File size: 6,252 Bytes
d33638d |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6489292667099286,
"eval_steps": 25,
"global_step": 125,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.12978585334198572,
"grad_norm": 64.38245391845703,
"learning_rate": 5e-07,
"logits/chosen": -1.9029332399368286,
"logits/rejected": -2.053706407546997,
"logps/chosen": -40.4902458190918,
"logps/rejected": -25.3558406829834,
"loss": 0.5968,
"rewards/accuracies": 0.800000011920929,
"rewards/chosen": 0.17978771030902863,
"rewards/margins": 0.2116149365901947,
"rewards/rejected": -0.031827230006456375,
"step": 25
},
{
"epoch": 0.12978585334198572,
"eval_logits/chosen": -1.9241564273834229,
"eval_logits/rejected": -2.0354554653167725,
"eval_logps/chosen": -38.01565933227539,
"eval_logps/rejected": -26.247798919677734,
"eval_loss": 0.454921156167984,
"eval_rewards/accuracies": 1.0,
"eval_rewards/chosen": 0.4693543612957001,
"eval_rewards/margins": 0.5530296564102173,
"eval_rewards/rejected": -0.083675317466259,
"eval_runtime": 140.2735,
"eval_samples_per_second": 0.585,
"eval_steps_per_second": 0.585,
"step": 25
},
{
"epoch": 0.25957170668397145,
"grad_norm": 40.388370513916016,
"learning_rate": 5e-07,
"logits/chosen": -1.9818081855773926,
"logits/rejected": -2.0913336277008057,
"logps/chosen": -34.876155853271484,
"logps/rejected": -27.348379135131836,
"loss": 0.3498,
"rewards/accuracies": 1.0,
"rewards/chosen": 0.7389992475509644,
"rewards/margins": 0.8872407674789429,
"rewards/rejected": -0.14824140071868896,
"step": 50
},
{
"epoch": 0.25957170668397145,
"eval_logits/chosen": -2.0032734870910645,
"eval_logits/rejected": -2.0942301750183105,
"eval_logps/chosen": -32.67618942260742,
"eval_logps/rejected": -27.68032455444336,
"eval_loss": 0.2584493160247803,
"eval_rewards/accuracies": 1.0,
"eval_rewards/chosen": 1.003301739692688,
"eval_rewards/margins": 1.2302298545837402,
"eval_rewards/rejected": -0.22692809998989105,
"eval_runtime": 140.4996,
"eval_samples_per_second": 0.584,
"eval_steps_per_second": 0.584,
"step": 50
},
{
"epoch": 0.3893575600259572,
"grad_norm": 29.64296531677246,
"learning_rate": 5e-07,
"logits/chosen": -2.0457983016967773,
"logits/rejected": -2.112644910812378,
"logps/chosen": -29.919565200805664,
"logps/rejected": -29.504945755004883,
"loss": 0.1989,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.2103655338287354,
"rewards/margins": 1.545750379562378,
"rewards/rejected": -0.33538496494293213,
"step": 75
},
{
"epoch": 0.3893575600259572,
"eval_logits/chosen": -2.056947946548462,
"eval_logits/rejected": -2.1299691200256348,
"eval_logps/chosen": -28.753862380981445,
"eval_logps/rejected": -30.1635684967041,
"eval_loss": 0.14609307050704956,
"eval_rewards/accuracies": 1.0,
"eval_rewards/chosen": 1.3955342769622803,
"eval_rewards/margins": 1.8707866668701172,
"eval_rewards/rejected": -0.4752523899078369,
"eval_runtime": 140.5032,
"eval_samples_per_second": 0.584,
"eval_steps_per_second": 0.584,
"step": 75
},
{
"epoch": 0.5191434133679429,
"grad_norm": 15.144841194152832,
"learning_rate": 5e-07,
"logits/chosen": -1.9773192405700684,
"logits/rejected": -2.081099271774292,
"logps/chosen": -27.414873123168945,
"logps/rejected": -32.0408935546875,
"loss": 0.1067,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.5709582567214966,
"rewards/margins": 2.2332875728607178,
"rewards/rejected": -0.6623291969299316,
"step": 100
},
{
"epoch": 0.5191434133679429,
"eval_logits/chosen": -2.0898687839508057,
"eval_logits/rejected": -2.1492760181427,
"eval_logps/chosen": -25.59548568725586,
"eval_logps/rejected": -34.3668098449707,
"eval_loss": 0.07369648665189743,
"eval_rewards/accuracies": 1.0,
"eval_rewards/chosen": 1.7113721370697021,
"eval_rewards/margins": 2.6069483757019043,
"eval_rewards/rejected": -0.8955763578414917,
"eval_runtime": 140.7464,
"eval_samples_per_second": 0.583,
"eval_steps_per_second": 0.583,
"step": 100
},
{
"epoch": 0.6489292667099286,
"grad_norm": 6.891702175140381,
"learning_rate": 5e-07,
"logits/chosen": -2.0497264862060547,
"logits/rejected": -2.113835334777832,
"logps/chosen": -25.3034725189209,
"logps/rejected": -37.589698791503906,
"loss": 0.0501,
"rewards/accuracies": 1.0,
"rewards/chosen": 1.810562014579773,
"rewards/margins": 3.047495126724243,
"rewards/rejected": -1.2369328737258911,
"step": 125
},
{
"epoch": 0.6489292667099286,
"eval_logits/chosen": -2.117217540740967,
"eval_logits/rejected": -2.166142463684082,
"eval_logps/chosen": -24.0587100982666,
"eval_logps/rejected": -42.671173095703125,
"eval_loss": 0.02941078133881092,
"eval_rewards/accuracies": 1.0,
"eval_rewards/chosen": 1.8650493621826172,
"eval_rewards/margins": 3.59106183052063,
"eval_rewards/rejected": -1.7260124683380127,
"eval_runtime": 140.3665,
"eval_samples_per_second": 0.584,
"eval_steps_per_second": 0.584,
"step": 125
}
],
"logging_steps": 25,
"max_steps": 384,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|