| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018889754669311233, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00037779509338622464, | |
| "eval_loss": 1.3661420345306396, | |
| "eval_runtime": 601.355, | |
| "eval_samples_per_second": 7.413, | |
| "eval_steps_per_second": 3.707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037779509338622466, | |
| "eval_loss": 1.3595200777053833, | |
| "eval_runtime": 604.1422, | |
| "eval_samples_per_second": 7.379, | |
| "eval_steps_per_second": 3.69, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007555901867724493, | |
| "eval_loss": 1.3265780210494995, | |
| "eval_runtime": 599.8781, | |
| "eval_samples_per_second": 7.432, | |
| "eval_steps_per_second": 3.716, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01133385280158674, | |
| "eval_loss": 1.274393081665039, | |
| "eval_runtime": 606.4167, | |
| "eval_samples_per_second": 7.351, | |
| "eval_steps_per_second": 3.676, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015111803735448986, | |
| "grad_norm": 0.5035961866378784, | |
| "learning_rate": 2.9289321881345257e-06, | |
| "loss": 1.3002, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015111803735448986, | |
| "eval_loss": 1.244433045387268, | |
| "eval_runtime": 595.3628, | |
| "eval_samples_per_second": 7.488, | |
| "eval_steps_per_second": 3.744, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018889754669311233, | |
| "eval_loss": 1.2388581037521362, | |
| "eval_runtime": 597.804, | |
| "eval_samples_per_second": 7.457, | |
| "eval_steps_per_second": 3.729, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2956458467328e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |