| { | |
| "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": 6e-06, | |
| "loss": 2.5647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6e-06, | |
| "loss": 2.6377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.3015994648178556, | |
| "eval_loss": 2.46875, | |
| "eval_runtime": 64.0845, | |
| "eval_samples_per_second": 4.915, | |
| "eval_steps_per_second": 0.624, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6e-06, | |
| "loss": 2.5046, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.3096454418293499, | |
| "eval_loss": 2.384765625, | |
| "eval_runtime": 64.5855, | |
| "eval_samples_per_second": 4.877, | |
| "eval_steps_per_second": 0.619, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6e-06, | |
| "loss": 2.4755, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.315568935109165, | |
| "eval_loss": 2.322265625, | |
| "eval_runtime": 64.83, | |
| "eval_samples_per_second": 4.859, | |
| "eval_steps_per_second": 0.617, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6e-06, | |
| "loss": 2.459, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.32014839141275925, | |
| "eval_loss": 2.271484375, | |
| "eval_runtime": 64.7722, | |
| "eval_samples_per_second": 4.863, | |
| "eval_steps_per_second": 0.618, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3602, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.3243203794927933, | |
| "eval_loss": 2.224609375, | |
| "eval_runtime": 63.7938, | |
| "eval_samples_per_second": 4.938, | |
| "eval_steps_per_second": 0.627, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3829, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.3275071458979505, | |
| "eval_loss": 2.189453125, | |
| "eval_runtime": 64.8117, | |
| "eval_samples_per_second": 4.86, | |
| "eval_steps_per_second": 0.617, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3188, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.331490603904397, | |
| "eval_loss": 2.146484375, | |
| "eval_runtime": 63.7849, | |
| "eval_samples_per_second": 4.938, | |
| "eval_steps_per_second": 0.627, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6e-06, | |
| "loss": 2.2895, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.3365140181232135, | |
| "eval_loss": 2.103515625, | |
| "eval_runtime": 64.7342, | |
| "eval_samples_per_second": 4.866, | |
| "eval_steps_per_second": 0.618, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3062, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.341166453810132, | |
| "eval_loss": 2.05859375, | |
| "eval_runtime": 64.7609, | |
| "eval_samples_per_second": 4.864, | |
| "eval_steps_per_second": 0.618, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 56, | |
| "total_flos": 3701894676480.0, | |
| "train_loss": 2.4000658307756697, | |
| "train_runtime": 10898.1431, | |
| "train_samples_per_second": 0.041, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "max_steps": 56, | |
| "num_train_epochs": 1, | |
| "total_flos": 3701894676480.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |