Hugging Face's logo

nicholasKluge
/
Harmless-RewardModel

Text Classification
Transformers
Safetensors
English
roberta
reward model
alignment
preference model
RLHF
Model card Files
xet
Community
nicholasKluge commited on
Commit
70e65be
·
verified ·
1 Parent(s): 12aaab0

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. config.json +33 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +15 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +57 -0
  10. trainer_state.json +193 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/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
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 514,
23
+ "model_type": "roberta",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.42.0.dev0",
30
+ "type_vocab_size": 1,
31
+ "use_cache": true,
32
+ "vocab_size": 50265
33
+ }
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:f6c5bd257a1b8740ba363118071b2abfd1e56fd18e6e1f5a9be8a35d5409460f
3
+ size 498609748
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b34533a3e65cb1d3d43d29f0ce158d78016b53477bf26cb092da70f71d2a033
3
+ size 997339386
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b5d8154cf48ab28a80f718a32b883a395d3b80d93ba467d6434f5e781a37814
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04c72869181363c7c0dcffb7a71857fd6a7c81a93e70aff2985fc26363295969
3
+ size 1064
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.1026072329688814,
5
+ "eval_steps": 1000,
6
+ "global_step": 10000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.21026072329688814,
13
+ "grad_norm": 2.809398889541626,
14
+ "learning_rate": 4.5e-05,
15
+ "loss": 0.6523,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.21026072329688814,
20
+ "eval_accuracy": 0.6497723106038205,
21
+ "eval_loss": 0.6366201639175415,
22
+ "eval_runtime": 70.6325,
23
+ "eval_samples_per_second": 239.394,
24
+ "eval_steps_per_second": 7.489,
25
+ "step": 1000
26
+ },
27
+ {
28
+ "epoch": 0.42052144659377627,
29
+ "grad_norm": 1.8323402404785156,
30
+ "learning_rate": 4e-05,
31
+ "loss": 0.643,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.42052144659377627,
36
+ "eval_accuracy": 0.6556271807912946,
37
+ "eval_loss": 0.6256184577941895,
38
+ "eval_runtime": 70.7729,
39
+ "eval_samples_per_second": 238.919,
40
+ "eval_steps_per_second": 7.475,
41
+ "step": 2000
42
+ },
43
+ {
44
+ "epoch": 0.6307821698906644,
45
+ "grad_norm": 2.800808906555176,
46
+ "learning_rate": 3.5e-05,
47
+ "loss": 0.6258,
48
+ "step": 3000
49
+ },
50
+ {
51
+ "epoch": 0.6307821698906644,
52
+ "eval_accuracy": 0.6687562836359335,
53
+ "eval_loss": 0.6168072819709778,
54
+ "eval_runtime": 70.6278,
55
+ "eval_samples_per_second": 239.41,
56
+ "eval_steps_per_second": 7.49,
57
+ "step": 3000
58
+ },
59
+ {
60
+ "epoch": 0.8410428931875525,
61
+ "grad_norm": 3.3484714031219482,
62
+ "learning_rate": 3e-05,
63
+ "loss": 0.6153,
64
+ "step": 4000
65
+ },
66
+ {
67
+ "epoch": 0.8410428931875525,
68
+ "eval_accuracy": 0.6773315985569814,
69
+ "eval_loss": 0.6092528104782104,
70
+ "eval_runtime": 70.616,
71
+ "eval_samples_per_second": 239.45,
72
+ "eval_steps_per_second": 7.491,
73
+ "step": 4000
74
+ },
75
+ {
76
+ "epoch": 1.0513036164844407,
77
+ "grad_norm": 2.8150999546051025,
78
+ "learning_rate": 2.5e-05,
79
+ "loss": 0.6059,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.0513036164844407,
84
+ "eval_accuracy": 0.6848423916257614,
85
+ "eval_loss": 0.5986923575401306,
86
+ "eval_runtime": 70.5783,
87
+ "eval_samples_per_second": 239.578,
88
+ "eval_steps_per_second": 7.495,
89
+ "step": 5000
90
+ },
91
+ {
92
+ "epoch": 1.2615643397813288,
93
+ "grad_norm": 3.897254467010498,
94
+ "learning_rate": 2e-05,
95
+ "loss": 0.5815,
96
+ "step": 6000
97
+ },
98
+ {
99
+ "epoch": 1.2615643397813288,
100
+ "eval_accuracy": 0.6794015021586137,
101
+ "eval_loss": 0.6166995763778687,
102
+ "eval_runtime": 70.7635,
103
+ "eval_samples_per_second": 238.951,
104
+ "eval_steps_per_second": 7.476,
105
+ "step": 6000
106
+ },
107
+ {
108
+ "epoch": 1.471825063078217,
109
+ "grad_norm": 3.7805373668670654,
110
+ "learning_rate": 1.5e-05,
111
+ "loss": 0.577,
112
+ "step": 7000
113
+ },
114
+ {
115
+ "epoch": 1.471825063078217,
116
+ "eval_accuracy": 0.6845466911112426,
117
+ "eval_loss": 0.6091504693031311,
118
+ "eval_runtime": 70.9254,
119
+ "eval_samples_per_second": 238.405,
120
+ "eval_steps_per_second": 7.459,
121
+ "step": 7000
122
+ },
123
+ {
124
+ "epoch": 1.682085786375105,
125
+ "grad_norm": 2.818917751312256,
126
+ "learning_rate": 1e-05,
127
+ "loss": 0.5777,
128
+ "step": 8000
129
+ },
130
+ {
131
+ "epoch": 1.682085786375105,
132
+ "eval_accuracy": 0.6845466911112426,
133
+ "eval_loss": 0.5907013416290283,
134
+ "eval_runtime": 70.6651,
135
+ "eval_samples_per_second": 239.284,
136
+ "eval_steps_per_second": 7.486,
137
+ "step": 8000
138
+ },
139
+ {
140
+ "epoch": 1.8923465096719934,
141
+ "grad_norm": 3.7022032737731934,
142
+ "learning_rate": 5e-06,
143
+ "loss": 0.5739,
144
+ "step": 9000
145
+ },
146
+ {
147
+ "epoch": 1.8923465096719934,
148
+ "eval_accuracy": 0.688154237388373,
149
+ "eval_loss": 0.5975272059440613,
150
+ "eval_runtime": 70.5471,
151
+ "eval_samples_per_second": 239.684,
152
+ "eval_steps_per_second": 7.499,
153
+ "step": 9000
154
+ },
155
+ {
156
+ "epoch": 2.1026072329688814,
157
+ "grad_norm": 3.167426824569702,
158
+ "learning_rate": 0.0,
159
+ "loss": 0.5533,
160
+ "step": 10000
161
+ },
162
+ {
163
+ "epoch": 2.1026072329688814,
164
+ "eval_accuracy": 0.6901058607841978,
165
+ "eval_loss": 0.6055890917778015,
166
+ "eval_runtime": 70.6977,
167
+ "eval_samples_per_second": 239.173,
168
+ "eval_steps_per_second": 7.483,
169
+ "step": 10000
170
+ }
171
+ ],
172
+ "logging_steps": 1000,
173
+ "max_steps": 10000,
174
+ "num_input_tokens_seen": 0,
175
+ "num_train_epochs": 3,
176
+ "save_steps": 1000,
177
+ "stateful_callbacks": {
178
+ "TrainerControl": {
179
+ "args": {
180
+ "should_epoch_stop": false,
181
+ "should_evaluate": false,
182
+ "should_log": false,
183
+ "should_save": true,
184
+ "should_training_stop": true
185
+ },
186
+ "attributes": {}
187
+ }
188
+ },
189
+ "total_flos": 0.0,
190
+ "train_batch_size": 32,
191
+ "trial_name": null,
192
+ "trial_params": null
193
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64cc0eada6dd2721e42349f8c2f40a229ff410670a5dffe8e8e25fe01282124c
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff