| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9917355371900827, | |
| "eval_steps": 20, | |
| "global_step": 420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9393939393939395e-05, | |
| "loss": 1.7928, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.761446475982666, | |
| "eval_runtime": 265.1251, | |
| "eval_samples_per_second": 1.43, | |
| "eval_steps_per_second": 0.717, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8585858585858588e-05, | |
| "loss": 1.7717, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.7594226598739624, | |
| "eval_runtime": 264.3622, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.719, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 1.7738, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.75676429271698, | |
| "eval_runtime": 264.5514, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.718, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6969696969696972e-05, | |
| "loss": 1.7557, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.7535144090652466, | |
| "eval_runtime": 264.2564, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.719, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.616161616161616e-05, | |
| "loss": 1.7501, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.7500460147857666, | |
| "eval_runtime": 264.3004, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.719, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.5353535353535354e-05, | |
| "loss": 1.7677, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.746537208557129, | |
| "eval_runtime": 264.535, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.718, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.4545454545454546e-05, | |
| "loss": 1.691, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.7429962158203125, | |
| "eval_runtime": 265.0443, | |
| "eval_samples_per_second": 1.43, | |
| "eval_steps_per_second": 0.717, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.3737373737373739e-05, | |
| "loss": 1.7598, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.7397080659866333, | |
| "eval_runtime": 260.5865, | |
| "eval_samples_per_second": 1.454, | |
| "eval_steps_per_second": 0.729, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.2929292929292931e-05, | |
| "loss": 1.7312, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.7369072437286377, | |
| "eval_runtime": 260.1744, | |
| "eval_samples_per_second": 1.457, | |
| "eval_steps_per_second": 0.73, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 1.7054, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.7343047857284546, | |
| "eval_runtime": 265.1106, | |
| "eval_samples_per_second": 1.43, | |
| "eval_steps_per_second": 0.717, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.1313131313131314e-05, | |
| "loss": 1.7627, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.7320263385772705, | |
| "eval_runtime": 265.2276, | |
| "eval_samples_per_second": 1.429, | |
| "eval_steps_per_second": 0.716, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.0505050505050507e-05, | |
| "loss": 1.7579, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.730188250541687, | |
| "eval_runtime": 264.9791, | |
| "eval_samples_per_second": 1.43, | |
| "eval_steps_per_second": 0.717, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.696969696969698e-06, | |
| "loss": 1.7473, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.7285958528518677, | |
| "eval_runtime": 264.7849, | |
| "eval_samples_per_second": 1.431, | |
| "eval_steps_per_second": 0.718, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 1.7621, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.727224349975586, | |
| "eval_runtime": 264.3951, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.719, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.08080808080808e-06, | |
| "loss": 1.7321, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.7259517908096313, | |
| "eval_runtime": 264.7615, | |
| "eval_samples_per_second": 1.431, | |
| "eval_steps_per_second": 0.718, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 1.7052, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.724865436553955, | |
| "eval_runtime": 264.4881, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.718, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.464646464646466e-06, | |
| "loss": 1.7461, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.723939061164856, | |
| "eval_runtime": 264.2839, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.719, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5.656565656565657e-06, | |
| "loss": 1.6807, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.7231345176696777, | |
| "eval_runtime": 263.8422, | |
| "eval_samples_per_second": 1.436, | |
| "eval_steps_per_second": 0.72, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.848484848484849e-06, | |
| "loss": 1.7458, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.7224739789962769, | |
| "eval_runtime": 263.8704, | |
| "eval_samples_per_second": 1.436, | |
| "eval_steps_per_second": 0.72, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.04040404040404e-06, | |
| "loss": 1.7315, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.7218880653381348, | |
| "eval_runtime": 263.8359, | |
| "eval_samples_per_second": 1.436, | |
| "eval_steps_per_second": 0.72, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.232323232323233e-06, | |
| "loss": 1.7252, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.7214322090148926, | |
| "eval_runtime": 263.8975, | |
| "eval_samples_per_second": 1.436, | |
| "eval_steps_per_second": 0.72, | |
| "step": 420 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 500, | |
| "num_train_epochs": 2, | |
| "save_steps": 20, | |
| "total_flos": 2.9254044925034496e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |