Hugging Face's logo

AdversarialRLHF
/
pythia410m-rm-tldr6.9b_prefix_in_chosen

Text Classification
Transformers
Safetensors
gpt_neox
Generated from Trainer
trl
reward-trainer
text-generation-inference
Model card Files Community
Muqeeth commited on
Commit
0ff65bd
·
verified ·
1 Parent(s): 4334f6b

Training in progress, step 365, checkpoint

Browse files
Files changed (10) hide show
  1. checkpoint-365/config.json +38 -0
  2. checkpoint-365/model.safetensors +3 -0
  3. checkpoint-365/optimizer.pt +3 -0
  4. checkpoint-365/rng_state.pth +3 -0
  5. checkpoint-365/scheduler.pt +3 -0
  6. checkpoint-365/special_tokens_map.json +30 -0
  7. checkpoint-365/tokenizer.json +0 -0
  8. checkpoint-365/tokenizer_config.json +219 -0
  9. checkpoint-365/trainer_state.json +295 -0
  10. checkpoint-365/training_args.bin +3 -0
checkpoint-365/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForSequenceClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 2048,
23
+ "model_type": "gpt_neox",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "pad_token_id": 1,
27
+ "partial_rotary_factor": 0.25,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000,
30
+ "rotary_emb_base": 10000,
31
+ "rotary_pct": 0.25,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.50.3",
35
+ "use_cache": true,
36
+ "use_parallel_residual": true,
37
+ "vocab_size": 50304
38
+ }
checkpoint-365/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a842b3fb16de8a09f48a66ce32a45dc70725a4f603467ae203b1d22c825545f6
3
+ size 1415329032
checkpoint-365/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ea50148011082a978689e1f8dce1fc61e3acc51426ccd074b7097949270ec5
3
+ size 2830833850
checkpoint-365/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
3
+ size 14244
checkpoint-365/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c8408a9a91277b772769373578daf631b24fb1b5b74c3e4a48155ba6fe9028
3
+ size 1064
checkpoint-365/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|padding|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-365/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-365/tokenizer_config.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ }
206
+ },
207
+ "bos_token": "<|endoftext|>",
208
+ "clean_up_tokenization_spaces": true,
209
+ "eos_token": "<|endoftext|>",
210
+ "extra_special_tokens": {},
211
+ "max_length": 580,
212
+ "model_max_length": 1000000000000000019884624838656,
213
+ "pad_token": "<|padding|>",
214
+ "stride": 0,
215
+ "tokenizer_class": "GPTNeoXTokenizer",
216
+ "truncation_side": "right",
217
+ "truncation_strategy": "longest_first",
218
+ "unk_token": "<|endoftext|>"
219
+ }
checkpoint-365/trainer_state.json ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.20012336371736,
6
+ "eval_steps": 365,
7
+ "global_step": 365,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.005482831882667398,
14
+ "grad_norm": 1.8271640439809084e-13,
15
+ "learning_rate": 9.999257569732963e-06,
16
+ "loss": 0.0547,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.010965663765334796,
21
+ "grad_norm": 1.8681511551469146e-14,
22
+ "learning_rate": 9.997030499412933e-06,
23
+ "loss": 0.0,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.016448495648002194,
28
+ "grad_norm": 1.2511433729323063e-11,
29
+ "learning_rate": 9.993319450417669e-06,
30
+ "loss": 0.0,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.021931327530669592,
35
+ "grad_norm": 3.090452546650191e-11,
36
+ "learning_rate": 9.988125524825216e-06,
37
+ "loss": 0.0,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.02741415941333699,
42
+ "grad_norm": 1.458404726736688e-14,
43
+ "learning_rate": 9.981450265086598e-06,
44
+ "loss": 0.0,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.03289699129600439,
49
+ "grad_norm": 3.242672515051115e-14,
50
+ "learning_rate": 9.973295653567764e-06,
51
+ "loss": 0.0,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.038379823178671786,
56
+ "grad_norm": 2.718872761479918e-14,
57
+ "learning_rate": 9.963664111960875e-06,
58
+ "loss": 0.0,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.043862655061339184,
63
+ "grad_norm": 9.169036085943105e-10,
64
+ "learning_rate": 9.952558500565135e-06,
65
+ "loss": 0.0,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.04934548694400658,
70
+ "grad_norm": 6.057082835297933e-09,
71
+ "learning_rate": 9.939982117437356e-06,
72
+ "loss": 0.0,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.05482831882667398,
77
+ "grad_norm": 2.746146947174566e-06,
78
+ "learning_rate": 9.925938697412536e-06,
79
+ "loss": 0.0,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.06031115070934138,
84
+ "grad_norm": 2.1543860384554137e-07,
85
+ "learning_rate": 9.910432410994701e-06,
86
+ "loss": 0.0,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.06579398259200878,
91
+ "grad_norm": 1.2734583378914976e-06,
92
+ "learning_rate": 9.893467863118402e-06,
93
+ "loss": 0.0,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.07127681447467617,
98
+ "grad_norm": 3.238647128256389e-09,
99
+ "learning_rate": 9.87505009178116e-06,
100
+ "loss": 0.0,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.07675964635734357,
105
+ "grad_norm": 1.8630474585279444e-07,
106
+ "learning_rate": 9.855184566547333e-06,
107
+ "loss": 0.0,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.08224247824001096,
112
+ "grad_norm": 1.8918351329944016e-09,
113
+ "learning_rate": 9.833877186923803e-06,
114
+ "loss": 0.0,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.08772531012267837,
119
+ "grad_norm": 1.6541060188224321e-10,
120
+ "learning_rate": 9.811134280607988e-06,
121
+ "loss": 0.0,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.09320814200534576,
126
+ "grad_norm": 0.0067967576906085014,
127
+ "learning_rate": 9.786962601608689e-06,
128
+ "loss": 0.0015,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.09869097388801316,
133
+ "grad_norm": 7.394525164272636e-05,
134
+ "learning_rate": 9.761369328240347e-06,
135
+ "loss": 0.0,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.10417380577068056,
140
+ "grad_norm": 2.62540652329335e-07,
141
+ "learning_rate": 9.734362060991274e-06,
142
+ "loss": 0.0,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.10965663765334796,
147
+ "grad_norm": 4.609726822479843e-09,
148
+ "learning_rate": 9.70594882026652e-06,
149
+ "loss": 0.0,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.11513946953601535,
154
+ "grad_norm": 8.970529319363152e-10,
155
+ "learning_rate": 9.676138044006051e-06,
156
+ "loss": 0.0,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.12062230141868276,
161
+ "grad_norm": 7.758627629250725e-10,
162
+ "learning_rate": 9.644938585178894e-06,
163
+ "loss": 0.0,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.12610513330135015,
168
+ "grad_norm": 3.484149357912969e-10,
169
+ "learning_rate": 9.61235970915407e-06,
170
+ "loss": 0.0,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.13158796518401755,
175
+ "grad_norm": 3.5987784974267356e-10,
176
+ "learning_rate": 9.57841109094903e-06,
177
+ "loss": 0.0,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.13707079706668493,
182
+ "grad_norm": 2.9926486289078014e-10,
183
+ "learning_rate": 9.543102812356446e-06,
184
+ "loss": 0.0,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.14255362894935233,
189
+ "grad_norm": 2.17573001282112e-10,
190
+ "learning_rate": 9.506445358950199e-06,
191
+ "loss": 0.0,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.14803646083201974,
196
+ "grad_norm": 1.5743054082584251e-10,
197
+ "learning_rate": 9.468449616971458e-06,
198
+ "loss": 0.0,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.15351929271468714,
203
+ "grad_norm": 3.0337881185005244e-07,
204
+ "learning_rate": 9.429126870095766e-06,
205
+ "loss": 0.0,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.15900212459735452,
210
+ "grad_norm": 2.075781768695606e-10,
211
+ "learning_rate": 9.388488796082113e-06,
212
+ "loss": 0.0,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.16448495648002193,
217
+ "grad_norm": 2.6534453922977264e-07,
218
+ "learning_rate": 9.346547463304953e-06,
219
+ "loss": 0.0,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.16996778836268933,
224
+ "grad_norm": 2.213984316767892e-06,
225
+ "learning_rate": 9.303315327170244e-06,
226
+ "loss": 0.0,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.17545062024535674,
231
+ "grad_norm": 1.0965933022744068e-10,
232
+ "learning_rate": 9.258805226416536e-06,
233
+ "loss": 0.0,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.1809334521280241,
238
+ "grad_norm": 9.682482593476038e-11,
239
+ "learning_rate": 9.213030379302223e-06,
240
+ "loss": 0.0,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.18641628401069152,
245
+ "grad_norm": 1.8911376631347565e-10,
246
+ "learning_rate": 9.166004379680094e-06,
247
+ "loss": 0.0,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.19189911589335892,
252
+ "grad_norm": 2.287967731939844e-10,
253
+ "learning_rate": 9.11774119296033e-06,
254
+ "loss": 0.0,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.19738194777602633,
259
+ "grad_norm": 1.6538861946635564e-10,
260
+ "learning_rate": 9.068255151963174e-06,
261
+ "loss": 0.0,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.20012336371736,
266
+ "eval_accuracy": 1.0,
267
+ "eval_loss": 8.152250430271124e-09,
268
+ "eval_runtime": 172.1258,
269
+ "eval_samples_per_second": 37.455,
270
+ "eval_steps_per_second": 4.683,
271
+ "step": 365
272
+ }
273
+ ],
274
+ "logging_steps": 10,
275
+ "max_steps": 1823,
276
+ "num_input_tokens_seen": 0,
277
+ "num_train_epochs": 1,
278
+ "save_steps": 365,
279
+ "stateful_callbacks": {
280
+ "TrainerControl": {
281
+ "args": {
282
+ "should_epoch_stop": false,
283
+ "should_evaluate": false,
284
+ "should_log": false,
285
+ "should_save": true,
286
+ "should_training_stop": false
287
+ },
288
+ "attributes": {}
289
+ }
290
+ },
291
+ "total_flos": 0.0,
292
+ "train_batch_size": 8,
293
+ "trial_name": null,
294
+ "trial_params": null
295
+ }
checkpoint-365/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926a7444a45d48efd4563a99c4488539f509a3f974643781d5e8dfc252c071a0
3
+ size 5624