File size: 8,110 Bytes
52df640 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7193320488118176,
"eval_steps": 500,
"global_step": 140,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"grad_norm": 6.844920635223389,
"learning_rate": 5e-05,
"logits/chosen": -3.09375,
"logits/rejected": -3.0625,
"logps/chosen": -258.0,
"logps/rejected": -322.0,
"loss": 1.0697,
"max_memory_allocated (GB)": 94.25,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.30078125,
"rewards/chosen": 0.67578125,
"rewards/margins": -0.4140625,
"rewards/rejected": 1.0859375,
"step": 10,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.1,
"grad_norm": 4.300484657287598,
"learning_rate": 0.0001,
"logits/chosen": -3.046875,
"logits/rejected": -3.03125,
"logps/chosen": -286.0,
"logps/rejected": -336.0,
"loss": 0.5736,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.69140625,
"rewards/chosen": -0.150390625,
"rewards/margins": 0.8046875,
"rewards/rejected": -0.95703125,
"step": 20,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.15,
"grad_norm": 1.9487425088882446,
"learning_rate": 0.00015,
"logits/chosen": -2.859375,
"logits/rejected": -2.84375,
"logps/chosen": -294.0,
"logps/rejected": -394.0,
"loss": 0.2394,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.90625,
"rewards/chosen": -1.984375,
"rewards/margins": 4.8125,
"rewards/rejected": -6.8125,
"step": 30,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.21,
"grad_norm": 1.0650818347930908,
"learning_rate": 0.0002,
"logits/chosen": -2.875,
"logits/rejected": -2.828125,
"logps/chosen": -284.0,
"logps/rejected": -388.0,
"loss": 0.1181,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.95703125,
"rewards/chosen": -0.62109375,
"rewards/margins": 5.0625,
"rewards/rejected": -5.6875,
"step": 40,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.26,
"grad_norm": 0.5032941699028015,
"learning_rate": 0.00025,
"logits/chosen": -2.890625,
"logits/rejected": -2.875,
"logps/chosen": -278.0,
"logps/rejected": -412.0,
"loss": 0.0583,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.984375,
"rewards/chosen": -0.8828125,
"rewards/margins": 6.96875,
"rewards/rejected": -7.84375,
"step": 50,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.31,
"grad_norm": 0.8771920800209045,
"learning_rate": 0.0003,
"logits/chosen": -2.828125,
"logits/rejected": -2.828125,
"logps/chosen": -312.0,
"logps/rejected": -474.0,
"loss": 0.0469,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.984375,
"rewards/chosen": -2.609375,
"rewards/margins": 11.5,
"rewards/rejected": -14.125,
"step": 60,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.36,
"grad_norm": 0.42379140853881836,
"learning_rate": 0.00035,
"logits/chosen": -2.84375,
"logits/rejected": -2.84375,
"logps/chosen": -280.0,
"logps/rejected": -436.0,
"loss": 0.0285,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.9921875,
"rewards/chosen": -0.9609375,
"rewards/margins": 9.9375,
"rewards/rejected": -10.9375,
"step": 70,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.41,
"grad_norm": 1.5195761919021606,
"learning_rate": 0.0004,
"logits/chosen": -2.78125,
"logits/rejected": -2.765625,
"logps/chosen": -292.0,
"logps/rejected": -450.0,
"loss": 0.0266,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.98828125,
"rewards/chosen": -1.4453125,
"rewards/margins": 10.75,
"rewards/rejected": -12.1875,
"step": 80,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.46,
"grad_norm": 2.770358085632324,
"learning_rate": 0.00045000000000000004,
"logits/chosen": -2.921875,
"logits/rejected": -2.9375,
"logps/chosen": -276.0,
"logps/rejected": -478.0,
"loss": 0.0486,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.984375,
"rewards/chosen": -1.5703125,
"rewards/margins": 13.375,
"rewards/rejected": -15.0,
"step": 90,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.51,
"grad_norm": 0.1556715965270996,
"learning_rate": 0.0005,
"logits/chosen": -2.75,
"logits/rejected": -2.71875,
"logps/chosen": -284.0,
"logps/rejected": -482.0,
"loss": 0.053,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.9765625,
"rewards/chosen": -1.3125,
"rewards/margins": 13.0,
"rewards/rejected": -14.375,
"step": 100,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.57,
"grad_norm": 0.40476056933403015,
"learning_rate": 0.0004998477067547739,
"logits/chosen": -2.875,
"logits/rejected": -2.875,
"logps/chosen": -296.0,
"logps/rejected": -444.0,
"loss": 0.0384,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.98828125,
"rewards/chosen": -1.2109375,
"rewards/margins": 10.5,
"rewards/rejected": -11.75,
"step": 110,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.62,
"grad_norm": 0.8060222864151001,
"learning_rate": 0.0004993910125649561,
"logits/chosen": -3.234375,
"logits/rejected": -3.234375,
"logps/chosen": -282.0,
"logps/rejected": -456.0,
"loss": 0.0183,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.9921875,
"rewards/chosen": -0.76171875,
"rewards/margins": 12.4375,
"rewards/rejected": -13.1875,
"step": 120,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.67,
"grad_norm": 0.5584326982498169,
"learning_rate": 0.0004986304738420684,
"logits/chosen": -3.140625,
"logits/rejected": -3.125,
"logps/chosen": -296.0,
"logps/rejected": -496.0,
"loss": 0.0294,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.984375,
"rewards/chosen": -1.875,
"rewards/margins": 14.8125,
"rewards/rejected": -16.75,
"step": 130,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.72,
"grad_norm": 1.2188811302185059,
"learning_rate": 0.0004975670171853926,
"logits/chosen": -3.21875,
"logits/rejected": -3.21875,
"logps/chosen": -300.0,
"logps/rejected": -478.0,
"loss": 0.0312,
"max_memory_allocated (GB)": 94.39,
"memory_allocated (GB)": 51.7,
"rewards/accuracies": 0.98828125,
"rewards/chosen": -1.3515625,
"rewards/margins": 13.0,
"rewards/rejected": -14.375,
"step": 140,
"total_memory_available (GB)": 94.62
}
],
"logging_steps": 10,
"max_steps": 1000,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 10,
"total_flos": 1.1758891922620416e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|