Hugging Face's logo

ZaaCo
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
Metrics Community
ZaaCo commited on
Commit
5ef596a
·
verified ·
1 Parent(s): db46906

Training in progress, epoch 1

Browse files
Files changed (21) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-856/config.json +25 -0
  3. run-2/checkpoint-856/model.safetensors +3 -0
  4. run-2/checkpoint-856/optimizer.pt +3 -0
  5. run-2/checkpoint-856/rng_state.pth +3 -0
  6. run-2/checkpoint-856/scheduler.pt +3 -0
  7. run-2/checkpoint-856/special_tokens_map.json +7 -0
  8. run-2/checkpoint-856/tokenizer.json +0 -0
  9. run-2/checkpoint-856/tokenizer_config.json +55 -0
  10. run-2/checkpoint-856/trainer_state.json +69 -0
  11. run-2/checkpoint-856/training_args.bin +3 -0
  12. run-2/checkpoint-856/vocab.txt +0 -0
  13. run-3/checkpoint-214/config.json +1 -1
  14. run-3/checkpoint-214/model.safetensors +1 -1
  15. run-3/checkpoint-214/optimizer.pt +1 -1
  16. run-3/checkpoint-214/rng_state.pth +2 -2
  17. run-3/checkpoint-214/scheduler.pt +1 -1
  18. run-3/checkpoint-214/trainer_state.json +9 -9
  19. run-3/checkpoint-214/training_args.bin +1 -1
  20. runs/Mar04_18-27-47_c54f83add3d5/events.out.tfevents.1709577595.c54f83add3d5.171.5 +3 -0
  21. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:354493ac69b1277ef98c691bbcd55203842bb4b6dffbd286d7d76b21299e92f7
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b38e30178be84fca14e28f4f3c3cf2c1b2b0ae3291096e7373a17a4ba23fec
3
  size 267832560
run-2/checkpoint-856/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354493ac69b1277ef98c691bbcd55203842bb4b6dffbd286d7d76b21299e92f7
3
+ size 267832560
run-2/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30cfe26b92b10cb2ae394a9c85d356c4a11360f109f00551f5475f686c6505fe
3
+ size 535727290
run-2/checkpoint-856/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f54138dee1f9afa7d3ff6d91294b01f404af474ee7f4654619a161a52bb2854c
3
+ size 14244
run-2/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d378df51ea4a8c259ebd0bc7bba21a39026b9a0e2a92015ffebe3bdd9be10cbc
3
+ size 1064
run-2/checkpoint-856/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-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-856/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-856/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-214",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 856,
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": 0.6336618065834045,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6976,
16
+ "eval_samples_per_second": 1495.066,
17
+ "eval_steps_per_second": 94.606,
18
+ "step": 214
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6176421642303467,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7645,
25
+ "eval_samples_per_second": 1364.241,
26
+ "eval_steps_per_second": 86.328,
27
+ "step": 428
28
+ },
29
+ {
30
+ "epoch": 2.34,
31
+ "grad_norm": 3.8267481327056885,
32
+ "learning_rate": 5.70366466984465e-07,
33
+ "loss": 0.6304,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 0.6142997145652771,
39
+ "eval_matthews_correlation": 0.0,
40
+ "eval_runtime": 1.1475,
41
+ "eval_samples_per_second": 908.928,
42
+ "eval_steps_per_second": 57.516,
43
+ "step": 642
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_loss": 0.6139855980873108,
48
+ "eval_matthews_correlation": 0.0,
49
+ "eval_runtime": 0.6988,
50
+ "eval_samples_per_second": 1492.507,
51
+ "eval_steps_per_second": 94.444,
52
+ "step": 856
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 856,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 4,
59
+ "save_steps": 500,
60
+ "total_flos": 8378304239604.0,
61
+ "train_batch_size": 4,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 1.3714429655581517e-06,
65
+ "num_train_epochs": 4,
66
+ "per_device_train_batch_size": 4,
67
+ "seed": 36
68
+ }
69
+ }
run-2/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8fc7225d64603a842fa6b6ef0515f5eada06b365317b2b6b8d70e87099bb1d
3
+ size 4984
run-2/checkpoint-856/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-214/config.json CHANGED
@@ -20,6 +20,6 @@
20
  "sinusoidal_pos_embds": false,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.38.1",
24
  "vocab_size": 30522
25
  }
 
20
  "sinusoidal_pos_embds": false,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
  "vocab_size": 30522
25
  }
run-3/checkpoint-214/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ff077a302ae188dc1ff17706725beab1e155e23b2ae9425ee1f8a59150e45ec
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b38e30178be84fca14e28f4f3c3cf2c1b2b0ae3291096e7373a17a4ba23fec
3
  size 267832560
run-3/checkpoint-214/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:668990eb253188b3ff83a900191f6e7d16fa8c326ebabd6b639854e126502b5d
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8004dbe29c0b223e4c276c2bcff8f32576fb7483bf122df086afbaeae377ad
3
  size 535727290
run-3/checkpoint-214/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:785c420669f92bfd5822f9fb2533c67efd966a766db2dcdc65d5723aaebcf725
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46a44649abb0ebbb9931bc723ea40b7c460ea7e31f9f41a216bd35145c60c9e
3
+ size 14308
run-3/checkpoint-214/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40dcf9c0c0dc2ab4a8126bbb644cca2b811e38befca459ec3ff292d579dcaf2d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79be7efa1b8419b7585dd03ba10962a2c1b6681881b8812bd35c19a986756a7
3
  size 1064
run-3/checkpoint-214/trainer_state.json CHANGED
@@ -10,26 +10,26 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.5915305018424988,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 0.7414,
16
- "eval_samples_per_second": 1406.855,
17
- "eval_steps_per_second": 89.024,
18
  "step": 214
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 428,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 2,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 4,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 9.511207398100714e-06,
31
- "num_train_epochs": 2,
32
  "per_device_train_batch_size": 4,
33
- "seed": 3
34
  }
35
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6153979301452637,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6974,
16
+ "eval_samples_per_second": 1495.562,
17
+ "eval_steps_per_second": 94.638,
18
  "step": 214
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 856,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 4,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "learning_rate": 3.459372063317158e-06,
31
+ "num_train_epochs": 4,
32
  "per_device_train_batch_size": 4,
33
+ "seed": 33
34
  }
35
  }
run-3/checkpoint-214/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6d0e3c171d892a7137b0069a11b5916f7df841be4d6e7a33f7fda92ec2c1986
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725d82177b4cbfe5fdec00f2a98d04c02900a76cd950f04ef533ba2d33dfbdfa
3
  size 4984
runs/Mar04_18-27-47_c54f83add3d5/events.out.tfevents.1709577595.c54f83add3d5.171.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c4f068f831078dc147bc444aaf6566c8d12082643837842b2b71d75810cea2
3
+ size 6446
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec8fc7225d64603a842fa6b6ef0515f5eada06b365317b2b6b8d70e87099bb1d
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725d82177b4cbfe5fdec00f2a98d04c02900a76cd950f04ef533ba2d33dfbdfa
3
  size 4984