| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2518891687657431, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005037783375314861, | |
| "eval_loss": 3.972001552581787, | |
| "eval_runtime": 6.021, | |
| "eval_samples_per_second": 13.951, | |
| "eval_steps_per_second": 6.976, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02518891687657431, | |
| "grad_norm": 4.353302955627441, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0829, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05037783375314862, | |
| "grad_norm": 4.353135108947754, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7437, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05037783375314862, | |
| "eval_loss": 3.277827262878418, | |
| "eval_runtime": 6.0452, | |
| "eval_samples_per_second": 13.895, | |
| "eval_steps_per_second": 6.948, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07556675062972293, | |
| "grad_norm": 3.972386360168457, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0014, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10075566750629723, | |
| "grad_norm": 5.532101631164551, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.498, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10075566750629723, | |
| "eval_loss": 2.5648317337036133, | |
| "eval_runtime": 6.0653, | |
| "eval_samples_per_second": 13.849, | |
| "eval_steps_per_second": 6.925, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12594458438287154, | |
| "grad_norm": 5.016425132751465, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.5382, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15113350125944586, | |
| "grad_norm": 5.500548362731934, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3807, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15113350125944586, | |
| "eval_loss": 2.414311647415161, | |
| "eval_runtime": 6.1428, | |
| "eval_samples_per_second": 13.675, | |
| "eval_steps_per_second": 6.837, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17632241813602015, | |
| "grad_norm": 4.241909980773926, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.263, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.20151133501259447, | |
| "grad_norm": 6.198630332946777, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4035, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20151133501259447, | |
| "eval_loss": 2.3978166580200195, | |
| "eval_runtime": 6.1463, | |
| "eval_samples_per_second": 13.667, | |
| "eval_steps_per_second": 6.833, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22670025188916876, | |
| "grad_norm": 3.865180015563965, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.273, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2518891687657431, | |
| "grad_norm": 4.703251361846924, | |
| "learning_rate": 0.0, | |
| "loss": 2.3153, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2518891687657431, | |
| "eval_loss": 2.3879706859588623, | |
| "eval_runtime": 6.0943, | |
| "eval_samples_per_second": 13.783, | |
| "eval_steps_per_second": 6.892, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |