Hugging Face's logo

CCChenRyan
/
LLM_T1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
CCChenRyan commited on
Commit
a19a6fb
·
1 Parent(s): f025e78

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-536/config.json +25 -0
  3. run-2/checkpoint-536/model.safetensors +3 -0
  4. run-2/checkpoint-536/optimizer.pt +3 -0
  5. run-2/checkpoint-536/rng_state.pth +3 -0
  6. run-2/checkpoint-536/scheduler.pt +3 -0
  7. run-2/checkpoint-536/special_tokens_map.json +7 -0
  8. run-2/checkpoint-536/tokenizer.json +0 -0
  9. run-2/checkpoint-536/tokenizer_config.json +55 -0
  10. run-2/checkpoint-536/trainer_state.json +50 -0
  11. run-2/checkpoint-536/training_args.bin +3 -0
  12. run-2/checkpoint-536/vocab.txt +0 -0
  13. run-3/checkpoint-1069/config.json +25 -0
  14. run-3/checkpoint-1069/model.safetensors +3 -0
  15. run-3/checkpoint-1069/optimizer.pt +3 -0
  16. run-3/checkpoint-1069/rng_state.pth +3 -0
  17. run-3/checkpoint-1069/scheduler.pt +3 -0
  18. run-3/checkpoint-1069/special_tokens_map.json +7 -0
  19. run-3/checkpoint-1069/tokenizer.json +0 -0
  20. run-3/checkpoint-1069/tokenizer_config.json +55 -0
  21. run-3/checkpoint-1069/trainer_state.json +47 -0
  22. run-3/checkpoint-1069/training_args.bin +3 -0
  23. run-3/checkpoint-1069/vocab.txt +0 -0
  24. runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703298272.17d63b357dd6.603.4 +2 -2
  25. runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703298345.17d63b357dd6.603.5 +3 -0
  26. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4478e11be320fca559d45a9351b361da80c8818133da7a6f341efff44a0097f0
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf7f59ed13b888a0489281dcc27320b6e23a655d73a6a8f0c88a019a914167e
3
  size 267832560
run-2/checkpoint-536/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-2/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e68822b798f4b050ce135089fee3d6c166f181583427e84b4a77005fe04d58ad
3
+ size 267832560
run-2/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fafbe4add2ae4d4430594d159ff209ccfd5f1b4f48785cc48582733d38b489a7
3
+ size 535727290
run-2/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241a81787b21510f2a6b884a029024a8844162c71275b910022fddadaed11c47
3
+ size 14244
run-2/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead53471094d90ea15ef621527be8fbd3228a976c1ec6bc14f3fb014eeb833d6
3
+ size 1064
run-2/checkpoint-536/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-2/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-536/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-2/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.471551419577941,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-536",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 536,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.5023595094680786,
14
+ "eval_matthews_correlation": 0.37427395551191556,
15
+ "eval_runtime": 0.7713,
16
+ "eval_samples_per_second": 1352.258,
17
+ "eval_steps_per_second": 85.57,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 6.325575181512268e-06,
23
+ "loss": 0.432,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5333026647567749,
29
+ "eval_matthews_correlation": 0.471551419577941,
30
+ "eval_runtime": 1.119,
31
+ "eval_samples_per_second": 932.089,
32
+ "eval_steps_per_second": 58.982,
33
+ "step": 536
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 536,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 2,
40
+ "save_steps": 500,
41
+ "total_flos": 96476109931320.0,
42
+ "train_batch_size": 32,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 9.418078603584933e-05,
46
+ "num_train_epochs": 2,
47
+ "per_device_train_batch_size": 32,
48
+ "seed": 11
49
+ }
50
+ }
run-2/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727bdb52dd4bd77c5c910659c380ef8fbdb5779a6ca87b401a9b9e31f1b5d726
3
+ size 4792
run-2/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1069/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-3/checkpoint-1069/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf7f59ed13b888a0489281dcc27320b6e23a655d73a6a8f0c88a019a914167e
3
+ size 267832560
run-3/checkpoint-1069/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9079265a15b3cc985809ea072bf80dcc47691398815138086debac693d8c599
3
+ size 535727290
run-3/checkpoint-1069/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:991df4aa76f24d91526e7e51a90de580470ee9ff4e3f5336667f187c26f0e6c4
3
+ size 14244
run-3/checkpoint-1069/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2a1192b6d20749b54ff4c9d6e8eba4366348085b1f82dd2d8c2144f4b16ef88
3
+ size 1064
run-3/checkpoint-1069/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-3/checkpoint-1069/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1069/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-3/checkpoint-1069/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.43113135892567,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1069",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1069,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "learning_rate": 3.847410505471434e-05,
14
+ "loss": 0.5687,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 3.136769481187829e-05,
20
+ "loss": 0.5213,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.47989290952682495,
26
+ "eval_matthews_correlation": 0.43113135892567,
27
+ "eval_runtime": 0.7438,
28
+ "eval_samples_per_second": 1402.351,
29
+ "eval_steps_per_second": 88.739,
30
+ "step": 1069
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 3207,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 3,
37
+ "save_steps": 500,
38
+ "total_flos": 37641439249344.0,
39
+ "train_batch_size": 8,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 4.5580515297550385e-05,
43
+ "num_train_epochs": 3,
44
+ "per_device_train_batch_size": 8,
45
+ "seed": 6
46
+ }
47
+ }
run-3/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47916063c9d08da0ea406bcd37dc65026cf97e4bfd39252c5a02963e5d083a2f
3
+ size 4792
run-3/checkpoint-1069/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703298272.17d63b357dd6.603.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec19eacfc164c0e933221d0224dd0aae92715756ab51b7ce02e2ea807d739ec1
3
- size 4838
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7c4616adfc66184187c43b79c9b5a0f39f79b81ad5f6b9324fc5cd6f8c0776
3
+ size 5527
runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703298345.17d63b357dd6.603.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8767921543efbbdc7915515d7d244adb5edeab776c3b4955c5d8d00b1f66e98e
3
+ size 5151
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:727bdb52dd4bd77c5c910659c380ef8fbdb5779a6ca87b401a9b9e31f1b5d726
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47916063c9d08da0ea406bcd37dc65026cf97e4bfd39252c5a02963e5d083a2f
3
  size 4792