| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4011026878015162, | |
| "eval_steps": 291, | |
| "global_step": 582, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06891798759476224, | |
| "grad_norm": 15.229249000549316, | |
| "learning_rate": 9.88326321974139e-06, | |
| "loss": 0.6365, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13783597518952448, | |
| "grad_norm": 8.109599113464355, | |
| "learning_rate": 9.53850386931162e-06, | |
| "loss": 0.596, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2005513439007581, | |
| "eval_accuracy": 0.6923223789408367, | |
| "eval_loss": 0.5818617343902588, | |
| "eval_runtime": 432.05, | |
| "eval_samples_per_second": 193.964, | |
| "eval_steps_per_second": 6.062, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.2067539627842867, | |
| "grad_norm": 11.597530364990234, | |
| "learning_rate": 8.981820387323976e-06, | |
| "loss": 0.5612, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.27567195037904896, | |
| "grad_norm": 6.839386940002441, | |
| "learning_rate": 8.239206948702616e-06, | |
| "loss": 0.5604, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34458993797381116, | |
| "grad_norm": 7.691589832305908, | |
| "learning_rate": 7.345339674168113e-06, | |
| "loss": 0.5382, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4011026878015162, | |
| "eval_accuracy": 0.7151261306412735, | |
| "eval_loss": 0.5512936115264893, | |
| "eval_runtime": 430.4828, | |
| "eval_samples_per_second": 194.67, | |
| "eval_steps_per_second": 6.084, | |
| "step": 582 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1451, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 291, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |