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
fcf16d4
·
1 Parent(s): 64cc59e

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-6/checkpoint-1088/config.json +87 -0
  3. run-6/checkpoint-1088/merges.txt +0 -0
  4. run-6/checkpoint-1088/model.safetensors +3 -0
  5. run-6/checkpoint-1088/optimizer.pt +3 -0
  6. run-6/checkpoint-1088/rng_state.pth +3 -0
  7. run-6/checkpoint-1088/scheduler.pt +3 -0
  8. run-6/checkpoint-1088/special_tokens_map.json +15 -0
  9. run-6/checkpoint-1088/tokenizer.json +0 -0
  10. run-6/checkpoint-1088/tokenizer_config.json +58 -0
  11. run-6/checkpoint-1088/trainer_state.json +72 -0
  12. run-6/checkpoint-1088/training_args.bin +3 -0
  13. run-6/checkpoint-1088/vocab.json +0 -0
  14. run-6/checkpoint-544/config.json +87 -0
  15. run-6/checkpoint-544/merges.txt +0 -0
  16. run-6/checkpoint-544/model.safetensors +3 -0
  17. run-6/checkpoint-544/optimizer.pt +3 -0
  18. run-6/checkpoint-544/rng_state.pth +3 -0
  19. run-6/checkpoint-544/scheduler.pt +3 -0
  20. run-6/checkpoint-544/special_tokens_map.json +15 -0
  21. run-6/checkpoint-544/tokenizer.json +0 -0
  22. run-6/checkpoint-544/tokenizer_config.json +58 -0
  23. run-6/checkpoint-544/trainer_state.json +48 -0
  24. run-6/checkpoint-544/training_args.bin +3 -0
  25. run-6/checkpoint-544/vocab.json +0 -0
  26. run-6/checkpoint-816/config.json +87 -0
  27. run-6/checkpoint-816/merges.txt +0 -0
  28. run-6/checkpoint-816/model.safetensors +3 -0
  29. run-6/checkpoint-816/optimizer.pt +3 -0
  30. run-6/checkpoint-816/rng_state.pth +3 -0
  31. run-6/checkpoint-816/scheduler.pt +3 -0
  32. run-6/checkpoint-816/special_tokens_map.json +15 -0
  33. run-6/checkpoint-816/tokenizer.json +0 -0
  34. run-6/checkpoint-816/tokenizer_config.json +58 -0
  35. run-6/checkpoint-816/trainer_state.json +57 -0
  36. run-6/checkpoint-816/training_args.bin +3 -0
  37. run-6/checkpoint-816/vocab.json +0 -0
  38. run-7/checkpoint-543/config.json +87 -0
  39. run-7/checkpoint-543/merges.txt +0 -0
  40. run-7/checkpoint-543/model.safetensors +3 -0
  41. run-7/checkpoint-543/optimizer.pt +3 -0
  42. run-7/checkpoint-543/rng_state.pth +3 -0
  43. run-7/checkpoint-543/scheduler.pt +3 -0
  44. run-7/checkpoint-543/special_tokens_map.json +15 -0
  45. run-7/checkpoint-543/tokenizer.json +0 -0
  46. run-7/checkpoint-543/tokenizer_config.json +58 -0
  47. run-7/checkpoint-543/trainer_state.json +39 -0
  48. run-7/checkpoint-543/training_args.bin +3 -0
  49. run-7/checkpoint-543/vocab.json +0 -0
  50. runs/Nov29_08-36-19_ba63dc4ccc8a/events.out.tfevents.1701250243.ba63dc4ccc8a.1291.30 +3 -0
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:b7a3449e8e890684fc08d8f3e279722b055660b6fd40b1f85e698643c5ac8003
3
  size 498692800
run-6/checkpoint-1088/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-1088/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-1088/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5037bbf74e7f37155bb4f4975bdc999c3c1cc7ba666ab9b0ff30d2e565fba93
3
+ size 498692800
run-6/checkpoint-1088/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a311064403c5ce5d4304ed6f5695e9b3620d258d4194ffae95966b0a4d6225b
3
+ size 997505402
run-6/checkpoint-1088/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748d3bfca3ad9ac13085e596565ee996594e77221ff78c2fae80219e62a6113b
3
+ size 14308
run-6/checkpoint-1088/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e90241dd7f49e3d079e0ca5db3a7344359537bac7eba09b18d8b7cd70798928
3
+ size 1064
run-6/checkpoint-1088/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-1088/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-1088/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-6/checkpoint-1088/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-6/checkpoint-272",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1088,
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": 0.22504137456417084,
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
+ "epoch": 1.84,
22
+ "learning_rate": 2.072408011895986e-06,
23
+ "loss": 0.2923,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_f1": 0.0,
29
+ "eval_loss": 0.18460310995578766,
30
+ "eval_runtime": 7.2932,
31
+ "eval_samples_per_second": 743.982,
32
+ "eval_steps_per_second": 5.896,
33
+ "step": 544
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_f1": 0.0,
38
+ "eval_loss": 0.17212247848510742,
39
+ "eval_runtime": 7.3993,
40
+ "eval_samples_per_second": 733.315,
41
+ "eval_steps_per_second": 5.811,
42
+ "step": 816
43
+ },
44
+ {
45
+ "epoch": 3.68,
46
+ "learning_rate": 3.101563011000796e-07,
47
+ "loss": 0.1813,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_f1": 0.0,
53
+ "eval_loss": 0.16888320446014404,
54
+ "eval_runtime": 7.2909,
55
+ "eval_samples_per_second": 744.216,
56
+ "eval_steps_per_second": 5.898,
57
+ "step": 1088
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1088,
62
+ "num_train_epochs": 4,
63
+ "save_steps": 500,
64
+ "total_flos": 536477094217728.0,
65
+ "trial_name": null,
66
+ "trial_params": {
67
+ "learning_rate": 3.834659722691893e-06,
68
+ "num_train_epochs": 4,
69
+ "per_device_train_batch_size": 16,
70
+ "seed": 8
71
+ }
72
+ }
run-6/checkpoint-1088/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7eada57037d8586533658d8935ee7f22a0b7f7fd4c4a8bd928fa69ced67e2f1
3
+ size 4600
run-6/checkpoint-1088/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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-6/checkpoint-544/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-544/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57789a94f32ed79a56c73114c9154bf530e1b552e00b160fa9dc4fb3204bb80f
3
+ size 498692800
run-6/checkpoint-544/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780335ad44874bd360f12e4b6894baea20527a7ca6ed61c168c877e81ea4e5d9
3
+ size 997505402
run-6/checkpoint-544/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ac7201827eeecdfca397fa160968b667f1f14b260f141d149f6a71ea87845b
3
+ size 14308
run-6/checkpoint-544/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1bd8bff79fc108d4de8073f0e7eeae39a6da2d555659f73196e6aea90865c7
3
+ size 1064
run-6/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-6/checkpoint-544/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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-6/checkpoint-544/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-6/checkpoint-272",
4
+ "epoch": 2.0,
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": 0.22504137456417084,
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
+ "epoch": 1.84,
22
+ "learning_rate": 2.072408011895986e-06,
23
+ "loss": 0.2923,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_f1": 0.0,
29
+ "eval_loss": 0.18460310995578766,
30
+ "eval_runtime": 7.2932,
31
+ "eval_samples_per_second": 743.982,
32
+ "eval_steps_per_second": 5.896,
33
+ "step": 544
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 1088,
38
+ "num_train_epochs": 4,
39
+ "save_steps": 500,
40
+ "total_flos": 274028341601280.0,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "learning_rate": 3.834659722691893e-06,
44
+ "num_train_epochs": 4,
45
+ "per_device_train_batch_size": 16,
46
+ "seed": 8
47
+ }
48
+ }
run-6/checkpoint-544/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7eada57037d8586533658d8935ee7f22a0b7f7fd4c4a8bd928fa69ced67e2f1
3
+ size 4600
run-6/checkpoint-544/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-816/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-816/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-816/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d213bf45d0dfd5f27f5b2e3a591f2bd3d8d013e652225abaccb5dd122b7ff8
3
+ size 498692800
run-6/checkpoint-816/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e694c0ac93670c94f44c509862b7d052aefe4819791a15244150ff1bc73657
3
+ size 997505402
run-6/checkpoint-816/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb907d901bbdfea7d120dd97d67a8b4d27bbc21b5cf3dfe229307f6e82892568
3
+ size 14308
run-6/checkpoint-816/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deddf15aefe572151a0308e48b75fe06f73afdfe042f05d0175a484516778d03
3
+ size 1064
run-6/checkpoint-816/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-816/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-816/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-6/checkpoint-816/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-6/checkpoint-272",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 816,
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": 0.22504137456417084,
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
+ "epoch": 1.84,
22
+ "learning_rate": 2.072408011895986e-06,
23
+ "loss": 0.2923,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_f1": 0.0,
29
+ "eval_loss": 0.18460310995578766,
30
+ "eval_runtime": 7.2932,
31
+ "eval_samples_per_second": 743.982,
32
+ "eval_steps_per_second": 5.896,
33
+ "step": 544
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_f1": 0.0,
38
+ "eval_loss": 0.17212247848510742,
39
+ "eval_runtime": 7.3993,
40
+ "eval_samples_per_second": 733.315,
41
+ "eval_steps_per_second": 5.811,
42
+ "step": 816
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 1088,
47
+ "num_train_epochs": 4,
48
+ "save_steps": 500,
49
+ "total_flos": 274028341601280.0,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "learning_rate": 3.834659722691893e-06,
53
+ "num_train_epochs": 4,
54
+ "per_device_train_batch_size": 16,
55
+ "seed": 8
56
+ }
57
+ }
run-6/checkpoint-816/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7eada57037d8586533658d8935ee7f22a0b7f7fd4c4a8bd928fa69ced67e2f1
3
+ size 4600
run-6/checkpoint-816/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-543/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-7/checkpoint-543/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-543/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a3449e8e890684fc08d8f3e279722b055660b6fd40b1f85e698643c5ac8003
3
+ size 498692800
run-7/checkpoint-543/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b18f78bd5f2b65a82687404e4dc97b7129b1bde508768823ac87b0422b57f9
3
+ size 997505402
run-7/checkpoint-543/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e24978152619ec15f6095e7483d283fe34357e052b745ae578f25262ebe065
3
+ size 14244
run-7/checkpoint-543/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bbc3a3aa06b42a3750a6eb1f7f625e4e288ede3f04f6c46d90b4e7c31d06755
3
+ size 1064
run-7/checkpoint-543/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-7/checkpoint-543/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-543/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-7/checkpoint-543/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-7/checkpoint-543",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 543,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.92,
13
+ "learning_rate": 1.1527630160580087e-06,
14
+ "loss": 0.4203,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_f1": 0.0,
20
+ "eval_loss": 0.24394913017749786,
21
+ "eval_runtime": 7.1324,
22
+ "eval_samples_per_second": 760.758,
23
+ "eval_steps_per_second": 6.029,
24
+ "step": 543
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 2715,
29
+ "num_train_epochs": 5,
30
+ "save_steps": 500,
31
+ "total_flos": 131586238464000.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "learning_rate": 1.4129804011726834e-06,
35
+ "num_train_epochs": 5,
36
+ "per_device_train_batch_size": 8,
37
+ "seed": 39
38
+ }
39
+ }
run-7/checkpoint-543/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d85a487b186b2ec09553cc5af5b6b832b2afbe566bfea82dd57b5a50d64e96
3
+ size 4600
run-7/checkpoint-543/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Nov29_08-36-19_ba63dc4ccc8a/events.out.tfevents.1701250243.ba63dc4ccc8a.1291.30 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8bfd3485d85c6aecf282386632e8610184f4445f93fea684c125dca078f5e7a
3
+ size 6369