Hugging Face's logo

cbrew475
/
mpnet-metric

Text Classification
Transformers
PyTorch
mpnet
Inference Endpoints
Model card Files Community
cbrew475 commited on
Commit
58d6414
•
1 Parent(s): 290a7b8

Training in progress, step 200

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-1000/config.json +183 -0
  2. checkpoint-1000/optimizer.pt +3 -0
  3. checkpoint-1000/pytorch_model.bin +3 -0
  4. checkpoint-1000/rng_state.pth +3 -0
  5. checkpoint-1000/scheduler.pt +3 -0
  6. checkpoint-1000/special_tokens_map.json +1 -0
  7. checkpoint-1000/tokenizer.json +0 -0
  8. checkpoint-1000/tokenizer_config.json +1 -0
  9. checkpoint-1000/trainer_state.json +138 -0
  10. checkpoint-1000/training_args.bin +3 -0
  11. checkpoint-1000/vocab.txt +0 -0
  12. checkpoint-1200/config.json +183 -0
  13. checkpoint-1200/optimizer.pt +3 -0
  14. checkpoint-1200/pytorch_model.bin +3 -0
  15. checkpoint-1200/rng_state.pth +3 -0
  16. checkpoint-1200/scheduler.pt +3 -0
  17. checkpoint-1200/special_tokens_map.json +1 -0
  18. checkpoint-1200/tokenizer.json +0 -0
  19. checkpoint-1200/tokenizer_config.json +1 -0
  20. checkpoint-1200/trainer_state.json +160 -0
  21. checkpoint-1200/training_args.bin +3 -0
  22. checkpoint-1200/vocab.txt +0 -0
  23. checkpoint-1400/config.json +183 -0
  24. checkpoint-1400/optimizer.pt +3 -0
  25. checkpoint-1400/pytorch_model.bin +3 -0
  26. checkpoint-1400/rng_state.pth +3 -0
  27. checkpoint-1400/scheduler.pt +3 -0
  28. checkpoint-1400/special_tokens_map.json +1 -0
  29. checkpoint-1400/tokenizer.json +0 -0
  30. checkpoint-1400/tokenizer_config.json +1 -0
  31. checkpoint-1400/trainer_state.json +182 -0
  32. checkpoint-1400/training_args.bin +3 -0
  33. checkpoint-1400/vocab.txt +0 -0
  34. checkpoint-1600/config.json +183 -0
  35. checkpoint-1600/optimizer.pt +3 -0
  36. checkpoint-1600/pytorch_model.bin +3 -0
  37. checkpoint-1600/rng_state.pth +3 -0
  38. checkpoint-1600/scheduler.pt +3 -0
  39. checkpoint-1600/special_tokens_map.json +1 -0
  40. checkpoint-1600/tokenizer.json +0 -0
  41. checkpoint-1600/tokenizer_config.json +1 -0
  42. checkpoint-1600/trainer_state.json +210 -0
  43. checkpoint-1600/training_args.bin +3 -0
  44. checkpoint-1600/vocab.txt +0 -0
  45. checkpoint-200/optimizer.pt +1 -1
  46. checkpoint-200/pytorch_model.bin +1 -1
  47. checkpoint-200/scheduler.pt +1 -1
  48. checkpoint-200/trainer_state.json +15 -15
  49. checkpoint-200/training_args.bin +1 -1
  50. pytorch_model.bin +1 -1
checkpoint-1000/config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
3
+ "architectures": [
4
+ "MPNetTwoClassForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20",
34
+ "21": "LABEL_21",
35
+ "22": "LABEL_22",
36
+ "23": "LABEL_23",
37
+ "24": "LABEL_24",
38
+ "25": "LABEL_25",
39
+ "26": "LABEL_26",
40
+ "27": "LABEL_27",
41
+ "28": "LABEL_28",
42
+ "29": "LABEL_29",
43
+ "30": "LABEL_30",
44
+ "31": "LABEL_31",
45
+ "32": "LABEL_32",
46
+ "33": "LABEL_33",
47
+ "34": "LABEL_34",
48
+ "35": "LABEL_35",
49
+ "36": "LABEL_36",
50
+ "37": "LABEL_37",
51
+ "38": "LABEL_38",
52
+ "39": "LABEL_39",
53
+ "40": "LABEL_40",
54
+ "41": "LABEL_41",
55
+ "42": "LABEL_42",
56
+ "43": "LABEL_43",
57
+ "44": "LABEL_44",
58
+ "45": "LABEL_45",
59
+ "46": "LABEL_46",
60
+ "47": "LABEL_47",
61
+ "48": "LABEL_48",
62
+ "49": "LABEL_49",
63
+ "50": "LABEL_50",
64
+ "51": "LABEL_51",
65
+ "52": "LABEL_52",
66
+ "53": "LABEL_53",
67
+ "54": "LABEL_54",
68
+ "55": "LABEL_55",
69
+ "56": "LABEL_56",
70
+ "57": "LABEL_57",
71
+ "58": "LABEL_58",
72
+ "59": "LABEL_59",
73
+ "60": "LABEL_60",
74
+ "61": "LABEL_61",
75
+ "62": "LABEL_62",
76
+ "63": "LABEL_63",
77
+ "64": "LABEL_64",
78
+ "65": "LABEL_65",
79
+ "66": "LABEL_66",
80
+ "67": "LABEL_67",
81
+ "68": "LABEL_68",
82
+ "69": "LABEL_69",
83
+ "70": "LABEL_70",
84
+ "71": "LABEL_71",
85
+ "72": "LABEL_72",
86
+ "73": "LABEL_73",
87
+ "74": "LABEL_74",
88
+ "75": "LABEL_75",
89
+ "76": "LABEL_76"
90
+ },
91
+ "initializer_range": 0.02,
92
+ "intermediate_size": 3072,
93
+ "label2id": {
94
+ "LABEL_0": 0,
95
+ "LABEL_1": 1,
96
+ "LABEL_10": 10,
97
+ "LABEL_11": 11,
98
+ "LABEL_12": 12,
99
+ "LABEL_13": 13,
100
+ "LABEL_14": 14,
101
+ "LABEL_15": 15,
102
+ "LABEL_16": 16,
103
+ "LABEL_17": 17,
104
+ "LABEL_18": 18,
105
+ "LABEL_19": 19,
106
+ "LABEL_2": 2,
107
+ "LABEL_20": 20,
108
+ "LABEL_21": 21,
109
+ "LABEL_22": 22,
110
+ "LABEL_23": 23,
111
+ "LABEL_24": 24,
112
+ "LABEL_25": 25,
113
+ "LABEL_26": 26,
114
+ "LABEL_27": 27,
115
+ "LABEL_28": 28,
116
+ "LABEL_29": 29,
117
+ "LABEL_3": 3,
118
+ "LABEL_30": 30,
119
+ "LABEL_31": 31,
120
+ "LABEL_32": 32,
121
+ "LABEL_33": 33,
122
+ "LABEL_34": 34,
123
+ "LABEL_35": 35,
124
+ "LABEL_36": 36,
125
+ "LABEL_37": 37,
126
+ "LABEL_38": 38,
127
+ "LABEL_39": 39,
128
+ "LABEL_4": 4,
129
+ "LABEL_40": 40,
130
+ "LABEL_41": 41,
131
+ "LABEL_42": 42,
132
+ "LABEL_43": 43,
133
+ "LABEL_44": 44,
134
+ "LABEL_45": 45,
135
+ "LABEL_46": 46,
136
+ "LABEL_47": 47,
137
+ "LABEL_48": 48,
138
+ "LABEL_49": 49,
139
+ "LABEL_5": 5,
140
+ "LABEL_50": 50,
141
+ "LABEL_51": 51,
142
+ "LABEL_52": 52,
143
+ "LABEL_53": 53,
144
+ "LABEL_54": 54,
145
+ "LABEL_55": 55,
146
+ "LABEL_56": 56,
147
+ "LABEL_57": 57,
148
+ "LABEL_58": 58,
149
+ "LABEL_59": 59,
150
+ "LABEL_6": 6,
151
+ "LABEL_60": 60,
152
+ "LABEL_61": 61,
153
+ "LABEL_62": 62,
154
+ "LABEL_63": 63,
155
+ "LABEL_64": 64,
156
+ "LABEL_65": 65,
157
+ "LABEL_66": 66,
158
+ "LABEL_67": 67,
159
+ "LABEL_68": 68,
160
+ "LABEL_69": 69,
161
+ "LABEL_7": 7,
162
+ "LABEL_70": 70,
163
+ "LABEL_71": 71,
164
+ "LABEL_72": 72,
165
+ "LABEL_73": 73,
166
+ "LABEL_74": 74,
167
+ "LABEL_75": 75,
168
+ "LABEL_76": 76,
169
+ "LABEL_8": 8,
170
+ "LABEL_9": 9
171
+ },
172
+ "layer_norm_eps": 1e-05,
173
+ "max_position_embeddings": 514,
174
+ "model_type": "mpnet",
175
+ "num_attention_heads": 12,
176
+ "num_hidden_layers": 12,
177
+ "pad_token_id": 1,
178
+ "problem_type": "single_label_classification",
179
+ "relative_attention_num_buckets": 32,
180
+ "torch_dtype": "float32",
181
+ "transformers_version": "4.15.0",
182
+ "vocab_size": 30527
183
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6fbd690369d6e3616036cfdc100848a3e841b36dac017b6ee7830d307b640f
3
+ size 1762416361
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e7a028d53860fa196202d559b57e2290209c3973186b652b21fe6b840b7257
3
+ size 440628841
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dca373b306073fa617b95a237ca97a3222b3daab0d287f0ba15112f603ec89d
3
+ size 15523
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feca2bfe2c8d3d4dcdae71baa79d9d0ed4f85859b043bf149b68a4d3756d37e3
3
+ size 623
checkpoint-1000/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-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "sentence-transformers/all-mpnet-base-v2", "tokenizer_class": "MPNetTokenizer"}
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9253246753246753,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
4
+ "epoch": 22.727272727272727,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.27,
12
+ "eval_accuracy": 0.8318181818181818,
13
+ "eval_f1": 0.7902944410637314,
14
+ "eval_loss": 1.6091233491897583,
15
+ "eval_matthews_correlation": 0.8302307602375942,
16
+ "eval_runtime": 2.3926,
17
+ "eval_samples_per_second": 1287.31,
18
+ "eval_steps_per_second": 8.359,
19
+ "step": 100
20
+ },
21
+ {
22
+ "epoch": 4.55,
23
+ "eval_accuracy": 0.9097402597402597,
24
+ "eval_f1": 0.9022270624577644,
25
+ "eval_loss": 1.493744969367981,
26
+ "eval_matthews_correlation": 0.9085414308645802,
27
+ "eval_runtime": 2.2329,
28
+ "eval_samples_per_second": 1379.356,
29
+ "eval_steps_per_second": 8.957,
30
+ "step": 200
31
+ },
32
+ {
33
+ "epoch": 6.82,
34
+ "eval_accuracy": 0.9074675324675324,
35
+ "eval_f1": 0.9101059174003832,
36
+ "eval_loss": 1.6116833686828613,
37
+ "eval_matthews_correlation": 0.9062636808107568,
38
+ "eval_runtime": 2.0808,
39
+ "eval_samples_per_second": 1480.17,
40
+ "eval_steps_per_second": 9.611,
41
+ "step": 300
42
+ },
43
+ {
44
+ "epoch": 9.09,
45
+ "eval_accuracy": 0.9116883116883117,
46
+ "eval_f1": 0.9107923483520103,
47
+ "eval_loss": 1.7615087032318115,
48
+ "eval_matthews_correlation": 0.9104826579369623,
49
+ "eval_runtime": 2.0461,
50
+ "eval_samples_per_second": 1505.281,
51
+ "eval_steps_per_second": 9.775,
52
+ "step": 400
53
+ },
54
+ {
55
+ "epoch": 11.36,
56
+ "learning_rate": 7.155392473834015e-05,
57
+ "loss": 1.11,
58
+ "step": 500
59
+ },
60
+ {
61
+ "epoch": 11.36,
62
+ "eval_accuracy": 0.9214285714285714,
63
+ "eval_f1": 0.9220448276410765,
64
+ "eval_loss": 1.6972297430038452,
65
+ "eval_matthews_correlation": 0.9203565343150704,
66
+ "eval_runtime": 2.2225,
67
+ "eval_samples_per_second": 1385.841,
68
+ "eval_steps_per_second": 8.999,
69
+ "step": 500
70
+ },
71
+ {
72
+ "epoch": 13.64,
73
+ "eval_accuracy": 0.9152597402597402,
74
+ "eval_f1": 0.9167090407433226,
75
+ "eval_loss": 1.8113186359405518,
76
+ "eval_matthews_correlation": 0.9141050375877964,
77
+ "eval_runtime": 2.1877,
78
+ "eval_samples_per_second": 1407.878,
79
+ "eval_steps_per_second": 9.142,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 15.91,
84
+ "eval_accuracy": 0.9233766233766234,
85
+ "eval_f1": 0.9233717578523983,
86
+ "eval_loss": 1.7811164855957031,
87
+ "eval_matthews_correlation": 0.9223362098152555,
88
+ "eval_runtime": 2.1835,
89
+ "eval_samples_per_second": 1410.568,
90
+ "eval_steps_per_second": 9.16,
91
+ "step": 700
92
+ },
93
+ {
94
+ "epoch": 18.18,
95
+ "eval_accuracy": 0.9217532467532468,
96
+ "eval_f1": 0.9214852887010235,
97
+ "eval_loss": 1.8843683004379272,
98
+ "eval_matthews_correlation": 0.9206850394304873,
99
+ "eval_runtime": 2.0522,
100
+ "eval_samples_per_second": 1500.797,
101
+ "eval_steps_per_second": 9.745,
102
+ "step": 800
103
+ },
104
+ {
105
+ "epoch": 20.45,
106
+ "eval_accuracy": 0.9262987012987013,
107
+ "eval_f1": 0.9262818516710309,
108
+ "eval_loss": 1.8115458488464355,
109
+ "eval_matthews_correlation": 0.9252924239497049,
110
+ "eval_runtime": 2.1444,
111
+ "eval_samples_per_second": 1436.288,
112
+ "eval_steps_per_second": 9.327,
113
+ "step": 900
114
+ },
115
+ {
116
+ "epoch": 22.73,
117
+ "learning_rate": 4.315951015963374e-05,
118
+ "loss": 0.2649,
119
+ "step": 1000
120
+ },
121
+ {
122
+ "epoch": 22.73,
123
+ "eval_accuracy": 0.9253246753246753,
124
+ "eval_f1": 0.9247932657728088,
125
+ "eval_loss": 1.8234479427337646,
126
+ "eval_matthews_correlation": 0.9243123665760975,
127
+ "eval_runtime": 2.1932,
128
+ "eval_samples_per_second": 1404.357,
129
+ "eval_steps_per_second": 9.119,
130
+ "step": 1000
131
+ }
132
+ ],
133
+ "max_steps": 1760,
134
+ "num_train_epochs": 40,
135
+ "total_flos": 5211163956730776.0,
136
+ "trial_name": null,
137
+ "trial_params": null
138
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c42ab0f0f935f26044abc1eee53bffa956d44049a74430ab81b2071afeed33
3
+ size 2927
checkpoint-1000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
3
+ "architectures": [
4
+ "MPNetTwoClassForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20",
34
+ "21": "LABEL_21",
35
+ "22": "LABEL_22",
36
+ "23": "LABEL_23",
37
+ "24": "LABEL_24",
38
+ "25": "LABEL_25",
39
+ "26": "LABEL_26",
40
+ "27": "LABEL_27",
41
+ "28": "LABEL_28",
42
+ "29": "LABEL_29",
43
+ "30": "LABEL_30",
44
+ "31": "LABEL_31",
45
+ "32": "LABEL_32",
46
+ "33": "LABEL_33",
47
+ "34": "LABEL_34",
48
+ "35": "LABEL_35",
49
+ "36": "LABEL_36",
50
+ "37": "LABEL_37",
51
+ "38": "LABEL_38",
52
+ "39": "LABEL_39",
53
+ "40": "LABEL_40",
54
+ "41": "LABEL_41",
55
+ "42": "LABEL_42",
56
+ "43": "LABEL_43",
57
+ "44": "LABEL_44",
58
+ "45": "LABEL_45",
59
+ "46": "LABEL_46",
60
+ "47": "LABEL_47",
61
+ "48": "LABEL_48",
62
+ "49": "LABEL_49",
63
+ "50": "LABEL_50",
64
+ "51": "LABEL_51",
65
+ "52": "LABEL_52",
66
+ "53": "LABEL_53",
67
+ "54": "LABEL_54",
68
+ "55": "LABEL_55",
69
+ "56": "LABEL_56",
70
+ "57": "LABEL_57",
71
+ "58": "LABEL_58",
72
+ "59": "LABEL_59",
73
+ "60": "LABEL_60",
74
+ "61": "LABEL_61",
75
+ "62": "LABEL_62",
76
+ "63": "LABEL_63",
77
+ "64": "LABEL_64",
78
+ "65": "LABEL_65",
79
+ "66": "LABEL_66",
80
+ "67": "LABEL_67",
81
+ "68": "LABEL_68",
82
+ "69": "LABEL_69",
83
+ "70": "LABEL_70",
84
+ "71": "LABEL_71",
85
+ "72": "LABEL_72",
86
+ "73": "LABEL_73",
87
+ "74": "LABEL_74",
88
+ "75": "LABEL_75",
89
+ "76": "LABEL_76"
90
+ },
91
+ "initializer_range": 0.02,
92
+ "intermediate_size": 3072,
93
+ "label2id": {
94
+ "LABEL_0": 0,
95
+ "LABEL_1": 1,
96
+ "LABEL_10": 10,
97
+ "LABEL_11": 11,
98
+ "LABEL_12": 12,
99
+ "LABEL_13": 13,
100
+ "LABEL_14": 14,
101
+ "LABEL_15": 15,
102
+ "LABEL_16": 16,
103
+ "LABEL_17": 17,
104
+ "LABEL_18": 18,
105
+ "LABEL_19": 19,
106
+ "LABEL_2": 2,
107
+ "LABEL_20": 20,
108
+ "LABEL_21": 21,
109
+ "LABEL_22": 22,
110
+ "LABEL_23": 23,
111
+ "LABEL_24": 24,
112
+ "LABEL_25": 25,
113
+ "LABEL_26": 26,
114
+ "LABEL_27": 27,
115
+ "LABEL_28": 28,
116
+ "LABEL_29": 29,
117
+ "LABEL_3": 3,
118
+ "LABEL_30": 30,
119
+ "LABEL_31": 31,
120
+ "LABEL_32": 32,
121
+ "LABEL_33": 33,
122
+ "LABEL_34": 34,
123
+ "LABEL_35": 35,
124
+ "LABEL_36": 36,
125
+ "LABEL_37": 37,
126
+ "LABEL_38": 38,
127
+ "LABEL_39": 39,
128
+ "LABEL_4": 4,
129
+ "LABEL_40": 40,
130
+ "LABEL_41": 41,
131
+ "LABEL_42": 42,
132
+ "LABEL_43": 43,
133
+ "LABEL_44": 44,
134
+ "LABEL_45": 45,
135
+ "LABEL_46": 46,
136
+ "LABEL_47": 47,
137
+ "LABEL_48": 48,
138
+ "LABEL_49": 49,
139
+ "LABEL_5": 5,
140
+ "LABEL_50": 50,
141
+ "LABEL_51": 51,
142
+ "LABEL_52": 52,
143
+ "LABEL_53": 53,
144
+ "LABEL_54": 54,
145
+ "LABEL_55": 55,
146
+ "LABEL_56": 56,
147
+ "LABEL_57": 57,
148
+ "LABEL_58": 58,
149
+ "LABEL_59": 59,
150
+ "LABEL_6": 6,
151
+ "LABEL_60": 60,
152
+ "LABEL_61": 61,
153
+ "LABEL_62": 62,
154
+ "LABEL_63": 63,
155
+ "LABEL_64": 64,
156
+ "LABEL_65": 65,
157
+ "LABEL_66": 66,
158
+ "LABEL_67": 67,
159
+ "LABEL_68": 68,
160
+ "LABEL_69": 69,
161
+ "LABEL_7": 7,
162
+ "LABEL_70": 70,
163
+ "LABEL_71": 71,
164
+ "LABEL_72": 72,
165
+ "LABEL_73": 73,
166
+ "LABEL_74": 74,
167
+ "LABEL_75": 75,
168
+ "LABEL_76": 76,
169
+ "LABEL_8": 8,
170
+ "LABEL_9": 9
171
+ },
172
+ "layer_norm_eps": 1e-05,
173
+ "max_position_embeddings": 514,
174
+ "model_type": "mpnet",
175
+ "num_attention_heads": 12,
176
+ "num_hidden_layers": 12,
177
+ "pad_token_id": 1,
178
+ "problem_type": "single_label_classification",
179
+ "relative_attention_num_buckets": 32,
180
+ "torch_dtype": "float32",
181
+ "transformers_version": "4.15.0",
182
+ "vocab_size": 30527
183
+ }
checkpoint-1200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8152ff1e218b144efe1ce5ea43c5d39d08605eaff7683056b743d8dbb75abe7
3
+ size 1762416361
checkpoint-1200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02af93f89516c3d0481213a738b5e67528be2c49521d2a84035351b10691eb6
3
+ size 440628841
checkpoint-1200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a3a87c5a3a39304e01fec1305a0a9b9438d3f71751ecfb19e5d132933a0680
3
+ size 15523
checkpoint-1200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41fd94b0ee352fbf0612f4b6546da6b390ff2da284386ec6ff938dc120b29e80
3
+ size 623
checkpoint-1200/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-1200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "sentence-transformers/all-mpnet-base-v2", "tokenizer_class": "MPNetTokenizer"}
checkpoint-1200/trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9253246753246753,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
4
+ "epoch": 27.272727272727273,
5
+ "global_step": 1200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.27,
12
+ "eval_accuracy": 0.8318181818181818,
13
+ "eval_f1": 0.7902944410637314,
14
+ "eval_loss": 1.6091233491897583,
15
+ "eval_matthews_correlation": 0.8302307602375942,
16
+ "eval_runtime": 2.3926,
17
+ "eval_samples_per_second": 1287.31,
18
+ "eval_steps_per_second": 8.359,
19
+ "step": 100
20
+ },
21
+ {
22
+ "epoch": 4.55,
23
+ "eval_accuracy": 0.9097402597402597,
24
+ "eval_f1": 0.9022270624577644,
25
+ "eval_loss": 1.493744969367981,
26
+ "eval_matthews_correlation": 0.9085414308645802,
27
+ "eval_runtime": 2.2329,
28
+ "eval_samples_per_second": 1379.356,
29
+ "eval_steps_per_second": 8.957,
30
+ "step": 200
31
+ },
32
+ {
33
+ "epoch": 6.82,
34
+ "eval_accuracy": 0.9074675324675324,
35
+ "eval_f1": 0.9101059174003832,
36
+ "eval_loss": 1.6116833686828613,
37
+ "eval_matthews_correlation": 0.9062636808107568,
38
+ "eval_runtime": 2.0808,
39
+ "eval_samples_per_second": 1480.17,
40
+ "eval_steps_per_second": 9.611,
41
+ "step": 300
42
+ },
43
+ {
44
+ "epoch": 9.09,
45
+ "eval_accuracy": 0.9116883116883117,
46
+ "eval_f1": 0.9107923483520103,
47
+ "eval_loss": 1.7615087032318115,
48
+ "eval_matthews_correlation": 0.9104826579369623,
49
+ "eval_runtime": 2.0461,
50
+ "eval_samples_per_second": 1505.281,
51
+ "eval_steps_per_second": 9.775,
52
+ "step": 400
53
+ },
54
+ {
55
+ "epoch": 11.36,
56
+ "learning_rate": 7.155392473834015e-05,
57
+ "loss": 1.11,
58
+ "step": 500
59
+ },
60
+ {
61
+ "epoch": 11.36,
62
+ "eval_accuracy": 0.9214285714285714,
63
+ "eval_f1": 0.9220448276410765,
64
+ "eval_loss": 1.6972297430038452,
65
+ "eval_matthews_correlation": 0.9203565343150704,
66
+ "eval_runtime": 2.2225,
67
+ "eval_samples_per_second": 1385.841,
68
+ "eval_steps_per_second": 8.999,
69
+ "step": 500
70
+ },
71
+ {
72
+ "epoch": 13.64,
73
+ "eval_accuracy": 0.9152597402597402,
74
+ "eval_f1": 0.9167090407433226,
75
+ "eval_loss": 1.8113186359405518,
76
+ "eval_matthews_correlation": 0.9141050375877964,
77
+ "eval_runtime": 2.1877,
78
+ "eval_samples_per_second": 1407.878,
79
+ "eval_steps_per_second": 9.142,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 15.91,
84
+ "eval_accuracy": 0.9233766233766234,
85
+ "eval_f1": 0.9233717578523983,
86
+ "eval_loss": 1.7811164855957031,
87
+ "eval_matthews_correlation": 0.9223362098152555,
88
+ "eval_runtime": 2.1835,
89
+ "eval_samples_per_second": 1410.568,
90
+ "eval_steps_per_second": 9.16,
91
+ "step": 700
92
+ },
93
+ {
94
+ "epoch": 18.18,
95
+ "eval_accuracy": 0.9217532467532468,
96
+ "eval_f1": 0.9214852887010235,
97
+ "eval_loss": 1.8843683004379272,
98
+ "eval_matthews_correlation": 0.9206850394304873,
99
+ "eval_runtime": 2.0522,
100
+ "eval_samples_per_second": 1500.797,
101
+ "eval_steps_per_second": 9.745,
102
+ "step": 800
103
+ },
104
+ {
105
+ "epoch": 20.45,
106
+ "eval_accuracy": 0.9262987012987013,
107
+ "eval_f1": 0.9262818516710309,
108
+ "eval_loss": 1.8115458488464355,
109
+ "eval_matthews_correlation": 0.9252924239497049,
110
+ "eval_runtime": 2.1444,
111
+ "eval_samples_per_second": 1436.288,
112
+ "eval_steps_per_second": 9.327,
113
+ "step": 900
114
+ },
115
+ {
116
+ "epoch": 22.73,
117
+ "learning_rate": 4.315951015963374e-05,
118
+ "loss": 0.2649,
119
+ "step": 1000
120
+ },
121
+ {
122
+ "epoch": 22.73,
123
+ "eval_accuracy": 0.9253246753246753,
124
+ "eval_f1": 0.9247932657728088,
125
+ "eval_loss": 1.8234479427337646,
126
+ "eval_matthews_correlation": 0.9243123665760975,
127
+ "eval_runtime": 2.1932,
128
+ "eval_samples_per_second": 1404.357,
129
+ "eval_steps_per_second": 9.119,
130
+ "step": 1000
131
+ },
132
+ {
133
+ "epoch": 25.0,
134
+ "eval_accuracy": 0.922077922077922,
135
+ "eval_f1": 0.9224540465415363,
136
+ "eval_loss": 1.9049001932144165,
137
+ "eval_matthews_correlation": 0.9210122650149767,
138
+ "eval_runtime": 2.0808,
139
+ "eval_samples_per_second": 1480.22,
140
+ "eval_steps_per_second": 9.612,
141
+ "step": 1100
142
+ },
143
+ {
144
+ "epoch": 27.27,
145
+ "eval_accuracy": 0.923051948051948,
146
+ "eval_f1": 0.9227416902243171,
147
+ "eval_loss": 1.8450692892074585,
148
+ "eval_matthews_correlation": 0.9220102988157652,
149
+ "eval_runtime": 2.2557,
150
+ "eval_samples_per_second": 1365.457,
151
+ "eval_steps_per_second": 8.867,
152
+ "step": 1200
153
+ }
154
+ ],
155
+ "max_steps": 1760,
156
+ "num_train_epochs": 40,
157
+ "total_flos": 6260938915100496.0,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }
checkpoint-1200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c42ab0f0f935f26044abc1eee53bffa956d44049a74430ab81b2071afeed33
3
+ size 2927
checkpoint-1200/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1400/config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
3
+ "architectures": [
4
+ "MPNetTwoClassForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20",
34
+ "21": "LABEL_21",
35
+ "22": "LABEL_22",
36
+ "23": "LABEL_23",
37
+ "24": "LABEL_24",
38
+ "25": "LABEL_25",
39
+ "26": "LABEL_26",
40
+ "27": "LABEL_27",
41
+ "28": "LABEL_28",
42
+ "29": "LABEL_29",
43
+ "30": "LABEL_30",
44
+ "31": "LABEL_31",
45
+ "32": "LABEL_32",
46
+ "33": "LABEL_33",
47
+ "34": "LABEL_34",
48
+ "35": "LABEL_35",
49
+ "36": "LABEL_36",
50
+ "37": "LABEL_37",
51
+ "38": "LABEL_38",
52
+ "39": "LABEL_39",
53
+ "40": "LABEL_40",
54
+ "41": "LABEL_41",
55
+ "42": "LABEL_42",
56
+ "43": "LABEL_43",
57
+ "44": "LABEL_44",
58
+ "45": "LABEL_45",
59
+ "46": "LABEL_46",
60
+ "47": "LABEL_47",
61
+ "48": "LABEL_48",
62
+ "49": "LABEL_49",
63
+ "50": "LABEL_50",
64
+ "51": "LABEL_51",
65
+ "52": "LABEL_52",
66
+ "53": "LABEL_53",
67
+ "54": "LABEL_54",
68
+ "55": "LABEL_55",
69
+ "56": "LABEL_56",
70
+ "57": "LABEL_57",
71
+ "58": "LABEL_58",
72
+ "59": "LABEL_59",
73
+ "60": "LABEL_60",
74
+ "61": "LABEL_61",
75
+ "62": "LABEL_62",
76
+ "63": "LABEL_63",
77
+ "64": "LABEL_64",
78
+ "65": "LABEL_65",
79
+ "66": "LABEL_66",
80
+ "67": "LABEL_67",
81
+ "68": "LABEL_68",
82
+ "69": "LABEL_69",
83
+ "70": "LABEL_70",
84
+ "71": "LABEL_71",
85
+ "72": "LABEL_72",
86
+ "73": "LABEL_73",
87
+ "74": "LABEL_74",
88
+ "75": "LABEL_75",
89
+ "76": "LABEL_76"
90
+ },
91
+ "initializer_range": 0.02,
92
+ "intermediate_size": 3072,
93
+ "label2id": {
94
+ "LABEL_0": 0,
95
+ "LABEL_1": 1,
96
+ "LABEL_10": 10,
97
+ "LABEL_11": 11,
98
+ "LABEL_12": 12,
99
+ "LABEL_13": 13,
100
+ "LABEL_14": 14,
101
+ "LABEL_15": 15,
102
+ "LABEL_16": 16,
103
+ "LABEL_17": 17,
104
+ "LABEL_18": 18,
105
+ "LABEL_19": 19,
106
+ "LABEL_2": 2,
107
+ "LABEL_20": 20,
108
+ "LABEL_21": 21,
109
+ "LABEL_22": 22,
110
+ "LABEL_23": 23,
111
+ "LABEL_24": 24,
112
+ "LABEL_25": 25,
113
+ "LABEL_26": 26,
114
+ "LABEL_27": 27,
115
+ "LABEL_28": 28,
116
+ "LABEL_29": 29,
117
+ "LABEL_3": 3,
118
+ "LABEL_30": 30,
119
+ "LABEL_31": 31,
120
+ "LABEL_32": 32,
121
+ "LABEL_33": 33,
122
+ "LABEL_34": 34,
123
+ "LABEL_35": 35,
124
+ "LABEL_36": 36,
125
+ "LABEL_37": 37,
126
+ "LABEL_38": 38,
127
+ "LABEL_39": 39,
128
+ "LABEL_4": 4,
129
+ "LABEL_40": 40,
130
+ "LABEL_41": 41,
131
+ "LABEL_42": 42,
132
+ "LABEL_43": 43,
133
+ "LABEL_44": 44,
134
+ "LABEL_45": 45,
135
+ "LABEL_46": 46,
136
+ "LABEL_47": 47,
137
+ "LABEL_48": 48,
138
+ "LABEL_49": 49,
139
+ "LABEL_5": 5,
140
+ "LABEL_50": 50,
141
+ "LABEL_51": 51,
142
+ "LABEL_52": 52,
143
+ "LABEL_53": 53,
144
+ "LABEL_54": 54,
145
+ "LABEL_55": 55,
146
+ "LABEL_56": 56,
147
+ "LABEL_57": 57,
148
+ "LABEL_58": 58,
149
+ "LABEL_59": 59,
150
+ "LABEL_6": 6,
151
+ "LABEL_60": 60,
152
+ "LABEL_61": 61,
153
+ "LABEL_62": 62,
154
+ "LABEL_63": 63,
155
+ "LABEL_64": 64,
156
+ "LABEL_65": 65,
157
+ "LABEL_66": 66,
158
+ "LABEL_67": 67,
159
+ "LABEL_68": 68,
160
+ "LABEL_69": 69,
161
+ "LABEL_7": 7,
162
+ "LABEL_70": 70,
163
+ "LABEL_71": 71,
164
+ "LABEL_72": 72,
165
+ "LABEL_73": 73,
166
+ "LABEL_74": 74,
167
+ "LABEL_75": 75,
168
+ "LABEL_76": 76,
169
+ "LABEL_8": 8,
170
+ "LABEL_9": 9
171
+ },
172
+ "layer_norm_eps": 1e-05,
173
+ "max_position_embeddings": 514,
174
+ "model_type": "mpnet",
175
+ "num_attention_heads": 12,
176
+ "num_hidden_layers": 12,
177
+ "pad_token_id": 1,
178
+ "problem_type": "single_label_classification",
179
+ "relative_attention_num_buckets": 32,
180
+ "torch_dtype": "float32",
181
+ "transformers_version": "4.15.0",
182
+ "vocab_size": 30527
183
+ }
checkpoint-1400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f7494ca9c62e07dc54ba966431d85cf54f54e739e23a12b9b7bd9ac08f8457
3
+ size 1762416361
checkpoint-1400/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7762822ec73f201eed1006a049ea13bd4abf3cd160c080bcd27c0abc41c68e38
3
+ size 440628841
checkpoint-1400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:369127e719bb7e1e6de9348658a2d19987a9aa2095c93d1633ad1f7c5e3a08b9
3
+ size 15523
checkpoint-1400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f155ee9ac8792705990c42599f6317481ad9165d346d3b73154385d7645ea3ff
3
+ size 623
checkpoint-1400/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-1400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1400/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "sentence-transformers/all-mpnet-base-v2", "tokenizer_class": "MPNetTokenizer"}
checkpoint-1400/trainer_state.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9253246753246753,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
4
+ "epoch": 31.818181818181817,
5
+ "global_step": 1400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.27,
12
+ "eval_accuracy": 0.8318181818181818,
13
+ "eval_f1": 0.7902944410637314,
14
+ "eval_loss": 1.6091233491897583,
15
+ "eval_matthews_correlation": 0.8302307602375942,
16
+ "eval_runtime": 2.3926,
17
+ "eval_samples_per_second": 1287.31,
18
+ "eval_steps_per_second": 8.359,
19
+ "step": 100
20
+ },
21
+ {
22
+ "epoch": 4.55,
23
+ "eval_accuracy": 0.9097402597402597,
24
+ "eval_f1": 0.9022270624577644,
25
+ "eval_loss": 1.493744969367981,
26
+ "eval_matthews_correlation": 0.9085414308645802,
27
+ "eval_runtime": 2.2329,
28
+ "eval_samples_per_second": 1379.356,
29
+ "eval_steps_per_second": 8.957,
30
+ "step": 200
31
+ },
32
+ {
33
+ "epoch": 6.82,
34
+ "eval_accuracy": 0.9074675324675324,
35
+ "eval_f1": 0.9101059174003832,
36
+ "eval_loss": 1.6116833686828613,
37
+ "eval_matthews_correlation": 0.9062636808107568,
38
+ "eval_runtime": 2.0808,
39
+ "eval_samples_per_second": 1480.17,
40
+ "eval_steps_per_second": 9.611,
41
+ "step": 300
42
+ },
43
+ {
44
+ "epoch": 9.09,
45
+ "eval_accuracy": 0.9116883116883117,
46
+ "eval_f1": 0.9107923483520103,
47
+ "eval_loss": 1.7615087032318115,
48
+ "eval_matthews_correlation": 0.9104826579369623,
49
+ "eval_runtime": 2.0461,
50
+ "eval_samples_per_second": 1505.281,
51
+ "eval_steps_per_second": 9.775,
52
+ "step": 400
53
+ },
54
+ {
55
+ "epoch": 11.36,
56
+ "learning_rate": 7.155392473834015e-05,
57
+ "loss": 1.11,
58
+ "step": 500
59
+ },
60
+ {
61
+ "epoch": 11.36,
62
+ "eval_accuracy": 0.9214285714285714,
63
+ "eval_f1": 0.9220448276410765,
64
+ "eval_loss": 1.6972297430038452,
65
+ "eval_matthews_correlation": 0.9203565343150704,
66
+ "eval_runtime": 2.2225,
67
+ "eval_samples_per_second": 1385.841,
68
+ "eval_steps_per_second": 8.999,
69
+ "step": 500
70
+ },
71
+ {
72
+ "epoch": 13.64,
73
+ "eval_accuracy": 0.9152597402597402,
74
+ "eval_f1": 0.9167090407433226,
75
+ "eval_loss": 1.8113186359405518,
76
+ "eval_matthews_correlation": 0.9141050375877964,
77
+ "eval_runtime": 2.1877,
78
+ "eval_samples_per_second": 1407.878,
79
+ "eval_steps_per_second": 9.142,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 15.91,
84
+ "eval_accuracy": 0.9233766233766234,
85
+ "eval_f1": 0.9233717578523983,
86
+ "eval_loss": 1.7811164855957031,
87
+ "eval_matthews_correlation": 0.9223362098152555,
88
+ "eval_runtime": 2.1835,
89
+ "eval_samples_per_second": 1410.568,
90
+ "eval_steps_per_second": 9.16,
91
+ "step": 700
92
+ },
93
+ {
94
+ "epoch": 18.18,
95
+ "eval_accuracy": 0.9217532467532468,
96
+ "eval_f1": 0.9214852887010235,
97
+ "eval_loss": 1.8843683004379272,
98
+ "eval_matthews_correlation": 0.9206850394304873,
99
+ "eval_runtime": 2.0522,
100
+ "eval_samples_per_second": 1500.797,
101
+ "eval_steps_per_second": 9.745,
102
+ "step": 800
103
+ },
104
+ {
105
+ "epoch": 20.45,
106
+ "eval_accuracy": 0.9262987012987013,
107
+ "eval_f1": 0.9262818516710309,
108
+ "eval_loss": 1.8115458488464355,
109
+ "eval_matthews_correlation": 0.9252924239497049,
110
+ "eval_runtime": 2.1444,
111
+ "eval_samples_per_second": 1436.288,
112
+ "eval_steps_per_second": 9.327,
113
+ "step": 900
114
+ },
115
+ {
116
+ "epoch": 22.73,
117
+ "learning_rate": 4.315951015963374e-05,
118
+ "loss": 0.2649,
119
+ "step": 1000
120
+ },
121
+ {
122
+ "epoch": 22.73,
123
+ "eval_accuracy": 0.9253246753246753,
124
+ "eval_f1": 0.9247932657728088,
125
+ "eval_loss": 1.8234479427337646,
126
+ "eval_matthews_correlation": 0.9243123665760975,
127
+ "eval_runtime": 2.1932,
128
+ "eval_samples_per_second": 1404.357,
129
+ "eval_steps_per_second": 9.119,
130
+ "step": 1000
131
+ },
132
+ {
133
+ "epoch": 25.0,
134
+ "eval_accuracy": 0.922077922077922,
135
+ "eval_f1": 0.9224540465415363,
136
+ "eval_loss": 1.9049001932144165,
137
+ "eval_matthews_correlation": 0.9210122650149767,
138
+ "eval_runtime": 2.0808,
139
+ "eval_samples_per_second": 1480.22,
140
+ "eval_steps_per_second": 9.612,
141
+ "step": 1100
142
+ },
143
+ {
144
+ "epoch": 27.27,
145
+ "eval_accuracy": 0.923051948051948,
146
+ "eval_f1": 0.9227416902243171,
147
+ "eval_loss": 1.8450692892074585,
148
+ "eval_matthews_correlation": 0.9220102988157652,
149
+ "eval_runtime": 2.2557,
150
+ "eval_samples_per_second": 1365.457,
151
+ "eval_steps_per_second": 8.867,
152
+ "step": 1200
153
+ },
154
+ {
155
+ "epoch": 29.55,
156
+ "eval_accuracy": 0.9246753246753247,
157
+ "eval_f1": 0.9247293404638837,
158
+ "eval_loss": 1.8730789422988892,
159
+ "eval_matthews_correlation": 0.923653963691168,
160
+ "eval_runtime": 2.2969,
161
+ "eval_samples_per_second": 1340.938,
162
+ "eval_steps_per_second": 8.707,
163
+ "step": 1300
164
+ },
165
+ {
166
+ "epoch": 31.82,
167
+ "eval_accuracy": 0.9246753246753247,
168
+ "eval_f1": 0.9244083266025087,
169
+ "eval_loss": 1.8740190267562866,
170
+ "eval_matthews_correlation": 0.9236516840026499,
171
+ "eval_runtime": 2.387,
172
+ "eval_samples_per_second": 1290.296,
173
+ "eval_steps_per_second": 8.379,
174
+ "step": 1400
175
+ }
176
+ ],
177
+ "max_steps": 1760,
178
+ "num_train_epochs": 40,
179
+ "total_flos": 7316347820044758.0,
180
+ "trial_name": null,
181
+ "trial_params": null
182
+ }
checkpoint-1400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c42ab0f0f935f26044abc1eee53bffa956d44049a74430ab81b2071afeed33
3
+ size 2927
checkpoint-1400/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1600/config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
3
+ "architectures": [
4
+ "MPNetTwoClassForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20",
34
+ "21": "LABEL_21",
35
+ "22": "LABEL_22",
36
+ "23": "LABEL_23",
37
+ "24": "LABEL_24",
38
+ "25": "LABEL_25",
39
+ "26": "LABEL_26",
40
+ "27": "LABEL_27",
41
+ "28": "LABEL_28",
42
+ "29": "LABEL_29",
43
+ "30": "LABEL_30",
44
+ "31": "LABEL_31",
45
+ "32": "LABEL_32",
46
+ "33": "LABEL_33",
47
+ "34": "LABEL_34",
48
+ "35": "LABEL_35",
49
+ "36": "LABEL_36",
50
+ "37": "LABEL_37",
51
+ "38": "LABEL_38",
52
+ "39": "LABEL_39",
53
+ "40": "LABEL_40",
54
+ "41": "LABEL_41",
55
+ "42": "LABEL_42",
56
+ "43": "LABEL_43",
57
+ "44": "LABEL_44",
58
+ "45": "LABEL_45",
59
+ "46": "LABEL_46",
60
+ "47": "LABEL_47",
61
+ "48": "LABEL_48",
62
+ "49": "LABEL_49",
63
+ "50": "LABEL_50",
64
+ "51": "LABEL_51",
65
+ "52": "LABEL_52",
66
+ "53": "LABEL_53",
67
+ "54": "LABEL_54",
68
+ "55": "LABEL_55",
69
+ "56": "LABEL_56",
70
+ "57": "LABEL_57",
71
+ "58": "LABEL_58",
72
+ "59": "LABEL_59",
73
+ "60": "LABEL_60",
74
+ "61": "LABEL_61",
75
+ "62": "LABEL_62",
76
+ "63": "LABEL_63",
77
+ "64": "LABEL_64",
78
+ "65": "LABEL_65",
79
+ "66": "LABEL_66",
80
+ "67": "LABEL_67",
81
+ "68": "LABEL_68",
82
+ "69": "LABEL_69",
83
+ "70": "LABEL_70",
84
+ "71": "LABEL_71",
85
+ "72": "LABEL_72",
86
+ "73": "LABEL_73",
87
+ "74": "LABEL_74",
88
+ "75": "LABEL_75",
89
+ "76": "LABEL_76"
90
+ },
91
+ "initializer_range": 0.02,
92
+ "intermediate_size": 3072,
93
+ "label2id": {
94
+ "LABEL_0": 0,
95
+ "LABEL_1": 1,
96
+ "LABEL_10": 10,
97
+ "LABEL_11": 11,
98
+ "LABEL_12": 12,
99
+ "LABEL_13": 13,
100
+ "LABEL_14": 14,
101
+ "LABEL_15": 15,
102
+ "LABEL_16": 16,
103
+ "LABEL_17": 17,
104
+ "LABEL_18": 18,
105
+ "LABEL_19": 19,
106
+ "LABEL_2": 2,
107
+ "LABEL_20": 20,
108
+ "LABEL_21": 21,
109
+ "LABEL_22": 22,
110
+ "LABEL_23": 23,
111
+ "LABEL_24": 24,
112
+ "LABEL_25": 25,
113
+ "LABEL_26": 26,
114
+ "LABEL_27": 27,
115
+ "LABEL_28": 28,
116
+ "LABEL_29": 29,
117
+ "LABEL_3": 3,
118
+ "LABEL_30": 30,
119
+ "LABEL_31": 31,
120
+ "LABEL_32": 32,
121
+ "LABEL_33": 33,
122
+ "LABEL_34": 34,
123
+ "LABEL_35": 35,
124
+ "LABEL_36": 36,
125
+ "LABEL_37": 37,
126
+ "LABEL_38": 38,
127
+ "LABEL_39": 39,
128
+ "LABEL_4": 4,
129
+ "LABEL_40": 40,
130
+ "LABEL_41": 41,
131
+ "LABEL_42": 42,
132
+ "LABEL_43": 43,
133
+ "LABEL_44": 44,
134
+ "LABEL_45": 45,
135
+ "LABEL_46": 46,
136
+ "LABEL_47": 47,
137
+ "LABEL_48": 48,
138
+ "LABEL_49": 49,
139
+ "LABEL_5": 5,
140
+ "LABEL_50": 50,
141
+ "LABEL_51": 51,
142
+ "LABEL_52": 52,
143
+ "LABEL_53": 53,
144
+ "LABEL_54": 54,
145
+ "LABEL_55": 55,
146
+ "LABEL_56": 56,
147
+ "LABEL_57": 57,
148
+ "LABEL_58": 58,
149
+ "LABEL_59": 59,
150
+ "LABEL_6": 6,
151
+ "LABEL_60": 60,
152
+ "LABEL_61": 61,
153
+ "LABEL_62": 62,
154
+ "LABEL_63": 63,
155
+ "LABEL_64": 64,
156
+ "LABEL_65": 65,
157
+ "LABEL_66": 66,
158
+ "LABEL_67": 67,
159
+ "LABEL_68": 68,
160
+ "LABEL_69": 69,
161
+ "LABEL_7": 7,
162
+ "LABEL_70": 70,
163
+ "LABEL_71": 71,
164
+ "LABEL_72": 72,
165
+ "LABEL_73": 73,
166
+ "LABEL_74": 74,
167
+ "LABEL_75": 75,
168
+ "LABEL_76": 76,
169
+ "LABEL_8": 8,
170
+ "LABEL_9": 9
171
+ },
172
+ "layer_norm_eps": 1e-05,
173
+ "max_position_embeddings": 514,
174
+ "model_type": "mpnet",
175
+ "num_attention_heads": 12,
176
+ "num_hidden_layers": 12,
177
+ "pad_token_id": 1,
178
+ "problem_type": "single_label_classification",
179
+ "relative_attention_num_buckets": 32,
180
+ "torch_dtype": "float32",
181
+ "transformers_version": "4.15.0",
182
+ "vocab_size": 30527
183
+ }
checkpoint-1600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a289d9f9a63589d4d7260de4482446e36bc27c5c9ac0edc981b5582c95e4683c
3
+ size 1762416361
checkpoint-1600/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4859a07b191e3e73976ecec968d6234877e94a699c4346ce1d122c9bac151fa
3
+ size 440628841
checkpoint-1600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dcf95e1cd12026b87cf8d04e291fe2bbc0ab3d6499e8e6ce42f522f3d3416fc
3
+ size 15523
checkpoint-1600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18fe8e94444983d8df05ce07e7ef777d9d5484aaa22294ca10dc48641c22d087
3
+ size 623
checkpoint-1600/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-1600/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1600/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "sentence-transformers/all-mpnet-base-v2", "tokenizer_class": "MPNetTokenizer"}
checkpoint-1600/trainer_state.json ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9253246753246753,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
4
+ "epoch": 36.36363636363637,
5
+ "global_step": 1600,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.27,
12
+ "eval_accuracy": 0.8318181818181818,
13
+ "eval_f1": 0.7902944410637314,
14
+ "eval_loss": 1.6091233491897583,
15
+ "eval_matthews_correlation": 0.8302307602375942,
16
+ "eval_runtime": 2.3926,
17
+ "eval_samples_per_second": 1287.31,
18
+ "eval_steps_per_second": 8.359,
19
+ "step": 100
20
+ },
21
+ {
22
+ "epoch": 4.55,
23
+ "eval_accuracy": 0.9097402597402597,
24
+ "eval_f1": 0.9022270624577644,
25
+ "eval_loss": 1.493744969367981,
26
+ "eval_matthews_correlation": 0.9085414308645802,
27
+ "eval_runtime": 2.2329,
28
+ "eval_samples_per_second": 1379.356,
29
+ "eval_steps_per_second": 8.957,
30
+ "step": 200
31
+ },
32
+ {
33
+ "epoch": 6.82,
34
+ "eval_accuracy": 0.9074675324675324,
35
+ "eval_f1": 0.9101059174003832,
36
+ "eval_loss": 1.6116833686828613,
37
+ "eval_matthews_correlation": 0.9062636808107568,
38
+ "eval_runtime": 2.0808,
39
+ "eval_samples_per_second": 1480.17,
40
+ "eval_steps_per_second": 9.611,
41
+ "step": 300
42
+ },
43
+ {
44
+ "epoch": 9.09,
45
+ "eval_accuracy": 0.9116883116883117,
46
+ "eval_f1": 0.9107923483520103,
47
+ "eval_loss": 1.7615087032318115,
48
+ "eval_matthews_correlation": 0.9104826579369623,
49
+ "eval_runtime": 2.0461,
50
+ "eval_samples_per_second": 1505.281,
51
+ "eval_steps_per_second": 9.775,
52
+ "step": 400
53
+ },
54
+ {
55
+ "epoch": 11.36,
56
+ "learning_rate": 7.155392473834015e-05,
57
+ "loss": 1.11,
58
+ "step": 500
59
+ },
60
+ {
61
+ "epoch": 11.36,
62
+ "eval_accuracy": 0.9214285714285714,
63
+ "eval_f1": 0.9220448276410765,
64
+ "eval_loss": 1.6972297430038452,
65
+ "eval_matthews_correlation": 0.9203565343150704,
66
+ "eval_runtime": 2.2225,
67
+ "eval_samples_per_second": 1385.841,
68
+ "eval_steps_per_second": 8.999,
69
+ "step": 500
70
+ },
71
+ {
72
+ "epoch": 13.64,
73
+ "eval_accuracy": 0.9152597402597402,
74
+ "eval_f1": 0.9167090407433226,
75
+ "eval_loss": 1.8113186359405518,
76
+ "eval_matthews_correlation": 0.9141050375877964,
77
+ "eval_runtime": 2.1877,
78
+ "eval_samples_per_second": 1407.878,
79
+ "eval_steps_per_second": 9.142,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 15.91,
84
+ "eval_accuracy": 0.9233766233766234,
85
+ "eval_f1": 0.9233717578523983,
86
+ "eval_loss": 1.7811164855957031,
87
+ "eval_matthews_correlation": 0.9223362098152555,
88
+ "eval_runtime": 2.1835,
89
+ "eval_samples_per_second": 1410.568,
90
+ "eval_steps_per_second": 9.16,
91
+ "step": 700
92
+ },
93
+ {
94
+ "epoch": 18.18,
95
+ "eval_accuracy": 0.9217532467532468,
96
+ "eval_f1": 0.9214852887010235,
97
+ "eval_loss": 1.8843683004379272,
98
+ "eval_matthews_correlation": 0.9206850394304873,
99
+ "eval_runtime": 2.0522,
100
+ "eval_samples_per_second": 1500.797,
101
+ "eval_steps_per_second": 9.745,
102
+ "step": 800
103
+ },
104
+ {
105
+ "epoch": 20.45,
106
+ "eval_accuracy": 0.9262987012987013,
107
+ "eval_f1": 0.9262818516710309,
108
+ "eval_loss": 1.8115458488464355,
109
+ "eval_matthews_correlation": 0.9252924239497049,
110
+ "eval_runtime": 2.1444,
111
+ "eval_samples_per_second": 1436.288,
112
+ "eval_steps_per_second": 9.327,
113
+ "step": 900
114
+ },
115
+ {
116
+ "epoch": 22.73,
117
+ "learning_rate": 4.315951015963374e-05,
118
+ "loss": 0.2649,
119
+ "step": 1000
120
+ },
121
+ {
122
+ "epoch": 22.73,
123
+ "eval_accuracy": 0.9253246753246753,
124
+ "eval_f1": 0.9247932657728088,
125
+ "eval_loss": 1.8234479427337646,
126
+ "eval_matthews_correlation": 0.9243123665760975,
127
+ "eval_runtime": 2.1932,
128
+ "eval_samples_per_second": 1404.357,
129
+ "eval_steps_per_second": 9.119,
130
+ "step": 1000
131
+ },
132
+ {
133
+ "epoch": 25.0,
134
+ "eval_accuracy": 0.922077922077922,
135
+ "eval_f1": 0.9224540465415363,
136
+ "eval_loss": 1.9049001932144165,
137
+ "eval_matthews_correlation": 0.9210122650149767,
138
+ "eval_runtime": 2.0808,
139
+ "eval_samples_per_second": 1480.22,
140
+ "eval_steps_per_second": 9.612,
141
+ "step": 1100
142
+ },
143
+ {
144
+ "epoch": 27.27,
145
+ "eval_accuracy": 0.923051948051948,
146
+ "eval_f1": 0.9227416902243171,
147
+ "eval_loss": 1.8450692892074585,
148
+ "eval_matthews_correlation": 0.9220102988157652,
149
+ "eval_runtime": 2.2557,
150
+ "eval_samples_per_second": 1365.457,
151
+ "eval_steps_per_second": 8.867,
152
+ "step": 1200
153
+ },
154
+ {
155
+ "epoch": 29.55,
156
+ "eval_accuracy": 0.9246753246753247,
157
+ "eval_f1": 0.9247293404638837,
158
+ "eval_loss": 1.8730789422988892,
159
+ "eval_matthews_correlation": 0.923653963691168,
160
+ "eval_runtime": 2.2969,
161
+ "eval_samples_per_second": 1340.938,
162
+ "eval_steps_per_second": 8.707,
163
+ "step": 1300
164
+ },
165
+ {
166
+ "epoch": 31.82,
167
+ "eval_accuracy": 0.9246753246753247,
168
+ "eval_f1": 0.9244083266025087,
169
+ "eval_loss": 1.8740190267562866,
170
+ "eval_matthews_correlation": 0.9236516840026499,
171
+ "eval_runtime": 2.387,
172
+ "eval_samples_per_second": 1290.296,
173
+ "eval_steps_per_second": 8.379,
174
+ "step": 1400
175
+ },
176
+ {
177
+ "epoch": 34.09,
178
+ "learning_rate": 1.4765095580927333e-05,
179
+ "loss": 0.0389,
180
+ "step": 1500
181
+ },
182
+ {
183
+ "epoch": 34.09,
184
+ "eval_accuracy": 0.9246753246753247,
185
+ "eval_f1": 0.9244532660143726,
186
+ "eval_loss": 1.8869105577468872,
187
+ "eval_matthews_correlation": 0.9236551007788375,
188
+ "eval_runtime": 2.1101,
189
+ "eval_samples_per_second": 1459.615,
190
+ "eval_steps_per_second": 9.478,
191
+ "step": 1500
192
+ },
193
+ {
194
+ "epoch": 36.36,
195
+ "eval_accuracy": 0.9246753246753247,
196
+ "eval_f1": 0.924467296959124,
197
+ "eval_loss": 1.8934658765792847,
198
+ "eval_matthews_correlation": 0.9236529443080341,
199
+ "eval_runtime": 2.1553,
200
+ "eval_samples_per_second": 1429.032,
201
+ "eval_steps_per_second": 9.279,
202
+ "step": 1600
203
+ }
204
+ ],
205
+ "max_steps": 1760,
206
+ "num_train_epochs": 40,
207
+ "total_flos": 8360620865327346.0,
208
+ "trial_name": null,
209
+ "trial_params": null
210
+ }
checkpoint-1600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c42ab0f0f935f26044abc1eee53bffa956d44049a74430ab81b2071afeed33
3
+ size 2927
checkpoint-1600/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2979f5a51267ee0c0c373f9f035fb2e2b8229506d1023586861f639df3d9a9fa
3
  size 1762415977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eecff5ab8f89402d58f7ed974e07f032b21e67946910e0635ba9886cb2afc4e6
3
  size 1762415977
checkpoint-200/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5b0b383500f4dcc3c0595a040a5e477c72085e98f61a78f53ff861bd54b1d9c
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:549089aa1f255ccecf0880bc0c22f868cc5ea7c448cda89ed820990fd83109d9
3
  size 440628841
checkpoint-200/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18b89ee3f3cf93d0936c9fd811e6d1aa61c52a2e733fde49a7af9b2ca477364e
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5018587775c7b083b4101057d469fd2b2321faa509a26cd15926106289ea924
3
  size 623
checkpoint-200/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9097402597402597,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-200",
4
  "epoch": 4.545454545454545,
5
  "global_step": 200,
@@ -9,24 +9,24 @@
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
- "eval_accuracy": 0.8318181818181818,
13
- "eval_f1": 0.7902944410637314,
14
- "eval_loss": 1.6091233491897583,
15
- "eval_matthews_correlation": 0.8302307602375942,
16
- "eval_runtime": 2.3926,
17
- "eval_samples_per_second": 1287.31,
18
- "eval_steps_per_second": 8.359,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.9097402597402597,
24
- "eval_f1": 0.9022270624577644,
25
- "eval_loss": 1.493744969367981,
26
- "eval_matthews_correlation": 0.9085414308645802,
27
- "eval_runtime": 2.2329,
28
- "eval_samples_per_second": 1379.356,
29
- "eval_steps_per_second": 8.957,
30
  "step": 200
31
  }
32
  ],
 
1
  {
2
+ "best_metric": 0.887987012987013,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-200",
4
  "epoch": 4.545454545454545,
5
  "global_step": 200,
 
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
+ "eval_accuracy": 0.8142857142857143,
13
+ "eval_f1": 0.7560937888521767,
14
+ "eval_loss": 1.7447705268859863,
15
+ "eval_matthews_correlation": 0.8126177011565009,
16
+ "eval_runtime": 2.0925,
17
+ "eval_samples_per_second": 1471.902,
18
+ "eval_steps_per_second": 9.558,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.887987012987013,
24
+ "eval_f1": 0.8583599902717473,
25
+ "eval_loss": 1.4869961738586426,
26
+ "eval_matthews_correlation": 0.8865740061102044,
27
+ "eval_runtime": 2.18,
28
+ "eval_samples_per_second": 1412.832,
29
+ "eval_steps_per_second": 9.174,
30
  "step": 200
31
  }
32
  ],
checkpoint-200/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63c42ab0f0f935f26044abc1eee53bffa956d44049a74430ab81b2071afeed33
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb330247ef49097404916bd0eff46ae70c1cc4fe1196d63e7c0227b2204c3c90
3
  size 2927
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68d41b461f353414d3fc6bc9f53595678985571407faa01b5677e7d2398dbb41
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:549089aa1f255ccecf0880bc0c22f868cc5ea7c448cda89ed820990fd83109d9
3
  size 440628841