Hugging Face's logo

kbberendsen
/
deberta-v3-large-finetuned-cola-midterm

Text Classification
Transformers
TensorBoard
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kbberendsen commited on
Commit
3a969a4
·
verified ·
1 Parent(s): 6416698

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-428/added_tokens.json +3 -0
  3. run-3/checkpoint-428/config.json +35 -0
  4. run-3/checkpoint-428/model.safetensors +3 -0
  5. run-3/checkpoint-428/optimizer.pt +3 -0
  6. run-3/checkpoint-428/rng_state.pth +3 -0
  7. run-3/checkpoint-428/scheduler.pt +3 -0
  8. run-3/checkpoint-428/special_tokens_map.json +15 -0
  9. run-3/checkpoint-428/spm.model +3 -0
  10. run-3/checkpoint-428/tokenizer.json +0 -0
  11. run-3/checkpoint-428/tokenizer_config.json +58 -0
  12. run-3/checkpoint-428/trainer_state.json +44 -0
  13. run-3/checkpoint-428/training_args.bin +3 -0
  14. run-4/checkpoint-214/added_tokens.json +3 -0
  15. run-4/checkpoint-214/config.json +35 -0
  16. run-4/checkpoint-214/model.safetensors +3 -0
  17. run-4/checkpoint-214/optimizer.pt +3 -0
  18. run-4/checkpoint-214/rng_state.pth +3 -0
  19. run-4/checkpoint-214/scheduler.pt +3 -0
  20. run-4/checkpoint-214/special_tokens_map.json +15 -0
  21. run-4/checkpoint-214/spm.model +3 -0
  22. run-4/checkpoint-214/tokenizer.json +0 -0
  23. run-4/checkpoint-214/tokenizer_config.json +58 -0
  24. run-4/checkpoint-214/trainer_state.json +35 -0
  25. run-4/checkpoint-214/training_args.bin +3 -0
  26. runs/Feb29_09-36-41_12cf901772ff/events.out.tfevents.1709204789.12cf901772ff.264.8 +3 -0
  27. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d27952fe13fd3bcf65eddbdd6237e7a718b346a95a0de852ae7d2509925e0aa
3
  size 1740304440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed0085ac41a5bcd84e866387f78a2cc5ea10014d7377e2313d8fb76bd60ed805
3
  size 1740304440
run-3/checkpoint-428/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
run-3/checkpoint-428/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.38.1",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
run-3/checkpoint-428/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c03d40877cd61f30c11b2fbfd7380293ff05d71d1de4469672472c645bd18c
3
+ size 1740304440
run-3/checkpoint-428/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16559e90bb38a31cd260ff8ee032ebd14b0e1bb4829937352f49cd796c33bd1
3
+ size 3480840240
run-3/checkpoint-428/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f01cb1bb38f610c4727200fc5d42260edf15689e88dd0669958910a49ea120c
3
+ size 14244
run-3/checkpoint-428/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87dab7aa05be61a63a9fc397e1306f8bbe6f1a15055446d9a9cc38e38a2645aa
3
+ size 1064
run-3/checkpoint-428/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
run-3/checkpoint-428/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
run-3/checkpoint-428/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-428/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
run-3/checkpoint-428/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-3/checkpoint-214",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 428,
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": 0.6239587664604187,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 8.4185,
16
+ "eval_samples_per_second": 123.894,
17
+ "eval_steps_per_second": 7.84,
18
+ "step": 214
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6267099380493164,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 8.5011,
25
+ "eval_samples_per_second": 122.69,
26
+ "eval_steps_per_second": 7.764,
27
+ "step": 428
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 428,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 4,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 6.93139822379791e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 4,
42
+ "seed": 12
43
+ }
44
+ }
run-3/checkpoint-428/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365374e711b9f598c24804c684864116b73578314660a35beaf262cdfdbadba4
3
+ size 4984
run-4/checkpoint-214/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
run-4/checkpoint-214/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.38.1",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
run-4/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed0085ac41a5bcd84e866387f78a2cc5ea10014d7377e2313d8fb76bd60ed805
3
+ size 1740304440
run-4/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e3d408885fcb823a6b5dbac8984faceb3fa8aab5f7e4bb72361e9962a574797
3
+ size 3480840240
run-4/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ba18c06312e2dc421eff17e5639fdf94152250aa995a29d2d71b88dc17ca18
3
+ size 14244
run-4/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b846bb4d8df0df14d5656c4b462fb4901e46e422b089eeaeca302f64e608b0
3
+ size 1064
run-4/checkpoint-214/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
run-4/checkpoint-214/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
run-4/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-214/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
run-4/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5768865343306099,
3
+ "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-4/checkpoint-214",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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": 0.6170005798339844,
14
+ "eval_matthews_correlation": 0.5768865343306099,
15
+ "eval_runtime": 8.4232,
16
+ "eval_samples_per_second": 123.824,
17
+ "eval_steps_per_second": 7.835,
18
+ "step": 214
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 214,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 4,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 5.867793986596445e-05,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 4,
33
+ "seed": 34
34
+ }
35
+ }
run-4/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33d0ef89bb64ba73efac087f009cee2aeb0216a1c22a9d12358d5aa1a8ec123
3
+ size 4984
runs/Feb29_09-36-41_12cf901772ff/events.out.tfevents.1709204789.12cf901772ff.264.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62811205544dd6c5505de6210559a249d4e3d4d3a937d4da8d101f02a1659fe
3
+ size 5497
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:365374e711b9f598c24804c684864116b73578314660a35beaf262cdfdbadba4
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33d0ef89bb64ba73efac087f009cee2aeb0216a1c22a9d12358d5aa1a8ec123
3
  size 4984