| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8022053756030324, | |
| "eval_steps": 291, | |
| "global_step": 1164, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06891798759476224, | |
| "grad_norm": 4.911224365234375, | |
| "learning_rate": 9.92330596776479e-06, | |
| "loss": 0.611, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13783597518952448, | |
| "grad_norm": 5.295703887939453, | |
| "learning_rate": 9.62094968320582e-06, | |
| "loss": 0.5048, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2005513439007581, | |
| "eval_accuracy": 0.768430347724398, | |
| "eval_loss": 0.4736328125, | |
| "eval_runtime": 2043.705, | |
| "eval_samples_per_second": 41.005, | |
| "eval_steps_per_second": 5.126, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.2067539627842867, | |
| "grad_norm": 6.278463363647461, | |
| "learning_rate": 9.102819483545054e-06, | |
| "loss": 0.4554, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.27567195037904896, | |
| "grad_norm": 5.069440841674805, | |
| "learning_rate": 8.39310930928775e-06, | |
| "loss": 0.4329, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34458993797381116, | |
| "grad_norm": 6.920823574066162, | |
| "learning_rate": 7.524958872697738e-06, | |
| "loss": 0.4188, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4011026878015162, | |
| "eval_accuracy": 0.7951242213789647, | |
| "eval_loss": 0.4287109375, | |
| "eval_runtime": 2033.241, | |
| "eval_samples_per_second": 41.216, | |
| "eval_steps_per_second": 5.152, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.4135079255685734, | |
| "grad_norm": 6.235529899597168, | |
| "learning_rate": 6.5389062084740715e-06, | |
| "loss": 0.3976, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4824259131633356, | |
| "grad_norm": 6.048646926879883, | |
| "learning_rate": 5.4809947618915035e-06, | |
| "loss": 0.3846, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5513439007580979, | |
| "grad_norm": 8.15500259399414, | |
| "learning_rate": 4.400623403379149e-06, | |
| "loss": 0.3628, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6016540317022743, | |
| "eval_accuracy": 0.8028209350612158, | |
| "eval_loss": 0.4140625, | |
| "eval_runtime": 2030.717, | |
| "eval_samples_per_second": 41.267, | |
| "eval_steps_per_second": 5.159, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 0.6202618883528601, | |
| "grad_norm": 6.805386066436768, | |
| "learning_rate": 3.3482397624875462e-06, | |
| "loss": 0.3539, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6891798759476223, | |
| "grad_norm": 6.361441612243652, | |
| "learning_rate": 2.3729845903505033e-06, | |
| "loss": 0.3244, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7580978635423845, | |
| "grad_norm": 7.689145565032959, | |
| "learning_rate": 1.5203971464583544e-06, | |
| "loss": 0.3203, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8022053756030324, | |
| "eval_accuracy": 0.8129042266294361, | |
| "eval_loss": 0.39794921875, | |
| "eval_runtime": 2032.3908, | |
| "eval_samples_per_second": 41.233, | |
| "eval_steps_per_second": 5.155, | |
| "step": 1164 | |
| } | |
| ], | |
| "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": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |