Srjnnnn commited on
Commit
dd74fc5
1 Parent(s): 6998d87

Finish train

Browse files
checkpoint-500/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5
27
+ },
28
+ "max_position_embeddings": 512,
29
+ "model_type": "distilbert",
30
+ "n_heads": 12,
31
+ "n_layers": 6,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "qa_dropout": 0.1,
35
+ "seq_classif_dropout": 0.2,
36
+ "sinusoidal_pos_embds": false,
37
+ "tie_weights_": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.16.2",
40
+ "vocab_size": 30522
41
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22eb1322fd4634dbeaeeee50c8d1a069282cdd7e89f77b2906da39cf46ee2c68
3
+ size 535726074
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df399436adfb8510e30ec0defb53b5e3fc4a59015200e39b1432caae8807ffd
3
+ size 267874026
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67c0aa61895b13a42e8b2b0e79ed731100aba61704f0f1748098ea855bafc6ee
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f29365aa09523198baebebe95ffb09ad5f00205c944d1df89a9000244c3bc23
3
+ size 1064
checkpoint-500/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-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 500,
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": 1e-05,
13
+ "loss": 0.8564,
14
+ "step": 250
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.9025,
19
+ "eval_f1": 0.9003875072639731,
20
+ "eval_loss": 0.3279983699321747,
21
+ "eval_runtime": 0.9562,
22
+ "eval_samples_per_second": 2091.684,
23
+ "eval_steps_per_second": 33.467,
24
+ "step": 250
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0,
29
+ "loss": 0.2543,
30
+ "step": 500
31
+ }
32
+ ],
33
+ "max_steps": 500,
34
+ "num_train_epochs": 2,
35
+ "total_flos": 720342861696000.0,
36
+ "trial_name": null,
37
+ "trial_params": null
38
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d9117fe1dbb3e95b6bdfa9115f0dd4ce25d6f70baa06a5d6a6123b4547be19
3
+ size 3512
checkpoint-500/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": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5
27
+ },
28
+ "max_position_embeddings": 512,
29
+ "model_type": "distilbert",
30
+ "n_heads": 12,
31
+ "n_layers": 6,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "qa_dropout": 0.1,
35
+ "seq_classif_dropout": 0.2,
36
+ "sinusoidal_pos_embds": false,
37
+ "tie_weights_": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.16.2",
40
+ "vocab_size": 30522
41
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df399436adfb8510e30ec0defb53b5e3fc4a59015200e39b1432caae8807ffd
3
+ size 267874026
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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d9117fe1dbb3e95b6bdfa9115f0dd4ce25d6f70baa06a5d6a6123b4547be19
3
+ size 3512
vocab.txt ADDED
The diff for this file is too large to render. See raw diff