| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011327914814080599, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011327914814080598, | |
| "grad_norm": 0.034137170761823654, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3644, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011327914814080598, | |
| "eval_loss": 10.371950149536133, | |
| "eval_runtime": 12.562, | |
| "eval_samples_per_second": 295.893, | |
| "eval_steps_per_second": 147.986, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022655829628161195, | |
| "grad_norm": 0.03926686570048332, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3752, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003398374444224179, | |
| "grad_norm": 0.03290453553199768, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3657, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003398374444224179, | |
| "eval_loss": 10.37191104888916, | |
| "eval_runtime": 12.5661, | |
| "eval_samples_per_second": 295.796, | |
| "eval_steps_per_second": 147.938, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004531165925632239, | |
| "grad_norm": 0.04086960479617119, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3717, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005663957407040299, | |
| "grad_norm": 0.03967590257525444, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3784, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006796748888448359, | |
| "grad_norm": 0.046869322657585144, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3747, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006796748888448359, | |
| "eval_loss": 10.371750831604004, | |
| "eval_runtime": 12.7077, | |
| "eval_samples_per_second": 292.5, | |
| "eval_steps_per_second": 146.289, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007929540369856419, | |
| "grad_norm": 0.039001643657684326, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3767, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009062331851264478, | |
| "grad_norm": 0.045184794813394547, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3748, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010195123332672538, | |
| "grad_norm": 0.040985699743032455, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3765, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010195123332672538, | |
| "eval_loss": 10.371465682983398, | |
| "eval_runtime": 12.6792, | |
| "eval_samples_per_second": 293.156, | |
| "eval_steps_per_second": 146.618, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011327914814080599, | |
| "grad_norm": 0.03805907815694809, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3725, | |
| "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": 229523619840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |