HikasaHana commited on
Commit
bebf2ef
·
verified ·
1 Parent(s): 584382f

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d78992e35935d5f911a751b5d9af9f3337a0fdf972c4ad150fa4832b8cd50fd8
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017c7fd8cdfc40d05e660a28f8fdb8f78171b64c8062416c21332a818b8614b2
3
  size 409103316
run-10/checkpoint-533/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/chinese-bert-wwm-ext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE",
15
+ "2": "NEUTRAL"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "NEGATIVE": 0,
21
+ "NEUTRAL": 2,
22
+ "POSITIVE": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 21128
43
+ }
run-10/checkpoint-533/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017c7fd8cdfc40d05e660a28f8fdb8f78171b64c8062416c21332a818b8614b2
3
+ size 409103316
run-10/checkpoint-533/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e19e72f374009303cfa0d8fdee04ea10831e8ab72e735a981ce54f9efd0fd01
3
+ size 818327802
run-10/checkpoint-533/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cd3c5a8822e67ef4af7188dd571a48877b29db4a131ffc031fd52e683869738
3
+ size 14244
run-10/checkpoint-533/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f450011aad75d26fc5c2e12873d37b9371d1f657e166248ef40a367734ee46aa
3
+ size 1064
run-10/checkpoint-533/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-10/checkpoint-533/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-10/checkpoint-533/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6418591737747192,
3
+ "best_model_checkpoint": "BERT-WMM/run-10/checkpoint-533",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 533,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.94,
13
+ "grad_norm": 11.003177642822266,
14
+ "learning_rate": 3.5116101047118276e-06,
15
+ "loss": 0.7883,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7370892018779343,
21
+ "eval_loss": 0.6418591737747192,
22
+ "eval_runtime": 2.0865,
23
+ "eval_samples_per_second": 1020.838,
24
+ "eval_steps_per_second": 64.222,
25
+ "step": 533
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 3198,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 6,
32
+ "save_steps": 500,
33
+ "total_flos": 359491040412336.0,
34
+ "train_batch_size": 16,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 4.162390331678438e-06,
38
+ "num_train_epochs": 6,
39
+ "per_device_train_batch_size": 16,
40
+ "weight_decay": 0.000561727996440909
41
+ }
42
+ }
run-10/checkpoint-533/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463ccff4ed8095e86330c3c3432b5d925d66b9d6c0bdc70b6bd557b17c7bd922
3
+ size 4856
run-10/checkpoint-533/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713430555.da5e8340a418.15241.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c95ef3291ff24ee128252a83459caaf7cf631c62b266af17a63d5cd92765d6
3
+ size 5234
runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713430578.da5e8340a418.15241.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c567eeba67064e635441525cc2e02d6c8d8e3c052ec3400c7f25ce23f763cc2
3
+ size 6722
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4bb84483d3f37a31eb4791395662665a1f55283f28759b8d3e52c8a7e2c3a0c
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463ccff4ed8095e86330c3c3432b5d925d66b9d6c0bdc70b6bd557b17c7bd922
3
  size 4856