kbberendsen commited on
Commit
167a9a0
1 Parent(s): cc6c2d7

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-108/added_tokens.json +3 -0
  3. run-5/checkpoint-108/config.json +35 -0
  4. run-5/checkpoint-108/model.safetensors +3 -0
  5. run-5/checkpoint-108/optimizer.pt +3 -0
  6. run-5/checkpoint-108/rng_state.pth +3 -0
  7. run-5/checkpoint-108/scheduler.pt +3 -0
  8. run-5/checkpoint-108/special_tokens_map.json +15 -0
  9. run-5/checkpoint-108/spm.model +3 -0
  10. run-5/checkpoint-108/tokenizer.json +0 -0
  11. run-5/checkpoint-108/tokenizer_config.json +58 -0
  12. run-5/checkpoint-108/trainer_state.json +44 -0
  13. run-5/checkpoint-108/training_args.bin +3 -0
  14. run-5/checkpoint-162/added_tokens.json +3 -0
  15. run-5/checkpoint-162/config.json +35 -0
  16. run-5/checkpoint-162/model.safetensors +3 -0
  17. run-5/checkpoint-162/optimizer.pt +3 -0
  18. run-5/checkpoint-162/rng_state.pth +3 -0
  19. run-5/checkpoint-162/scheduler.pt +3 -0
  20. run-5/checkpoint-162/special_tokens_map.json +15 -0
  21. run-5/checkpoint-162/spm.model +3 -0
  22. run-5/checkpoint-162/tokenizer.json +0 -0
  23. run-5/checkpoint-162/tokenizer_config.json +58 -0
  24. run-5/checkpoint-162/trainer_state.json +53 -0
  25. run-5/checkpoint-162/training_args.bin +3 -0
  26. run-5/checkpoint-216/added_tokens.json +3 -0
  27. run-5/checkpoint-216/config.json +35 -0
  28. run-5/checkpoint-216/model.safetensors +3 -0
  29. run-5/checkpoint-216/optimizer.pt +3 -0
  30. run-5/checkpoint-216/rng_state.pth +3 -0
  31. run-5/checkpoint-216/scheduler.pt +3 -0
  32. run-5/checkpoint-216/special_tokens_map.json +15 -0
  33. run-5/checkpoint-216/spm.model +3 -0
  34. run-5/checkpoint-216/tokenizer.json +0 -0
  35. run-5/checkpoint-216/tokenizer_config.json +58 -0
  36. run-5/checkpoint-216/trainer_state.json +62 -0
  37. run-5/checkpoint-216/training_args.bin +3 -0
  38. run-6/checkpoint-107/added_tokens.json +3 -0
  39. run-6/checkpoint-107/config.json +35 -0
  40. run-6/checkpoint-107/model.safetensors +3 -0
  41. run-6/checkpoint-107/optimizer.pt +3 -0
  42. run-6/checkpoint-107/rng_state.pth +3 -0
  43. run-6/checkpoint-107/scheduler.pt +3 -0
  44. run-6/checkpoint-107/special_tokens_map.json +15 -0
  45. run-6/checkpoint-107/spm.model +3 -0
  46. run-6/checkpoint-107/tokenizer.json +0 -0
  47. run-6/checkpoint-107/tokenizer_config.json +58 -0
  48. run-6/checkpoint-107/trainer_state.json +35 -0
  49. run-6/checkpoint-107/training_args.bin +3 -0
  50. runs/Feb29_09-36-41_12cf901772ff/events.out.tfevents.1709206595.12cf901772ff.264.10 +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a269d6549a6bb9163b2a81c39e9536c96e9c4775f67e700b6e67f75025827cb
3
  size 1740304440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa0c2cf3c52f53b9ca38387637f4eb929df1ff5cf5bcf70ad52b98d1e63d64fa
3
  size 1740304440
run-5/checkpoint-108/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
run-5/checkpoint-108/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-5/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c8febe95fca6356111d59b0f60bce601a6f03bd8a0477194cbe3c0a79d1ae9
3
+ size 1740304440
run-5/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24c52369f4a16c2dc562aab9ba93819545198957850437b8deb6127e1071b05
3
+ size 3480840240
run-5/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1c94e30e1df0cc77c507c84d602b3edbbc9cd1d65db9f3429a74a9a6613a64
3
+ size 14308
run-5/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba341a9312ab81ad558aafce557103331c088078ef61851dcee1236b5c2c4bcd
3
+ size 1064
run-5/checkpoint-108/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-5/checkpoint-108/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
run-5/checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-108/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-5/checkpoint-108/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-5/checkpoint-54",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 108,
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": 0.6138535737991333,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 8.6936,
16
+ "eval_samples_per_second": 119.973,
17
+ "eval_steps_per_second": 7.592,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6022257208824158,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 9.1939,
25
+ "eval_samples_per_second": 113.445,
26
+ "eval_steps_per_second": 7.179,
27
+ "step": 108
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 216,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 16,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.1908992105042739e-06,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 16,
42
+ "seed": 32
43
+ }
44
+ }
run-5/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:149f15ce87dbce1b98901d72c3882980c391ff03669e53e6884075e2117e145d
3
+ size 4984
run-5/checkpoint-162/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
run-5/checkpoint-162/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-5/checkpoint-162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b076f12317d4f11dc1cb7a3c474d63ebab377105e4a65b5158f16d6ef08cdea8
3
+ size 1740304440
run-5/checkpoint-162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1545075ac60952c546be6466f2307777a7dd9c94c46b29415aec904d2577be1
3
+ size 3480840240
run-5/checkpoint-162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785d59a97549ce821bae8036237f4d74dad2e6bd42bdaac96b2eb0d7a403b330
3
+ size 14308
run-5/checkpoint-162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a1cff49d4e513169499ee23b3c9f559f58f162e33326a673fd733b169806ab
3
+ size 1064
run-5/checkpoint-162/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-5/checkpoint-162/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
run-5/checkpoint-162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-162/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-5/checkpoint-162/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-5/checkpoint-54",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 162,
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": 0.6138535737991333,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 8.6936,
16
+ "eval_samples_per_second": 119.973,
17
+ "eval_steps_per_second": 7.592,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6022257208824158,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 9.1939,
25
+ "eval_samples_per_second": 113.445,
26
+ "eval_steps_per_second": 7.179,
27
+ "step": 108
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.576120138168335,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 9.1717,
34
+ "eval_samples_per_second": 113.719,
35
+ "eval_steps_per_second": 7.196,
36
+ "step": 162
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 216,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 16,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.1908992105042739e-06,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 16,
51
+ "seed": 32
52
+ }
53
+ }
run-5/checkpoint-162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:149f15ce87dbce1b98901d72c3882980c391ff03669e53e6884075e2117e145d
3
+ size 4984
run-5/checkpoint-216/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
run-5/checkpoint-216/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-5/checkpoint-216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:addabb5339f337ffac0d1166770586fb556a9f1ab9b8531ca018eb1bb36201f4
3
+ size 1740304440
run-5/checkpoint-216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:602b71bb475381b503996a33224e8e89840074a8c5ca407bceed0d6f00e60103
3
+ size 3480840240
run-5/checkpoint-216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61f2edb0925c95c76bf49e091298f246e7b119a7b31611c02421546f277a822
3
+ size 14308
run-5/checkpoint-216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a52ac87b02695bd00b299cf36634b51d7e6c50fe16e59b7dcdab7b1a93f248
3
+ size 1064
run-5/checkpoint-216/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-5/checkpoint-216/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
run-5/checkpoint-216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-216/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-5/checkpoint-216/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-5/checkpoint-54",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 216,
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": 0.6138535737991333,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 8.6936,
16
+ "eval_samples_per_second": 119.973,
17
+ "eval_steps_per_second": 7.592,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6022257208824158,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 9.1939,
25
+ "eval_samples_per_second": 113.445,
26
+ "eval_steps_per_second": 7.179,
27
+ "step": 108
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.576120138168335,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 9.1717,
34
+ "eval_samples_per_second": 113.719,
35
+ "eval_steps_per_second": 7.196,
36
+ "step": 162
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.5622713565826416,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 9.1866,
43
+ "eval_samples_per_second": 113.535,
44
+ "eval_steps_per_second": 7.184,
45
+ "step": 216
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 216,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 16,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 1.1908992105042739e-06,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 16,
60
+ "seed": 32
61
+ }
62
+ }
run-5/checkpoint-216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:149f15ce87dbce1b98901d72c3882980c391ff03669e53e6884075e2117e145d
3
+ size 4984
run-6/checkpoint-107/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
run-6/checkpoint-107/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-6/checkpoint-107/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa0c2cf3c52f53b9ca38387637f4eb929df1ff5cf5bcf70ad52b98d1e63d64fa
3
+ size 1740304440
run-6/checkpoint-107/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b896e98bf755a7dc2a528baefbae2960645661685fbdf8fa315c3d19eab23090
3
+ size 3480840240
run-6/checkpoint-107/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3da8dbe35692dbd3a6c4009f27204107916c4ce621e4bfd6fdf59f19a6ac8fb
3
+ size 14308
run-6/checkpoint-107/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c24124ad363a06ecd14c4e41f154aeda430d878ae19db95f813e0982bcf68c1
3
+ size 1064
run-6/checkpoint-107/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-6/checkpoint-107/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
run-6/checkpoint-107/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-107/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-6/checkpoint-107/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6341623601616364,
3
+ "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-6/checkpoint-107",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 107,
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": 0.3793746829032898,
14
+ "eval_matthews_correlation": 0.6341623601616364,
15
+ "eval_runtime": 8.6397,
16
+ "eval_samples_per_second": 120.722,
17
+ "eval_steps_per_second": 7.639,
18
+ "step": 107
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 107,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 8,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 2.7164693557968536e-05,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 8,
33
+ "seed": 20
34
+ }
35
+ }
run-6/checkpoint-107/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:159af02c54f84ba50c6d67a66cea100e15963f8a7c919a8fac00904a25b4d737
3
+ size 4984
runs/Feb29_09-36-41_12cf901772ff/events.out.tfevents.1709206595.12cf901772ff.264.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cccb66c196c90b133d28cd492b9f2bd9f48d5172094a0a111dd95bbced635f87
3
+ size 5486