Hugging Face's logo

dannychou
/
Homework01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
dannychou commited on
Commit
8c21509
·
1 Parent(s): 969579b

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-268/config.json +25 -0
  3. run-1/checkpoint-268/model.safetensors +3 -0
  4. run-1/checkpoint-268/optimizer.pt +3 -0
  5. run-1/checkpoint-268/rng_state.pth +3 -0
  6. run-1/checkpoint-268/scheduler.pt +3 -0
  7. run-1/checkpoint-268/special_tokens_map.json +7 -0
  8. run-1/checkpoint-268/tokenizer.json +0 -0
  9. run-1/checkpoint-268/tokenizer_config.json +55 -0
  10. run-1/checkpoint-268/trainer_state.json +44 -0
  11. run-1/checkpoint-268/training_args.bin +3 -0
  12. run-1/checkpoint-268/vocab.txt +0 -0
  13. run-2/checkpoint-1069/config.json +25 -0
  14. run-2/checkpoint-1069/model.safetensors +3 -0
  15. run-2/checkpoint-1069/optimizer.pt +3 -0
  16. run-2/checkpoint-1069/rng_state.pth +3 -0
  17. run-2/checkpoint-1069/scheduler.pt +3 -0
  18. run-2/checkpoint-1069/special_tokens_map.json +7 -0
  19. run-2/checkpoint-1069/tokenizer.json +0 -0
  20. run-2/checkpoint-1069/tokenizer_config.json +55 -0
  21. run-2/checkpoint-1069/trainer_state.json +47 -0
  22. run-2/checkpoint-1069/training_args.bin +3 -0
  23. run-2/checkpoint-1069/vocab.txt +0 -0
  24. runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298338.067bf7a71e5c.178.3 +2 -2
  25. runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298398.067bf7a71e5c.178.4 +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 sha256:423056ddaddf4aef86c7064ff159e87e7b35b228be94506323ee8a1e455e2554
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bec0752242fc63e8b206e77d3c8ac72b7cb9dab8b2989039ad7d94d3c8532ef
3
  size 267832560
run-1/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-1/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25265a377e2a1d8d5dc98759fce95a1a0da5ff400719f6bb18cf714335b05a0a
3
+ size 267832560
run-1/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9c648345c41418a6ba23972b4543f2c1cf275b07181ed6d58cfb4a44fa244c
3
+ size 535727290
run-1/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640e878fb44de1f78e15163ccd29c8cb2b9049be582fd6d9b5d6f3822eab0e24
3
+ size 14244
run-1/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c18c8493deffc350dcbb6ad98f7b287842d5b1e712f432c9caf3c872801e8e20
3
+ size 1064
run-1/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-1/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4923279883713507,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.47876012325286865,
14
+ "eval_matthews_correlation": 0.4371673984776278,
15
+ "eval_runtime": 0.7278,
16
+ "eval_samples_per_second": 1433.019,
17
+ "eval_steps_per_second": 90.68,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5014826059341431,
23
+ "eval_matthews_correlation": 0.4923279883713507,
24
+ "eval_runtime": 1.1181,
25
+ "eval_samples_per_second": 932.81,
26
+ "eval_steps_per_second": 59.027,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 268,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 6.107045565717829e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 36
43
+ }
44
+ }
run-1/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277096935da4fb9d72e1021ff312ab04473990a792125849681cf4e78451d2cc
3
+ size 4792
run-1/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-1069/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bec0752242fc63e8b206e77d3c8ac72b7cb9dab8b2989039ad7d94d3c8532ef
3
+ size 267832560
run-2/checkpoint-1069/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b385e8c21535879348b99255fc74c54802d14cb482c4c555fc9e159ad89e5d
3
+ size 535727290
run-2/checkpoint-1069/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03db186bb2363a7920040f817c5e61a675a3e74cc9ac579c1371075761f0cead
3
+ size 14308
run-2/checkpoint-1069/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512f9a00c2185f2da9538dc0de68041960cdcaf10cdcfe4fc827ae18a611776c
3
+ size 1064
run-2/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-2/checkpoint-1069/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-1069/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.40338161890982716,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 6.6708093441865215e-06,
14
+ "loss": 0.5482,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 8.089382157273638e-07,
20
+ "loss": 0.5013,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.5058290362358093,
26
+ "eval_matthews_correlation": 0.40338161890982716,
27
+ "eval_runtime": 0.7312,
28
+ "eval_samples_per_second": 1426.432,
29
+ "eval_steps_per_second": 90.263,
30
+ "step": 1069
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 1069,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 1,
37
+ "save_steps": 500,
38
+ "total_flos": 37691114523840.0,
39
+ "train_batch_size": 8,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 1.253268047264568e-05,
43
+ "num_train_epochs": 1,
44
+ "per_device_train_batch_size": 8,
45
+ "seed": 31
46
+ }
47
+ }
run-2/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6f2b7146eb66983a55e188316e8e52af9cd7317586708733346093cf6c0c1a
3
+ size 4792
run-2/checkpoint-1069/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298338.067bf7a71e5c.178.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40edf1884cfe8f4276091104eda48b6061518d2d0b3fec881087a87e7964eb60
3
- size 4684
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c605ed681da24dd9036e7ccd839a9ceda2d74c7d8f5e84c181dd845fb24f24
3
+ size 5373
runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298398.067bf7a71e5c.178.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e07e1df3486c7d53f5c1551aa3cb466e27ac9d020ec4d9c45b7293483b4c46
3
+ size 5351
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:277096935da4fb9d72e1021ff312ab04473990a792125849681cf4e78451d2cc
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6f2b7146eb66983a55e188316e8e52af9cd7317586708733346093cf6c0c1a
3
  size 4792