| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 49.9957805907173, | |
| "global_step": 5900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7731608395748838, | |
| "eval_loss": 1.273674726486206, | |
| "eval_runtime": 27.8473, | |
| "eval_samples_per_second": 71.353, | |
| "eval_steps_per_second": 3.591, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7844064852916506, | |
| "eval_loss": 1.149436354637146, | |
| "eval_runtime": 27.7157, | |
| "eval_samples_per_second": 71.692, | |
| "eval_steps_per_second": 3.608, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7886655417073725, | |
| "eval_loss": 1.115924596786499, | |
| "eval_runtime": 27.7526, | |
| "eval_samples_per_second": 71.597, | |
| "eval_steps_per_second": 3.603, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7905562627668078, | |
| "eval_loss": 1.0954861640930176, | |
| "eval_runtime": 27.7193, | |
| "eval_samples_per_second": 71.683, | |
| "eval_steps_per_second": 3.608, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 4.5762711864406784e-05, | |
| "loss": 3.3542, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7918075332800458, | |
| "eval_loss": 1.0870832204818726, | |
| "eval_runtime": 27.7224, | |
| "eval_samples_per_second": 71.675, | |
| "eval_steps_per_second": 3.607, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7928476272240149, | |
| "eval_loss": 1.0806066989898682, | |
| "eval_runtime": 27.72, | |
| "eval_samples_per_second": 71.681, | |
| "eval_steps_per_second": 3.607, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7931219594027847, | |
| "eval_loss": 1.0786826610565186, | |
| "eval_runtime": 27.7079, | |
| "eval_samples_per_second": 71.712, | |
| "eval_steps_per_second": 3.609, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7938285127840768, | |
| "eval_loss": 1.0748920440673828, | |
| "eval_runtime": 27.7168, | |
| "eval_samples_per_second": 71.689, | |
| "eval_steps_per_second": 3.608, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 4.152542372881356e-05, | |
| "loss": 1.0048, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7937554891105914, | |
| "eval_loss": 1.0768133401870728, | |
| "eval_runtime": 27.8358, | |
| "eval_samples_per_second": 71.383, | |
| "eval_steps_per_second": 3.592, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.793783119689748, | |
| "eval_loss": 1.076497197151184, | |
| "eval_runtime": 27.7645, | |
| "eval_samples_per_second": 71.566, | |
| "eval_steps_per_second": 3.602, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7941719214107384, | |
| "eval_loss": 1.0760843753814697, | |
| "eval_runtime": 28.0837, | |
| "eval_samples_per_second": 70.753, | |
| "eval_steps_per_second": 3.561, | |
| "step": 1298 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7943712563032259, | |
| "eval_loss": 1.078471064567566, | |
| "eval_runtime": 27.7304, | |
| "eval_samples_per_second": 71.654, | |
| "eval_steps_per_second": 3.606, | |
| "step": 1416 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 3.728813559322034e-05, | |
| "loss": 0.9221, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7942034992154889, | |
| "eval_loss": 1.0854936838150024, | |
| "eval_runtime": 27.702, | |
| "eval_samples_per_second": 71.728, | |
| "eval_steps_per_second": 3.61, | |
| "step": 1534 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7943969132695856, | |
| "eval_loss": 1.0861722230911255, | |
| "eval_runtime": 27.7005, | |
| "eval_samples_per_second": 71.731, | |
| "eval_steps_per_second": 3.61, | |
| "step": 1652 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7947047968659029, | |
| "eval_loss": 1.0891741514205933, | |
| "eval_runtime": 27.7017, | |
| "eval_samples_per_second": 71.729, | |
| "eval_steps_per_second": 3.61, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7944600688790866, | |
| "eval_loss": 1.0921040773391724, | |
| "eval_runtime": 27.6967, | |
| "eval_samples_per_second": 71.741, | |
| "eval_steps_per_second": 3.611, | |
| "step": 1888 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 3.305084745762712e-05, | |
| "loss": 0.8534, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7944245438487423, | |
| "eval_loss": 1.0993601083755493, | |
| "eval_runtime": 27.7053, | |
| "eval_samples_per_second": 71.719, | |
| "eval_steps_per_second": 3.609, | |
| "step": 2006 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7944719105558681, | |
| "eval_loss": 1.100709319114685, | |
| "eval_runtime": 27.7072, | |
| "eval_samples_per_second": 71.714, | |
| "eval_steps_per_second": 3.609, | |
| "step": 2124 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7942567867610053, | |
| "eval_loss": 1.1095192432403564, | |
| "eval_runtime": 27.6924, | |
| "eval_samples_per_second": 71.753, | |
| "eval_steps_per_second": 3.611, | |
| "step": 2242 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7939962698718138, | |
| "eval_loss": 1.1117533445358276, | |
| "eval_runtime": 27.706, | |
| "eval_samples_per_second": 71.717, | |
| "eval_steps_per_second": 3.609, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7940456101917365, | |
| "eval_loss": 1.1208868026733398, | |
| "eval_runtime": 27.7121, | |
| "eval_samples_per_second": 71.702, | |
| "eval_steps_per_second": 3.609, | |
| "step": 2478 | |
| }, | |
| { | |
| "epoch": 21.19, | |
| "learning_rate": 2.88135593220339e-05, | |
| "loss": 0.7959, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7939271934239222, | |
| "eval_loss": 1.1249679327011108, | |
| "eval_runtime": 27.7085, | |
| "eval_samples_per_second": 71.711, | |
| "eval_steps_per_second": 3.609, | |
| "step": 2596 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7937811460769512, | |
| "eval_loss": 1.1323717832565308, | |
| "eval_runtime": 27.7079, | |
| "eval_samples_per_second": 71.712, | |
| "eval_steps_per_second": 3.609, | |
| "step": 2714 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7939074572959531, | |
| "eval_loss": 1.136080026626587, | |
| "eval_runtime": 27.704, | |
| "eval_samples_per_second": 71.723, | |
| "eval_steps_per_second": 3.61, | |
| "step": 2832 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7935601014436977, | |
| "eval_loss": 1.1441864967346191, | |
| "eval_runtime": 27.6972, | |
| "eval_samples_per_second": 71.74, | |
| "eval_steps_per_second": 3.61, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 2.457627118644068e-05, | |
| "loss": 0.7458, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7934377374502897, | |
| "eval_loss": 1.1540361642837524, | |
| "eval_runtime": 27.7164, | |
| "eval_samples_per_second": 71.69, | |
| "eval_steps_per_second": 3.608, | |
| "step": 3068 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7932680067497557, | |
| "eval_loss": 1.1579915285110474, | |
| "eval_runtime": 27.7102, | |
| "eval_samples_per_second": 71.706, | |
| "eval_steps_per_second": 3.609, | |
| "step": 3186 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.793429842999102, | |
| "eval_loss": 1.1653059720993042, | |
| "eval_runtime": 27.7095, | |
| "eval_samples_per_second": 71.708, | |
| "eval_steps_per_second": 3.609, | |
| "step": 3304 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7931002496620189, | |
| "eval_loss": 1.1742562055587769, | |
| "eval_runtime": 27.7109, | |
| "eval_samples_per_second": 71.705, | |
| "eval_steps_per_second": 3.609, | |
| "step": 3422 | |
| }, | |
| { | |
| "epoch": 29.66, | |
| "learning_rate": 2.033898305084746e-05, | |
| "loss": 0.7034, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7932344553322084, | |
| "eval_loss": 1.1726936101913452, | |
| "eval_runtime": 27.7127, | |
| "eval_samples_per_second": 71.7, | |
| "eval_steps_per_second": 3.608, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7930153843117519, | |
| "eval_loss": 1.1811208724975586, | |
| "eval_runtime": 27.7003, | |
| "eval_samples_per_second": 71.732, | |
| "eval_steps_per_second": 3.61, | |
| "step": 3658 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7930114370861581, | |
| "eval_loss": 1.1879879236221313, | |
| "eval_runtime": 27.7125, | |
| "eval_samples_per_second": 71.701, | |
| "eval_steps_per_second": 3.608, | |
| "step": 3776 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7927528938097634, | |
| "eval_loss": 1.1952810287475586, | |
| "eval_runtime": 27.7028, | |
| "eval_samples_per_second": 71.726, | |
| "eval_steps_per_second": 3.61, | |
| "step": 3894 | |
| }, | |
| { | |
| "epoch": 33.89, | |
| "learning_rate": 1.6101694915254237e-05, | |
| "loss": 0.6688, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7928298647088428, | |
| "eval_loss": 1.200770378112793, | |
| "eval_runtime": 27.7087, | |
| "eval_samples_per_second": 71.71, | |
| "eval_steps_per_second": 3.609, | |
| "step": 4012 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7926384242675429, | |
| "eval_loss": 1.205856442451477, | |
| "eval_runtime": 27.7159, | |
| "eval_samples_per_second": 71.692, | |
| "eval_steps_per_second": 3.608, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7925101394357441, | |
| "eval_loss": 1.2133612632751465, | |
| "eval_runtime": 27.7077, | |
| "eval_samples_per_second": 71.713, | |
| "eval_steps_per_second": 3.609, | |
| "step": 4248 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7922279128057866, | |
| "eval_loss": 1.2220430374145508, | |
| "eval_runtime": 27.7023, | |
| "eval_samples_per_second": 71.727, | |
| "eval_steps_per_second": 3.61, | |
| "step": 4366 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7922910684152876, | |
| "eval_loss": 1.2201595306396484, | |
| "eval_runtime": 27.6967, | |
| "eval_samples_per_second": 71.741, | |
| "eval_steps_per_second": 3.611, | |
| "step": 4484 | |
| }, | |
| { | |
| "epoch": 38.14, | |
| "learning_rate": 1.1864406779661018e-05, | |
| "loss": 0.6427, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7922890948024907, | |
| "eval_loss": 1.2266799211502075, | |
| "eval_runtime": 27.7206, | |
| "eval_samples_per_second": 71.68, | |
| "eval_steps_per_second": 3.607, | |
| "step": 4602 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7919200292094694, | |
| "eval_loss": 1.2350112199783325, | |
| "eval_runtime": 27.709, | |
| "eval_samples_per_second": 71.709, | |
| "eval_steps_per_second": 3.609, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.792095680748394, | |
| "eval_loss": 1.23201584815979, | |
| "eval_runtime": 27.6985, | |
| "eval_samples_per_second": 71.737, | |
| "eval_steps_per_second": 3.61, | |
| "step": 4838 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.791866741663953, | |
| "eval_loss": 1.2356910705566406, | |
| "eval_runtime": 27.7184, | |
| "eval_samples_per_second": 71.685, | |
| "eval_steps_per_second": 3.608, | |
| "step": 4956 | |
| }, | |
| { | |
| "epoch": 42.37, | |
| "learning_rate": 7.627118644067798e-06, | |
| "loss": 0.6219, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.791991079270158, | |
| "eval_loss": 1.23865807056427, | |
| "eval_runtime": 27.7193, | |
| "eval_samples_per_second": 71.683, | |
| "eval_steps_per_second": 3.608, | |
| "step": 5074 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7919575278526106, | |
| "eval_loss": 1.2408578395843506, | |
| "eval_runtime": 27.719, | |
| "eval_samples_per_second": 71.684, | |
| "eval_steps_per_second": 3.608, | |
| "step": 5192 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.791886477791922, | |
| "eval_loss": 1.244328260421753, | |
| "eval_runtime": 27.7249, | |
| "eval_samples_per_second": 71.668, | |
| "eval_steps_per_second": 3.607, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7917897707648737, | |
| "eval_loss": 1.2477593421936035, | |
| "eval_runtime": 27.6986, | |
| "eval_samples_per_second": 71.736, | |
| "eval_steps_per_second": 3.61, | |
| "step": 5428 | |
| }, | |
| { | |
| "epoch": 46.61, | |
| "learning_rate": 3.3898305084745763e-06, | |
| "loss": 0.6097, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7917739818624984, | |
| "eval_loss": 1.2487553358078003, | |
| "eval_runtime": 27.7426, | |
| "eval_samples_per_second": 71.623, | |
| "eval_steps_per_second": 3.605, | |
| "step": 5546 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7917522721217325, | |
| "eval_loss": 1.2487850189208984, | |
| "eval_runtime": 27.7184, | |
| "eval_samples_per_second": 71.685, | |
| "eval_steps_per_second": 3.608, | |
| "step": 5664 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7917424040577479, | |
| "eval_loss": 1.2495468854904175, | |
| "eval_runtime": 27.7228, | |
| "eval_samples_per_second": 71.674, | |
| "eval_steps_per_second": 3.607, | |
| "step": 5782 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.791762140185717, | |
| "eval_loss": 1.2498760223388672, | |
| "eval_runtime": 27.7268, | |
| "eval_samples_per_second": 71.664, | |
| "eval_steps_per_second": 3.607, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 5900, | |
| "total_flos": 6.1908182433792e+16, | |
| "train_loss": 0.9664699619099245, | |
| "train_runtime": 20866.4149, | |
| "train_samples_per_second": 22.711, | |
| "train_steps_per_second": 0.283 | |
| } | |
| ], | |
| "max_steps": 5900, | |
| "num_train_epochs": 50, | |
| "total_flos": 6.1908182433792e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |