| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09248554913294797, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018497109826589597, | |
| "grad_norm": 0.4005250036716461, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3445, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018497109826589597, | |
| "eval_loss": 1.5440045595169067, | |
| "eval_runtime": 88.5603, | |
| "eval_samples_per_second": 1.039, | |
| "eval_steps_per_second": 0.519, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03699421965317919, | |
| "grad_norm": 0.35564154386520386, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4499, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03699421965317919, | |
| "eval_loss": 1.533196210861206, | |
| "eval_runtime": 2.4743, | |
| "eval_samples_per_second": 37.182, | |
| "eval_steps_per_second": 18.591, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.055491329479768786, | |
| "grad_norm": 0.4461635649204254, | |
| "learning_rate": 3e-05, | |
| "loss": 1.5661, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07398843930635839, | |
| "grad_norm": 0.4539560079574585, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4482, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07398843930635839, | |
| "eval_loss": 1.5172789096832275, | |
| "eval_runtime": 2.4993, | |
| "eval_samples_per_second": 36.81, | |
| "eval_steps_per_second": 18.405, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09248554913294797, | |
| "grad_norm": 0.41485077142715454, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4503, | |
| "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": 4161519558328320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |