| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00030105066682722703, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0105066682722702e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.0105066682722702e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 278.6864, | |
| "eval_samples_per_second": 50.189, | |
| "eval_steps_per_second": 25.096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.0210133365445404e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.031520004816811e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.031520004816811e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 276.5809, | |
| "eval_samples_per_second": 50.571, | |
| "eval_steps_per_second": 25.287, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012042026673089081, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015052533341361352, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018063040009633623, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00018063040009633623, | |
| "eval_loss": NaN, | |
| "eval_runtime": 277.3715, | |
| "eval_samples_per_second": 50.427, | |
| "eval_steps_per_second": 25.215, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002107354667790589, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00024084053346178162, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002709456001445043, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002709456001445043, | |
| "eval_loss": NaN, | |
| "eval_runtime": 277.2149, | |
| "eval_samples_per_second": 50.455, | |
| "eval_steps_per_second": 25.23, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00030105066682722703, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 624864830423040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |