| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003389859236095221, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.3898592360952214e-05, | |
| "grad_norm": 1.1323820352554321, | |
| "learning_rate": 2e-05, | |
| "loss": 4.9511, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.3898592360952214e-05, | |
| "eval_loss": 1.405200719833374, | |
| "eval_runtime": 676.0509, | |
| "eval_samples_per_second": 18.373, | |
| "eval_steps_per_second": 9.187, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.779718472190443e-05, | |
| "grad_norm": 1.070298194885254, | |
| "learning_rate": 4e-05, | |
| "loss": 4.6739, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010169577708285663, | |
| "grad_norm": 0.8583049178123474, | |
| "learning_rate": 6e-05, | |
| "loss": 5.5206, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010169577708285663, | |
| "eval_loss": 1.403877854347229, | |
| "eval_runtime": 678.4949, | |
| "eval_samples_per_second": 18.307, | |
| "eval_steps_per_second": 9.154, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013559436944380885, | |
| "grad_norm": 1.0343353748321533, | |
| "learning_rate": 8e-05, | |
| "loss": 5.3455, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00016949296180476106, | |
| "grad_norm": 0.9739586710929871, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0044, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020339155416571327, | |
| "grad_norm": 1.296633243560791, | |
| "learning_rate": 0.00012, | |
| "loss": 5.8559, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020339155416571327, | |
| "eval_loss": 1.389311671257019, | |
| "eval_runtime": 683.5542, | |
| "eval_samples_per_second": 18.171, | |
| "eval_steps_per_second": 9.086, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00023729014652666548, | |
| "grad_norm": 1.5781192779541016, | |
| "learning_rate": 0.00014, | |
| "loss": 5.821, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002711887388876177, | |
| "grad_norm": 1.797141194343567, | |
| "learning_rate": 0.00016, | |
| "loss": 6.7544, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003050873312485699, | |
| "grad_norm": 7.586959362030029, | |
| "learning_rate": 0.00018, | |
| "loss": 5.3672, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003050873312485699, | |
| "eval_loss": 1.2876554727554321, | |
| "eval_runtime": 677.3722, | |
| "eval_samples_per_second": 18.337, | |
| "eval_steps_per_second": 9.169, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003389859236095221, | |
| "grad_norm": 1.8961583375930786, | |
| "learning_rate": 0.0002, | |
| "loss": 4.9622, | |
| "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": 3397367365632000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |