Spaces:
Runtime error
Runtime error
File size: 9,813 Bytes
8dc7642 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 | {
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.625,
"eval_steps": 500,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.375,
"completions/clipped_ratio": 0.0,
"completions/max_length": 3.0,
"completions/max_terminated_length": 3.0,
"completions/mean_length": 2.375,
"completions/mean_terminated_length": 2.375,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.0625,
"frac_reward_zero_std": 0.5,
"grad_norm": 5.300995349884033,
"kl": 0.0,
"learning_rate": 0.0,
"loss": 0.01562187448143959,
"num_tokens": 8343.0,
"reward": 0.125,
"reward_std": 0.25,
"rewards/reward_from_oracle/mean": 0.125,
"rewards/reward_from_oracle/std": 0.3535533845424652,
"step": 1
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.375,
"completions/clipped_ratio": 0.0,
"completions/max_length": 3.0,
"completions/max_terminated_length": 3.0,
"completions/mean_length": 2.375,
"completions/mean_terminated_length": 2.375,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.125,
"frac_reward_zero_std": 0.0,
"grad_norm": 9.095938682556152,
"kl": 0.0,
"learning_rate": 5e-06,
"loss": 0.029151180759072304,
"num_tokens": 16682.0,
"reward": 0.375,
"reward_std": 0.5386751294136047,
"rewards/reward_from_oracle/mean": 0.375,
"rewards/reward_from_oracle/std": 0.5175492167472839,
"step": 2
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.375,
"completions/clipped_ratio": 0.0,
"completions/max_length": 3.0,
"completions/max_terminated_length": 3.0,
"completions/mean_length": 2.375,
"completions/mean_terminated_length": 2.375,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.1875,
"frac_reward_zero_std": 0.0,
"grad_norm": 8.75147533416748,
"kl": 0.0,
"learning_rate": 4.849231551964771e-06,
"loss": 0.023432811722159386,
"num_tokens": 25025.0,
"reward": 0.25,
"reward_std": 0.5,
"rewards/reward_from_oracle/mean": 0.25,
"rewards/reward_from_oracle/std": 0.4629100561141968,
"step": 3
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.125,
"completions/clipped_ratio": 0.0,
"completions/max_length": 3.0,
"completions/max_terminated_length": 3.0,
"completions/mean_length": 2.125,
"completions/mean_terminated_length": 2.125,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.25,
"frac_reward_zero_std": 0.0,
"grad_norm": 10.478106498718262,
"kl": 0.0,
"learning_rate": 4.415111107797445e-06,
"loss": 0.013529304414987564,
"num_tokens": 33362.0,
"reward": 0.5,
"reward_std": 0.5773502588272095,
"rewards/reward_from_oracle/mean": 0.5,
"rewards/reward_from_oracle/std": 0.5345224738121033,
"step": 4
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.125,
"completions/clipped_ratio": 0.0,
"completions/max_length": 3.0,
"completions/max_terminated_length": 3.0,
"completions/mean_length": 2.125,
"completions/mean_terminated_length": 2.125,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.3125,
"frac_reward_zero_std": 0.0,
"grad_norm": 8.125267028808594,
"kl": 0.0,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.013529304414987564,
"num_tokens": 41707.0,
"reward": 0.625,
"reward_std": 0.5386751294136047,
"rewards/reward_from_oracle/mean": 0.625,
"rewards/reward_from_oracle/std": 0.5175492167472839,
"step": 5
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.0,
"completions/clipped_ratio": 0.0,
"completions/max_length": 2.0,
"completions/max_terminated_length": 2.0,
"completions/mean_length": 2.0,
"completions/mean_terminated_length": 2.0,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.375,
"frac_reward_zero_std": 0.5,
"grad_norm": 3.183867931365967,
"kl": 0.0,
"learning_rate": 2.9341204441673267e-06,
"loss": 0.0,
"num_tokens": 50047.0,
"reward": 0.875,
"reward_std": 0.25,
"rewards/reward_from_oracle/mean": 0.875,
"rewards/reward_from_oracle/std": 0.3535533845424652,
"step": 6
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.0,
"completions/clipped_ratio": 0.0,
"completions/max_length": 2.0,
"completions/max_terminated_length": 2.0,
"completions/mean_length": 2.0,
"completions/mean_terminated_length": 2.0,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.4375,
"frac_reward_zero_std": 0.0,
"grad_norm": 7.007436275482178,
"kl": 0.0,
"learning_rate": 2.0658795558326745e-06,
"loss": 0.0,
"num_tokens": 58391.0,
"reward": 0.75,
"reward_std": 0.5,
"rewards/reward_from_oracle/mean": 0.75,
"rewards/reward_from_oracle/std": 0.4629100561141968,
"step": 7
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.0,
"completions/clipped_ratio": 0.0,
"completions/max_length": 2.0,
"completions/max_terminated_length": 2.0,
"completions/mean_length": 2.0,
"completions/mean_terminated_length": 2.0,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.5,
"frac_reward_zero_std": 0.5,
"grad_norm": 3.759775161743164,
"kl": 0.0,
"learning_rate": 1.2500000000000007e-06,
"loss": 1.862645149230957e-09,
"num_tokens": 66727.0,
"reward": 0.875,
"reward_std": 0.25,
"rewards/reward_from_oracle/mean": 0.875,
"rewards/reward_from_oracle/std": 0.3535533845424652,
"step": 8
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.0,
"completions/clipped_ratio": 0.0,
"completions/max_length": 2.0,
"completions/max_terminated_length": 2.0,
"completions/mean_length": 2.0,
"completions/mean_terminated_length": 2.0,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.5625,
"frac_reward_zero_std": 0.0,
"grad_norm": 7.748785495758057,
"kl": 0.0,
"learning_rate": 5.848888922025553e-07,
"loss": 1.862645149230957e-09,
"num_tokens": 75063.0,
"reward": 0.75,
"reward_std": 0.5,
"rewards/reward_from_oracle/mean": 0.75,
"rewards/reward_from_oracle/std": 0.4629100561141968,
"step": 9
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completion_length": 2.0,
"completions/clipped_ratio": 0.0,
"completions/max_length": 2.0,
"completions/max_terminated_length": 2.0,
"completions/mean_length": 2.0,
"completions/mean_terminated_length": 2.0,
"completions/min_length": 2.0,
"completions/min_terminated_length": 2.0,
"epoch": 0.625,
"frac_reward_zero_std": 1.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 1.507684480352292e-07,
"loss": 0.0,
"num_tokens": 83403.0,
"reward": 1.0,
"reward_std": 0.0,
"rewards/reward_from_oracle/mean": 1.0,
"rewards/reward_from_oracle/std": 0.0,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 83403,
"num_train_epochs": 1,
"save_steps": 10,
"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": 8,
"trial_name": null,
"trial_params": null
}
|