File size: 8,282 Bytes
3bb9cae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 159.53125,
      "epoch": 0.1,
      "grad_norm": 42.64451599121094,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 0.2750730898696929,
      "reward_std": 0.33796203549718484,
      "rewards/concensus_correctness_reward_func": 0.06018749997019768,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.12097934319172055,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.031093750149011612,
      "step": 2
    },
    {
      "completion_length": 129.5,
      "epoch": 0.2,
      "grad_norm": 33.4676628112793,
      "kl": 0.0017403407077836164,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 0.08828154078219086,
      "reward_std": 0.09351343158414238,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.11493779090233147,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.026656249538064003,
      "step": 4
    },
    {
      "completion_length": 156.6875,
      "epoch": 0.3,
      "grad_norm": 23.76153564453125,
      "kl": 0.016077187114206026,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.20646477834088728,
      "reward_std": 0.22474737564334646,
      "rewards/concensus_correctness_reward_func": 0.05999999865889549,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.0922772788326256,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.008312500081956387,
      "step": 6
    },
    {
      "completion_length": 140.78125,
      "epoch": 0.4,
      "grad_norm": 17.65758514404297,
      "kl": 0.009867031902103918,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.33196004456840456,
      "reward_std": 0.34907107069011545,
      "rewards/concensus_correctness_reward_func": 0.07918750122189522,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.1137725441949442,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.013999999966472387,
      "step": 8
    },
    {
      "completion_length": 188.21875,
      "epoch": 0.5,
      "grad_norm": 11.617631912231445,
      "kl": 0.00979025863125571,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 0.30701479013077915,
      "reward_std": 0.3836260371335811,
      "rewards/concensus_correctness_reward_func": 0.051750000566244125,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.1222335389466025,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.008031250443309546,
      "step": 10
    },
    {
      "completion_length": 158.5,
      "epoch": 0.6,
      "grad_norm": 10.506937980651855,
      "kl": 0.015619799527485156,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 0.3158440781990066,
      "reward_std": 0.09872026408629608,
      "rewards/concensus_correctness_reward_func": 0.11999999731779099,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.10565658047562465,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.03481250139884651,
      "step": 12
    },
    {
      "completion_length": 173.8125,
      "epoch": 0.7,
      "grad_norm": 5.180370330810547,
      "kl": 0.015626165712092188,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 0.33155799441738054,
      "reward_std": 0.31527659608400427,
      "rewards/concensus_correctness_reward_func": 0.07293750066310167,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.11968300043372437,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.013937500305473804,
      "step": 14
    },
    {
      "completion_length": 138.34375,
      "epoch": 0.8,
      "grad_norm": 12.473709106445312,
      "kl": 0.029021206886682194,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 0.6483697192743421,
      "reward_std": 0.21503988321637735,
      "rewards/concensus_correctness_reward_func": 0.3017500005662441,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.1563384763430804,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.002781250048428774,
      "step": 16
    },
    {
      "completion_length": 176.5625,
      "epoch": 0.9,
      "grad_norm": 10.102160453796387,
      "kl": 0.007534470460086595,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 0.14994344190927222,
      "reward_std": 0.15157496054234798,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.12247469584690407,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.03503125044517219,
      "step": 18
    },
    {
      "completion_length": 173.1875,
      "epoch": 1.0,
      "grad_norm": 7.306704998016357,
      "kl": 0.006795531931857113,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.1505529017886147,
      "reward_std": 0.1496142033720389,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.13749039953108877,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.0494375005364418,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.1270371521732158e-05,
      "train_runtime": 15994.6068,
      "train_samples_per_second": 0.02,
      "train_steps_per_second": 0.001
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}