Hugging Face's logo

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

Text Classification
Transformers
PyTorch
electra
generated_from_trainer
Inference Endpoints
Model card Files Community
1
ChrisZeng commited on
Commit
59d260d
•
1 Parent(s): 93446f4

Training in progress, epoch 0

Browse files
Files changed (19) hide show
  1. checkpoint-210/config.json +41 -0
  2. checkpoint-210/optimizer.pt +3 -0
  3. checkpoint-210/pytorch_model.bin +3 -0
  4. checkpoint-210/rng_state.pth +3 -0
  5. checkpoint-210/scaler.pt +3 -0
  6. checkpoint-210/scheduler.pt +3 -0
  7. checkpoint-210/special_tokens_map.json +1 -0
  8. checkpoint-210/tokenizer.json +0 -0
  9. checkpoint-210/tokenizer_config.json +1 -0
  10. checkpoint-210/trainer_state.json +32 -0
  11. checkpoint-210/training_args.bin +3 -0
  12. checkpoint-210/vocab.txt +0 -0
  13. config.json +41 -0
  14. pytorch_model.bin +3 -0
  15. special_tokens_map.json +1 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +1 -0
  18. training_args.bin +3 -0
  19. vocab.txt +0 -0
checkpoint-210/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": "4.17.0",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 30522
41
+ }
checkpoint-210/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5917d47330c873595676ca37e1fdc54b1c99db101e97e164e74f804df1c01ffb
3
+ size 2681386461
checkpoint-210/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428bc09f739865ff5e71dc377b36b6ab981ecb6c272e3fabf4768b5bf7398865
3
+ size 1340745837
checkpoint-210/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2555445a05959fd07872728f9788d4f0c489bf9295e2f4b96029e7e70f6c94c
3
+ size 14503
checkpoint-210/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0f8ae4ae153dc6d377d71c66f44368d3bceae6c8c866e7e36158f53422ce87
3
+ size 559
checkpoint-210/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9ee01bf51e4b10fd76ee1ec9a597116ddac8c245646175d7b9b2273cfc4a86
3
+ size 623
checkpoint-210/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-210/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-210/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-210/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4019607603549957,
3
+ "best_model_checkpoint": "outputs/electra-nli-efl/checkpoint-210",
4
+ "epoch": 0.9955555555555555,
5
+ "global_step": 210,
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": 0.4175,
14
+ "step": 210
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7316666666666667,
19
+ "eval_f1": 0.7305281480923569,
20
+ "eval_loss": 0.4019607603549957,
21
+ "eval_runtime": 11.5986,
22
+ "eval_samples_per_second": 258.651,
23
+ "eval_steps_per_second": 32.331,
24
+ "step": 210
25
+ }
26
+ ],
27
+ "max_steps": 4200,
28
+ "num_train_epochs": 20,
29
+ "total_flos": 4166446220096256.0,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-210/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c104103a95a8e00f67dc451eba8bec78c0cbf934c84f4059200155cf9a45b752
3
+ size 3119
checkpoint-210/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
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": "4.17.0",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 30522
41
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428bc09f739865ff5e71dc377b36b6ab981ecb6c272e3fabf4768b5bf7398865
3
+ size 1340745837
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c104103a95a8e00f67dc451eba8bec78c0cbf934c84f4059200155cf9a45b752
3
+ size 3119
vocab.txt ADDED
The diff for this file is too large to render. See raw diff