| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0027785495971103086, | |
| "eval_steps": 5, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005557099194220616, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 73.9887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005557099194220616, | |
| "eval_loss": NaN, | |
| "eval_runtime": 562.7215, | |
| "eval_samples_per_second": 5.386, | |
| "eval_steps_per_second": 2.694, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011114198388441233, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016671297582661851, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 2.8229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022228396776882466, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0027785495971103086, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0027785495971103086, | |
| "eval_loss": NaN, | |
| "eval_runtime": 273.9949, | |
| "eval_samples_per_second": 11.062, | |
| "eval_steps_per_second": 5.533, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6229908095238144.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |