| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027926960257787327, | |
| "eval_steps": 10, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021482277121374865, | |
| "eval_loss": 9.146766662597656, | |
| "eval_runtime": 6.1234, | |
| "eval_samples_per_second": 32.008, | |
| "eval_steps_per_second": 16.004, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010741138560687433, | |
| "grad_norm": 48.73690414428711, | |
| "learning_rate": 5e-05, | |
| "loss": 9.132, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "grad_norm": 42.14037322998047, | |
| "learning_rate": 0.0001, | |
| "loss": 7.8659, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "eval_loss": 6.615852355957031, | |
| "eval_runtime": 6.0593, | |
| "eval_samples_per_second": 32.347, | |
| "eval_steps_per_second": 16.173, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 332529571725312.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |