| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02942258183155572, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001471129091577786, | |
| "eval_loss": 2.445326089859009, | |
| "eval_runtime": 103.0161, | |
| "eval_samples_per_second": 11.115, | |
| "eval_steps_per_second": 1.398, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004413387274733358, | |
| "grad_norm": 1.040910005569458, | |
| "learning_rate": 1.5e-05, | |
| "loss": 9.5736, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00735564545788893, | |
| "eval_loss": 2.441359758377075, | |
| "eval_runtime": 103.7991, | |
| "eval_samples_per_second": 11.031, | |
| "eval_steps_per_second": 1.387, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008826774549466716, | |
| "grad_norm": 1.0511504411697388, | |
| "learning_rate": 3e-05, | |
| "loss": 9.7365, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013240161824200073, | |
| "grad_norm": 1.3530985116958618, | |
| "learning_rate": 4.5e-05, | |
| "loss": 9.7514, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01471129091577786, | |
| "eval_loss": 2.3896217346191406, | |
| "eval_runtime": 103.8136, | |
| "eval_samples_per_second": 11.029, | |
| "eval_steps_per_second": 1.387, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017653549098933432, | |
| "grad_norm": 1.658168077468872, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 9.3972, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02206693637366679, | |
| "grad_norm": 1.7478517293930054, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 9.1795, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02206693637366679, | |
| "eval_loss": 2.2163238525390625, | |
| "eval_runtime": 103.8055, | |
| "eval_samples_per_second": 11.03, | |
| "eval_steps_per_second": 1.387, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026480323648400146, | |
| "grad_norm": 1.6007380485534668, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 8.6175, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02942258183155572, | |
| "eval_loss": 2.0439629554748535, | |
| "eval_runtime": 103.8112, | |
| "eval_samples_per_second": 11.03, | |
| "eval_steps_per_second": 1.387, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.613858577416192e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |