| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4934210526315789, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006578947368421052, | |
| "grad_norm": 4.683763027191162, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.3874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006578947368421052, | |
| "eval_loss": 1.5863150358200073, | |
| "eval_runtime": 12.1886, | |
| "eval_samples_per_second": 10.584, | |
| "eval_steps_per_second": 5.333, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013157894736842105, | |
| "grad_norm": 4.751871109008789, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.8587, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019736842105263157, | |
| "grad_norm": 5.826901435852051, | |
| "learning_rate": 0.0001, | |
| "loss": 12.0305, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 5.796934127807617, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 12.1736, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03289473684210526, | |
| "grad_norm": 5.535815715789795, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 10.7405, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.039473684210526314, | |
| "grad_norm": 5.5817975997924805, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.2704, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.046052631578947366, | |
| "grad_norm": 6.0977983474731445, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.8744, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 6.505789279937744, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 10.0401, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05921052631578947, | |
| "grad_norm": 5.587679386138916, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.4585, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "grad_norm": 5.400643348693848, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 11.9279, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07236842105263158, | |
| "grad_norm": 5.925045013427734, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 8.0437, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 5.797214984893799, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.5078, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08552631578947369, | |
| "grad_norm": 5.878451347351074, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 11.8092, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09210526315789473, | |
| "grad_norm": 6.047119617462158, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 11.2271, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09868421052631579, | |
| "grad_norm": 6.350561618804932, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.6742, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 6.4842047691345215, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 9.9198, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1118421052631579, | |
| "grad_norm": 6.810247898101807, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 10.6038, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11842105263157894, | |
| "grad_norm": 5.906208515167236, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.2307, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 6.2693772315979, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 13.0133, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 6.6559271812438965, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 10.8347, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13815789473684212, | |
| "grad_norm": 6.143450736999512, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 12.0125, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14473684210526316, | |
| "grad_norm": 6.3912224769592285, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 10.9285, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1513157894736842, | |
| "grad_norm": 7.889128684997559, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 11.2765, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 6.0514020919799805, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.144, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16447368421052633, | |
| "grad_norm": 7.878673553466797, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 11.0654, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16447368421052633, | |
| "eval_loss": 1.369149088859558, | |
| "eval_runtime": 12.2247, | |
| "eval_samples_per_second": 10.552, | |
| "eval_steps_per_second": 5.317, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17105263157894737, | |
| "grad_norm": 6.711698532104492, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 10.4598, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17763157894736842, | |
| "grad_norm": 5.988046646118164, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 12.4122, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 6.7396345138549805, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 10.6514, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19078947368421054, | |
| "grad_norm": 7.260731220245361, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 10.9607, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "grad_norm": 6.341261863708496, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 12.1942, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20394736842105263, | |
| "grad_norm": 7.080831527709961, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 13.2871, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 9.200007438659668, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 11.3735, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.21710526315789475, | |
| "grad_norm": 8.438835144042969, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 9.7034, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2236842105263158, | |
| "grad_norm": 8.435461044311523, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 12.39, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23026315789473684, | |
| "grad_norm": 7.083141326904297, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 11.1461, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 6.454171657562256, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 8.7345, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24342105263157895, | |
| "grad_norm": 8.99131965637207, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 10.1263, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 9.920761108398438, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 9.2578, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2565789473684211, | |
| "grad_norm": 9.285501480102539, | |
| "learning_rate": 5e-05, | |
| "loss": 8.6679, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 9.787482261657715, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 8.7731, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26973684210526316, | |
| "grad_norm": 9.969244956970215, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 9.7417, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.27631578947368424, | |
| "grad_norm": 11.214414596557617, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.0999, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.28289473684210525, | |
| "grad_norm": 7.822074890136719, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 10.8718, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2894736842105263, | |
| "grad_norm": 10.223742485046387, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 10.8404, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.29605263157894735, | |
| "grad_norm": 6.327630996704102, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.2936, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3026315789473684, | |
| "grad_norm": 5.0185651779174805, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 8.2814, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3092105263157895, | |
| "grad_norm": 5.958381175994873, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 10.0383, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 5.123436450958252, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 12.5394, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3223684210526316, | |
| "grad_norm": 5.286769866943359, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 10.9169, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "grad_norm": 5.482089042663574, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 11.8786, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "eval_loss": 1.3653817176818848, | |
| "eval_runtime": 12.2397, | |
| "eval_samples_per_second": 10.54, | |
| "eval_steps_per_second": 5.311, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3355263157894737, | |
| "grad_norm": 6.4667439460754395, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.2426, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.34210526315789475, | |
| "grad_norm": 5.597299098968506, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 9.1077, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.34868421052631576, | |
| "grad_norm": 4.8260884284973145, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 11.6975, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.35526315789473684, | |
| "grad_norm": 5.861974716186523, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.6898, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3618421052631579, | |
| "grad_norm": 4.4668378829956055, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 12.0545, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 5.416546821594238, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 12.0258, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 6.295071125030518, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 9.6541, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3815789473684211, | |
| "grad_norm": 5.567584037780762, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 12.2458, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.3881578947368421, | |
| "grad_norm": 6.616762638092041, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 12.9287, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 5.237483501434326, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.8718, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.40131578947368424, | |
| "grad_norm": 5.236186981201172, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 12.2105, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.40789473684210525, | |
| "grad_norm": 6.172914505004883, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 12.6731, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4144736842105263, | |
| "grad_norm": 5.345962047576904, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 12.0877, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 5.08330774307251, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 10.9855, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4276315789473684, | |
| "grad_norm": 5.678718566894531, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 10.4774, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4342105263157895, | |
| "grad_norm": 7.054388999938965, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9022, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4407894736842105, | |
| "grad_norm": 6.364291191101074, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 8.7441, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4473684210526316, | |
| "grad_norm": 5.535186290740967, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 11.2657, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.45394736842105265, | |
| "grad_norm": 5.470834255218506, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.0374, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "grad_norm": 6.9800705909729, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 12.873, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46710526315789475, | |
| "grad_norm": 6.102013111114502, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 11.3473, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 7.423451900482178, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 12.4332, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.48026315789473684, | |
| "grad_norm": 6.381293296813965, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 11.5429, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4868421052631579, | |
| "grad_norm": 7.644157886505127, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 11.1958, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.4934210526315789, | |
| "grad_norm": 7.911625862121582, | |
| "learning_rate": 0.0, | |
| "loss": 12.3073, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4934210526315789, | |
| "eval_loss": 1.3638100624084473, | |
| "eval_runtime": 12.2644, | |
| "eval_samples_per_second": 10.518, | |
| "eval_steps_per_second": 5.3, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 9.86082145468416e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |