Hugging Face's logo

LarryTW
/
llm_NLP

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
Metrics Community
LarryTW commited on
Commit
fe6fdc0
·
1 Parent(s): c7ac3b3

Training in progress, epoch 2

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-1070/config.json +25 -0
  3. run-0/checkpoint-1070/model.safetensors +3 -0
  4. run-0/checkpoint-1070/optimizer.pt +3 -0
  5. run-0/checkpoint-1070/rng_state.pth +3 -0
  6. run-0/checkpoint-1070/scheduler.pt +3 -0
  7. run-0/checkpoint-1070/special_tokens_map.json +7 -0
  8. run-0/checkpoint-1070/tokenizer.json +0 -0
  9. run-0/checkpoint-1070/tokenizer_config.json +55 -0
  10. run-0/checkpoint-1070/trainer_state.json +56 -0
  11. run-0/checkpoint-1070/training_args.bin +3 -0
  12. run-0/checkpoint-1070/vocab.txt +0 -0
  13. run-0/checkpoint-535/config.json +25 -0
  14. run-0/checkpoint-535/model.safetensors +3 -0
  15. run-0/checkpoint-535/optimizer.pt +3 -0
  16. run-0/checkpoint-535/rng_state.pth +3 -0
  17. run-0/checkpoint-535/scheduler.pt +3 -0
  18. run-0/checkpoint-535/special_tokens_map.json +7 -0
  19. run-0/checkpoint-535/tokenizer.json +0 -0
  20. run-0/checkpoint-535/tokenizer_config.json +55 -0
  21. run-0/checkpoint-535/trainer_state.json +41 -0
  22. run-0/checkpoint-535/training_args.bin +3 -0
  23. run-0/checkpoint-535/vocab.txt +0 -0
  24. runs/Dec23_01-44-29_cab255cafe95/events.out.tfevents.1703296147.cab255cafe95.13310.2 +3 -0
  25. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:572638c2fbfca2d1fd97eab7e51304ea6f80dea75c8ea60297bad1874ddcf3ac
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ec2baa14a8ccb68b4c83301cf966fb0e0f2e5c8eb8719c767bf410a98892df
3
  size 267832560
run-0/checkpoint-1070/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ec2baa14a8ccb68b4c83301cf966fb0e0f2e5c8eb8719c767bf410a98892df
3
+ size 267832560
run-0/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00bd97078c3838baa01faa29d5dd8d341c04b225ad7d298899b34cd010c44682
3
+ size 535727290
run-0/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b1fdb9e2fa8c5a5da2db0687852f5f05e14f913960dc4bb4008cfc508b4d6d
3
+ size 14308
run-0/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894ec78df122f5d7e942abcd45c6e9e17e2c18d6a530738ce29f85a3d59efb9c
3
+ size 1064
run-0/checkpoint-1070/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-0/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-1070/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1070,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 6.837169275748106e-07,
14
+ "loss": 0.6115,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5967965126037598,
20
+ "eval_matthews_correlation": 0.0,
21
+ "eval_runtime": 0.7905,
22
+ "eval_samples_per_second": 1319.501,
23
+ "eval_steps_per_second": 83.497,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 8.396523671971359e-08,
29
+ "loss": 0.5803,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5847072005271912,
35
+ "eval_matthews_correlation": 0.0,
36
+ "eval_runtime": 0.8007,
37
+ "eval_samples_per_second": 1302.61,
38
+ "eval_steps_per_second": 82.428,
39
+ "step": 1070
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1070,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 2,
46
+ "save_steps": 500,
47
+ "total_flos": 85092192859320.0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 1.283468618429908e-06,
52
+ "num_train_epochs": 2,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 29
55
+ }
56
+ }
run-0/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27371d800578375cff3a5ebae676f3b731d8801c23d1044ac8562c49ded1f098
3
+ size 4792
run-0/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-535/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-535/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:092d6295e2e5f2508285d2826217a6d1872748c7ac2e28a2e609b58e94aa6c3d
3
+ size 267832560
run-0/checkpoint-535/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af604a6067d2f2414d682d3a267f0b743812a98bff97e22db36a2f3c89b31f7
3
+ size 535727290
run-0/checkpoint-535/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f1677f31a80965f9b60a7f71c5fa4298deeea07df8bd61fc2bea8bda5d6ef6
3
+ size 14308
run-0/checkpoint-535/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54cdd554fb052efa517623039baa03270c3cc43df1281b6a140406d120857f49
3
+ size 1064
run-0/checkpoint-535/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-0/checkpoint-535/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-535/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-535/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 535,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 6.837169275748106e-07,
14
+ "loss": 0.6115,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5967965126037598,
20
+ "eval_matthews_correlation": 0.0,
21
+ "eval_runtime": 0.7905,
22
+ "eval_samples_per_second": 1319.501,
23
+ "eval_steps_per_second": 83.497,
24
+ "step": 535
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 1070,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 2,
31
+ "save_steps": 500,
32
+ "total_flos": 42849063859008.0,
33
+ "train_batch_size": 16,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "learning_rate": 1.283468618429908e-06,
37
+ "num_train_epochs": 2,
38
+ "per_device_train_batch_size": 16,
39
+ "seed": 29
40
+ }
41
+ }
run-0/checkpoint-535/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27371d800578375cff3a5ebae676f3b731d8801c23d1044ac8562c49ded1f098
3
+ size 4792
run-0/checkpoint-535/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_01-44-29_cab255cafe95/events.out.tfevents.1703296147.cab255cafe95.13310.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9fea5f6ab199b3e4b8e48213d843faba0354de0325f7065f2986964167081f
3
+ size 5682
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e943ffb3b04cb1822129ad96c8192c7d89973d3ebe8287b4d5f1e95a51fe569
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27371d800578375cff3a5ebae676f3b731d8801c23d1044ac8562c49ded1f098
3
  size 4792