| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007903888713246918, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015807777426493836, | |
| "eval_loss": NaN, | |
| "eval_runtime": 117.4353, | |
| "eval_samples_per_second": 22.685, | |
| "eval_steps_per_second": 11.342, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015807777426493834, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020550110654441985, | |
| "eval_loss": NaN, | |
| "eval_runtime": 116.4203, | |
| "eval_samples_per_second": 22.883, | |
| "eval_steps_per_second": 11.441, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003161555485298767, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004110022130888397, | |
| "eval_loss": NaN, | |
| "eval_runtime": 116.5254, | |
| "eval_samples_per_second": 22.862, | |
| "eval_steps_per_second": 11.431, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00474233322794815, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0061650331963325955, | |
| "eval_loss": NaN, | |
| "eval_runtime": 116.4533, | |
| "eval_samples_per_second": 22.876, | |
| "eval_steps_per_second": 11.438, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006323110970597534, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.8338, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007903888713246918, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "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": 1.339110249725952e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |