Hugging Face's logo

ChrisZeng
/
electra-large-discriminator-nli-efl-tweeteval

Text Classification
Transformers
PyTorch
electra
Generated from Trainer
Inference Endpoints
Model card Files Community
1
ChrisZeng commited on
Commit
ce99229
•
1 Parent(s): 0480777

Training in progress, epoch 4

Browse files
Files changed (26) hide show
  1. checkpoint-652/config.json +41 -0
  2. checkpoint-652/optimizer.pt +3 -0
  3. checkpoint-652/pytorch_model.bin +3 -0
  4. checkpoint-652/rng_state.pth +3 -0
  5. checkpoint-652/scaler.pt +3 -0
  6. checkpoint-652/scheduler.pt +3 -0
  7. checkpoint-652/special_tokens_map.json +1 -0
  8. checkpoint-652/tokenizer.json +0 -0
  9. checkpoint-652/tokenizer_config.json +1 -0
  10. checkpoint-652/trainer_state.json +80 -0
  11. checkpoint-652/training_args.bin +3 -0
  12. checkpoint-652/vocab.txt +0 -0
  13. checkpoint-815/config.json +41 -0
  14. checkpoint-815/optimizer.pt +3 -0
  15. checkpoint-815/pytorch_model.bin +3 -0
  16. checkpoint-815/rng_state.pth +3 -0
  17. checkpoint-815/scaler.pt +3 -0
  18. checkpoint-815/scheduler.pt +3 -0
  19. checkpoint-815/special_tokens_map.json +1 -0
  20. checkpoint-815/tokenizer.json +0 -0
  21. checkpoint-815/tokenizer_config.json +1 -0
  22. checkpoint-815/trainer_state.json +96 -0
  23. checkpoint-815/training_args.bin +3 -0
  24. checkpoint-815/vocab.txt +0 -0
  25. pytorch_model.bin +1 -1
  26. training_args.bin +1 -1
checkpoint-652/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-652/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b941a9d3d5f0904b9be07c1e13a18bae3fac4b04b65ace1eb83cbbb5b629ee
3
+ size 2681485310
checkpoint-652/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743c3cf66ebcaa120ff0414f34b1f2897e119bb20e1c6c2c08e5861da71cdcb0
3
+ size 1340743917
checkpoint-652/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefbc7ba730396aa917684b6305ceba5776fcc8f2998891d41516ba8262da7c5
3
+ size 14503
checkpoint-652/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2db05efd116af28262c4e96e4840706c52a752454954028a2d8e32d6300b1e
3
+ size 559
checkpoint-652/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a157602c28dafa1a0271775fa975aab22e5621dd748103545f800233df8f5450
3
+ size 623
checkpoint-652/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-652/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-652/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-652/trainer_state.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3068828284740448,
3
+ "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-652",
4
+ "epoch": 3.9973231357552583,
5
+ "global_step": 652,
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
+ "max_steps": 3260,
76
+ "num_train_epochs": 20,
77
+ "total_flos": 1.2184053565654464e+16,
78
+ "trial_name": null,
79
+ "trial_params": null
80
+ }
checkpoint-652/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82126e010e751131ea0bffbc21275298a6bdbc244157fe27eed5dd4b7b0d6e0f
3
+ size 3119
checkpoint-652/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-815/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-815/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e442450e8cd52442bde80cb4c5d1310a90067d38639466cab2419adbc6654816
3
+ size 2681490814
checkpoint-815/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144b4da96d7effe4b95740b14231286e40378d2374cf162d73586ae4d8dcf8af
3
+ size 1340743917
checkpoint-815/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c726a4aa63d9bd90a506c784ff97322020e4f71cf490bdb933f60b3449d3305
3
+ size 14503
checkpoint-815/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da72ce8dde138a0cdbd363df00f1844a99e2301d5909310e0da6fbcd75a035a
3
+ size 559
checkpoint-815/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad42bdc4a1db64a469af268c60e8c94de7907ce695dc2ec26a965499c4160890
3
+ size 623
checkpoint-815/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-815/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-815/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-815/trainer_state.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.30303624272346497,
3
+ "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-815",
4
+ "epoch": 4.997323135755258,
5
+ "global_step": 815,
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
+ "max_steps": 3260,
92
+ "num_train_epochs": 20,
93
+ "total_flos": 1.5229673797195776e+16,
94
+ "trial_name": null,
95
+ "trial_params": null
96
+ }
checkpoint-815/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-815/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:a8cc6e01615d9fbc03a612a6299c16196268fe2e23e228d881f2f3bfa6b3ee9c
3
  size 1340743917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144b4da96d7effe4b95740b14231286e40378d2374cf162d73586ae4d8dcf8af
3
  size 1340743917
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82126e010e751131ea0bffbc21275298a6bdbc244157fe27eed5dd4b7b0d6e0f
3
  size 3119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50dde5eeea306f54118173d342686475ad9209b6c2cac103f7b114d5f582dc36
3
  size 3119