| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0025559758715877723, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.1119517431755445e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 195.6688, | |
| "eval_samples_per_second": 21.051, | |
| "eval_steps_per_second": 10.528, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005111951743175544, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006645537266128208, | |
| "eval_loss": NaN, | |
| "eval_runtime": 195.0678, | |
| "eval_samples_per_second": 21.116, | |
| "eval_steps_per_second": 10.56, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0010223903486351088, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013291074532256416, | |
| "eval_loss": NaN, | |
| "eval_runtime": 195.0362, | |
| "eval_samples_per_second": 21.119, | |
| "eval_steps_per_second": 10.562, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0015335855229526632, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001993661179838462, | |
| "eval_loss": NaN, | |
| "eval_runtime": 195.0267, | |
| "eval_samples_per_second": 21.12, | |
| "eval_steps_per_second": 10.563, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0020447806972702176, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0025559758715877723, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7952453861376000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |