Hugging Face's logo

Tomkao0214
/
learningllm

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
Tomkao0214 commited on
Commit
a122073
·
1 Parent(s): adadb7e

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-6/checkpoint-536/config.json +25 -0
  3. run-6/checkpoint-536/model.safetensors +3 -0
  4. run-6/checkpoint-536/optimizer.pt +3 -0
  5. run-6/checkpoint-536/rng_state.pth +3 -0
  6. run-6/checkpoint-536/scheduler.pt +3 -0
  7. run-6/checkpoint-536/special_tokens_map.json +7 -0
  8. run-6/checkpoint-536/tokenizer.json +0 -0
  9. run-6/checkpoint-536/tokenizer_config.json +55 -0
  10. run-6/checkpoint-536/trainer_state.json +50 -0
  11. run-6/checkpoint-536/training_args.bin +3 -0
  12. run-6/checkpoint-536/vocab.txt +0 -0
  13. run-8/checkpoint-2138/config.json +25 -0
  14. run-8/checkpoint-2138/model.safetensors +3 -0
  15. run-8/checkpoint-2138/optimizer.pt +3 -0
  16. run-8/checkpoint-2138/rng_state.pth +3 -0
  17. run-8/checkpoint-2138/scheduler.pt +3 -0
  18. run-8/checkpoint-2138/special_tokens_map.json +7 -0
  19. run-8/checkpoint-2138/tokenizer.json +0 -0
  20. run-8/checkpoint-2138/tokenizer_config.json +55 -0
  21. run-8/checkpoint-2138/trainer_state.json +59 -0
  22. run-8/checkpoint-2138/training_args.bin +3 -0
  23. run-8/checkpoint-2138/vocab.txt +0 -0
  24. runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703300002.39bac3413ec0.1762.9 +3 -0
  25. runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703300032.39bac3413ec0.1762.10 +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:bf0e8845471395af3cbf3cbbab882273a0fc98ea4f4cf90d415638c3cb075e76
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7325d90d0c9c99b39fa9cab1a46ae1d8745ad2e449f765021d517982a1bb53
3
  size 267832560
run-6/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-6/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc41fa51e840dac1e12eb7c53f33bbee9d058e5f4795500e1c1362f8a4d0be0d
3
+ size 267832560
run-6/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e4135fdacbdf75b197bbf3248668a633eef4af7f89056b2db43355918da79ac
3
+ size 535727290
run-6/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6536bff7ec3ce1377f3ea566776ef9860011a5efc655ee337e64204b055f7144
3
+ size 14244
run-6/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c812beca7c33a019580500ff4f4feffa22c07f38ec19a7b01a2f45dd70eac34a
3
+ size 1064
run-6/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-6/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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-6/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.24176551775185876,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/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": 0.5563415884971619,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7953,
16
+ "eval_samples_per_second": 1311.386,
17
+ "eval_steps_per_second": 82.983,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 3.648912445858465e-07,
23
+ "loss": 0.5527,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.536371648311615,
29
+ "eval_matthews_correlation": 0.24176551775185876,
30
+ "eval_runtime": 0.789,
31
+ "eval_samples_per_second": 1321.879,
32
+ "eval_steps_per_second": 83.647,
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": 96250760118372.0,
42
+ "train_batch_size": 32,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 5.432825197167048e-06,
46
+ "num_train_epochs": 2,
47
+ "per_device_train_batch_size": 32,
48
+ "seed": 2
49
+ }
50
+ }
run-6/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca18acd2750e09b809189d05af435a5f54f149c3821f062cd81ada53fff09639
3
+ size 4792
run-6/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-2138/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-8/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7325d90d0c9c99b39fa9cab1a46ae1d8745ad2e449f765021d517982a1bb53
3
+ size 267832560
run-8/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31132122cacdf8cba14ed792ac7f4acf67c51dc9f5769ddd8b5596c071bb2198
3
+ size 535727290
run-8/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc503f7d73524ef1ec1ebba4392611ea5af52f401ba35909bd19b94018e06f6d
3
+ size 14244
run-8/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1b8383f2a865c494d556ca27c67e8284be5a0a696abe2b13e336368c0b7a65
3
+ size 1064
run-8/checkpoint-2138/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-8/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-2138/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-8/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.41820216419095174,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-2138",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2138,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 3.0616680644448215e-06,
14
+ "loss": 0.6093,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 2.8715495805622565e-06,
20
+ "loss": 0.5712,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 2.6814310966796923e-06,
26
+ "loss": 0.5189,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 2.4913126127971277e-06,
32
+ "loss": 0.5311,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.5466733574867249,
38
+ "eval_matthews_correlation": 0.41820216419095174,
39
+ "eval_runtime": 0.7262,
40
+ "eval_samples_per_second": 1436.166,
41
+ "eval_steps_per_second": 90.879,
42
+ "step": 2138
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 8552,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 4,
49
+ "save_steps": 500,
50
+ "total_flos": 35569048891464.0,
51
+ "train_batch_size": 4,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 3.251786548327386e-06,
55
+ "num_train_epochs": 4,
56
+ "per_device_train_batch_size": 4,
57
+ "seed": 36
58
+ }
59
+ }
run-8/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5ddd248539884628461fd776db8546d1dd11f41bc207fe497af7c7cc2d0672
3
+ size 4792
run-8/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703300002.39bac3413ec0.1762.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b25c0cce8bb707960b68d6dd7fe3537a765b96402da860cd30d3af0a8dbb95
3
+ size 4843
runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703300032.39bac3413ec0.1762.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879c78d927f94a370a6c7e305cc1016c16dec493cffecd541d5e22d0f2ea838d
3
+ size 6276
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca18acd2750e09b809189d05af435a5f54f149c3821f062cd81ada53fff09639
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5ddd248539884628461fd776db8546d1dd11f41bc207fe497af7c7cc2d0672
3
  size 4792