| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002894495634135752, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.2161062601508354e-05, | |
| "grad_norm": 0.34671255946159363, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8799, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.2161062601508354e-05, | |
| "eval_loss": 1.3069854974746704, | |
| "eval_runtime": 426.236, | |
| "eval_samples_per_second": 30.715, | |
| "eval_steps_per_second": 15.358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.432212520301671e-05, | |
| "grad_norm": 0.5184245705604553, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4976, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.648318780452506e-05, | |
| "grad_norm": 0.40598493814468384, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9936, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.648318780452506e-05, | |
| "eval_loss": 1.305471420288086, | |
| "eval_runtime": 426.4665, | |
| "eval_samples_per_second": 30.699, | |
| "eval_steps_per_second": 15.349, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012864425040603342, | |
| "grad_norm": 0.5355951189994812, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2788, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00016080531300754176, | |
| "grad_norm": 0.39149630069732666, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7972, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001929663756090501, | |
| "grad_norm": 0.4673765003681183, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2453, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001929663756090501, | |
| "eval_loss": 1.2842456102371216, | |
| "eval_runtime": 427.2413, | |
| "eval_samples_per_second": 30.643, | |
| "eval_steps_per_second": 15.322, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00022512743821055849, | |
| "grad_norm": 0.46411532163619995, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1691, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00025728850081206683, | |
| "grad_norm": 0.45140358805656433, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1133, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002894495634135752, | |
| "grad_norm": 0.6007004380226135, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0593, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002894495634135752, | |
| "eval_loss": 1.2019928693771362, | |
| "eval_runtime": 426.4899, | |
| "eval_samples_per_second": 30.697, | |
| "eval_steps_per_second": 15.349, | |
| "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": 799547448360960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |