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
7059176
·
1 Parent(s): 5e8183f

Training in progress, epoch 1

Browse files
Files changed (35) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-102/config.json +87 -0
  3. run-5/checkpoint-102/merges.txt +0 -0
  4. run-5/checkpoint-102/model.safetensors +3 -0
  5. run-5/checkpoint-102/optimizer.pt +3 -0
  6. run-5/checkpoint-102/rng_state.pth +3 -0
  7. run-5/checkpoint-102/scheduler.pt +3 -0
  8. run-5/checkpoint-102/special_tokens_map.json +15 -0
  9. run-5/checkpoint-102/tokenizer.json +0 -0
  10. run-5/checkpoint-102/tokenizer_config.json +58 -0
  11. run-5/checkpoint-102/trainer_state.json +51 -0
  12. run-5/checkpoint-102/training_args.bin +3 -0
  13. run-5/checkpoint-102/vocab.json +0 -0
  14. run-5/checkpoint-68/config.json +87 -0
  15. run-5/checkpoint-68/merges.txt +0 -0
  16. run-5/checkpoint-68/model.safetensors +3 -0
  17. run-5/checkpoint-68/optimizer.pt +3 -0
  18. run-5/checkpoint-68/rng_state.pth +3 -0
  19. run-5/checkpoint-68/scheduler.pt +3 -0
  20. run-5/checkpoint-68/special_tokens_map.json +15 -0
  21. run-5/checkpoint-68/tokenizer.json +0 -0
  22. run-5/checkpoint-68/tokenizer_config.json +58 -0
  23. run-5/checkpoint-68/trainer_state.json +42 -0
  24. run-5/checkpoint-68/training_args.bin +3 -0
  25. run-5/checkpoint-68/vocab.json +0 -0
  26. run-8/checkpoint-68/model.safetensors +1 -1
  27. run-8/checkpoint-68/optimizer.pt +1 -1
  28. run-8/checkpoint-68/rng_state.pth +1 -1
  29. run-8/checkpoint-68/scheduler.pt +1 -1
  30. run-8/checkpoint-68/trainer_state.json +14 -23
  31. run-8/checkpoint-68/training_args.bin +1 -1
  32. runs/Dec02_00-42-23_dee53d4911c1/events.out.tfevents.1701479699.dee53d4911c1.2599.6 +3 -0
  33. runs/Dec02_00-42-23_dee53d4911c1/events.out.tfevents.1701479753.dee53d4911c1.2599.7 +3 -0
  34. runs/Dec02_00-42-23_dee53d4911c1/events.out.tfevents.1701479814.dee53d4911c1.2599.8 +3 -0
  35. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b33ec426cfd02bf378f44eb294e444be5835714acb961c82eae85bede3b52cc5
3
  size 498692800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d499dcbbb1c13a7f2117fbed7ff560f2d63a9c25bcac26a0808a9d2e3dccc7
3
  size 498692800
run-5/checkpoint-102/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-102/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-102/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8b3e39a0831827b44479057e04b173f4f7db77b7af835d8a301c3b914df80ba
3
+ size 498692800
run-5/checkpoint-102/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a66087603151f7092036beb70e88ec148f607c7dea7d4406ca023bb2f5ecca6
3
+ size 997505402
run-5/checkpoint-102/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2374225f5f4919e76243b3e54f3a6caa3cb1c9af1cfa1b8c34133b3b3df74881
3
+ size 14244
run-5/checkpoint-102/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77982933524cbe87699ed932b3935d3e6bdb50a26ece989c13d8e9ea22d03f4a
3
+ size 1064
run-5/checkpoint-102/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-102/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-102/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-102/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.17727272727272728,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-5/checkpoint-102",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 102,
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": 0.11453362255965294,
14
+ "eval_loss": 0.658923864364624,
15
+ "eval_runtime": 1.9095,
16
+ "eval_samples_per_second": 141.922,
17
+ "eval_steps_per_second": 1.047,
18
+ "step": 34
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.1654601861427094,
23
+ "eval_loss": 0.5335023403167725,
24
+ "eval_runtime": 1.9358,
25
+ "eval_samples_per_second": 139.991,
26
+ "eval_steps_per_second": 1.033,
27
+ "step": 68
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.17727272727272728,
32
+ "eval_loss": 0.48925167322158813,
33
+ "eval_runtime": 1.9124,
34
+ "eval_samples_per_second": 141.703,
35
+ "eval_steps_per_second": 1.046,
36
+ "step": 102
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 102,
41
+ "num_train_epochs": 3,
42
+ "save_steps": 500,
43
+ "total_flos": 0,
44
+ "trial_name": null,
45
+ "trial_params": {
46
+ "learning_rate": 2.5977656724527755e-06,
47
+ "num_train_epochs": 3,
48
+ "per_device_train_batch_size": 64,
49
+ "seed": 18
50
+ }
51
+ }
run-5/checkpoint-102/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8305cf5973378f6c2a1e58633c4ba54a59139308f5fc01c583f9453884a5a6
3
+ size 4600
run-5/checkpoint-102/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/checkpoint-68/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-68/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e94ad2a64ebc3a42cacbbf0caa2cb6dd5942aa1d5f5f23baf28d32a1ee28196
3
+ size 498692800
run-5/checkpoint-68/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2589e4a14aca6cbdcd93058351620d7abf1abd044f2b7d7eb5bd623e5f5e29e2
3
+ size 997505402
run-5/checkpoint-68/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a1920f6201d5f19118ace70fbb32ca05a5db223a4b8685b778ce901adfda85c
3
+ size 14244
run-5/checkpoint-68/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d501e346ff7e8f9152722dc94982a5d9a0ce074659a906056cdc3953ec2eb8ea
3
+ size 1064
run-5/checkpoint-68/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-68/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-68/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-68/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1654601861427094,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-5/checkpoint-68",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 68,
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": 0.11453362255965294,
14
+ "eval_loss": 0.658923864364624,
15
+ "eval_runtime": 1.9095,
16
+ "eval_samples_per_second": 141.922,
17
+ "eval_steps_per_second": 1.047,
18
+ "step": 34
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.1654601861427094,
23
+ "eval_loss": 0.5335023403167725,
24
+ "eval_runtime": 1.9358,
25
+ "eval_samples_per_second": 139.991,
26
+ "eval_steps_per_second": 1.033,
27
+ "step": 68
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 102,
32
+ "num_train_epochs": 3,
33
+ "save_steps": 500,
34
+ "total_flos": 0,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 2.5977656724527755e-06,
38
+ "num_train_epochs": 3,
39
+ "per_device_train_batch_size": 64,
40
+ "seed": 18
41
+ }
42
+ }
run-5/checkpoint-68/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8305cf5973378f6c2a1e58633c4ba54a59139308f5fc01c583f9453884a5a6
3
+ size 4600
run-5/checkpoint-68/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-68/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b83caa9613d72d938746fc4ec3b412661cc5a6c3577a06ce72f90bd3842a6c50
3
  size 498692800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d499dcbbb1c13a7f2117fbed7ff560f2d63a9c25bcac26a0808a9d2e3dccc7
3
  size 498692800
run-8/checkpoint-68/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c13ba73f47dd010a250398f5d20892a32fe80a748dc9b9dcbb459068aab66c7d
3
  size 997505402
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30de3c6396c51934a2faff9860f63ecf2a9cea7a7d34556997b427dd3b3a1223
3
  size 997505402
run-8/checkpoint-68/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a24218243d1ccb016ce89308b023a87c568b2d6773cc34be6d4269e217a0a38b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbdf4b99ba4ac03634cf5eeac7de87c1f1f1b80a6cbdd5110c52ee8ac52f484d
3
  size 14244
run-8/checkpoint-68/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e7c294e270b84a3a02cdb577c3f402d881d914590745be08017a8d6a1309089
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceaf8ab0c789c635126d95046e8b5984c519b75c66f7ffe1ce78d75e35ae39cc
3
  size 1064
run-8/checkpoint-68/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.04377880184331797,
3
- "best_model_checkpoint": "roberta-base-finetuned/run-8/checkpoint-34",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 68,
7
  "is_hyper_param_search": true,
@@ -10,33 +10,24 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_f1": 0.04377880184331797,
14
- "eval_loss": 0.5592500567436218,
15
- "eval_runtime": 1.7744,
16
- "eval_samples_per_second": 152.723,
17
- "eval_steps_per_second": 1.127,
18
- "step": 34
19
- },
20
- {
21
- "epoch": 2.0,
22
- "eval_f1": 0.0,
23
- "eval_loss": 0.4034463167190552,
24
- "eval_runtime": 1.7797,
25
- "eval_samples_per_second": 152.272,
26
- "eval_steps_per_second": 1.124,
27
  "step": 68
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 102,
32
- "num_train_epochs": 3,
33
  "save_steps": 500,
34
  "total_flos": 0,
35
  "trial_name": null,
36
  "trial_params": {
37
- "learning_rate": 4.8351875015937635e-06,
38
- "num_train_epochs": 3,
39
- "per_device_train_batch_size": 64,
40
- "seed": 5
41
  }
42
  }
 
1
  {
2
+ "best_metric": 0.24291497975708504,
3
+ "best_model_checkpoint": "roberta-base-finetuned/run-8/checkpoint-68",
4
+ "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 68,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_f1": 0.24291497975708504,
14
+ "eval_loss": 0.43356165289878845,
15
+ "eval_runtime": 1.8995,
16
+ "eval_samples_per_second": 142.671,
17
+ "eval_steps_per_second": 1.053,
 
 
 
 
 
 
 
 
 
18
  "step": 68
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 136,
23
+ "num_train_epochs": 2,
24
  "save_steps": 500,
25
  "total_flos": 0,
26
  "trial_name": null,
27
  "trial_params": {
28
+ "learning_rate": 3.402910583353012e-06,
29
+ "num_train_epochs": 2,
30
+ "per_device_train_batch_size": 32,
31
+ "seed": 16
32
  }
33
  }
run-8/checkpoint-68/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afa99ccabeea36db44e1ab6cb39e76a8e71734feff3d6d93dc85a8b98a00aa7d
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5216db630c0a9fb7db1f143b7369f9ca9a1e350c57e0375e6a821a75b05d3a6
3
  size 4600
runs/Dec02_00-42-23_dee53d4911c1/events.out.tfevents.1701479699.dee53d4911c1.2599.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7132aea2b49960a3a44178ed0d164f30a23740dacef39c57c39d8641b952d515
3
+ size 5738
runs/Dec02_00-42-23_dee53d4911c1/events.out.tfevents.1701479753.dee53d4911c1.2599.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bda58e54f643f64c0118f7ed0bff512df6bb6a027935bd50201e78ede01b890
3
+ size 5737
runs/Dec02_00-42-23_dee53d4911c1/events.out.tfevents.1701479814.dee53d4911c1.2599.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131e6756c350e41e40ce25f156d05433bf5cf6bd847ea30660583d0e9a9f08f5
3
+ size 6403
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab8305cf5973378f6c2a1e58633c4ba54a59139308f5fc01c583f9453884a5a6
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5216db630c0a9fb7db1f143b7369f9ca9a1e350c57e0375e6a821a75b05d3a6
3
  size 4600