| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00023334953816237238, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.778317938745747e-05, | |
| "grad_norm": 1.6048940420150757, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5142, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.778317938745747e-05, | |
| "eval_loss": 3.8527331352233887, | |
| "eval_runtime": 164.0325, | |
| "eval_samples_per_second": 33.006, | |
| "eval_steps_per_second": 16.503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015556635877491494, | |
| "grad_norm": 2.2154529094696045, | |
| "learning_rate": 4e-05, | |
| "loss": 4.0158, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00023334953816237238, | |
| "grad_norm": 1.6464277505874634, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7409, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023334953816237238, | |
| "eval_loss": 3.837887763977051, | |
| "eval_runtime": 163.416, | |
| "eval_samples_per_second": 33.13, | |
| "eval_steps_per_second": 16.565, | |
| "step": 3 | |
| } | |
| ], | |
| "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": 554869274443776.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |