Hugging Face's logo

flyingswan3000
/
HW01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
flyingswan3000 commited on
Commit
c4bc743
·
1 Parent(s): 81ff745

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. run-6/checkpoint-268/config.json +25 -0
  2. run-6/checkpoint-268/model.safetensors +3 -0
  3. run-6/checkpoint-268/optimizer.pt +3 -0
  4. run-6/checkpoint-268/rng_state.pth +3 -0
  5. run-6/checkpoint-268/scheduler.pt +3 -0
  6. run-6/checkpoint-268/special_tokens_map.json +7 -0
  7. run-6/checkpoint-268/tokenizer.json +0 -0
  8. run-6/checkpoint-268/tokenizer_config.json +55 -0
  9. run-6/checkpoint-268/trainer_state.json +44 -0
  10. run-6/checkpoint-268/training_args.bin +3 -0
  11. run-6/checkpoint-268/vocab.txt +0 -0
  12. run-6/checkpoint-402/config.json +25 -0
  13. run-6/checkpoint-402/model.safetensors +3 -0
  14. run-6/checkpoint-402/optimizer.pt +3 -0
  15. run-6/checkpoint-402/rng_state.pth +3 -0
  16. run-6/checkpoint-402/scheduler.pt +3 -0
  17. run-6/checkpoint-402/special_tokens_map.json +7 -0
  18. run-6/checkpoint-402/tokenizer.json +0 -0
  19. run-6/checkpoint-402/tokenizer_config.json +55 -0
  20. run-6/checkpoint-402/trainer_state.json +53 -0
  21. run-6/checkpoint-402/training_args.bin +3 -0
  22. run-6/checkpoint-402/vocab.txt +0 -0
  23. runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298982.786cd877caf6.1133.9 +3 -0
  24. runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703299003.786cd877caf6.1133.10 +3 -0
  25. runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703299023.786cd877caf6.1133.11 +3 -0
  26. runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703299124.786cd877caf6.1133.12 +3 -0
run-6/checkpoint-268/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-6/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d618e23e3e5070e71381667089f3081e02c435bffac27460fe63d9f30aef4c1
3
+ size 267832560
run-6/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d120ec1da236174206e0ec17430040b5d183cee4bf9b9eff0bc2334d869e771b
3
+ size 535727290
run-6/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9be7e0d36dddb54eaecfb0b77dc53cd069e477606d40da682f3bc5bf96dd61b
3
+ size 14244
run-6/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b2c6e8a47a73242e1771bdcedb9f081e61f57603c664c480f58e59feee5442d
3
+ size 1064
run-6/checkpoint-268/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-6/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-268/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-6/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5091281484717528,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola-hw01/run-6/checkpoint-268",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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": 0.4709751605987549,
14
+ "eval_matthews_correlation": 0.42688451387061943,
15
+ "eval_runtime": 1.0375,
16
+ "eval_samples_per_second": 1005.269,
17
+ "eval_steps_per_second": 63.612,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.48096877336502075,
23
+ "eval_matthews_correlation": 0.5091281484717528,
24
+ "eval_runtime": 0.8273,
25
+ "eval_samples_per_second": 1260.656,
26
+ "eval_steps_per_second": 79.773,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 402,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 5.0568164357979843e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 16
43
+ }
44
+ }
run-6/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349eb54dfb356b807b426134ae60f49a653b5a3e87b92d9c01d994d673f65149
3
+ size 4792
run-6/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-402/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-6/checkpoint-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec43caea3102f42de3e56419e34a66f4d9d3335d2798c85c1cb8ccc7053c7b17
3
+ size 267832560
run-6/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a3b77816c0ca87575e70f917b12aa7c8bdbf2bf75778b731874af7639308f8
3
+ size 535727290
run-6/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b644fd2574610d8fd36b5284fef156006ec73d3aa1020e0532977932344510
3
+ size 14244
run-6/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dab3924dac198fc279c3a7a64dc509bf9a09e60d58895cf550af8cf029d2a64
3
+ size 1064
run-6/checkpoint-402/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-6/checkpoint-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-402/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-6/checkpoint-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5215162259225145,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola-hw01/run-6/checkpoint-402",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 402,
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": 0.4709751605987549,
14
+ "eval_matthews_correlation": 0.42688451387061943,
15
+ "eval_runtime": 1.0375,
16
+ "eval_samples_per_second": 1005.269,
17
+ "eval_steps_per_second": 63.612,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.48096877336502075,
23
+ "eval_matthews_correlation": 0.5091281484717528,
24
+ "eval_runtime": 0.8273,
25
+ "eval_samples_per_second": 1260.656,
26
+ "eval_steps_per_second": 79.773,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5687949657440186,
32
+ "eval_matthews_correlation": 0.5215162259225145,
33
+ "eval_runtime": 0.8027,
34
+ "eval_samples_per_second": 1299.382,
35
+ "eval_steps_per_second": 82.224,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 402,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 5.0568164357979843e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 16
52
+ }
53
+ }
run-6/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349eb54dfb356b807b426134ae60f49a653b5a3e87b92d9c01d994d673f65149
3
+ size 4792
run-6/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298982.786cd877caf6.1133.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01eed3b54f960267024d3a6456223f577ff1493720e49eed461c973635aac66
3
+ size 4698
runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703299003.786cd877caf6.1133.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88394f90d479f78e0ad62f81822c110c1e02a21ea012d873b67b3367458f4cb
3
+ size 4697
runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703299023.786cd877caf6.1133.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bfad9813f72e8a0f8397e0150757c0db125486dc8e7bd35c4261602054e43e
3
+ size 4699
runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703299124.786cd877caf6.1133.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b183fd95bafc521b3599e8285119c2bb9115c9421a1fce3b57ecea6af570fc
3
+ size 5723