| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00044325095021922455, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4775031673974151e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 572.0497, | |
| "eval_samples_per_second": 49.817, | |
| "eval_steps_per_second": 24.909, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.432509502192245e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.387515836987076e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 575.9449, | |
| "eval_samples_per_second": 49.48, | |
| "eval_steps_per_second": 24.74, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.86501900438449e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013297528506576737, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00014775031673974152, | |
| "eval_loss": NaN, | |
| "eval_runtime": 570.9582, | |
| "eval_samples_per_second": 49.913, | |
| "eval_steps_per_second": 24.956, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001773003800876898, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00022162547510961228, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00022162547510961228, | |
| "eval_loss": NaN, | |
| "eval_runtime": 571.2623, | |
| "eval_samples_per_second": 49.886, | |
| "eval_steps_per_second": 24.943, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00026595057013153474, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00029550063347948304, | |
| "eval_loss": NaN, | |
| "eval_runtime": 575.6298, | |
| "eval_samples_per_second": 49.508, | |
| "eval_steps_per_second": 24.754, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00031027566515345715, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0003546007601753796, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0003693757918493538, | |
| "eval_loss": NaN, | |
| "eval_runtime": 574.4066, | |
| "eval_samples_per_second": 49.613, | |
| "eval_steps_per_second": 24.806, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0003989258551973021, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00044325095021922455, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00044325095021922455, | |
| "eval_loss": NaN, | |
| "eval_runtime": 550.6746, | |
| "eval_samples_per_second": 51.751, | |
| "eval_steps_per_second": 25.876, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "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": 540715725619200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |