Hugging Face's logo

youralien
/
roberta-reflections-goodareas

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
youralien commited on
Commit
e4fc915
·
verified ·
1 Parent(s): 9778162

Upload trained RoBERTa model

Browse files
Files changed (33) hide show
  1. README.md +86 -0
  2. checkpoint-1600/config.json +35 -0
  3. checkpoint-1600/merges.txt +0 -0
  4. checkpoint-1600/model.safetensors +3 -0
  5. checkpoint-1600/optimizer.pt +3 -0
  6. checkpoint-1600/rng_state.pth +3 -0
  7. checkpoint-1600/scheduler.pt +3 -0
  8. checkpoint-1600/special_tokens_map.json +15 -0
  9. checkpoint-1600/tokenizer.json +0 -0
  10. checkpoint-1600/tokenizer_config.json +58 -0
  11. checkpoint-1600/trainer_state.json +413 -0
  12. checkpoint-1600/training_args.bin +3 -0
  13. checkpoint-1600/vocab.json +0 -0
  14. checkpoint-560/config.json +35 -0
  15. checkpoint-560/merges.txt +0 -0
  16. checkpoint-560/model.safetensors +3 -0
  17. checkpoint-560/optimizer.pt +3 -0
  18. checkpoint-560/rng_state.pth +3 -0
  19. checkpoint-560/scheduler.pt +3 -0
  20. checkpoint-560/special_tokens_map.json +15 -0
  21. checkpoint-560/tokenizer.json +0 -0
  22. checkpoint-560/tokenizer_config.json +58 -0
  23. checkpoint-560/trainer_state.json +166 -0
  24. checkpoint-560/training_args.bin +3 -0
  25. checkpoint-560/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 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-Reflections-goodareas-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-Reflections-goodareas-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: 0.4328
25
+ - Accuracy: 0.8678
26
+ - Precision: 0.4273
27
+ - Recall: 0.5402
28
+ - F1: 0.4772
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: 9.49118803819061e-06
48
+ - train_batch_size: 32
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: 20
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
+ | 0.3453 | 1.0 | 80 | 0.2368 | 0.8845 | 0.4444 | 0.1379 | 0.2105 |
60
+ | 0.2686 | 2.0 | 160 | 0.1995 | 0.8883 | 0.0 | 0.0 | 0.0 |
61
+ | 0.2467 | 3.0 | 240 | 0.2582 | 0.8755 | 0.4561 | 0.5977 | 0.5174 |
62
+ | 0.2346 | 4.0 | 320 | 0.1663 | 0.9012 | 0.6923 | 0.2069 | 0.3186 |
63
+ | 0.2153 | 5.0 | 400 | 0.1441 | 0.9037 | 0.8 | 0.1839 | 0.2991 |
64
+ | 0.2003 | 6.0 | 480 | 0.2784 | 0.8267 | 0.3571 | 0.6897 | 0.4706 |
65
+ | 0.1806 | 7.0 | 560 | 0.1637 | 0.8999 | 0.5495 | 0.5747 | 0.5618 |
66
+ | 0.1477 | 8.0 | 640 | 0.2062 | 0.8639 | 0.4275 | 0.6437 | 0.5138 |
67
+ | 0.1234 | 9.0 | 720 | 0.2175 | 0.8626 | 0.4167 | 0.5747 | 0.4831 |
68
+ | 0.1116 | 10.0 | 800 | 0.1914 | 0.8845 | 0.4810 | 0.4368 | 0.4578 |
69
+ | 0.0959 | 11.0 | 880 | 0.3313 | 0.8485 | 0.3916 | 0.6437 | 0.4870 |
70
+ | 0.0933 | 12.0 | 960 | 0.3027 | 0.8575 | 0.4048 | 0.5862 | 0.4789 |
71
+ | 0.0796 | 13.0 | 1040 | 0.3267 | 0.8575 | 0.4032 | 0.5747 | 0.4739 |
72
+ | 0.0688 | 14.0 | 1120 | 0.2958 | 0.8819 | 0.4731 | 0.5057 | 0.4889 |
73
+ | 0.0723 | 15.0 | 1200 | 0.4122 | 0.8575 | 0.4032 | 0.5747 | 0.4739 |
74
+ | 0.048 | 16.0 | 1280 | 0.5274 | 0.8447 | 0.3851 | 0.6552 | 0.4851 |
75
+ | 0.0504 | 17.0 | 1360 | 0.5241 | 0.8562 | 0.4031 | 0.5977 | 0.4815 |
76
+ | 0.0353 | 18.0 | 1440 | 0.4845 | 0.8601 | 0.4098 | 0.5747 | 0.4785 |
77
+ | 0.0485 | 19.0 | 1520 | 0.5141 | 0.8562 | 0.4031 | 0.5977 | 0.4815 |
78
+ | 0.0481 | 20.0 | 1600 | 0.4328 | 0.8678 | 0.4273 | 0.5402 | 0.4772 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.48.3
84
+ - Pytorch 2.5.1+cu124
85
+ - Datasets 2.21.0
86
+ - Tokenizers 0.21.0
checkpoint-1600/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-1600/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ebf47dec1ac43f57228e18575cfc7e5fb1a666f1647ffacef26427b3e6a1ab
3
+ size 1421495416
checkpoint-1600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b569f947226399aeed48cd5279bf0c2291ee665519d5293f854add30a5657b9
3
+ size 2843228717
checkpoint-1600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aaffce7babf997dc5fa3942d23f3fe89cd1be900f8063c5742e433aa4a492c7
3
+ size 14244
checkpoint-1600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f462eae5de6170103b75a48d331948c6e76e54fbc91c09466f9080d52789bea
3
+ size 1064
checkpoint-1600/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-1600/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1600/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-1600/trainer_state.json ADDED
@@ -0,0 +1,413 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5617977528089888,
3
+ "best_model_checkpoint": "roberta-Reflections-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-560",
4
+ "epoch": 20.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1600,
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": 65.6139144897461,
14
+ "learning_rate": 9.01662863628108e-06,
15
+ "loss": 0.3453,
16
+ "step": 80
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8844672657252889,
21
+ "eval_f1": 0.21052631578947367,
22
+ "eval_loss": 0.236761674284935,
23
+ "eval_precision": 0.4444444444444444,
24
+ "eval_recall": 0.13793103448275862,
25
+ "eval_runtime": 3.0292,
26
+ "eval_samples_per_second": 257.161,
27
+ "eval_steps_per_second": 16.176,
28
+ "step": 80
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 11.26146411895752,
33
+ "learning_rate": 8.54206923437155e-06,
34
+ "loss": 0.2686,
35
+ "step": 160
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8883183568677792,
40
+ "eval_f1": 0.0,
41
+ "eval_loss": 0.19945281744003296,
42
+ "eval_precision": 0.0,
43
+ "eval_recall": 0.0,
44
+ "eval_runtime": 3.1517,
45
+ "eval_samples_per_second": 247.167,
46
+ "eval_steps_per_second": 15.547,
47
+ "step": 160
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 17.682777404785156,
52
+ "learning_rate": 8.067509832462019e-06,
53
+ "loss": 0.2467,
54
+ "step": 240
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8754813863928113,
59
+ "eval_f1": 0.5174129353233831,
60
+ "eval_loss": 0.2581908404827118,
61
+ "eval_precision": 0.45614035087719296,
62
+ "eval_recall": 0.5977011494252874,
63
+ "eval_runtime": 3.0214,
64
+ "eval_samples_per_second": 257.831,
65
+ "eval_steps_per_second": 16.218,
66
+ "step": 240
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 15.032783508300781,
71
+ "learning_rate": 7.592950430552488e-06,
72
+ "loss": 0.2346,
73
+ "step": 320
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.9011553273427471,
78
+ "eval_f1": 0.3185840707964602,
79
+ "eval_loss": 0.16634990274906158,
80
+ "eval_precision": 0.6923076923076923,
81
+ "eval_recall": 0.20689655172413793,
82
+ "eval_runtime": 3.0455,
83
+ "eval_samples_per_second": 255.788,
84
+ "eval_steps_per_second": 16.089,
85
+ "step": 320
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 11.804676055908203,
90
+ "learning_rate": 7.118391028642958e-06,
91
+ "loss": 0.2153,
92
+ "step": 400
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.9037227214377407,
97
+ "eval_f1": 0.29906542056074764,
98
+ "eval_loss": 0.14412762224674225,
99
+ "eval_precision": 0.8,
100
+ "eval_recall": 0.1839080459770115,
101
+ "eval_runtime": 3.0668,
102
+ "eval_samples_per_second": 254.013,
103
+ "eval_steps_per_second": 15.978,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 38.897178649902344,
109
+ "learning_rate": 6.643831626733427e-06,
110
+ "loss": 0.2003,
111
+ "step": 480
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.8267008985879333,
116
+ "eval_f1": 0.47058823529411764,
117
+ "eval_loss": 0.2783520519733429,
118
+ "eval_precision": 0.35714285714285715,
119
+ "eval_recall": 0.6896551724137931,
120
+ "eval_runtime": 3.1385,
121
+ "eval_samples_per_second": 248.208,
122
+ "eval_steps_per_second": 15.613,
123
+ "step": 480
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 46.657535552978516,
128
+ "learning_rate": 6.169272224823897e-06,
129
+ "loss": 0.1806,
130
+ "step": 560
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.8998716302952503,
135
+ "eval_f1": 0.5617977528089888,
136
+ "eval_loss": 0.16373790800571442,
137
+ "eval_precision": 0.5494505494505495,
138
+ "eval_recall": 0.5747126436781609,
139
+ "eval_runtime": 3.0921,
140
+ "eval_samples_per_second": 251.934,
141
+ "eval_steps_per_second": 15.847,
142
+ "step": 560
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "grad_norm": 79.26252746582031,
147
+ "learning_rate": 5.694712822914366e-06,
148
+ "loss": 0.1477,
149
+ "step": 640
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_accuracy": 0.8639281129653402,
154
+ "eval_f1": 0.5137614678899083,
155
+ "eval_loss": 0.20617738366127014,
156
+ "eval_precision": 0.42748091603053434,
157
+ "eval_recall": 0.6436781609195402,
158
+ "eval_runtime": 3.766,
159
+ "eval_samples_per_second": 206.852,
160
+ "eval_steps_per_second": 13.011,
161
+ "step": 640
162
+ },
163
+ {
164
+ "epoch": 9.0,
165
+ "grad_norm": 18.165985107421875,
166
+ "learning_rate": 5.220153421004836e-06,
167
+ "loss": 0.1234,
168
+ "step": 720
169
+ },
170
+ {
171
+ "epoch": 9.0,
172
+ "eval_accuracy": 0.8626444159178434,
173
+ "eval_f1": 0.4830917874396135,
174
+ "eval_loss": 0.21749651432037354,
175
+ "eval_precision": 0.4166666666666667,
176
+ "eval_recall": 0.5747126436781609,
177
+ "eval_runtime": 3.0317,
178
+ "eval_samples_per_second": 256.949,
179
+ "eval_steps_per_second": 16.162,
180
+ "step": 720
181
+ },
182
+ {
183
+ "epoch": 10.0,
184
+ "grad_norm": 2.0673418045043945,
185
+ "learning_rate": 4.745594019095305e-06,
186
+ "loss": 0.1116,
187
+ "step": 800
188
+ },
189
+ {
190
+ "epoch": 10.0,
191
+ "eval_accuracy": 0.8844672657252889,
192
+ "eval_f1": 0.4578313253012048,
193
+ "eval_loss": 0.19141623377799988,
194
+ "eval_precision": 0.4810126582278481,
195
+ "eval_recall": 0.4367816091954023,
196
+ "eval_runtime": 3.1007,
197
+ "eval_samples_per_second": 251.234,
198
+ "eval_steps_per_second": 15.803,
199
+ "step": 800
200
+ },
201
+ {
202
+ "epoch": 11.0,
203
+ "grad_norm": 0.15599511563777924,
204
+ "learning_rate": 4.271034617185775e-06,
205
+ "loss": 0.0959,
206
+ "step": 880
207
+ },
208
+ {
209
+ "epoch": 11.0,
210
+ "eval_accuracy": 0.8485237483953787,
211
+ "eval_f1": 0.48695652173913045,
212
+ "eval_loss": 0.33126145601272583,
213
+ "eval_precision": 0.3916083916083916,
214
+ "eval_recall": 0.6436781609195402,
215
+ "eval_runtime": 3.2233,
216
+ "eval_samples_per_second": 241.681,
217
+ "eval_steps_per_second": 15.202,
218
+ "step": 880
219
+ },
220
+ {
221
+ "epoch": 12.0,
222
+ "grad_norm": 0.9359363317489624,
223
+ "learning_rate": 3.796475215276244e-06,
224
+ "loss": 0.0933,
225
+ "step": 960
226
+ },
227
+ {
228
+ "epoch": 12.0,
229
+ "eval_accuracy": 0.8575096277278562,
230
+ "eval_f1": 0.4788732394366197,
231
+ "eval_loss": 0.3026818335056305,
232
+ "eval_precision": 0.40476190476190477,
233
+ "eval_recall": 0.5862068965517241,
234
+ "eval_runtime": 3.0182,
235
+ "eval_samples_per_second": 258.097,
236
+ "eval_steps_per_second": 16.235,
237
+ "step": 960
238
+ },
239
+ {
240
+ "epoch": 13.0,
241
+ "grad_norm": 0.1464570015668869,
242
+ "learning_rate": 3.3219158133667136e-06,
243
+ "loss": 0.0796,
244
+ "step": 1040
245
+ },
246
+ {
247
+ "epoch": 13.0,
248
+ "eval_accuracy": 0.8575096277278562,
249
+ "eval_f1": 0.47393364928909953,
250
+ "eval_loss": 0.32667848467826843,
251
+ "eval_precision": 0.4032258064516129,
252
+ "eval_recall": 0.5747126436781609,
253
+ "eval_runtime": 3.0299,
254
+ "eval_samples_per_second": 257.1,
255
+ "eval_steps_per_second": 16.172,
256
+ "step": 1040
257
+ },
258
+ {
259
+ "epoch": 14.0,
260
+ "grad_norm": 0.5023568868637085,
261
+ "learning_rate": 2.847356411457183e-06,
262
+ "loss": 0.0688,
263
+ "step": 1120
264
+ },
265
+ {
266
+ "epoch": 14.0,
267
+ "eval_accuracy": 0.8818998716302953,
268
+ "eval_f1": 0.4888888888888889,
269
+ "eval_loss": 0.2957651913166046,
270
+ "eval_precision": 0.4731182795698925,
271
+ "eval_recall": 0.5057471264367817,
272
+ "eval_runtime": 3.2559,
273
+ "eval_samples_per_second": 239.256,
274
+ "eval_steps_per_second": 15.049,
275
+ "step": 1120
276
+ },
277
+ {
278
+ "epoch": 15.0,
279
+ "grad_norm": 0.34069183468818665,
280
+ "learning_rate": 2.3727970095476526e-06,
281
+ "loss": 0.0723,
282
+ "step": 1200
283
+ },
284
+ {
285
+ "epoch": 15.0,
286
+ "eval_accuracy": 0.8575096277278562,
287
+ "eval_f1": 0.47393364928909953,
288
+ "eval_loss": 0.412211537361145,
289
+ "eval_precision": 0.4032258064516129,
290
+ "eval_recall": 0.5747126436781609,
291
+ "eval_runtime": 3.0316,
292
+ "eval_samples_per_second": 256.961,
293
+ "eval_steps_per_second": 16.163,
294
+ "step": 1200
295
+ },
296
+ {
297
+ "epoch": 16.0,
298
+ "grad_norm": 0.027584612369537354,
299
+ "learning_rate": 1.898237607638122e-06,
300
+ "loss": 0.048,
301
+ "step": 1280
302
+ },
303
+ {
304
+ "epoch": 16.0,
305
+ "eval_accuracy": 0.8446726572528883,
306
+ "eval_f1": 0.4851063829787234,
307
+ "eval_loss": 0.5274401307106018,
308
+ "eval_precision": 0.38513513513513514,
309
+ "eval_recall": 0.6551724137931034,
310
+ "eval_runtime": 3.6161,
311
+ "eval_samples_per_second": 215.424,
312
+ "eval_steps_per_second": 13.55,
313
+ "step": 1280
314
+ },
315
+ {
316
+ "epoch": 17.0,
317
+ "grad_norm": 0.9135520458221436,
318
+ "learning_rate": 1.4236782057285915e-06,
319
+ "loss": 0.0504,
320
+ "step": 1360
321
+ },
322
+ {
323
+ "epoch": 17.0,
324
+ "eval_accuracy": 0.8562259306803595,
325
+ "eval_f1": 0.48148148148148145,
326
+ "eval_loss": 0.5240976214408875,
327
+ "eval_precision": 0.40310077519379844,
328
+ "eval_recall": 0.5977011494252874,
329
+ "eval_runtime": 3.0559,
330
+ "eval_samples_per_second": 254.916,
331
+ "eval_steps_per_second": 16.035,
332
+ "step": 1360
333
+ },
334
+ {
335
+ "epoch": 18.0,
336
+ "grad_norm": 0.006816316395998001,
337
+ "learning_rate": 9.49118803819061e-07,
338
+ "loss": 0.0353,
339
+ "step": 1440
340
+ },
341
+ {
342
+ "epoch": 18.0,
343
+ "eval_accuracy": 0.8600770218228498,
344
+ "eval_f1": 0.4784688995215311,
345
+ "eval_loss": 0.484482079744339,
346
+ "eval_precision": 0.4098360655737705,
347
+ "eval_recall": 0.5747126436781609,
348
+ "eval_runtime": 3.0044,
349
+ "eval_samples_per_second": 259.286,
350
+ "eval_steps_per_second": 16.309,
351
+ "step": 1440
352
+ },
353
+ {
354
+ "epoch": 19.0,
355
+ "grad_norm": 0.03107047826051712,
356
+ "learning_rate": 4.745594019095305e-07,
357
+ "loss": 0.0485,
358
+ "step": 1520
359
+ },
360
+ {
361
+ "epoch": 19.0,
362
+ "eval_accuracy": 0.8562259306803595,
363
+ "eval_f1": 0.48148148148148145,
364
+ "eval_loss": 0.5140769481658936,
365
+ "eval_precision": 0.40310077519379844,
366
+ "eval_recall": 0.5977011494252874,
367
+ "eval_runtime": 2.9889,
368
+ "eval_samples_per_second": 260.628,
369
+ "eval_steps_per_second": 16.394,
370
+ "step": 1520
371
+ },
372
+ {
373
+ "epoch": 20.0,
374
+ "grad_norm": 0.014716532081365585,
375
+ "learning_rate": 0.0,
376
+ "loss": 0.0481,
377
+ "step": 1600
378
+ },
379
+ {
380
+ "epoch": 20.0,
381
+ "eval_accuracy": 0.8677792041078306,
382
+ "eval_f1": 0.47715736040609136,
383
+ "eval_loss": 0.432771772146225,
384
+ "eval_precision": 0.42727272727272725,
385
+ "eval_recall": 0.5402298850574713,
386
+ "eval_runtime": 3.0006,
387
+ "eval_samples_per_second": 259.618,
388
+ "eval_steps_per_second": 16.33,
389
+ "step": 1600
390
+ }
391
+ ],
392
+ "logging_steps": 100,
393
+ "max_steps": 1600,
394
+ "num_input_tokens_seen": 0,
395
+ "num_train_epochs": 20,
396
+ "save_steps": 500,
397
+ "stateful_callbacks": {
398
+ "TrainerControl": {
399
+ "args": {
400
+ "should_epoch_stop": false,
401
+ "should_evaluate": false,
402
+ "should_log": false,
403
+ "should_save": true,
404
+ "should_training_stop": true
405
+ },
406
+ "attributes": {}
407
+ }
408
+ },
409
+ "total_flos": 1.3332559558031616e+16,
410
+ "train_batch_size": 32,
411
+ "trial_name": null,
412
+ "trial_params": null
413
+ }
checkpoint-1600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0557217f2922d1d78cae1ace55d5bb55927ee532e76734b644ec3800e9deef52
3
+ size 5496
checkpoint-1600/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-560/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-560/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-560/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9167951d5fef326c9b79b320958979c6cd9e2dacb6826c98362cbd99f47898a4
3
+ size 1421495416
checkpoint-560/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e9db95f73a8df95982a7809bee6fe19ebcb9dcda8392b2db9ebc9d25fca2f1
3
+ size 2843228717
checkpoint-560/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a7269e243c3ea49c99daad4ffb39b1462efa574c1399726124e1a73ce219270
3
+ size 14244
checkpoint-560/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b7782761d00496ccc59c8f519ec82318d0c2e596d9f3e6a6e8554065041665
3
+ size 1064
checkpoint-560/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-560/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-560/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-560/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5617977528089888,
3
+ "best_model_checkpoint": "roberta-Reflections-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-560",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 560,
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": 65.6139144897461,
14
+ "learning_rate": 9.01662863628108e-06,
15
+ "loss": 0.3453,
16
+ "step": 80
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8844672657252889,
21
+ "eval_f1": 0.21052631578947367,
22
+ "eval_loss": 0.236761674284935,
23
+ "eval_precision": 0.4444444444444444,
24
+ "eval_recall": 0.13793103448275862,
25
+ "eval_runtime": 3.0292,
26
+ "eval_samples_per_second": 257.161,
27
+ "eval_steps_per_second": 16.176,
28
+ "step": 80
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 11.26146411895752,
33
+ "learning_rate": 8.54206923437155e-06,
34
+ "loss": 0.2686,
35
+ "step": 160
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8883183568677792,
40
+ "eval_f1": 0.0,
41
+ "eval_loss": 0.19945281744003296,
42
+ "eval_precision": 0.0,
43
+ "eval_recall": 0.0,
44
+ "eval_runtime": 3.1517,
45
+ "eval_samples_per_second": 247.167,
46
+ "eval_steps_per_second": 15.547,
47
+ "step": 160
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 17.682777404785156,
52
+ "learning_rate": 8.067509832462019e-06,
53
+ "loss": 0.2467,
54
+ "step": 240
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8754813863928113,
59
+ "eval_f1": 0.5174129353233831,
60
+ "eval_loss": 0.2581908404827118,
61
+ "eval_precision": 0.45614035087719296,
62
+ "eval_recall": 0.5977011494252874,
63
+ "eval_runtime": 3.0214,
64
+ "eval_samples_per_second": 257.831,
65
+ "eval_steps_per_second": 16.218,
66
+ "step": 240
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 15.032783508300781,
71
+ "learning_rate": 7.592950430552488e-06,
72
+ "loss": 0.2346,
73
+ "step": 320
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.9011553273427471,
78
+ "eval_f1": 0.3185840707964602,
79
+ "eval_loss": 0.16634990274906158,
80
+ "eval_precision": 0.6923076923076923,
81
+ "eval_recall": 0.20689655172413793,
82
+ "eval_runtime": 3.0455,
83
+ "eval_samples_per_second": 255.788,
84
+ "eval_steps_per_second": 16.089,
85
+ "step": 320
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 11.804676055908203,
90
+ "learning_rate": 7.118391028642958e-06,
91
+ "loss": 0.2153,
92
+ "step": 400
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.9037227214377407,
97
+ "eval_f1": 0.29906542056074764,
98
+ "eval_loss": 0.14412762224674225,
99
+ "eval_precision": 0.8,
100
+ "eval_recall": 0.1839080459770115,
101
+ "eval_runtime": 3.0668,
102
+ "eval_samples_per_second": 254.013,
103
+ "eval_steps_per_second": 15.978,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 38.897178649902344,
109
+ "learning_rate": 6.643831626733427e-06,
110
+ "loss": 0.2003,
111
+ "step": 480
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.8267008985879333,
116
+ "eval_f1": 0.47058823529411764,
117
+ "eval_loss": 0.2783520519733429,
118
+ "eval_precision": 0.35714285714285715,
119
+ "eval_recall": 0.6896551724137931,
120
+ "eval_runtime": 3.1385,
121
+ "eval_samples_per_second": 248.208,
122
+ "eval_steps_per_second": 15.613,
123
+ "step": 480
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 46.657535552978516,
128
+ "learning_rate": 6.169272224823897e-06,
129
+ "loss": 0.1806,
130
+ "step": 560
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.8998716302952503,
135
+ "eval_f1": 0.5617977528089888,
136
+ "eval_loss": 0.16373790800571442,
137
+ "eval_precision": 0.5494505494505495,
138
+ "eval_recall": 0.5747126436781609,
139
+ "eval_runtime": 3.0921,
140
+ "eval_samples_per_second": 251.934,
141
+ "eval_steps_per_second": 15.847,
142
+ "step": 560
143
+ }
144
+ ],
145
+ "logging_steps": 100,
146
+ "max_steps": 1600,
147
+ "num_input_tokens_seen": 0,
148
+ "num_train_epochs": 20,
149
+ "save_steps": 500,
150
+ "stateful_callbacks": {
151
+ "TrainerControl": {
152
+ "args": {
153
+ "should_epoch_stop": false,
154
+ "should_evaluate": false,
155
+ "should_log": false,
156
+ "should_save": true,
157
+ "should_training_stop": false
158
+ },
159
+ "attributes": {}
160
+ }
161
+ },
162
+ "total_flos": 4630799707588824.0,
163
+ "train_batch_size": 32,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }
checkpoint-560/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0557217f2922d1d78cae1ace55d5bb55927ee532e76734b644ec3800e9deef52
3
+ size 5496
checkpoint-560/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 sha256:9167951d5fef326c9b79b320958979c6cd9e2dacb6826c98362cbd99f47898a4
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 sha256:0557217f2922d1d78cae1ace55d5bb55927ee532e76734b644ec3800e9deef52
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff