File size: 7,350 Bytes
983fcfc |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.10660980810234541,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.010660980810234541,
"grad_norm": 0.051327500492334366,
"learning_rate": 4.999451708687114e-06,
"logits/chosen": 14.755006790161133,
"logits/rejected": 14.735244750976562,
"logps/chosen": -0.29377540946006775,
"logps/rejected": -0.30969956517219543,
"loss": 0.952,
"rewards/accuracies": 0.4375,
"rewards/chosen": -0.44066309928894043,
"rewards/margins": 0.023886267095804214,
"rewards/rejected": -0.46454939246177673,
"step": 10
},
{
"epoch": 0.021321961620469083,
"grad_norm": 0.04346882924437523,
"learning_rate": 4.997807075247147e-06,
"logits/chosen": 14.513801574707031,
"logits/rejected": 14.946454048156738,
"logps/chosen": -0.27995699644088745,
"logps/rejected": -0.30138006806373596,
"loss": 0.9726,
"rewards/accuracies": 0.4124999940395355,
"rewards/chosen": -0.4199354648590088,
"rewards/margins": 0.03213457390666008,
"rewards/rejected": -0.45207005739212036,
"step": 20
},
{
"epoch": 0.031982942430703626,
"grad_norm": 0.05228634551167488,
"learning_rate": 4.9950668210706795e-06,
"logits/chosen": 14.266324043273926,
"logits/rejected": 14.423965454101562,
"logps/chosen": -0.2919609546661377,
"logps/rejected": -0.32358455657958984,
"loss": 0.9622,
"rewards/accuracies": 0.5,
"rewards/chosen": -0.43794146180152893,
"rewards/margins": 0.047435395419597626,
"rewards/rejected": -0.48537683486938477,
"step": 30
},
{
"epoch": 0.042643923240938165,
"grad_norm": 0.05487598106265068,
"learning_rate": 4.9912321481237616e-06,
"logits/chosen": 14.965211868286133,
"logits/rejected": 15.058088302612305,
"logps/chosen": -0.277716726064682,
"logps/rejected": -0.3055034577846527,
"loss": 0.9403,
"rewards/accuracies": 0.4000000059604645,
"rewards/chosen": -0.4165751039981842,
"rewards/margins": 0.04168009012937546,
"rewards/rejected": -0.4582551419734955,
"step": 40
},
{
"epoch": 0.053304904051172705,
"grad_norm": 0.057255037128925323,
"learning_rate": 4.986304738420684e-06,
"logits/chosen": 14.539288520812988,
"logits/rejected": 15.174041748046875,
"logps/chosen": -0.26362231373786926,
"logps/rejected": -0.3325727581977844,
"loss": 0.9588,
"rewards/accuracies": 0.4749999940395355,
"rewards/chosen": -0.3954334557056427,
"rewards/margins": 0.10342560708522797,
"rewards/rejected": -0.49885907769203186,
"step": 50
},
{
"epoch": 0.053304904051172705,
"eval_logits/chosen": 14.618952751159668,
"eval_logits/rejected": 15.176809310913086,
"eval_logps/chosen": -0.2685677409172058,
"eval_logps/rejected": -0.3283654451370239,
"eval_loss": 0.9551004767417908,
"eval_rewards/accuracies": 0.5131579041481018,
"eval_rewards/chosen": -0.4028516113758087,
"eval_rewards/margins": 0.08969658613204956,
"eval_rewards/rejected": -0.4925481975078583,
"eval_runtime": 21.4453,
"eval_samples_per_second": 28.305,
"eval_steps_per_second": 3.544,
"step": 50
},
{
"epoch": 0.06396588486140725,
"grad_norm": 0.05227242782711983,
"learning_rate": 4.980286753286196e-06,
"logits/chosen": 14.787714004516602,
"logits/rejected": 15.379422187805176,
"logps/chosen": -0.3143109679222107,
"logps/rejected": -0.3425135612487793,
"loss": 0.9636,
"rewards/accuracies": 0.4625000059604645,
"rewards/chosen": -0.4714665412902832,
"rewards/margins": 0.042303841561079025,
"rewards/rejected": -0.513770341873169,
"step": 60
},
{
"epoch": 0.07462686567164178,
"grad_norm": 0.0658508762717247,
"learning_rate": 4.973180832407471e-06,
"logits/chosen": 15.149365425109863,
"logits/rejected": 15.115835189819336,
"logps/chosen": -0.31501108407974243,
"logps/rejected": -0.2854115962982178,
"loss": 0.9677,
"rewards/accuracies": 0.36250001192092896,
"rewards/chosen": -0.47251659631729126,
"rewards/margins": -0.04439922422170639,
"rewards/rejected": -0.4281173646450043,
"step": 70
},
{
"epoch": 0.08528784648187633,
"grad_norm": 0.06567618995904922,
"learning_rate": 4.964990092676263e-06,
"logits/chosen": 15.393908500671387,
"logits/rejected": 15.454248428344727,
"logps/chosen": -0.31166282296180725,
"logps/rejected": -0.3178747594356537,
"loss": 0.9609,
"rewards/accuracies": 0.42500001192092896,
"rewards/chosen": -0.4674941897392273,
"rewards/margins": 0.009317949414253235,
"rewards/rejected": -0.47681212425231934,
"step": 80
},
{
"epoch": 0.09594882729211088,
"grad_norm": 0.07566913962364197,
"learning_rate": 4.9557181268217225e-06,
"logits/chosen": 15.229632377624512,
"logits/rejected": 15.477168083190918,
"logps/chosen": -0.3294064998626709,
"logps/rejected": -0.3528878390789032,
"loss": 0.9587,
"rewards/accuracies": 0.4749999940395355,
"rewards/chosen": -0.49410971999168396,
"rewards/margins": 0.03522203490138054,
"rewards/rejected": -0.5293318033218384,
"step": 90
},
{
"epoch": 0.10660980810234541,
"grad_norm": 0.09082464128732681,
"learning_rate": 4.9453690018345144e-06,
"logits/chosen": 14.481330871582031,
"logits/rejected": 15.092982292175293,
"logps/chosen": -0.2656436562538147,
"logps/rejected": -0.33982905745506287,
"loss": 0.9548,
"rewards/accuracies": 0.5625,
"rewards/chosen": -0.39846545457839966,
"rewards/margins": 0.11127817630767822,
"rewards/rejected": -0.5097435712814331,
"step": 100
},
{
"epoch": 0.10660980810234541,
"eval_logits/chosen": 14.7100830078125,
"eval_logits/rejected": 15.274725914001465,
"eval_logps/chosen": -0.26462864875793457,
"eval_logps/rejected": -0.331702321767807,
"eval_loss": 0.947841465473175,
"eval_rewards/accuracies": 0.5394737124443054,
"eval_rewards/chosen": -0.39694297313690186,
"eval_rewards/margins": 0.10061051696538925,
"eval_rewards/rejected": -0.4975534677505493,
"eval_runtime": 21.4421,
"eval_samples_per_second": 28.309,
"eval_steps_per_second": 3.544,
"step": 100
}
],
"logging_steps": 10,
"max_steps": 1500,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.4067267787698995e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|