| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 552, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.36231884057971014, |
| "grad_norm": 11.473546981811523, |
| "learning_rate": 9.408212560386473e-06, |
| "loss": 2.518828125, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7246376811594203, |
| "grad_norm": 19.91433334350586, |
| "learning_rate": 8.804347826086957e-06, |
| "loss": 2.4250390625, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5803093314170837, |
| "eval_runtime": 29.4101, |
| "eval_samples_per_second": 16.661, |
| "eval_steps_per_second": 2.108, |
| "step": 138 |
| }, |
| { |
| "epoch": 1.0869565217391304, |
| "grad_norm": 16.91636085510254, |
| "learning_rate": 8.20048309178744e-06, |
| "loss": 2.2990234375, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.4492753623188406, |
| "grad_norm": 13.255877494812012, |
| "learning_rate": 7.596618357487924e-06, |
| "loss": 2.378984375, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.8115942028985508, |
| "grad_norm": 18.71368980407715, |
| "learning_rate": 6.992753623188407e-06, |
| "loss": 2.15296875, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.5362404584884644, |
| "eval_runtime": 27.8676, |
| "eval_samples_per_second": 17.583, |
| "eval_steps_per_second": 2.225, |
| "step": 276 |
| }, |
| { |
| "epoch": 2.1739130434782608, |
| "grad_norm": 9.45117473602295, |
| "learning_rate": 6.3888888888888885e-06, |
| "loss": 2.009921875, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.536231884057971, |
| "grad_norm": 8.40969467163086, |
| "learning_rate": 5.785024154589373e-06, |
| "loss": 2.07037109375, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.898550724637681, |
| "grad_norm": 10.270116806030273, |
| "learning_rate": 5.181159420289855e-06, |
| "loss": 1.952861328125, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.47528699040412903, |
| "eval_runtime": 27.7881, |
| "eval_samples_per_second": 17.633, |
| "eval_steps_per_second": 2.231, |
| "step": 414 |
| }, |
| { |
| "epoch": 3.260869565217391, |
| "grad_norm": 17.692113876342773, |
| "learning_rate": 4.5772946859903385e-06, |
| "loss": 1.79087890625, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.6231884057971016, |
| "grad_norm": 13.763245582580566, |
| "learning_rate": 3.973429951690821e-06, |
| "loss": 1.650498046875, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.9855072463768115, |
| "grad_norm": 33.43427276611328, |
| "learning_rate": 3.3695652173913045e-06, |
| "loss": 1.610087890625, |
| "step": 550 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.410451203584671, |
| "eval_runtime": 27.8228, |
| "eval_samples_per_second": 17.611, |
| "eval_steps_per_second": 2.228, |
| "step": 552 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 828, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.003460608777011e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
