Hugging Face's logo

jerawincel
/
roberta-base-finetuned

Text Classification
Transformers
TensorBoard
Safetensors
roberta
text-embeddings-inference
Model card Files
xet
 Metrics Community
jerawincel commited on
Commit
1610cce
·
1 Parent(s): e95b402

Training in progress, epoch 4

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-272/config.json +87 -0
  3. run-5/checkpoint-272/merges.txt +0 -0
  4. run-5/checkpoint-272/model.safetensors +3 -0
  5. run-5/checkpoint-272/optimizer.pt +3 -0
  6. run-5/checkpoint-272/rng_state.pth +3 -0
  7. run-5/checkpoint-272/scheduler.pt +3 -0
  8. run-5/checkpoint-272/special_tokens_map.json +15 -0
  9. run-5/checkpoint-272/tokenizer.json +0 -0
  10. run-5/checkpoint-272/tokenizer_config.json +58 -0
  11. run-5/checkpoint-272/trainer_state.json +42 -0
  12. run-5/checkpoint-272/training_args.bin +3 -0
  13. run-5/checkpoint-272/vocab.json +0 -0
  14. run-6/checkpoint-136/config.json +87 -0
  15. run-6/checkpoint-136/merges.txt +0 -0
  16. run-6/checkpoint-136/model.safetensors +3 -0
  17. run-6/checkpoint-136/optimizer.pt +3 -0
  18. run-6/checkpoint-136/rng_state.pth +3 -0
  19. run-6/checkpoint-136/scheduler.pt +3 -0
  20. run-6/checkpoint-136/special_tokens_map.json +15 -0
  21. run-6/checkpoint-136/tokenizer.json +0 -0
  22. run-6/checkpoint-136/tokenizer_config.json +58 -0
  23. run-6/checkpoint-136/trainer_state.json +42 -0
  24. run-6/checkpoint-136/training_args.bin +3 -0
  25. run-6/checkpoint-136/vocab.json +0 -0
  26. run-6/checkpoint-204/config.json +87 -0
  27. run-6/checkpoint-204/merges.txt +0 -0
  28. run-6/checkpoint-204/model.safetensors +3 -0
  29. run-6/checkpoint-204/optimizer.pt +3 -0
  30. run-6/checkpoint-204/rng_state.pth +3 -0
  31. run-6/checkpoint-204/scheduler.pt +3 -0
  32. run-6/checkpoint-204/special_tokens_map.json +15 -0
  33. run-6/checkpoint-204/tokenizer.json +0 -0
  34. run-6/checkpoint-204/tokenizer_config.json +58 -0
  35. run-6/checkpoint-204/trainer_state.json +51 -0
  36. run-6/checkpoint-204/training_args.bin +3 -0
  37. run-6/checkpoint-204/vocab.json +0 -0
  38. run-6/checkpoint-272/model.safetensors +1 -1
  39. run-6/checkpoint-272/optimizer.pt +1 -1
  40. run-6/checkpoint-272/rng_state.pth +1 -1
  41. run-6/checkpoint-272/scheduler.pt +1 -1
  42. run-6/checkpoint-272/tokenizer.json +2 -2
  43. run-6/checkpoint-272/tokenizer_config.json +1 -1
  44. run-6/checkpoint-272/trainer_state.json +39 -12
  45. run-6/checkpoint-272/training_args.bin +1 -1
  46. run-6/checkpoint-68/config.json +87 -0
  47. run-6/checkpoint-68/merges.txt +0 -0
  48. run-6/checkpoint-68/model.safetensors +3 -0
  49. run-6/checkpoint-68/optimizer.pt +3 -0
  50. run-6/checkpoint-68/rng_state.pth +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d69cb13fd2d8fdeab4fc14d97b5df2c7103232ecee077b6bc544cc617c7c31a
3
  size 498692800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24df4b297f9fa796d4993f1c3a655ab4472259e1580b2510586de3527689e7da
3
  size 498692800
run-5/checkpoint-272/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1,
48
+ "LABEL_10": 10,
49
+ "LABEL_11": 11,
50
+ "LABEL_12": 12,
51
+ "LABEL_13": 13,
52
+ "LABEL_14": 14,
53
+ "LABEL_15": 15,
54
+ "LABEL_16": 16,
55
+ "LABEL_17": 17,
56
+ "LABEL_18": 18,
57
+ "LABEL_19": 19,
58
+ "LABEL_2": 2,
59
+ "LABEL_20": 20,
60
+ "LABEL_21": 21,
61
+ "LABEL_22": 22,
62
+ "LABEL_23": 23,
63
+ "LABEL_24": 24,
64
+ "LABEL_25": 25,
65
+ "LABEL_26": 26,
66
+ "LABEL_27": 27,
67
+ "LABEL_3": 3,
68
+ "LABEL_4": 4,
69
+ "LABEL_5": 5,
70
+ "LABEL_6": 6,
71
+ "LABEL_7": 7,
72
+ "LABEL_8": 8,
73
+ "LABEL_9": 9
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "max_position_embeddings": 514,
77
+ "model_type": "roberta",
78
+ "num_attention_heads": 12,
79
+ "num_hidden_layers": 12,
80
+ "pad_token_id": 1,
81
+ "position_embedding_type": "absolute",
82
+ "torch_dtype": "float32",
83
+ "transformers_version": "4.35.2",
84
+ "type_vocab_size": 1,
85
+ "use_cache": true,
86
+ "vocab_size": 50265
87
+ }
run-5/checkpoint-272/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-272/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a33f8374f0b009669599ddd495aba375d673c547ceda3e1c14837ab4afa758
3
+ size 498692800
run-5/checkpoint-272/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ff2d2bfcfa54e192cf372585ea91c76ebb608da530976894325e4a16d9b212
3
+ size 997505402
run-5/checkpoint-272/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823b0a05c87e760485d9d141a1d80d22ad6f3a0c9d14baa34c611af6732e5309
3
+ size 14244
run-5/checkpoint-272/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c950336249eeab44c29e3dd0cf06efdbc4e8502eb7c2d477aade0a9d5f13c345
3
+ size 1064
run-5/checkpoint-272/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
run-5/checkpoint-272/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-272/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "do_lower_case": false,
49
+ "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 128,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
run-5/checkpoint-272/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-5/checkpoint-136",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 272,
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_f1": 0.0,
14
+ "eval_loss": 0.1628250777721405,
15
+ "eval_runtime": 1.768,
16
+ "eval_samples_per_second": 153.277,
17
+ "eval_steps_per_second": 1.131,
18
+ "step": 136
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.0,
23
+ "eval_loss": 0.15479044616222382,
24
+ "eval_runtime": 1.7694,
25
+ "eval_samples_per_second": 153.156,
26
+ "eval_steps_per_second": 1.13,
27
+ "step": 272
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 272,
32
+ "num_train_epochs": 2,
33
+ "save_steps": 500,
34
+ "total_flos": 0,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 2.4061789637885192e-05,
38
+ "num_train_epochs": 2,
39
+ "per_device_train_batch_size": 16,
40
+ "seed": 5
41
+ }
42
+ }
run-5/checkpoint-272/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e561920b0ab584c535b322f98226660fd2c79e91313f6c5e56d4ca00280fc3
3
+ size 4600
run-5/checkpoint-272/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-136/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1,
48
+ "LABEL_10": 10,
49
+ "LABEL_11": 11,
50
+ "LABEL_12": 12,
51
+ "LABEL_13": 13,
52
+ "LABEL_14": 14,
53
+ "LABEL_15": 15,
54
+ "LABEL_16": 16,
55
+ "LABEL_17": 17,
56
+ "LABEL_18": 18,
57
+ "LABEL_19": 19,
58
+ "LABEL_2": 2,
59
+ "LABEL_20": 20,
60
+ "LABEL_21": 21,
61
+ "LABEL_22": 22,
62
+ "LABEL_23": 23,
63
+ "LABEL_24": 24,
64
+ "LABEL_25": 25,
65
+ "LABEL_26": 26,
66
+ "LABEL_27": 27,
67
+ "LABEL_3": 3,
68
+ "LABEL_4": 4,
69
+ "LABEL_5": 5,
70
+ "LABEL_6": 6,
71
+ "LABEL_7": 7,
72
+ "LABEL_8": 8,
73
+ "LABEL_9": 9
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "max_position_embeddings": 514,
77
+ "model_type": "roberta",
78
+ "num_attention_heads": 12,
79
+ "num_hidden_layers": 12,
80
+ "pad_token_id": 1,
81
+ "position_embedding_type": "absolute",
82
+ "torch_dtype": "float32",
83
+ "transformers_version": "4.35.2",
84
+ "type_vocab_size": 1,
85
+ "use_cache": true,
86
+ "vocab_size": 50265
87
+ }
run-6/checkpoint-136/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-136/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d4f80f9793e83ad34de9d967d2991deab27b8e34c5def3d33e1594aaa84166
3
+ size 498692800
run-6/checkpoint-136/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5824c696cdfd89fb76098526cfcac2176baa740714d67e3cff6ae2fc18ff372
3
+ size 997505402
run-6/checkpoint-136/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48110f108e6a5c46c9507598e8bde0de764b16fafd8a07d876a0cf62355a332c
3
+ size 14308
run-6/checkpoint-136/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6a398aec080996e6a1b063886e28816554bddb4bb1071b4cf89cb31b63b27d
3
+ size 1064
run-6/checkpoint-136/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
run-6/checkpoint-136/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-136/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "do_lower_case": false,
49
+ "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 128,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
run-6/checkpoint-136/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-6/checkpoint-68",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 136,
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_f1": 0.0,
14
+ "eval_loss": 0.27623069286346436,
15
+ "eval_runtime": 1.7887,
16
+ "eval_samples_per_second": 151.505,
17
+ "eval_steps_per_second": 1.118,
18
+ "step": 68
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.0,
23
+ "eval_loss": 0.21532878279685974,
24
+ "eval_runtime": 1.7558,
25
+ "eval_samples_per_second": 154.348,
26
+ "eval_steps_per_second": 1.139,
27
+ "step": 136
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 340,
32
+ "num_train_epochs": 5,
33
+ "save_steps": 500,
34
+ "total_flos": 0,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 9.656231101012835e-06,
38
+ "num_train_epochs": 5,
39
+ "per_device_train_batch_size": 32,
40
+ "seed": 13
41
+ }
42
+ }
run-6/checkpoint-136/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a125737cc9b04c4061972a35907d68d87488b05a430e52db5906b8a58739987f
3
+ size 4600
run-6/checkpoint-136/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-204/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1,
48
+ "LABEL_10": 10,
49
+ "LABEL_11": 11,
50
+ "LABEL_12": 12,
51
+ "LABEL_13": 13,
52
+ "LABEL_14": 14,
53
+ "LABEL_15": 15,
54
+ "LABEL_16": 16,
55
+ "LABEL_17": 17,
56
+ "LABEL_18": 18,
57
+ "LABEL_19": 19,
58
+ "LABEL_2": 2,
59
+ "LABEL_20": 20,
60
+ "LABEL_21": 21,
61
+ "LABEL_22": 22,
62
+ "LABEL_23": 23,
63
+ "LABEL_24": 24,
64
+ "LABEL_25": 25,
65
+ "LABEL_26": 26,
66
+ "LABEL_27": 27,
67
+ "LABEL_3": 3,
68
+ "LABEL_4": 4,
69
+ "LABEL_5": 5,
70
+ "LABEL_6": 6,
71
+ "LABEL_7": 7,
72
+ "LABEL_8": 8,
73
+ "LABEL_9": 9
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "max_position_embeddings": 514,
77
+ "model_type": "roberta",
78
+ "num_attention_heads": 12,
79
+ "num_hidden_layers": 12,
80
+ "pad_token_id": 1,
81
+ "position_embedding_type": "absolute",
82
+ "torch_dtype": "float32",
83
+ "transformers_version": "4.35.2",
84
+ "type_vocab_size": 1,
85
+ "use_cache": true,
86
+ "vocab_size": 50265
87
+ }
run-6/checkpoint-204/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-204/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:951368aedb90f2b811cb85753dcdd207637783c1f31aa00810f63fa3bccf9fd0
3
+ size 498692800
run-6/checkpoint-204/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd76bf2a83f994330e0134ce397067df011e5be2eb2d9b9f79d380b47de4040d
3
+ size 997505402
run-6/checkpoint-204/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc14a5b892c07b34237a7c212063297e2616310add1966fef13fefce9e62437
3
+ size 14308
run-6/checkpoint-204/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1691de8e5d89384b5a01a9060f1d7c0c59dd0da9b4ea9811b0f1dbc7dc7e349
3
+ size 1064
run-6/checkpoint-204/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
run-6/checkpoint-204/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-204/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "do_lower_case": false,
49
+ "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 128,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
run-6/checkpoint-204/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-6/checkpoint-68",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 204,
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_f1": 0.0,
14
+ "eval_loss": 0.27623069286346436,
15
+ "eval_runtime": 1.7887,
16
+ "eval_samples_per_second": 151.505,
17
+ "eval_steps_per_second": 1.118,
18
+ "step": 68
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.0,
23
+ "eval_loss": 0.21532878279685974,
24
+ "eval_runtime": 1.7558,
25
+ "eval_samples_per_second": 154.348,
26
+ "eval_steps_per_second": 1.139,
27
+ "step": 136
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.0,
32
+ "eval_loss": 0.19268403947353363,
33
+ "eval_runtime": 1.769,
34
+ "eval_samples_per_second": 153.196,
35
+ "eval_steps_per_second": 1.131,
36
+ "step": 204
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 340,
41
+ "num_train_epochs": 5,
42
+ "save_steps": 500,
43
+ "total_flos": 0,
44
+ "trial_name": null,
45
+ "trial_params": {
46
+ "learning_rate": 9.656231101012835e-06,
47
+ "num_train_epochs": 5,
48
+ "per_device_train_batch_size": 32,
49
+ "seed": 13
50
+ }
51
+ }
run-6/checkpoint-204/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a125737cc9b04c4061972a35907d68d87488b05a430e52db5906b8a58739987f
3
+ size 4600
run-6/checkpoint-204/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-272/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b73dbfff76d25896418567d170743886cdad4d4f1d0ae47918f16e1a9e98d553
3
  size 498692800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24df4b297f9fa796d4993f1c3a655ab4472259e1580b2510586de3527689e7da
3
  size 498692800
run-6/checkpoint-272/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff197fe7ece3cb4afbcad8cb274537c7bce55ef6690484cce16d9c325f4a89be
3
  size 997505402
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:363fbebfa284d8cc54fafd67b32758d29d648ac6ca9f5967ccfd1e82b8cab4b0
3
  size 997505402
run-6/checkpoint-272/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8963118a7aaf4f81d375c22ec40cc54385266242f47882eda34f40a268bf65d3
3
  size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1395490277a30f2427a1fc55275bdbc591209f5a83c3f349e99a1f03b2975ce
3
  size 14308
run-6/checkpoint-272/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:653522563fa3a3592b7c4aabc6e929e927a5791729e025eeec9153ed873bc6bd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09b7d77263aa0a9bb24739a2c6e6452dfedbb4047ff897efcb64ba3ce4da6e2d
3
  size 1064
run-6/checkpoint-272/tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 64,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 64
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 128,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 128
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
run-6/checkpoint-272/tokenizer_config.json CHANGED
@@ -49,7 +49,7 @@
49
  "eos_token": "</s>",
50
  "errors": "replace",
51
  "mask_token": "<mask>",
52
- "model_max_length": 64,
53
  "pad_token": "<pad>",
54
  "sep_token": "</s>",
55
  "tokenizer_class": "RobertaTokenizer",
 
49
  "eos_token": "</s>",
50
  "errors": "replace",
51
  "mask_token": "<mask>",
52
+ "model_max_length": 128,
53
  "pad_token": "<pad>",
54
  "sep_token": "</s>",
55
  "tokenizer_class": "RobertaTokenizer",
run-6/checkpoint-272/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "best_metric": 0.0,
3
- "best_model_checkpoint": "roberta-base-finetuned/run-6/checkpoint-272",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 272,
7
  "is_hyper_param_search": true,
@@ -11,23 +11,50 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_f1": 0.0,
14
- "eval_loss": 0.22504137456417084,
15
- "eval_runtime": 7.2135,
16
- "eval_samples_per_second": 752.201,
17
- "eval_steps_per_second": 5.961,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  "step": 272
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 1088,
23
- "num_train_epochs": 4,
24
  "save_steps": 500,
25
  "total_flos": 0,
26
  "trial_name": null,
27
  "trial_params": {
28
- "learning_rate": 3.834659722691893e-06,
29
- "num_train_epochs": 4,
30
- "per_device_train_batch_size": 16,
31
- "seed": 8
32
  }
33
  }
 
1
  {
2
  "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-6/checkpoint-68",
4
+ "epoch": 4.0,
5
  "eval_steps": 500,
6
  "global_step": 272,
7
  "is_hyper_param_search": true,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_f1": 0.0,
14
+ "eval_loss": 0.27623069286346436,
15
+ "eval_runtime": 1.7887,
16
+ "eval_samples_per_second": 151.505,
17
+ "eval_steps_per_second": 1.118,
18
+ "step": 68
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.0,
23
+ "eval_loss": 0.21532878279685974,
24
+ "eval_runtime": 1.7558,
25
+ "eval_samples_per_second": 154.348,
26
+ "eval_steps_per_second": 1.139,
27
+ "step": 136
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.0,
32
+ "eval_loss": 0.19268403947353363,
33
+ "eval_runtime": 1.769,
34
+ "eval_samples_per_second": 153.196,
35
+ "eval_steps_per_second": 1.131,
36
+ "step": 204
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_f1": 0.0,
41
+ "eval_loss": 0.18309621512889862,
42
+ "eval_runtime": 1.7578,
43
+ "eval_samples_per_second": 154.173,
44
+ "eval_steps_per_second": 1.138,
45
  "step": 272
46
  }
47
  ],
48
  "logging_steps": 500,
49
+ "max_steps": 340,
50
+ "num_train_epochs": 5,
51
  "save_steps": 500,
52
  "total_flos": 0,
53
  "trial_name": null,
54
  "trial_params": {
55
+ "learning_rate": 9.656231101012835e-06,
56
+ "num_train_epochs": 5,
57
+ "per_device_train_batch_size": 32,
58
+ "seed": 13
59
  }
60
  }
run-6/checkpoint-272/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7eada57037d8586533658d8935ee7f22a0b7f7fd4c4a8bd928fa69ced67e2f1
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a125737cc9b04c4061972a35907d68d87488b05a430e52db5906b8a58739987f
3
  size 4600
run-6/checkpoint-68/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1,
48
+ "LABEL_10": 10,
49
+ "LABEL_11": 11,
50
+ "LABEL_12": 12,
51
+ "LABEL_13": 13,
52
+ "LABEL_14": 14,
53
+ "LABEL_15": 15,
54
+ "LABEL_16": 16,
55
+ "LABEL_17": 17,
56
+ "LABEL_18": 18,
57
+ "LABEL_19": 19,
58
+ "LABEL_2": 2,
59
+ "LABEL_20": 20,
60
+ "LABEL_21": 21,
61
+ "LABEL_22": 22,
62
+ "LABEL_23": 23,
63
+ "LABEL_24": 24,
64
+ "LABEL_25": 25,
65
+ "LABEL_26": 26,
66
+ "LABEL_27": 27,
67
+ "LABEL_3": 3,
68
+ "LABEL_4": 4,
69
+ "LABEL_5": 5,
70
+ "LABEL_6": 6,
71
+ "LABEL_7": 7,
72
+ "LABEL_8": 8,
73
+ "LABEL_9": 9
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "max_position_embeddings": 514,
77
+ "model_type": "roberta",
78
+ "num_attention_heads": 12,
79
+ "num_hidden_layers": 12,
80
+ "pad_token_id": 1,
81
+ "position_embedding_type": "absolute",
82
+ "torch_dtype": "float32",
83
+ "transformers_version": "4.35.2",
84
+ "type_vocab_size": 1,
85
+ "use_cache": true,
86
+ "vocab_size": 50265
87
+ }
run-6/checkpoint-68/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-68/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb194a90f64cdadaf0548defc82f3f9d42bcb3e01e68c650558cc65aaafe26df
3
+ size 498692800
run-6/checkpoint-68/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5de3f9a2fc39dc0aa541b3053ce17a42b08a2c097b88dabcf990b978add9b2e5
3
+ size 997505402
run-6/checkpoint-68/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af50c8be9865745d31c3ed67983d1179439e59589353b5e68f077457eee7cccc
3
+ size 14308