| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007668221611604575, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.520246235116194e-05, | |
| "grad_norm": 11.390654563903809, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.520246235116194e-05, | |
| "eval_loss": 1.6326349973678589, | |
| "eval_runtime": 97.9639, | |
| "eval_samples_per_second": 50.447, | |
| "eval_steps_per_second": 25.224, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017040492470232388, | |
| "grad_norm": 16.750507354736328, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9276, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00025560738705348587, | |
| "grad_norm": 13.093873023986816, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2497, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025560738705348587, | |
| "eval_loss": 1.5361175537109375, | |
| "eval_runtime": 96.3426, | |
| "eval_samples_per_second": 51.296, | |
| "eval_steps_per_second": 25.648, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00034080984940464777, | |
| "grad_norm": 8.885797500610352, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0354, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004260123117558097, | |
| "grad_norm": 7.249693393707275, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9423, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005112147741069717, | |
| "grad_norm": 10.092117309570312, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2452, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005112147741069717, | |
| "eval_loss": 0.8979904055595398, | |
| "eval_runtime": 94.4489, | |
| "eval_samples_per_second": 52.325, | |
| "eval_steps_per_second": 26.162, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005964172364581337, | |
| "grad_norm": 5.180422782897949, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5217, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006816196988092955, | |
| "grad_norm": 9.183744430541992, | |
| "learning_rate": 0.00016, | |
| "loss": 0.654, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007668221611604575, | |
| "grad_norm": 6.878085613250732, | |
| "learning_rate": 0.00018, | |
| "loss": 0.3706, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007668221611604575, | |
| "eval_loss": 0.32512030005455017, | |
| "eval_runtime": 95.6597, | |
| "eval_samples_per_second": 51.662, | |
| "eval_steps_per_second": 25.831, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 80134347423744.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |