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
2495de4
·
1 Parent(s): acf6433

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-2/checkpoint-272/config.json +87 -0
  3. run-2/checkpoint-272/merges.txt +0 -0
  4. run-2/checkpoint-272/model.safetensors +3 -0
  5. run-2/checkpoint-272/optimizer.pt +3 -0
  6. run-2/checkpoint-272/rng_state.pth +3 -0
  7. run-2/checkpoint-272/scheduler.pt +3 -0
  8. run-2/checkpoint-272/special_tokens_map.json +15 -0
  9. run-2/checkpoint-272/tokenizer.json +0 -0
  10. run-2/checkpoint-272/tokenizer_config.json +58 -0
  11. run-2/checkpoint-272/trainer_state.json +42 -0
  12. run-2/checkpoint-272/training_args.bin +3 -0
  13. run-2/checkpoint-272/vocab.json +0 -0
  14. run-2/checkpoint-408/config.json +87 -0
  15. run-2/checkpoint-408/merges.txt +0 -0
  16. run-2/checkpoint-408/model.safetensors +3 -0
  17. run-2/checkpoint-408/optimizer.pt +3 -0
  18. run-2/checkpoint-408/rng_state.pth +3 -0
  19. run-2/checkpoint-408/scheduler.pt +3 -0
  20. run-2/checkpoint-408/special_tokens_map.json +15 -0
  21. run-2/checkpoint-408/tokenizer.json +0 -0
  22. run-2/checkpoint-408/tokenizer_config.json +58 -0
  23. run-2/checkpoint-408/trainer_state.json +51 -0
  24. run-2/checkpoint-408/training_args.bin +3 -0
  25. run-2/checkpoint-408/vocab.json +0 -0
  26. run-2/checkpoint-544/config.json +87 -0
  27. run-2/checkpoint-544/merges.txt +0 -0
  28. run-2/checkpoint-544/model.safetensors +3 -0
  29. run-2/checkpoint-544/optimizer.pt +3 -0
  30. run-2/checkpoint-544/rng_state.pth +3 -0
  31. run-2/checkpoint-544/scheduler.pt +3 -0
  32. run-2/checkpoint-544/special_tokens_map.json +15 -0
  33. run-2/checkpoint-544/tokenizer.json +0 -0
  34. run-2/checkpoint-544/tokenizer_config.json +58 -0
  35. run-2/checkpoint-544/trainer_state.json +66 -0
  36. run-2/checkpoint-544/training_args.bin +3 -0
  37. run-2/checkpoint-544/vocab.json +0 -0
  38. run-3/checkpoint-272/model.safetensors +1 -1
  39. run-3/checkpoint-272/optimizer.pt +1 -1
  40. run-3/checkpoint-272/rng_state.pth +2 -2
  41. run-3/checkpoint-272/scheduler.pt +1 -1
  42. run-3/checkpoint-272/trainer_state.json +12 -21
  43. run-3/checkpoint-272/training_args.bin +1 -1
  44. run-3/checkpoint-544/model.safetensors +1 -1
  45. run-3/checkpoint-544/optimizer.pt +1 -1
  46. run-3/checkpoint-544/rng_state.pth +2 -2
  47. run-3/checkpoint-544/scheduler.pt +1 -1
  48. run-3/checkpoint-544/trainer_state.json +21 -39
  49. run-3/checkpoint-544/training_args.bin +1 -1
  50. runs/Nov29_08-36-19_ba63dc4ccc8a/events.out.tfevents.1701248867.ba63dc4ccc8a.1291.26 +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aa5bbd9d01dec8b7e71e53606089c393a6a8c958484b768f5305f75244aa175
3
  size 498692800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec49f3a0b2296e4d011156d27067cbc32d943744daa803b56c53b9ce1820e6d
3
  size 498692800
run-2/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-2/checkpoint-272/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-272/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46cd563207f13ad00c4a4136629b4acaddf357417a2d0781246bb9343bdf8fec
3
+ size 498692800
run-2/checkpoint-272/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61cc2bdaa84a6ff4d37e730529b3c96cd61ba11a87f74288b79ee1d7d0752f06
3
+ size 997505402
run-2/checkpoint-272/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:101860b7624c5970c96a2aa296cfb8a02d2094abd45875d9bdc5199e5b10d090
3
+ size 14308
run-2/checkpoint-272/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa33883d32685fe9296b90ccd40b6bd4c2bcd00a8e51580508490626d3e95a05
3
+ size 1064
run-2/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-2/checkpoint-272/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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": 64,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
run-2/checkpoint-272/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-2/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": 0.16469642519950867,
15
+ "eval_runtime": 7.1826,
16
+ "eval_samples_per_second": 755.433,
17
+ "eval_steps_per_second": 5.987,
18
+ "step": 136
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.0,
23
+ "eval_loss": 0.15205536782741547,
24
+ "eval_runtime": 7.2634,
25
+ "eval_samples_per_second": 747.028,
26
+ "eval_steps_per_second": 5.92,
27
+ "step": 272
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 544,
32
+ "num_train_epochs": 4,
33
+ "save_steps": 500,
34
+ "total_flos": 0,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 1.926138732305906e-05,
38
+ "num_train_epochs": 4,
39
+ "per_device_train_batch_size": 32,
40
+ "seed": 17
41
+ }
42
+ }
run-2/checkpoint-272/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ce51cd4ed85cb1b73361ac4ad1622b2a30b61996e1e2ff676bdd08f4451b31
3
+ size 4600
run-2/checkpoint-272/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-408/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-2/checkpoint-408/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-408/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b23c775983b2ac78067e9cc93bcdb74803afb3dabd4aea56ed787caa3a63375
3
+ size 498692800
run-2/checkpoint-408/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e093ef5a37cde1885f2cd13cd26049a9713d7291d5f5778f111ba1c07f7362
3
+ size 997505402
run-2/checkpoint-408/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ec960123b64d53301ab0c29adf76c1774104eed44f92e04822a5329ca86006
3
+ size 14308
run-2/checkpoint-408/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2322e78bbdb7c8ef9bf17a3b071e2a1c21041232209cfe5d068037d1a10f7fa0
3
+ size 1064
run-2/checkpoint-408/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-2/checkpoint-408/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-408/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": 64,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
run-2/checkpoint-408/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.004065676309616888,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-408",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 408,
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": 0.16469642519950867,
15
+ "eval_runtime": 7.1826,
16
+ "eval_samples_per_second": 755.433,
17
+ "eval_steps_per_second": 5.987,
18
+ "step": 136
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.0,
23
+ "eval_loss": 0.15205536782741547,
24
+ "eval_runtime": 7.2634,
25
+ "eval_samples_per_second": 747.028,
26
+ "eval_steps_per_second": 5.92,
27
+ "step": 272
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.004065676309616888,
32
+ "eval_loss": 0.14375817775726318,
33
+ "eval_runtime": 7.2392,
34
+ "eval_samples_per_second": 749.535,
35
+ "eval_steps_per_second": 5.94,
36
+ "step": 408
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 544,
41
+ "num_train_epochs": 4,
42
+ "save_steps": 500,
43
+ "total_flos": 0,
44
+ "trial_name": null,
45
+ "trial_params": {
46
+ "learning_rate": 1.926138732305906e-05,
47
+ "num_train_epochs": 4,
48
+ "per_device_train_batch_size": 32,
49
+ "seed": 17
50
+ }
51
+ }
run-2/checkpoint-408/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ce51cd4ed85cb1b73361ac4ad1622b2a30b61996e1e2ff676bdd08f4451b31
3
+ size 4600
run-2/checkpoint-408/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-544/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-2/checkpoint-544/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-544/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d06279b9d20621d0adfa9bd140405b4b8c77b92e56f32754e884054d0ef9cdcc
3
+ size 498692800
run-2/checkpoint-544/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:955dbecd318598578ff4f1871ea478ef2bf743749a6eec8a74ba760f464b6f10
3
+ size 997505402
run-2/checkpoint-544/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959bb0bf8818f5735f7f12101fb540108c71e5ef2b95632a65efa3cb17d48161
3
+ size 14308
run-2/checkpoint-544/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:192b1fd96dd73bebaac5316463458719eee3a1ea39f96327627fcc534568c37e
3
+ size 1064
run-2/checkpoint-544/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-2/checkpoint-544/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-544/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": 64,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
run-2/checkpoint-544/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.17824233255398156,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-544",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 544,
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": 0.16469642519950867,
15
+ "eval_runtime": 7.1826,
16
+ "eval_samples_per_second": 755.433,
17
+ "eval_steps_per_second": 5.987,
18
+ "step": 136
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.0,
23
+ "eval_loss": 0.15205536782741547,
24
+ "eval_runtime": 7.2634,
25
+ "eval_samples_per_second": 747.028,
26
+ "eval_steps_per_second": 5.92,
27
+ "step": 272
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.004065676309616888,
32
+ "eval_loss": 0.14375817775726318,
33
+ "eval_runtime": 7.2392,
34
+ "eval_samples_per_second": 749.535,
35
+ "eval_steps_per_second": 5.94,
36
+ "step": 408
37
+ },
38
+ {
39
+ "epoch": 3.68,
40
+ "learning_rate": 1.5579063276003652e-06,
41
+ "loss": 0.1843,
42
+ "step": 500
43
+ },
44
+ {
45
+ "epoch": 4.0,
46
+ "eval_f1": 0.17824233255398156,
47
+ "eval_loss": 0.14139315485954285,
48
+ "eval_runtime": 7.244,
49
+ "eval_samples_per_second": 749.033,
50
+ "eval_steps_per_second": 5.936,
51
+ "step": 544
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 544,
56
+ "num_train_epochs": 4,
57
+ "save_steps": 500,
58
+ "total_flos": 525259367388672.0,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "learning_rate": 1.926138732305906e-05,
62
+ "num_train_epochs": 4,
63
+ "per_device_train_batch_size": 32,
64
+ "seed": 17
65
+ }
66
+ }
run-2/checkpoint-544/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ce51cd4ed85cb1b73361ac4ad1622b2a30b61996e1e2ff676bdd08f4451b31
3
+ size 4600
run-2/checkpoint-544/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-272/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6434569cc25d7f86049ae7741255382edabf8fa518264194f349a4b17368b41
3
  size 498692800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec49f3a0b2296e4d011156d27067cbc32d943744daa803b56c53b9ce1820e6d
3
  size 498692800
run-3/checkpoint-272/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:197e099168db276ce460eb8a6dce54bbcc5341a7677ffbbb5e6fe73c252bfc5e
3
  size 997505402
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32802688230b2cca3f9e1a0a1db0bc0970bbc4a8132be3d86b2b86d3fd76da43
3
  size 997505402
run-3/checkpoint-272/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b32da7cbe3b600fd2457c969a5edd70b3539ce1948e49ebd6329cab0bb764a6a
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7627164f6a838ab6071d3af2f4c07c4ae2a8a7750ab699aa23e9b7b2754037c0
3
+ size 14244
run-3/checkpoint-272/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d32047097ae2473850fc82af0458d66a4a7f517b83f45933631d8c2235a15bb2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cbb06ded40b0bac91743e26822e9c4748c00cbfadf00fae5289f79eb8b9670d
3
  size 1064
run-3/checkpoint-272/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "best_metric": 0.0,
3
- "best_model_checkpoint": "roberta-base-finetuned/run-3/checkpoint-136",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 272,
7
  "is_hyper_param_search": true,
@@ -11,32 +11,23 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_f1": 0.0,
14
- "eval_loss": 0.2652469873428345,
15
- "eval_runtime": 7.1726,
16
- "eval_samples_per_second": 756.494,
17
- "eval_steps_per_second": 5.995,
18
- "step": 136
19
- },
20
- {
21
- "epoch": 2.0,
22
- "eval_f1": 0.0,
23
- "eval_loss": 0.2119114100933075,
24
- "eval_runtime": 7.1722,
25
- "eval_samples_per_second": 756.534,
26
- "eval_steps_per_second": 5.995,
27
  "step": 272
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 544,
32
- "num_train_epochs": 4,
33
  "save_steps": 500,
34
  "total_flos": 0,
35
  "trial_name": null,
36
  "trial_params": {
37
- "learning_rate": 5.397452827124417e-06,
38
- "num_train_epochs": 4,
39
- "per_device_train_batch_size": 32,
40
- "seed": 31
41
  }
42
  }
 
1
  {
2
  "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-3/checkpoint-272",
4
+ "epoch": 1.0,
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": 0.2641439437866211,
15
+ "eval_runtime": 7.1825,
16
+ "eval_samples_per_second": 755.446,
17
+ "eval_steps_per_second": 5.987,
 
 
 
 
 
 
 
 
 
18
  "step": 272
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 1360,
23
+ "num_train_epochs": 5,
24
  "save_steps": 500,
25
  "total_flos": 0,
26
  "trial_name": null,
27
  "trial_params": {
28
+ "learning_rate": 2.4573800348719033e-06,
29
+ "num_train_epochs": 5,
30
+ "per_device_train_batch_size": 16,
31
+ "seed": 4
32
  }
33
  }
run-3/checkpoint-272/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d637b1a3992216bd20d5154e652d7b76a207e651e512412a90c5c093c69e77f
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedcfdbe7c29e6f37dca0518c3a22279de6ad973240451544d5c9e7a0a75ce08
3
  size 4600
run-3/checkpoint-544/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:638ac615b1c5b44c87ed34654616c8e0acb5dd98e27ec55b4fe2fc58aca5c930
3
  size 498692800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdfce8f3032cbd8c4b0d74efef2735f8539055bec09a2233011c4eb0d661e48f
3
  size 498692800
run-3/checkpoint-544/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f23a0fa606516f4132ee3335ad7baeaa1652985f8f1b65e0572f98d98c0fbcd
3
  size 997505402
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24a56a0800a902724dc7c0b7f22b58754ff27f598a27152cb285236b7902db9
3
  size 997505402
run-3/checkpoint-544/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7de9e0ab1219ccc503123b8db841ec73510fd83da46358e56fdaba48b1908daf
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d8096c7b42f07796058e655ef84962bca1678f371ed9f7de40e1ebded0bb8e
3
+ size 14244
run-3/checkpoint-544/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c8c6b03dc187cd039317a54f71eaeebd325f09b8013b6b13be3cebff7431f2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f0956cfc7c916e4166a8d12e1f1101bc4cdef22391f28eb944635360adca66
3
  size 1064
run-3/checkpoint-544/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "best_metric": 0.0,
3
- "best_model_checkpoint": "roberta-base-finetuned/run-3/checkpoint-136",
4
- "epoch": 4.0,
5
  "eval_steps": 500,
6
  "global_step": 544,
7
  "is_hyper_param_search": true,
@@ -11,56 +11,38 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_f1": 0.0,
14
- "eval_loss": 0.2652469873428345,
15
- "eval_runtime": 7.1726,
16
- "eval_samples_per_second": 756.494,
17
- "eval_steps_per_second": 5.995,
18
- "step": 136
19
- },
20
- {
21
- "epoch": 2.0,
22
- "eval_f1": 0.0,
23
- "eval_loss": 0.2119114100933075,
24
- "eval_runtime": 7.1722,
25
- "eval_samples_per_second": 756.534,
26
- "eval_steps_per_second": 5.995,
27
  "step": 272
28
  },
29
  {
30
- "epoch": 3.0,
31
- "eval_f1": 0.0,
32
- "eval_loss": 0.1938687562942505,
33
- "eval_runtime": 7.5895,
34
- "eval_samples_per_second": 714.934,
35
- "eval_steps_per_second": 5.666,
36
- "step": 408
37
- },
38
- {
39
- "epoch": 3.68,
40
- "learning_rate": 4.365586845468279e-07,
41
- "loss": 0.2783,
42
  "step": 500
43
  },
44
  {
45
- "epoch": 4.0,
46
  "eval_f1": 0.0,
47
- "eval_loss": 0.18911533057689667,
48
- "eval_runtime": 7.2038,
49
- "eval_samples_per_second": 753.216,
50
- "eval_steps_per_second": 5.969,
51
  "step": 544
52
  }
53
  ],
54
  "logging_steps": 500,
55
- "max_steps": 544,
56
- "num_train_epochs": 4,
57
  "save_steps": 500,
58
- "total_flos": 525259367388672.0,
59
  "trial_name": null,
60
  "trial_params": {
61
- "learning_rate": 5.397452827124417e-06,
62
- "num_train_epochs": 4,
63
- "per_device_train_batch_size": 32,
64
- "seed": 31
65
  }
66
  }
 
1
  {
2
  "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-3/checkpoint-272",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 544,
7
  "is_hyper_param_search": true,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_f1": 0.0,
14
+ "eval_loss": 0.2641439437866211,
15
+ "eval_runtime": 7.1825,
16
+ "eval_samples_per_second": 755.446,
17
+ "eval_steps_per_second": 5.987,
 
 
 
 
 
 
 
 
 
18
  "step": 272
19
  },
20
  {
21
+ "epoch": 1.84,
22
+ "learning_rate": 1.5539314926395858e-06,
23
+ "loss": 0.3433,
 
 
 
 
 
 
 
 
 
24
  "step": 500
25
  },
26
  {
27
+ "epoch": 2.0,
28
  "eval_f1": 0.0,
29
+ "eval_loss": 0.21300381422042847,
30
+ "eval_runtime": 7.2308,
31
+ "eval_samples_per_second": 750.406,
32
+ "eval_steps_per_second": 5.947,
33
  "step": 544
34
  }
35
  ],
36
  "logging_steps": 500,
37
+ "max_steps": 1360,
38
+ "num_train_epochs": 5,
39
  "save_steps": 500,
40
+ "total_flos": 262810614772224.0,
41
  "trial_name": null,
42
  "trial_params": {
43
+ "learning_rate": 2.4573800348719033e-06,
44
+ "num_train_epochs": 5,
45
+ "per_device_train_batch_size": 16,
46
+ "seed": 4
47
  }
48
  }
run-3/checkpoint-544/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d637b1a3992216bd20d5154e652d7b76a207e651e512412a90c5c093c69e77f
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedcfdbe7c29e6f37dca0518c3a22279de6ad973240451544d5c9e7a0a75ce08
3
  size 4600
runs/Nov29_08-36-19_ba63dc4ccc8a/events.out.tfevents.1701248867.ba63dc4ccc8a.1291.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d5d2a0b05a38e8bc51baa184352d32132def18ae0d12be19896ad579581090
3
+ size 7674