosine_f1": 0.6525198938992042,
36
+ "eval_VitaminC_cosine_f1_threshold": 0.4987494945526123,
37
+ "eval_VitaminC_cosine_precision": 0.484251968503937,
38
+ "eval_VitaminC_cosine_recall": 1.0,
39
+ "eval_VitaminC_dot_accuracy": 0.55078125,
40
+ "eval_VitaminC_dot_accuracy_threshold": 417.45166015625,
41
+ "eval_VitaminC_dot_ap": 0.5125282416460941,
42
+ "eval_VitaminC_dot_f1": 0.6525198938992042,
43
+ "eval_VitaminC_dot_f1_threshold": 200.84530639648438,
44
+ "eval_VitaminC_dot_precision": 0.484251968503937,
45
+ "eval_VitaminC_dot_recall": 1.0,
46
+ "eval_VitaminC_euclidean_accuracy": 0.546875,
47
+ "eval_VitaminC_euclidean_accuracy_threshold": 6.841136932373047,
48
+ "eval_VitaminC_euclidean_ap": 0.512994913068431,
49
+ "eval_VitaminC_euclidean_f1": 0.6525198938992042,
50
+ "eval_VitaminC_euclidean_f1_threshold": 20.22179412841797,
51
+ "eval_VitaminC_euclidean_precision": 0.484251968503937,
52
+ "eval_VitaminC_euclidean_recall": 1.0,
53
+ "eval_VitaminC_manhattan_accuracy": 0.546875,
54
+ "eval_VitaminC_manhattan_accuracy_threshold": 117.1143569946289,
55
+ "eval_VitaminC_manhattan_ap": 0.5177961641566705,
56
+ "eval_VitaminC_manhattan_f1": 0.6542553191489362,
57
+ "eval_VitaminC_manhattan_f1_threshold": 292.3347473144531,
58
+ "eval_VitaminC_manhattan_precision": 0.48616600790513836,
59
+ "eval_VitaminC_manhattan_recall": 1.0,
60
+ "eval_VitaminC_max_accuracy": 0.55078125,
61
+ "eval_VitaminC_max_accuracy_threshold": 417.45166015625,
62
+ "eval_VitaminC_max_ap": 0.5177961641566705,
63
+ "eval_VitaminC_max_f1": 0.6542553191489362,
64
+ "eval_VitaminC_max_f1_threshold": 292.3347473144531,
65
+ "eval_VitaminC_max_precision": 0.48616600790513836,
66
+ "eval_VitaminC_max_recall": 1.0,
67
+ "eval_sequential_score": 0.5177961641566705,
68
+ "eval_sts-test_pearson_cosine": 0.017178505918243114,
69
+ "eval_sts-test_pearson_dot": 0.16228524441844774,
70
+ "eval_sts-test_pearson_euclidean": 0.024391561236282323,
71
+ "eval_sts-test_pearson_manhattan": 0.059272519732015624,
72
+ "eval_sts-test_pearson_max": 0.16228524441844774,
73
+ "eval_sts-test_spearman_cosine": 0.07115563415775981,
74
+ "eval_sts-test_spearman_dot": 0.1967074668301984,
75
+ "eval_sts-test_spearman_euclidean": 0.05117306486959643,
76
+ "eval_sts-test_spearman_manhattan": 0.07641354546391785,
77
+ "eval_sts-test_spearman_max": 0.1967074668301984,
78
+ "eval_vitaminc-pairs_loss": 2.72658371925354,
79
+ "eval_vitaminc-pairs_runtime": 1.4719,
80
+ "eval_vitaminc-pairs_samples_per_second": 73.373,
81
+ "eval_vitaminc-pairs_steps_per_second": 1.359,
82
+ "step": 2
83
+ },
84
+ {
85
+ "epoch": 0.05813953488372093,
86
+ "eval_negation-triplets_loss": 5.094177722930908,
87
+ "eval_negation-triplets_runtime": 0.3027,
88
+ "eval_negation-triplets_samples_per_second": 211.46,
89
+ "eval_negation-triplets_steps_per_second": 3.304,
90
+ "step": 2
91
+ },
92
+ {
93
+ "epoch": 0.05813953488372093,
94
+ "eval_scitail-pairs-pos_loss": 1.9183871746063232,
95
+ "eval_scitail-pairs-pos_runtime": 0.3785,
96
+ "eval_scitail-pairs-pos_samples_per_second": 142.654,
97
+ "eval_scitail-pairs-pos_steps_per_second": 2.642,
98
+ "step": 2
99
+ },
100
+ {
101
+ "epoch": 0.05813953488372093,
102
+ "eval_xsum-pairs_loss": 6.3277668952941895,
103
+ "eval_xsum-pairs_runtime": 3.4205,
104
+ "eval_xsum-pairs_samples_per_second": 37.422,
105
+ "eval_xsum-pairs_steps_per_second": 0.585,
106
+ "step": 2
107
+ },
108
+ {
109
+ "epoch": 0.05813953488372093,
110
+ "eval_sciq_pairs_loss": 0.36539140343666077,
111
+ "eval_sciq_pairs_runtime": 3.4462,
112
+ "eval_sciq_pairs_samples_per_second": 37.143,
113
+ "eval_sciq_pairs_steps_per_second": 0.58,
114
+ "step": 2
115
+ },
116
+ {
117
+ "epoch": 0.05813953488372093,
118
+ "eval_qasc_pairs_loss": 3.9689104557037354,
119
+ "eval_qasc_pairs_runtime": 0.6477,
120
+ "eval_qasc_pairs_samples_per_second": 197.636,
121
+ "eval_qasc_pairs_steps_per_second": 3.088,
122
+ "step": 2
123
+ },
124
+ {
125
+ "epoch": 0.05813953488372093,
126
+ "eval_openbookqa_pairs_loss": 4.7439374923706055,
127
+ "eval_openbookqa_pairs_runtime": 0.5759,
128
+ "eval_openbookqa_pairs_samples_per_second": 222.248,
129
+ "eval_openbookqa_pairs_steps_per_second": 3.473,
130
+ "step": 2
131
+ },
132
+ {
133
+ "epoch": 0.05813953488372093,
134
+ "eval_msmarco_pairs_loss": 10.51363754272461,
135
+ "eval_msmarco_pairs_runtime": 1.3036,
136
+ "eval_msmarco_pairs_samples_per_second": 98.189,
137
+ "eval_msmarco_pairs_steps_per_second": 1.534,
138
+ "step": 2
139
+ },
140
+ {
141
+ "epoch": 0.05813953488372093,
142
+ "eval_nq_pairs_loss": 4.969011306762695,
143
+ "eval_nq_pairs_runtime": 2.5922,
144
+ "eval_nq_pairs_samples_per_second": 49.378,
145
+ "eval_nq_pairs_steps_per_second": 0.772,
146
+ "step": 2
147
+ },
148
+ {
149
+ "epoch": 0.05813953488372093,
150
+ "eval_trivia_pairs_loss": 3.8609507083892822,
151
+ "eval_trivia_pairs_runtime": 4.3666,
152
+ "eval_trivia_pairs_samples_per_second": 29.314,
153
+ "eval_trivia_pairs_steps_per_second": 0.458,
154
+ "step": 2
155
+ },
156
+ {
157
+ "epoch": 0.05813953488372093,
158
+ "eval_gooaq_pairs_loss": 8.041110038757324,
159
+ "eval_gooaq_pairs_runtime": 0.9119,
160
+ "eval_gooaq_pairs_samples_per_second": 140.361,
161
+ "eval_gooaq_pairs_steps_per_second": 2.193,
162
+ "step": 2
163
+ },
164
+ {
165
+ "epoch": 0.05813953488372093,
166
+ "eval_paws-pos_loss": 2.21897029876709,
167
+ "eval_paws-pos_runtime": 0.6905,
168
+ "eval_paws-pos_samples_per_second": 185.364,
169
+ "eval_paws-pos_steps_per_second": 2.896,
170
+ "step": 2
171
+ },
172
+ {
173
+ "epoch": 0.0872093023255814,
174
+ "grad_norm": 15.801941871643066,
175
+ "learning_rate": 1e-05,
176
+ "loss": 6.7963,
177
+ "step": 3
178
+ },
179
+ {
180
+ "epoch": 0.11627906976744186,
181
+ "grad_norm": 11.94517993927002,
182
+ "learning_rate": 1.3333333333333333e-05,
183
+ "loss": 6.4488,
184
+ "step": 4
185
+ },
186
+ {
187
+ "epoch": 0.11627906976744186,
188
+ "eval_NLI-v2_cosine_accuracy": 1.0,
189
+ "eval_NLI-v2_dot_accuracy": 0.109375,
190
+ "eval_NLI-v2_euclidean_accuracy": 1.0,
191
+ "eval_NLI-v2_manhattan_accuracy": 1.0,
192
+ "eval_NLI-v2_max_accuracy": 1.0,
193
+ "eval_VitaminC_cosine_accuracy": 0.55078125,
194
+ "eval_VitaminC_cosine_accuracy_threshold": 0.9437637329101562,
195
+ "eval_VitaminC_cosine_ap": 0.5161989667198088,
196
+ "eval_VitaminC_cosine_f1": 0.6525198938992042,
197
+ "eval_VitaminC_cosine_f1_threshold": 0.56722092628479,
198
+ "eval_VitaminC_cosine_precision": 0.484251968503937,
199
+ "eval_VitaminC_cosine_recall": 1.0,
200
+ "eval_VitaminC_dot_accuracy": 0.546875,
201
+ "eval_VitaminC_dot_accuracy_threshold": 416.9976806640625,
202
+ "eval_VitaminC_dot_ap": 0.515337582265173,
203
+ "eval_VitaminC_dot_f1": 0.6507936507936508,
204
+ "eval_VitaminC_dot_f1_threshold": 223.1047821044922,
205
+ "eval_VitaminC_dot_precision": 0.4823529411764706,
206
+ "eval_VitaminC_dot_recall": 1.0,
207
+ "eval_VitaminC_euclidean_accuracy": 0.55078125,
208
+ "eval_VitaminC_euclidean_accuracy_threshold": 6.841610908508301,
209
+ "eval_VitaminC_euclidean_ap": 0.5167890569390883,
210
+ "eval_VitaminC_euclidean_f1": 0.6542553191489362,
211
+ "eval_VitaminC_euclidean_f1_threshold": 18.548978805541992,
212
+ "eval_VitaminC_euclidean_precision": 0.48616600790513836,
213
+ "eval_VitaminC_euclidean_recall": 1.0,
214
+ "eval_VitaminC_manhattan_accuracy": 0.54296875,
215
+ "eval_VitaminC_manhattan_accuracy_threshold": 110.40855407714844,
216
+ "eval_VitaminC_manhattan_ap": 0.5219582103185639,
217
+ "eval_VitaminC_manhattan_f1": 0.6542553191489362,
218
+ "eval_VitaminC_manhattan_f1_threshold": 282.48602294921875,
219
+ "eval_VitaminC_manhattan_precision": 0.48616600790513836,
220
+ "eval_VitaminC_manhattan_recall": 1.0,
221
+ "eval_VitaminC_max_accuracy": 0.55078125,
222
+ "eval_VitaminC_max_accuracy_threshold": 416.9976806640625,
223
+ "eval_VitaminC_max_ap": 0.5219582103185639,
224
+ "eval_VitaminC_max_f1": 0.6542553191489362,
225
+ "eval_VitaminC_max_f1_threshold": 282.48602294921875,
226
+ "eval_VitaminC_max_precision": 0.48616600790513836,
227
+ "eval_VitaminC_max_recall": 1.0,
228
+ "eval_sequential_score": 0.5219582103185639,
229
+ "eval_sts-test_pearson_cosine": 0.025276809579094173,
230
+ "eval_sts-test_pearson_dot": 0.21470147681711343,
231
+ "eval_sts-test_pearson_euclidean": 0.027783806662194415,
232
+ "eval_sts-test_pearson_manhattan": 0.059736177006118926,
233
+ "eval_sts-test_pearson_max": 0.21470147681711343,
234
+ "eval_sts-test_spearman_cosine": 0.0776783582433888,
235
+ "eval_sts-test_spearman_dot": 0.2491347682204262,
236
+ "eval_sts-test_spearman_euclidean": 0.054640386155863654,
237
+ "eval_sts-test_spearman_manhattan": 0.07764379287610436,
238
+ "eval_sts-test_spearman_max": 0.2491347682204262,
239
+ "eval_vitaminc-pairs_loss": 2.7045021057128906,
240
+ "eval_vitaminc-pairs_runtime": 1.4394,
241
+ "eval_vitaminc-pairs_samples_per_second": 75.033,
242
+ "eval_vitaminc-pairs_steps_per_second": 1.389,
243
+ "step": 4
244
+ },
245
+ {
246
+ "epoch": 0.11627906976744186,
247
+ "eval_negation-triplets_loss": 5.081584453582764,
248
+ "eval_negation-triplets_runtime": 0.2952,
249
+ "eval_negation-triplets_samples_per_second": 216.79,
250
+ "eval_negation-triplets_steps_per_second": 3.387,
251
+ "step": 4
252
+ },
253
+ {
254
+ "epoch": 0.11627906976744186,
255
+ "eval_scitail-pairs-pos_loss": 1.9186776876449585,
256
+ "eval_scitail-pairs-pos_runtime": 0.3702,
257
+ "eval_scitail-pairs-pos_samples_per_second": 145.879,
258
+ "eval_scitail-pairs-pos_steps_per_second": 2.701,
259
+ "step": 4
260
+ },
261
+ {
262
+ "epoch": 0.11627906976744186,
263
+ "eval_xsum-pairs_loss": 6.199001312255859,
264
+ "eval_xsum-pairs_runtime": 3.4227,
265
+ "eval_xsum-pairs_samples_per_second": 37.398,
266
+ "eval_xsum-pairs_steps_per_second": 0.584,
267
+ "step": 4
268
+ },
269
+ {
270
+ "epoch": 0.11627906976744186,
271
+ "eval_sciq_pairs_loss": 0.3414052426815033,
272
+ "eval_sciq_pairs_runtime": 3.4403,
273
+ "eval_sciq_pairs_samples_per_second": 37.206,
274
+ "eval_sciq_pairs_steps_per_second": 0.581,
275
+ "step": 4
276
+ },
277
+ {
278
+ "epoch": 0.11627906976744186,
279
+ "eval_qasc_pairs_loss": 3.662200927734375,
280
+ "eval_qasc_pairs_runtime": 0.6486,
281
+ "eval_qasc_pairs_samples_per_second": 197.349,
282
+ "eval_qasc_pairs_steps_per_second": 3.084,
283
+ "step": 4
284
+ },
285
+ {
286
+ "epoch": 0.11627906976744186,
287
+ "eval_openbookqa_pairs_loss": 4.650759220123291,
288
+ "eval_openbookqa_pairs_runtime": 0.5722,
289
+ "eval_openbookqa_pairs_samples_per_second": 223.702,
290
+ "eval_openbookqa_pairs_steps_per_second": 3.495,
291
+ "step": 4
292
+ },
293
+ {
294
+ "epoch": 0.11627906976744186,
295
+ "eval_msmarco_pairs_loss": 9.487885475158691,
296
+ "eval_msmarco_pairs_runtime": 1.2978,
297
+ "eval_msmarco_pairs_samples_per_second": 98.63,
298
+ "eval_msmarco_pairs_steps_per_second": 1.541,
299
+ "step": 4
300
+ },
301
+ {
302
+ "epoch": 0.11627906976744186,
303
+ "eval_nq_pairs_loss": 4.4714131355285645,
304
+ "eval_nq_pairs_runtime": 2.569,
305
+ "eval_nq_pairs_samples_per_second": 49.824,
306
+ "eval_nq_pairs_steps_per_second": 0.779,
307
+ "step": 4
308
+ },
309
+ {
310
+ "epoch": 0.11627906976744186,
311
+ "eval_trivia_pairs_loss": 3.5246145725250244,
312
+ "eval_trivia_pairs_runtime": 4.3557,
313
+ "eval_trivia_pairs_samples_per_second": 29.387,
314
+ "eval_trivia_pairs_steps_per_second": 0.459,
315
+ "step": 4
316
+ },
317
+ {
318
+ "epoch": 0.11627906976744186,
319
+ "eval_gooaq_pairs_loss": 7.395092010498047,
320
+ "eval_gooaq_pairs_runtime": 0.9109,
321
+ "eval_gooaq_pairs_samples_per_second": 140.521,
322
+ "eval_gooaq_pairs_steps_per_second": 2.196,
323
+ "step": 4
324
+ },
325
+ {
326
+ "epoch": 0.11627906976744186,
327
+ "eval_paws-pos_loss": 2.233201742172241,
328
+ "eval_paws-pos_runtime": 0.6853,
329
+ "eval_paws-pos_samples_per_second": 186.773,
330
+ "eval_paws-pos_steps_per_second": 2.918,
331
+ "step": 4
332
+ }
333
+ ],
334
+ "logging_steps": 1,
335
+ "max_steps": 34,
336
+ "num_input_tokens_seen": 0,
337
+ "num_train_epochs": 1,
338
+ "save_steps": 2,
339
+ "stateful_callbacks": {
340
+ "TrainerControl": {
341
+ "args": {
342
+ "should_epoch_stop": false,
343
+ "should_evaluate": false,
344
+ "should_log": false,
345
+ "should_save": true,
346
+ "should_training_stop": false
347
+ },
348
+ "attributes": {}
349
+ }
350
+ },
351
+ "total_flos": 0.0,
352
+ "train_batch_size": 224,
353
+ "trial_name": null,
354
+ "trial_params": null
355
+ }
checkpoint-4/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edceb7011ecd574f3e3fa5380c854a14e3b5904426b5550bdb62acd6cda68870
3
+ size 5688