| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0554089709762533, | |
| "eval_steps": 20, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9393939393939395e-05, | |
| "loss": 1.8159, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.7643083333969116, | |
| "eval_runtime": 200.2867, | |
| "eval_samples_per_second": 1.962, | |
| "eval_steps_per_second": 0.2, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8585858585858588e-05, | |
| "loss": 1.7363, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.7077617645263672, | |
| "eval_runtime": 200.122, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 1.6855, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.6695836782455444, | |
| "eval_runtime": 200.1343, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6969696969696972e-05, | |
| "loss": 1.6775, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.6478480100631714, | |
| "eval_runtime": 200.1259, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.616161616161616e-05, | |
| "loss": 1.6434, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.6339426040649414, | |
| "eval_runtime": 200.1147, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5353535353535354e-05, | |
| "loss": 1.6308, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.6241737604141235, | |
| "eval_runtime": 200.0709, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4545454545454546e-05, | |
| "loss": 1.6268, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6161283254623413, | |
| "eval_runtime": 200.0747, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3737373737373739e-05, | |
| "loss": 1.6548, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.609245777130127, | |
| "eval_runtime": 200.1029, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2929292929292931e-05, | |
| "loss": 1.6244, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.6044949293136597, | |
| "eval_runtime": 200.0563, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 1.5961, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.600788950920105, | |
| "eval_runtime": 200.0369, | |
| "eval_samples_per_second": 1.965, | |
| "eval_steps_per_second": 0.2, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1313131313131314e-05, | |
| "loss": 1.5935, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.597257137298584, | |
| "eval_runtime": 200.0532, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0505050505050507e-05, | |
| "loss": 1.6057, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.594172716140747, | |
| "eval_runtime": 200.1045, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.696969696969698e-06, | |
| "loss": 1.6175, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.591786503791809, | |
| "eval_runtime": 200.1191, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 1.604, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.59005606174469, | |
| "eval_runtime": 200.0537, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.08080808080808e-06, | |
| "loss": 1.6115, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.5883697271347046, | |
| "eval_runtime": 200.1226, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 1.5942, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.5865776538848877, | |
| "eval_runtime": 200.0942, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 6.464646464646466e-06, | |
| "loss": 1.587, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.5847071409225464, | |
| "eval_runtime": 200.1145, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.656565656565657e-06, | |
| "loss": 1.5937, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5834985971450806, | |
| "eval_runtime": 200.0727, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.848484848484849e-06, | |
| "loss": 1.5836, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.5821855068206787, | |
| "eval_runtime": 200.0752, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.04040404040404e-06, | |
| "loss": 1.6018, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.5811065435409546, | |
| "eval_runtime": 200.0657, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.232323232323233e-06, | |
| "loss": 1.612, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.580207347869873, | |
| "eval_runtime": 200.0806, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.4242424242424244e-06, | |
| "loss": 1.6067, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.5794427394866943, | |
| "eval_runtime": 200.0838, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.6161616161616164e-06, | |
| "loss": 1.6014, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.5789347887039185, | |
| "eval_runtime": 200.1151, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 8.080808080808082e-07, | |
| "loss": 1.5994, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.5785064697265625, | |
| "eval_runtime": 200.1139, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0, | |
| "loss": 1.5745, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 1.5784260034561157, | |
| "eval_runtime": 200.0898, | |
| "eval_samples_per_second": 1.964, | |
| "eval_steps_per_second": 0.2, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 500, | |
| "num_train_epochs": 2, | |
| "save_steps": 20, | |
| "total_flos": 3.504605136766894e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |