| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00475963826749167, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047596382674916705, | |
| "grad_norm": 1.7633370161056519, | |
| "learning_rate": 2e-05, | |
| "loss": 3.712, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00047596382674916705, | |
| "eval_loss": 3.891406536102295, | |
| "eval_runtime": 13.5956, | |
| "eval_samples_per_second": 65.094, | |
| "eval_steps_per_second": 32.584, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009519276534983341, | |
| "grad_norm": 1.8263545036315918, | |
| "learning_rate": 4e-05, | |
| "loss": 3.972, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014278914802475012, | |
| "grad_norm": 1.8914746046066284, | |
| "learning_rate": 6e-05, | |
| "loss": 3.9302, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014278914802475012, | |
| "eval_loss": 3.8839192390441895, | |
| "eval_runtime": 12.7196, | |
| "eval_samples_per_second": 69.578, | |
| "eval_steps_per_second": 34.828, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019038553069966682, | |
| "grad_norm": 1.9296693801879883, | |
| "learning_rate": 8e-05, | |
| "loss": 3.9524, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002379819133745835, | |
| "grad_norm": 2.067610740661621, | |
| "learning_rate": 0.0001, | |
| "loss": 3.8809, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028557829604950024, | |
| "grad_norm": 1.8746843338012695, | |
| "learning_rate": 0.00012, | |
| "loss": 3.8601, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0028557829604950024, | |
| "eval_loss": 3.7874338626861572, | |
| "eval_runtime": 12.7128, | |
| "eval_samples_per_second": 69.615, | |
| "eval_steps_per_second": 34.847, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033317467872441696, | |
| "grad_norm": 1.914277195930481, | |
| "learning_rate": 0.00014, | |
| "loss": 3.5256, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0038077106139933364, | |
| "grad_norm": 2.3482606410980225, | |
| "learning_rate": 0.00016, | |
| "loss": 3.717, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004283674440742504, | |
| "grad_norm": 2.182288408279419, | |
| "learning_rate": 0.00018, | |
| "loss": 3.6458, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004283674440742504, | |
| "eval_loss": 3.4977915287017822, | |
| "eval_runtime": 12.5666, | |
| "eval_samples_per_second": 70.425, | |
| "eval_steps_per_second": 35.252, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00475963826749167, | |
| "grad_norm": 2.146529197692871, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3027, | |
| "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": 240545515438080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |