| { | |
| "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": 3e-07, | |
| "loss": 2.5647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 3e-07, | |
| "loss": 2.6398, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.29866204463905616, | |
| "eval_loss": 2.505859375, | |
| "eval_runtime": 65.7499, | |
| "eval_samples_per_second": 4.791, | |
| "eval_steps_per_second": 0.608, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5823, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.29880800340570457, | |
| "eval_loss": 2.50390625, | |
| "eval_runtime": 66.4342, | |
| "eval_samples_per_second": 4.742, | |
| "eval_steps_per_second": 0.602, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3e-07, | |
| "loss": 2.6128, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.2991485738612175, | |
| "eval_loss": 2.498046875, | |
| "eval_runtime": 66.4484, | |
| "eval_samples_per_second": 4.741, | |
| "eval_steps_per_second": 0.602, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5775, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.2994526546250684, | |
| "eval_loss": 2.4921875, | |
| "eval_runtime": 66.4492, | |
| "eval_samples_per_second": 4.74, | |
| "eval_steps_per_second": 0.602, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3e-07, | |
| "loss": 2.527, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.2999452654625068, | |
| "eval_loss": 2.486328125, | |
| "eval_runtime": 65.4246, | |
| "eval_samples_per_second": 4.815, | |
| "eval_steps_per_second": 0.611, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5752, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.30033448884023595, | |
| "eval_loss": 2.48046875, | |
| "eval_runtime": 66.4667, | |
| "eval_samples_per_second": 4.739, | |
| "eval_steps_per_second": 0.602, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5131, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.30077844675545823, | |
| "eval_loss": 2.474609375, | |
| "eval_runtime": 66.403, | |
| "eval_samples_per_second": 4.744, | |
| "eval_steps_per_second": 0.602, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3e-07, | |
| "loss": 2.4436, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.3013501185914979, | |
| "eval_loss": 2.46875, | |
| "eval_runtime": 65.4356, | |
| "eval_samples_per_second": 4.814, | |
| "eval_steps_per_second": 0.611, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5114, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.30175150519978106, | |
| "eval_loss": 2.462890625, | |
| "eval_runtime": 66.4277, | |
| "eval_samples_per_second": 4.742, | |
| "eval_steps_per_second": 0.602, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 56, | |
| "total_flos": 3701894676480.0, | |
| "train_loss": 2.5400499616350447, | |
| "train_runtime": 12579.867, | |
| "train_samples_per_second": 0.035, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "max_steps": 56, | |
| "num_train_epochs": 1, | |
| "total_flos": 3701894676480.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |