| { | |
| "best_metric": 2.534163475036621, | |
| "best_model_checkpoint": "output/sam-kim/checkpoint-95", | |
| "epoch": 5.0, | |
| "global_step": 95, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00011506151581352585, | |
| "loss": 2.9091, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.293505690059801e-05, | |
| "loss": 2.4999, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4464961055407408e-05, | |
| "loss": 2.542, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.6480398178100586, | |
| "eval_runtime": 1.3808, | |
| "eval_samples_per_second": 17.381, | |
| "eval_steps_per_second": 2.173, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.35614586573241e-07, | |
| "loss": 2.3946, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.1079356352801514e-05, | |
| "loss": 2.3908, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 8.54403044178588e-05, | |
| "loss": 2.2627, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00012893189933276512, | |
| "loss": 2.2405, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.5858662128448486, | |
| "eval_runtime": 1.3854, | |
| "eval_samples_per_second": 17.324, | |
| "eval_steps_per_second": 2.165, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00013348306278066356, | |
| "loss": 2.2745, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 9.615630613119375e-05, | |
| "loss": 2.1057, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.1043693868806304e-05, | |
| "loss": 2.049, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.7169372193364486e-06, | |
| "loss": 1.9596, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.539033889770508, | |
| "eval_runtime": 1.3909, | |
| "eval_samples_per_second": 17.255, | |
| "eval_steps_per_second": 2.157, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 8.268100667234827e-06, | |
| "loss": 2.1846, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 5.175969558214116e-05, | |
| "loss": 2.0227, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.0001061206436471984, | |
| "loss": 1.9221, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00013626438541342674, | |
| "loss": 2.025, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.534473180770874, | |
| "eval_runtime": 1.388, | |
| "eval_samples_per_second": 17.292, | |
| "eval_steps_per_second": 2.161, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00012273503894459262, | |
| "loss": 1.9584, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 7.426494309940199e-05, | |
| "loss": 1.8797, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.2138484186474223e-05, | |
| "loss": 1.8496, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8918, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.534163475036621, | |
| "eval_runtime": 1.3695, | |
| "eval_samples_per_second": 17.524, | |
| "eval_steps_per_second": 2.191, | |
| "step": 95 | |
| } | |
| ], | |
| "max_steps": 190, | |
| "num_train_epochs": 10, | |
| "total_flos": 96024821760000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |