| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 236, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.423728813559322, | |
| "grad_norm": 1.3252296447753906, | |
| "learning_rate": 0.0004307909604519774, | |
| "loss": 3.0243, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "grad_norm": 1.302614450454712, | |
| "learning_rate": 0.00036016949152542374, | |
| "loss": 1.2356, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.9709166288375854, | |
| "eval_runtime": 5.194, | |
| "eval_samples_per_second": 20.216, | |
| "eval_steps_per_second": 2.695, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.271186440677966, | |
| "grad_norm": 0.6076271533966064, | |
| "learning_rate": 0.0002895480225988701, | |
| "loss": 1.2005, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "grad_norm": 1.1516226530075073, | |
| "learning_rate": 0.0002189265536723164, | |
| "loss": 1.2331, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.9370157718658447, | |
| "eval_runtime": 5.1425, | |
| "eval_samples_per_second": 20.418, | |
| "eval_steps_per_second": 2.722, | |
| "step": 236 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 354, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3711634067423232.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |