| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9335978527249388, | |
| "eval_steps": 250, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2333994631812347, | |
| "grad_norm": 5.120560169219971, | |
| "learning_rate": 8.987402315498223e-05, | |
| "loss": 0.4681, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2333994631812347, | |
| "eval_loss": 0.3557259440422058, | |
| "eval_runtime": 26.5914, | |
| "eval_samples_per_second": 3.272, | |
| "eval_steps_per_second": 3.272, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "grad_norm": 3.340378999710083, | |
| "learning_rate": 5.828471682626175e-05, | |
| "loss": 0.3022, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "eval_loss": 0.3018253445625305, | |
| "eval_runtime": 26.6712, | |
| "eval_samples_per_second": 3.262, | |
| "eval_steps_per_second": 3.262, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "grad_norm": 3.158240556716919, | |
| "learning_rate": 2.2174321662025427e-05, | |
| "loss": 0.2736, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "eval_loss": 0.2686610519886017, | |
| "eval_runtime": 26.6022, | |
| "eval_samples_per_second": 3.27, | |
| "eval_steps_per_second": 3.27, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "grad_norm": 3.1761715412139893, | |
| "learning_rate": 1.2487983905362933e-06, | |
| "loss": 0.2525, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "eval_loss": 0.259181410074234, | |
| "eval_runtime": 26.6606, | |
| "eval_samples_per_second": 3.263, | |
| "eval_steps_per_second": 3.263, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1071, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5404854903863296e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |