Hugging Face's logo

youralien
/
roberta-suggestions-badareas

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
youralien commited on
Commit
67538f2
·
verified ·
1 Parent(s): 203c450

Upload trained RoBERTa model

Browse files
Files changed (33) hide show
  1. README.md +76 -0
  2. checkpoint-1038/config.json +35 -0
  3. checkpoint-1038/merges.txt +0 -0
  4. checkpoint-1038/model.safetensors +3 -0
  5. checkpoint-1038/optimizer.pt +3 -0
  6. checkpoint-1038/rng_state.pth +3 -0
  7. checkpoint-1038/scheduler.pt +3 -0
  8. checkpoint-1038/special_tokens_map.json +15 -0
  9. checkpoint-1038/tokenizer.json +0 -0
  10. checkpoint-1038/tokenizer_config.json +58 -0
  11. checkpoint-1038/trainer_state.json +147 -0
  12. checkpoint-1038/training_args.bin +3 -0
  13. checkpoint-1038/vocab.json +0 -0
  14. checkpoint-1730/config.json +35 -0
  15. checkpoint-1730/merges.txt +0 -0
  16. checkpoint-1730/model.safetensors +3 -0
  17. checkpoint-1730/optimizer.pt +3 -0
  18. checkpoint-1730/rng_state.pth +3 -0
  19. checkpoint-1730/scheduler.pt +3 -0
  20. checkpoint-1730/special_tokens_map.json +15 -0
  21. checkpoint-1730/tokenizer.json +0 -0
  22. checkpoint-1730/tokenizer_config.json +58 -0
  23. checkpoint-1730/trainer_state.json +223 -0
  24. checkpoint-1730/training_args.bin +3 -0
  25. checkpoint-1730/vocab.json +0 -0
  26. config.json +35 -0
  27. merges.txt +0 -0
  28. model.safetensors +3 -0
  29. special_tokens_map.json +15 -0
  30. tokenizer.json +0 -0
  31. tokenizer_config.json +58 -0
  32. training_args.bin +3 -0
  33. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: FacebookAI/roberta-large
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - precision
10
+ - recall
11
+ - f1
12
+ model-index:
13
+ - name: roberta-Suggestions-badareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # roberta-Suggestions-badareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current
21
+
22
+ This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.2266
25
+ - Accuracy: 0.9294
26
+ - Precision: 0.5949
27
+ - Recall: 0.6714
28
+ - F1: 0.6309
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 6.024651483074167e-06
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 10
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
+ | 0.4316 | 1.0 | 173 | 0.1817 | 0.9101 | 0.0 | 0.0 | 0.0 |
60
+ | 0.2745 | 2.0 | 346 | 0.0870 | 0.9307 | 0.6905 | 0.4143 | 0.5179 |
61
+ | 0.2084 | 3.0 | 519 | 0.1992 | 0.9178 | 0.5288 | 0.7857 | 0.6322 |
62
+ | 0.1754 | 4.0 | 692 | 0.1870 | 0.9166 | 0.5248 | 0.7571 | 0.6199 |
63
+ | 0.1493 | 5.0 | 865 | 0.1543 | 0.9384 | 0.6618 | 0.6429 | 0.6522 |
64
+ | 0.1623 | 6.0 | 1038 | 0.1471 | 0.9409 | 0.6622 | 0.7 | 0.6806 |
65
+ | 0.13 | 7.0 | 1211 | 0.1875 | 0.9307 | 0.5976 | 0.7 | 0.6447 |
66
+ | 0.1037 | 8.0 | 1384 | 0.2628 | 0.9243 | 0.5591 | 0.7429 | 0.6380 |
67
+ | 0.1226 | 9.0 | 1557 | 0.2113 | 0.9294 | 0.5974 | 0.6571 | 0.6259 |
68
+ | 0.0893 | 10.0 | 1730 | 0.2266 | 0.9294 | 0.5949 | 0.6714 | 0.6309 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.48.3
74
+ - Pytorch 2.5.1+cu124
75
+ - Datasets 2.21.0
76
+ - Tokenizers 0.21.0
checkpoint-1038/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-large",
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": 1024,
13
+ "id2label": {
14
+ "0": "not selected",
15
+ "1": "selected"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "not selected": "0",
21
+ "selected": "1"
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 16,
27
+ "num_hidden_layers": 24,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.48.3",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 50265
35
+ }
checkpoint-1038/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1038/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f29e2bc4b7bd126d3baa29b63a151f2df802ecbefde7309ea1af97b9c30d7b4
3
+ size 1421495416
checkpoint-1038/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95dc3d3544f2eb30b89971d61e0a4ff63e89e530527641563d8184dc2059fb95
3
+ size 2843228717
checkpoint-1038/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f29f11a3bdb0e8c2ae5232c63fcc3c794887ef34474c3f670c9e55ca910d0e
3
+ size 14244
checkpoint-1038/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff6210ab8d1951dd081bb82165092397aa09778d8e5b21a5764e40179a641852
3
+ size 1064
checkpoint-1038/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
+ }
checkpoint-1038/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1038/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": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
checkpoint-1038/trainer_state.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6805555555555556,
3
+ "best_model_checkpoint": "roberta-Suggestions-badareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-1038",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1038,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 13.059974670410156,
14
+ "learning_rate": 5.4221863347667504e-06,
15
+ "loss": 0.4316,
16
+ "step": 173
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.9101412066752247,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.1816691905260086,
23
+ "eval_precision": 0.0,
24
+ "eval_recall": 0.0,
25
+ "eval_runtime": 5.9222,
26
+ "eval_samples_per_second": 131.539,
27
+ "eval_steps_per_second": 8.274,
28
+ "step": 173
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 16.06458854675293,
33
+ "learning_rate": 4.8197211864593334e-06,
34
+ "loss": 0.2745,
35
+ "step": 346
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.9306803594351734,
40
+ "eval_f1": 0.5178571428571429,
41
+ "eval_loss": 0.08700571209192276,
42
+ "eval_precision": 0.6904761904761905,
43
+ "eval_recall": 0.4142857142857143,
44
+ "eval_runtime": 5.9611,
45
+ "eval_samples_per_second": 130.681,
46
+ "eval_steps_per_second": 8.22,
47
+ "step": 346
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 1.4951728582382202,
52
+ "learning_rate": 4.2172560381519165e-06,
53
+ "loss": 0.2084,
54
+ "step": 519
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.9178433889602053,
59
+ "eval_f1": 0.632183908045977,
60
+ "eval_loss": 0.19922904670238495,
61
+ "eval_precision": 0.5288461538461539,
62
+ "eval_recall": 0.7857142857142857,
63
+ "eval_runtime": 6.1312,
64
+ "eval_samples_per_second": 127.056,
65
+ "eval_steps_per_second": 7.992,
66
+ "step": 519
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 20.864402770996094,
71
+ "learning_rate": 3.6147908898445e-06,
72
+ "loss": 0.1754,
73
+ "step": 692
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.9165596919127086,
78
+ "eval_f1": 0.6198830409356725,
79
+ "eval_loss": 0.18699409067630768,
80
+ "eval_precision": 0.5247524752475248,
81
+ "eval_recall": 0.7571428571428571,
82
+ "eval_runtime": 5.9026,
83
+ "eval_samples_per_second": 131.975,
84
+ "eval_steps_per_second": 8.301,
85
+ "step": 692
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 5.5924787521362305,
90
+ "learning_rate": 3.0123257415370833e-06,
91
+ "loss": 0.1493,
92
+ "step": 865
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.938382541720154,
97
+ "eval_f1": 0.6521739130434783,
98
+ "eval_loss": 0.15427254140377045,
99
+ "eval_precision": 0.6617647058823529,
100
+ "eval_recall": 0.6428571428571429,
101
+ "eval_runtime": 6.303,
102
+ "eval_samples_per_second": 123.592,
103
+ "eval_steps_per_second": 7.774,
104
+ "step": 865
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 49.685874938964844,
109
+ "learning_rate": 2.4098605932296667e-06,
110
+ "loss": 0.1623,
111
+ "step": 1038
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.9409499358151476,
116
+ "eval_f1": 0.6805555555555556,
117
+ "eval_loss": 0.14713026583194733,
118
+ "eval_precision": 0.6621621621621622,
119
+ "eval_recall": 0.7,
120
+ "eval_runtime": 6.2307,
121
+ "eval_samples_per_second": 125.026,
122
+ "eval_steps_per_second": 7.864,
123
+ "step": 1038
124
+ }
125
+ ],
126
+ "logging_steps": 100,
127
+ "max_steps": 1730,
128
+ "num_input_tokens_seen": 0,
129
+ "num_train_epochs": 10,
130
+ "save_steps": 500,
131
+ "stateful_callbacks": {
132
+ "TrainerControl": {
133
+ "args": {
134
+ "should_epoch_stop": false,
135
+ "should_evaluate": false,
136
+ "should_log": false,
137
+ "should_save": true,
138
+ "should_training_stop": false
139
+ },
140
+ "attributes": {}
141
+ }
142
+ },
143
+ "total_flos": 1.4226944280416784e+16,
144
+ "train_batch_size": 16,
145
+ "trial_name": null,
146
+ "trial_params": null
147
+ }
checkpoint-1038/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33cc3f71c709f06cbe1dbf09a19d8b32c093875b9b75281dad04588c3f6dee97
3
+ size 5496
checkpoint-1038/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1730/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-large",
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": 1024,
13
+ "id2label": {
14
+ "0": "not selected",
15
+ "1": "selected"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "not selected": "0",
21
+ "selected": "1"
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 16,
27
+ "num_hidden_layers": 24,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.48.3",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 50265
35
+ }
checkpoint-1730/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1730/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23d37af4485e2b8b7fdaef7df83067ad538095f406574a8295dd8d4a4b51337
3
+ size 1421495416
checkpoint-1730/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9e49faf885a65d6ac390663b0b6efacd36e506c059bd6e5e8fa5e23566947d6
3
+ size 2843228717
checkpoint-1730/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2a277c2db09c1f03c76ea73b7489c7d769a0ca50dd8beab9117758aba8df80
3
+ size 14244
checkpoint-1730/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589e14dc88bec2ff84853f23cbd32ef4dbf4d74f43a08f709d355d66d617b5c0
3
+ size 1064
checkpoint-1730/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
+ }
checkpoint-1730/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1730/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": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
checkpoint-1730/trainer_state.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6805555555555556,
3
+ "best_model_checkpoint": "roberta-Suggestions-badareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-1038",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1730,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 13.059974670410156,
14
+ "learning_rate": 5.4221863347667504e-06,
15
+ "loss": 0.4316,
16
+ "step": 173
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.9101412066752247,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.1816691905260086,
23
+ "eval_precision": 0.0,
24
+ "eval_recall": 0.0,
25
+ "eval_runtime": 5.9222,
26
+ "eval_samples_per_second": 131.539,
27
+ "eval_steps_per_second": 8.274,
28
+ "step": 173
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 16.06458854675293,
33
+ "learning_rate": 4.8197211864593334e-06,
34
+ "loss": 0.2745,
35
+ "step": 346
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.9306803594351734,
40
+ "eval_f1": 0.5178571428571429,
41
+ "eval_loss": 0.08700571209192276,
42
+ "eval_precision": 0.6904761904761905,
43
+ "eval_recall": 0.4142857142857143,
44
+ "eval_runtime": 5.9611,
45
+ "eval_samples_per_second": 130.681,
46
+ "eval_steps_per_second": 8.22,
47
+ "step": 346
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 1.4951728582382202,
52
+ "learning_rate": 4.2172560381519165e-06,
53
+ "loss": 0.2084,
54
+ "step": 519
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.9178433889602053,
59
+ "eval_f1": 0.632183908045977,
60
+ "eval_loss": 0.19922904670238495,
61
+ "eval_precision": 0.5288461538461539,
62
+ "eval_recall": 0.7857142857142857,
63
+ "eval_runtime": 6.1312,
64
+ "eval_samples_per_second": 127.056,
65
+ "eval_steps_per_second": 7.992,
66
+ "step": 519
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 20.864402770996094,
71
+ "learning_rate": 3.6147908898445e-06,
72
+ "loss": 0.1754,
73
+ "step": 692
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.9165596919127086,
78
+ "eval_f1": 0.6198830409356725,
79
+ "eval_loss": 0.18699409067630768,
80
+ "eval_precision": 0.5247524752475248,
81
+ "eval_recall": 0.7571428571428571,
82
+ "eval_runtime": 5.9026,
83
+ "eval_samples_per_second": 131.975,
84
+ "eval_steps_per_second": 8.301,
85
+ "step": 692
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 5.5924787521362305,
90
+ "learning_rate": 3.0123257415370833e-06,
91
+ "loss": 0.1493,
92
+ "step": 865
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.938382541720154,
97
+ "eval_f1": 0.6521739130434783,
98
+ "eval_loss": 0.15427254140377045,
99
+ "eval_precision": 0.6617647058823529,
100
+ "eval_recall": 0.6428571428571429,
101
+ "eval_runtime": 6.303,
102
+ "eval_samples_per_second": 123.592,
103
+ "eval_steps_per_second": 7.774,
104
+ "step": 865
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 49.685874938964844,
109
+ "learning_rate": 2.4098605932296667e-06,
110
+ "loss": 0.1623,
111
+ "step": 1038
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.9409499358151476,
116
+ "eval_f1": 0.6805555555555556,
117
+ "eval_loss": 0.14713026583194733,
118
+ "eval_precision": 0.6621621621621622,
119
+ "eval_recall": 0.7,
120
+ "eval_runtime": 6.2307,
121
+ "eval_samples_per_second": 125.026,
122
+ "eval_steps_per_second": 7.864,
123
+ "step": 1038
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 1.6383557319641113,
128
+ "learning_rate": 1.80739544492225e-06,
129
+ "loss": 0.13,
130
+ "step": 1211
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.9306803594351734,
135
+ "eval_f1": 0.6447368421052632,
136
+ "eval_loss": 0.1874619573354721,
137
+ "eval_precision": 0.5975609756097561,
138
+ "eval_recall": 0.7,
139
+ "eval_runtime": 6.9577,
140
+ "eval_samples_per_second": 111.963,
141
+ "eval_steps_per_second": 7.043,
142
+ "step": 1211
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "grad_norm": 15.146454811096191,
147
+ "learning_rate": 1.2049302966148334e-06,
148
+ "loss": 0.1037,
149
+ "step": 1384
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_accuracy": 0.9242618741976893,
154
+ "eval_f1": 0.6380368098159509,
155
+ "eval_loss": 0.26284077763557434,
156
+ "eval_precision": 0.5591397849462365,
157
+ "eval_recall": 0.7428571428571429,
158
+ "eval_runtime": 5.9723,
159
+ "eval_samples_per_second": 130.436,
160
+ "eval_steps_per_second": 8.205,
161
+ "step": 1384
162
+ },
163
+ {
164
+ "epoch": 9.0,
165
+ "grad_norm": 40.48747634887695,
166
+ "learning_rate": 6.024651483074167e-07,
167
+ "loss": 0.1226,
168
+ "step": 1557
169
+ },
170
+ {
171
+ "epoch": 9.0,
172
+ "eval_accuracy": 0.9293966623876765,
173
+ "eval_f1": 0.6258503401360545,
174
+ "eval_loss": 0.21134264767169952,
175
+ "eval_precision": 0.5974025974025974,
176
+ "eval_recall": 0.6571428571428571,
177
+ "eval_runtime": 6.3059,
178
+ "eval_samples_per_second": 123.535,
179
+ "eval_steps_per_second": 7.77,
180
+ "step": 1557
181
+ },
182
+ {
183
+ "epoch": 10.0,
184
+ "grad_norm": 68.5556411743164,
185
+ "learning_rate": 0.0,
186
+ "loss": 0.0893,
187
+ "step": 1730
188
+ },
189
+ {
190
+ "epoch": 10.0,
191
+ "eval_accuracy": 0.9293966623876765,
192
+ "eval_f1": 0.6308724832214765,
193
+ "eval_loss": 0.2266077995300293,
194
+ "eval_precision": 0.5949367088607594,
195
+ "eval_recall": 0.6714285714285714,
196
+ "eval_runtime": 6.0665,
197
+ "eval_samples_per_second": 128.411,
198
+ "eval_steps_per_second": 8.077,
199
+ "step": 1730
200
+ }
201
+ ],
202
+ "logging_steps": 100,
203
+ "max_steps": 1730,
204
+ "num_input_tokens_seen": 0,
205
+ "num_train_epochs": 10,
206
+ "save_steps": 500,
207
+ "stateful_callbacks": {
208
+ "TrainerControl": {
209
+ "args": {
210
+ "should_epoch_stop": false,
211
+ "should_evaluate": false,
212
+ "should_log": false,
213
+ "should_save": true,
214
+ "should_training_stop": true
215
+ },
216
+ "attributes": {}
217
+ }
218
+ },
219
+ "total_flos": 2.371053993933845e+16,
220
+ "train_batch_size": 16,
221
+ "trial_name": null,
222
+ "trial_params": null
223
+ }
checkpoint-1730/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33cc3f71c709f06cbe1dbf09a19d8b32c093875b9b75281dad04588c3f6dee97
3
+ size 5496
checkpoint-1730/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-large",
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": 1024,
13
+ "id2label": {
14
+ "0": "not selected",
15
+ "1": "selected"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "not selected": "0",
21
+ "selected": "1"
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 16,
27
+ "num_hidden_layers": 24,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.48.3",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 50265
35
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f29e2bc4b7bd126d3baa29b63a151f2df802ecbefde7309ea1af97b9c30d7b4
3
+ size 1421495416
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33cc3f71c709f06cbe1dbf09a19d8b32c093875b9b75281dad04588c3f6dee97
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff