| { | |
| "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": 6e-06, | |
| "loss": 2.718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 6e-06, | |
| "loss": 2.5793, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.27131470139518427, | |
| "eval_loss": 2.572265625, | |
| "eval_runtime": 75.3129, | |
| "eval_samples_per_second": 4.833, | |
| "eval_steps_per_second": 0.611, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 6e-06, | |
| "loss": 2.5612, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.27501824131602803, | |
| "eval_loss": 2.5, | |
| "eval_runtime": 75.9396, | |
| "eval_samples_per_second": 4.793, | |
| "eval_steps_per_second": 0.606, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 6e-06, | |
| "loss": 2.5235, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.27841775930307117, | |
| "eval_loss": 2.447265625, | |
| "eval_runtime": 75.8369, | |
| "eval_samples_per_second": 4.8, | |
| "eval_steps_per_second": 0.607, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6e-06, | |
| "loss": 2.4961, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.2818393879762089, | |
| "eval_loss": 2.41015625, | |
| "eval_runtime": 75.7164, | |
| "eval_samples_per_second": 4.807, | |
| "eval_steps_per_second": 0.608, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6e-06, | |
| "loss": 2.4488, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.2848740796426913, | |
| "eval_loss": 2.3671875, | |
| "eval_runtime": 75.8548, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.606, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6e-06, | |
| "loss": 2.4121, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.2877761071926062, | |
| "eval_loss": 2.33203125, | |
| "eval_runtime": 75.8441, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.607, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3901, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.2902580317067239, | |
| "eval_loss": 2.302734375, | |
| "eval_runtime": 75.8507, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.606, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6e-06, | |
| "loss": 2.2845, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.29269573484865236, | |
| "eval_loss": 2.271484375, | |
| "eval_runtime": 75.7801, | |
| "eval_samples_per_second": 4.803, | |
| "eval_steps_per_second": 0.607, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3032, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.29554248568333075, | |
| "eval_loss": 2.2421875, | |
| "eval_runtime": 75.8262, | |
| "eval_samples_per_second": 4.8, | |
| "eval_steps_per_second": 0.607, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6e-06, | |
| "loss": 2.2954, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.2984555685762929, | |
| "eval_loss": 2.208984375, | |
| "eval_runtime": 75.8901, | |
| "eval_samples_per_second": 4.796, | |
| "eval_steps_per_second": 0.606, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3908, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.30088774404669777, | |
| "eval_loss": 2.18359375, | |
| "eval_runtime": 76.1084, | |
| "eval_samples_per_second": 4.783, | |
| "eval_steps_per_second": 0.604, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 6e-06, | |
| "loss": 2.2676, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.3035631370641431, | |
| "eval_loss": 2.150390625, | |
| "eval_runtime": 75.8379, | |
| "eval_samples_per_second": 4.8, | |
| "eval_steps_per_second": 0.607, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 75, | |
| "total_flos": 4974649540608.0, | |
| "train_loss": 2.4108121744791666, | |
| "train_runtime": 14351.1542, | |
| "train_samples_per_second": 0.042, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "max_steps": 75, | |
| "num_train_epochs": 1, | |
| "total_flos": 4974649540608.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |