ChrisZeng commited on
Commit
f70206f
1 Parent(s): ce99229

Training in progress, epoch 6

Browse files
checkpoint-1141/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ynie/electra-large-discriminator-snli_mnli_fever_anli_R1_R2_R3-nli",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 1024,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "neutral",
15
+ "2": "contradiction"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "contradiction": 2,
21
+ "entailment": 0,
22
+ "neutral": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "electra",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "multi_label_classification",
32
+ "summary_activation": "gelu",
33
+ "summary_last_dropout": 0.1,
34
+ "summary_type": "first",
35
+ "summary_use_proj": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.16.2",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 30522
41
+ }
checkpoint-1141/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645b21030c95ae40ac3efa58aeb77c516129c1e21a7b6f96040b285dab281f95
3
+ size 2681490814
checkpoint-1141/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8a61834396ae4adc1129d107763a962535223b9f1f71f8fd0280f439a14cc6
3
+ size 1340743917
checkpoint-1141/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ba5811f005ed35376bd706a06398b37e12b1ccc81171222e0877b0309aae66
3
+ size 14503
checkpoint-1141/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0aee3a000638d6ae74175a3b2b6f564e9d2f477833e8065876b7a2b068ece2
3
+ size 559
checkpoint-1141/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5cbabc59ca6629b30ec20ef4a37b261f5583c218af1ab376085065bb9a7ec5b
3
+ size 623
checkpoint-1141/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-1141/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1141/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "normalization": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-large-discriminator", "tokenizer_class": "ElectraTokenizer"}
checkpoint-1141/trainer_state.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2981628179550171,
3
+ "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-978",
4
+ "epoch": 6.997323135755258,
5
+ "global_step": 1141,
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": 9.499999999999999e-07,
13
+ "loss": 0.4384,
14
+ "step": 163
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7444061962134251,
19
+ "eval_f1": 0.7308261375858633,
20
+ "eval_loss": 0.39615127444267273,
21
+ "eval_runtime": 9.0599,
22
+ "eval_samples_per_second": 256.514,
23
+ "eval_steps_per_second": 32.119,
24
+ "step": 163
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 9e-07,
29
+ "loss": 0.3447,
30
+ "step": 326
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.76592082616179,
35
+ "eval_f1": 0.7552159046464709,
36
+ "eval_loss": 0.3409559428691864,
37
+ "eval_runtime": 9.4378,
38
+ "eval_samples_per_second": 246.244,
39
+ "eval_steps_per_second": 30.833,
40
+ "step": 326
41
+ },
42
+ {
43
+ "epoch": 3.0,
44
+ "learning_rate": 8.499999999999999e-07,
45
+ "loss": 0.3057,
46
+ "step": 489
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "eval_accuracy": 0.7749569707401033,
51
+ "eval_f1": 0.768808341108185,
52
+ "eval_loss": 0.32338443398475647,
53
+ "eval_runtime": 9.0418,
54
+ "eval_samples_per_second": 257.028,
55
+ "eval_steps_per_second": 32.184,
56
+ "step": 489
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 8e-07,
61
+ "loss": 0.287,
62
+ "step": 652
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_accuracy": 0.7857142857142857,
67
+ "eval_f1": 0.7778970154753132,
68
+ "eval_loss": 0.3068828284740448,
69
+ "eval_runtime": 9.3662,
70
+ "eval_samples_per_second": 248.128,
71
+ "eval_steps_per_second": 31.069,
72
+ "step": 652
73
+ },
74
+ {
75
+ "epoch": 5.0,
76
+ "learning_rate": 7.5e-07,
77
+ "loss": 0.2742,
78
+ "step": 815
79
+ },
80
+ {
81
+ "epoch": 5.0,
82
+ "eval_accuracy": 0.7887263339070568,
83
+ "eval_f1": 0.7821763089027973,
84
+ "eval_loss": 0.30303624272346497,
85
+ "eval_runtime": 8.908,
86
+ "eval_samples_per_second": 260.89,
87
+ "eval_steps_per_second": 32.667,
88
+ "step": 815
89
+ },
90
+ {
91
+ "epoch": 6.0,
92
+ "learning_rate": 7e-07,
93
+ "loss": 0.2676,
94
+ "step": 978
95
+ },
96
+ {
97
+ "epoch": 6.0,
98
+ "eval_accuracy": 0.7938898450946644,
99
+ "eval_f1": 0.7850614050415754,
100
+ "eval_loss": 0.2981628179550171,
101
+ "eval_runtime": 9.0189,
102
+ "eval_samples_per_second": 257.681,
103
+ "eval_steps_per_second": 32.266,
104
+ "step": 978
105
+ },
106
+ {
107
+ "epoch": 7.0,
108
+ "learning_rate": 6.5e-07,
109
+ "loss": 0.2585,
110
+ "step": 1141
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_accuracy": 0.7908777969018933,
115
+ "eval_f1": 0.7821955847641968,
116
+ "eval_loss": 0.3001907467842102,
117
+ "eval_runtime": 8.8872,
118
+ "eval_samples_per_second": 261.499,
119
+ "eval_steps_per_second": 32.744,
120
+ "step": 1141
121
+ }
122
+ ],
123
+ "max_steps": 3260,
124
+ "num_train_epochs": 20,
125
+ "total_flos": 2.131077947245901e+16,
126
+ "trial_name": null,
127
+ "trial_params": null
128
+ }
checkpoint-1141/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50dde5eeea306f54118173d342686475ad9209b6c2cac103f7b114d5f582dc36
3
+ size 3119
checkpoint-1141/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-978/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ynie/electra-large-discriminator-snli_mnli_fever_anli_R1_R2_R3-nli",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 1024,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "neutral",
15
+ "2": "contradiction"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "contradiction": 2,
21
+ "entailment": 0,
22
+ "neutral": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "electra",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "multi_label_classification",
32
+ "summary_activation": "gelu",
33
+ "summary_last_dropout": 0.1,
34
+ "summary_type": "first",
35
+ "summary_use_proj": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.16.2",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 30522
41
+ }
checkpoint-978/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f545bb9b4ba6c41b7833ebc1143df20d8bba9021ff50abab697bb844f1a988
3
+ size 2681490814
checkpoint-978/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1017cd7d6d785c901c6c1b5a7c8a543da183235f0b9932da80f8f3cd0484598b
3
+ size 1340743917
checkpoint-978/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e260b8f63ccafccd2ea0aa1da290f571ec2179e4f7f25fb9ca94c888b8be9ea
3
+ size 14503
checkpoint-978/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b3a2a3a2896c7e169e8b8bac61020f776a0ab80e208c27eb0f34d5035cc8fb
3
+ size 559
checkpoint-978/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511c9699b79f5054c4112d6785ff254f1cd47c675bf30666ab6edc5f165de28b
3
+ size 623
checkpoint-978/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-978/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-978/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "normalization": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-large-discriminator", "tokenizer_class": "ElectraTokenizer"}
checkpoint-978/trainer_state.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2981628179550171,
3
+ "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-978",
4
+ "epoch": 5.997323135755258,
5
+ "global_step": 978,
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": 9.499999999999999e-07,
13
+ "loss": 0.4384,
14
+ "step": 163
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7444061962134251,
19
+ "eval_f1": 0.7308261375858633,
20
+ "eval_loss": 0.39615127444267273,
21
+ "eval_runtime": 9.0599,
22
+ "eval_samples_per_second": 256.514,
23
+ "eval_steps_per_second": 32.119,
24
+ "step": 163
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 9e-07,
29
+ "loss": 0.3447,
30
+ "step": 326
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.76592082616179,
35
+ "eval_f1": 0.7552159046464709,
36
+ "eval_loss": 0.3409559428691864,
37
+ "eval_runtime": 9.4378,
38
+ "eval_samples_per_second": 246.244,
39
+ "eval_steps_per_second": 30.833,
40
+ "step": 326
41
+ },
42
+ {
43
+ "epoch": 3.0,
44
+ "learning_rate": 8.499999999999999e-07,
45
+ "loss": 0.3057,
46
+ "step": 489
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "eval_accuracy": 0.7749569707401033,
51
+ "eval_f1": 0.768808341108185,
52
+ "eval_loss": 0.32338443398475647,
53
+ "eval_runtime": 9.0418,
54
+ "eval_samples_per_second": 257.028,
55
+ "eval_steps_per_second": 32.184,
56
+ "step": 489
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 8e-07,
61
+ "loss": 0.287,
62
+ "step": 652
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_accuracy": 0.7857142857142857,
67
+ "eval_f1": 0.7778970154753132,
68
+ "eval_loss": 0.3068828284740448,
69
+ "eval_runtime": 9.3662,
70
+ "eval_samples_per_second": 248.128,
71
+ "eval_steps_per_second": 31.069,
72
+ "step": 652
73
+ },
74
+ {
75
+ "epoch": 5.0,
76
+ "learning_rate": 7.5e-07,
77
+ "loss": 0.2742,
78
+ "step": 815
79
+ },
80
+ {
81
+ "epoch": 5.0,
82
+ "eval_accuracy": 0.7887263339070568,
83
+ "eval_f1": 0.7821763089027973,
84
+ "eval_loss": 0.30303624272346497,
85
+ "eval_runtime": 8.908,
86
+ "eval_samples_per_second": 260.89,
87
+ "eval_steps_per_second": 32.667,
88
+ "step": 815
89
+ },
90
+ {
91
+ "epoch": 6.0,
92
+ "learning_rate": 7e-07,
93
+ "loss": 0.2676,
94
+ "step": 978
95
+ },
96
+ {
97
+ "epoch": 6.0,
98
+ "eval_accuracy": 0.7938898450946644,
99
+ "eval_f1": 0.7850614050415754,
100
+ "eval_loss": 0.2981628179550171,
101
+ "eval_runtime": 9.0189,
102
+ "eval_samples_per_second": 257.681,
103
+ "eval_steps_per_second": 32.266,
104
+ "step": 978
105
+ }
106
+ ],
107
+ "max_steps": 3260,
108
+ "num_train_epochs": 20,
109
+ "total_flos": 1.8270401372548416e+16,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }
checkpoint-978/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50dde5eeea306f54118173d342686475ad9209b6c2cac103f7b114d5f582dc36
3
+ size 3119
checkpoint-978/vocab.txt 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 sha256:144b4da96d7effe4b95740b14231286e40378d2374cf162d73586ae4d8dcf8af
3
  size 1340743917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8a61834396ae4adc1129d107763a962535223b9f1f71f8fd0280f439a14cc6
3
  size 1340743917