| { | |
| "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": 1e-06, | |
| "loss": 2.718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5852, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.26974484268246846, | |
| "eval_loss": 2.595703125, | |
| "eval_runtime": 73.3015, | |
| "eval_samples_per_second": 4.966, | |
| "eval_steps_per_second": 0.628, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5956, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.27058504875406286, | |
| "eval_loss": 2.576171875, | |
| "eval_runtime": 73.9801, | |
| "eval_samples_per_second": 4.92, | |
| "eval_steps_per_second": 0.622, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5961, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.27107148384814383, | |
| "eval_loss": 2.5546875, | |
| "eval_runtime": 73.8954, | |
| "eval_samples_per_second": 4.926, | |
| "eval_steps_per_second": 0.623, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5731, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.27218807349592056, | |
| "eval_loss": 2.53125, | |
| "eval_runtime": 73.9168, | |
| "eval_samples_per_second": 4.924, | |
| "eval_steps_per_second": 0.622, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5415, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.2733599398589338, | |
| "eval_loss": 2.51171875, | |
| "eval_runtime": 73.9155, | |
| "eval_samples_per_second": 4.925, | |
| "eval_steps_per_second": 0.622, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5168, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.2745704999226126, | |
| "eval_loss": 2.49609375, | |
| "eval_runtime": 73.8737, | |
| "eval_samples_per_second": 4.927, | |
| "eval_steps_per_second": 0.623, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1e-06, | |
| "loss": 2.4972, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.2755544254538218, | |
| "eval_loss": 2.482421875, | |
| "eval_runtime": 73.9197, | |
| "eval_samples_per_second": 4.924, | |
| "eval_steps_per_second": 0.622, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 2.4354, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.27611824794923384, | |
| "eval_loss": 2.47265625, | |
| "eval_runtime": 74.1261, | |
| "eval_samples_per_second": 4.911, | |
| "eval_steps_per_second": 0.621, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-06, | |
| "loss": 2.4055, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.2768423729188317, | |
| "eval_loss": 2.4609375, | |
| "eval_runtime": 73.8501, | |
| "eval_samples_per_second": 4.929, | |
| "eval_steps_per_second": 0.623, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 2.4681, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.27778207707785174, | |
| "eval_loss": 2.44921875, | |
| "eval_runtime": 73.8512, | |
| "eval_samples_per_second": 4.929, | |
| "eval_steps_per_second": 0.623, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-06, | |
| "loss": 2.5866, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.27841223163154755, | |
| "eval_loss": 2.435546875, | |
| "eval_runtime": 73.8943, | |
| "eval_samples_per_second": 4.926, | |
| "eval_steps_per_second": 0.623, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 2.4221, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.27929113140380746, | |
| "eval_loss": 2.423828125, | |
| "eval_runtime": 73.8857, | |
| "eval_samples_per_second": 4.927, | |
| "eval_steps_per_second": 0.623, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 75, | |
| "total_flos": 4974649540608.0, | |
| "train_loss": 2.5182421875, | |
| "train_runtime": 15501.0618, | |
| "train_samples_per_second": 0.039, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "max_steps": 75, | |
| "num_train_epochs": 1, | |
| "total_flos": 4974649540608.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |