| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003772161448509996, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "grad_norm": 1.882520318031311, | |
| "learning_rate": 1e-05, | |
| "loss": 2.7434, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "eval_loss": 2.650804042816162, | |
| "eval_runtime": 255.5443, | |
| "eval_samples_per_second": 8.738, | |
| "eval_steps_per_second": 4.371, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "grad_norm": 2.0661938190460205, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5946, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "eval_loss": 2.6367790699005127, | |
| "eval_runtime": 30.7814, | |
| "eval_samples_per_second": 72.544, | |
| "eval_steps_per_second": 36.288, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002263296869105998, | |
| "grad_norm": 1.9913994073867798, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6279, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003017729158807997, | |
| "grad_norm": 1.7731335163116455, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5344, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003017729158807997, | |
| "eval_loss": 2.5603933334350586, | |
| "eval_runtime": 30.7843, | |
| "eval_samples_per_second": 72.537, | |
| "eval_steps_per_second": 36.285, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "grad_norm": 1.918685793876648, | |
| "learning_rate": 5e-05, | |
| "loss": 2.589, | |
| "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": 1037701961220096.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |