| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003604902667627974, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003604902667627974, | |
| "grad_norm": 3.44784784829244e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003604902667627974, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 7.0816, | |
| "eval_samples_per_second": 165.075, | |
| "eval_steps_per_second": 82.608, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007209805335255948, | |
| "grad_norm": 2.3072683688951656e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010814708002883922, | |
| "grad_norm": 3.843647937173955e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010814708002883922, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 7.1024, | |
| "eval_samples_per_second": 164.593, | |
| "eval_steps_per_second": 82.367, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014419610670511895, | |
| "grad_norm": 1.0668237337085884e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001802451333813987, | |
| "grad_norm": 2.235065221611876e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0021629416005767843, | |
| "grad_norm": 2.0098446839256212e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0021629416005767843, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 7.2593, | |
| "eval_samples_per_second": 161.034, | |
| "eval_steps_per_second": 80.586, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025234318673395817, | |
| "grad_norm": 2.091787609970197e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002883922134102379, | |
| "grad_norm": 3.362276765983552e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0032444124008651765, | |
| "grad_norm": 1.613308813830372e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0032444124008651765, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 7.2074, | |
| "eval_samples_per_second": 162.194, | |
| "eval_steps_per_second": 81.166, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003604902667627974, | |
| "grad_norm": 4.368403824628331e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 373553971200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |