| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017191977077363897, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0019102196752626551, | |
| "grad_norm": 1.2701191902160645, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9644, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019102196752626551, | |
| "eval_loss": 3.0215418338775635, | |
| "eval_runtime": 14.0782, | |
| "eval_samples_per_second": 15.698, | |
| "eval_steps_per_second": 7.885, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038204393505253103, | |
| "grad_norm": 1.0936405658721924, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1595, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0057306590257879654, | |
| "grad_norm": 1.1901081800460815, | |
| "learning_rate": 6e-05, | |
| "loss": 3.0597, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0057306590257879654, | |
| "eval_loss": 3.0081992149353027, | |
| "eval_runtime": 12.9369, | |
| "eval_samples_per_second": 17.083, | |
| "eval_steps_per_second": 8.58, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007640878701050621, | |
| "grad_norm": 1.2270911931991577, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0984, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009551098376313277, | |
| "grad_norm": 1.2903715372085571, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8426, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011461318051575931, | |
| "grad_norm": 1.04902982711792, | |
| "learning_rate": 0.00012, | |
| "loss": 3.102, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011461318051575931, | |
| "eval_loss": 2.867784023284912, | |
| "eval_runtime": 12.9552, | |
| "eval_samples_per_second": 17.059, | |
| "eval_steps_per_second": 8.568, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013371537726838587, | |
| "grad_norm": 0.9108535051345825, | |
| "learning_rate": 0.00014, | |
| "loss": 2.7408, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015281757402101241, | |
| "grad_norm": 0.8048544526100159, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8938, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.017191977077363897, | |
| "grad_norm": 0.9372456669807434, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6786, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017191977077363897, | |
| "eval_loss": 2.7899086475372314, | |
| "eval_runtime": 12.9506, | |
| "eval_samples_per_second": 17.065, | |
| "eval_steps_per_second": 8.571, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3329215646662656.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |