| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003586800573888092, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000896700143472023, | |
| "grad_norm": 1.153688669204712, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.3182, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000896700143472023, | |
| "eval_loss": 1.9885040521621704, | |
| "eval_runtime": 63.7527, | |
| "eval_samples_per_second": 2.808, | |
| "eval_steps_per_second": 1.412, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001793400286944046, | |
| "grad_norm": 0.9341593384742737, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8483, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001793400286944046, | |
| "eval_loss": 1.6333410739898682, | |
| "eval_runtime": 65.274, | |
| "eval_samples_per_second": 2.742, | |
| "eval_steps_per_second": 1.379, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002690100430416069, | |
| "grad_norm": 0.6387659311294556, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5915, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002690100430416069, | |
| "eval_loss": 1.516692042350769, | |
| "eval_runtime": 64.2046, | |
| "eval_samples_per_second": 2.788, | |
| "eval_steps_per_second": 1.402, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003586800573888092, | |
| "grad_norm": 0.511236310005188, | |
| "learning_rate": 0.0, | |
| "loss": 1.4756, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003586800573888092, | |
| "eval_loss": 1.480790615081787, | |
| "eval_runtime": 64.3998, | |
| "eval_samples_per_second": 2.78, | |
| "eval_steps_per_second": 1.398, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2674400071936896.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |