| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3e-07, | |
| "loss": 2.718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5856, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.2696508722665664, | |
| "eval_loss": 2.595703125, | |
| "eval_runtime": 73.0734, | |
| "eval_samples_per_second": 4.981, | |
| "eval_steps_per_second": 0.63, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3e-07, | |
| "loss": 2.6027, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.26980564706922855, | |
| "eval_loss": 2.59375, | |
| "eval_runtime": 73.5378, | |
| "eval_samples_per_second": 4.95, | |
| "eval_steps_per_second": 0.626, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3e-07, | |
| "loss": 2.619, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.26998806022950894, | |
| "eval_loss": 2.587890625, | |
| "eval_runtime": 73.5544, | |
| "eval_samples_per_second": 4.949, | |
| "eval_steps_per_second": 0.625, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3e-07, | |
| "loss": 2.6121, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.27019258407588387, | |
| "eval_loss": 2.583984375, | |
| "eval_runtime": 73.6493, | |
| "eval_samples_per_second": 4.942, | |
| "eval_steps_per_second": 0.625, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3e-07, | |
| "loss": 2.6024, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.27057399341101557, | |
| "eval_loss": 2.576171875, | |
| "eval_runtime": 73.5651, | |
| "eval_samples_per_second": 4.948, | |
| "eval_steps_per_second": 0.625, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5878, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.270739823556725, | |
| "eval_loss": 2.5703125, | |
| "eval_runtime": 73.2671, | |
| "eval_samples_per_second": 4.968, | |
| "eval_steps_per_second": 0.628, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5541, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.2710327901474783, | |
| "eval_loss": 2.5625, | |
| "eval_runtime": 73.5901, | |
| "eval_samples_per_second": 4.946, | |
| "eval_steps_per_second": 0.625, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5207, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.27128706303756606, | |
| "eval_loss": 2.556640625, | |
| "eval_runtime": 73.6385, | |
| "eval_samples_per_second": 4.943, | |
| "eval_steps_per_second": 0.625, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3e-07, | |
| "loss": 2.4577, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.27152475291308287, | |
| "eval_loss": 2.548828125, | |
| "eval_runtime": 73.672, | |
| "eval_samples_per_second": 4.941, | |
| "eval_steps_per_second": 0.624, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5614, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.27176797046012335, | |
| "eval_loss": 2.54296875, | |
| "eval_runtime": 73.5346, | |
| "eval_samples_per_second": 4.95, | |
| "eval_steps_per_second": 0.626, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3e-07, | |
| "loss": 2.6959, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.27219360116744423, | |
| "eval_loss": 2.53515625, | |
| "eval_runtime": 73.3529, | |
| "eval_samples_per_second": 4.962, | |
| "eval_steps_per_second": 0.627, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5084, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.2725086784442921, | |
| "eval_loss": 2.529296875, | |
| "eval_runtime": 73.6241, | |
| "eval_samples_per_second": 4.944, | |
| "eval_steps_per_second": 0.625, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 75, | |
| "total_flos": 4974649540608.0, | |
| "train_loss": 2.57614501953125, | |
| "train_runtime": 16094.8553, | |
| "train_samples_per_second": 0.037, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "max_steps": 75, | |
| "num_train_epochs": 1, | |
| "total_flos": 4974649540608.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |