| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 56, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-06, | |
| "loss": 2.6396, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.29888098278902875, | |
| "eval_loss": 2.50390625, | |
| "eval_runtime": 65.6756, | |
| "eval_samples_per_second": 4.796, | |
| "eval_steps_per_second": 0.609, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5754, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.29990877577084474, | |
| "eval_loss": 2.490234375, | |
| "eval_runtime": 66.3232, | |
| "eval_samples_per_second": 4.749, | |
| "eval_steps_per_second": 0.603, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5859, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.3017940765067202, | |
| "eval_loss": 2.46484375, | |
| "eval_runtime": 66.3622, | |
| "eval_samples_per_second": 4.747, | |
| "eval_steps_per_second": 0.603, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5432, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.30347868393845406, | |
| "eval_loss": 2.443359375, | |
| "eval_runtime": 66.0194, | |
| "eval_samples_per_second": 4.771, | |
| "eval_steps_per_second": 0.606, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1e-06, | |
| "loss": 2.472, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.3053031685215593, | |
| "eval_loss": 2.423828125, | |
| "eval_runtime": 66.3343, | |
| "eval_samples_per_second": 4.749, | |
| "eval_steps_per_second": 0.603, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5184, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.3064465121936386, | |
| "eval_loss": 2.408203125, | |
| "eval_runtime": 66.2869, | |
| "eval_samples_per_second": 4.752, | |
| "eval_steps_per_second": 0.603, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 2.4524, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.30782703886152163, | |
| "eval_loss": 2.392578125, | |
| "eval_runtime": 66.3104, | |
| "eval_samples_per_second": 4.75, | |
| "eval_steps_per_second": 0.603, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1e-06, | |
| "loss": 2.3876, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.30921364714468164, | |
| "eval_loss": 2.37890625, | |
| "eval_runtime": 66.2891, | |
| "eval_samples_per_second": 4.752, | |
| "eval_steps_per_second": 0.603, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 2.4456, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.3103083378945448, | |
| "eval_loss": 2.36328125, | |
| "eval_runtime": 66.3214, | |
| "eval_samples_per_second": 4.75, | |
| "eval_steps_per_second": 0.603, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 56, | |
| "total_flos": 3701894676480.0, | |
| "train_loss": 2.499117170061384, | |
| "train_runtime": 11859.1153, | |
| "train_samples_per_second": 0.037, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "max_steps": 56, | |
| "num_train_epochs": 1, | |
| "total_flos": 3701894676480.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |