| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04932182490752158, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009864364981504316, | |
| "grad_norm": 0.11662397533655167, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5956, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009864364981504316, | |
| "eval_loss": 1.5963928699493408, | |
| "eval_runtime": 86.3397, | |
| "eval_samples_per_second": 1.981, | |
| "eval_steps_per_second": 0.996, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01972872996300863, | |
| "grad_norm": 0.11993740499019623, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5818, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01972872996300863, | |
| "eval_loss": 1.5912476778030396, | |
| "eval_runtime": 7.196, | |
| "eval_samples_per_second": 23.763, | |
| "eval_steps_per_second": 11.951, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029593094944512947, | |
| "grad_norm": 0.11248788237571716, | |
| "learning_rate": 3e-05, | |
| "loss": 1.5999, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03945745992601726, | |
| "grad_norm": 0.11268492788076401, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5774, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03945745992601726, | |
| "eval_loss": 1.5872379541397095, | |
| "eval_runtime": 7.2173, | |
| "eval_samples_per_second": 23.693, | |
| "eval_steps_per_second": 11.916, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04932182490752158, | |
| "grad_norm": 0.11259109526872635, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6465, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6514932543651840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |