| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022922636103151862, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002292263610315186, | |
| "grad_norm": 7.612102508544922, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6658, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002292263610315186, | |
| "eval_loss": 0.6854150891304016, | |
| "eval_runtime": 11.0145, | |
| "eval_samples_per_second": 16.705, | |
| "eval_steps_per_second": 8.353, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004584527220630372, | |
| "grad_norm": 8.802815437316895, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8533, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006876790830945559, | |
| "grad_norm": 6.691609859466553, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8252, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006876790830945559, | |
| "eval_loss": 0.6701761484146118, | |
| "eval_runtime": 10.4102, | |
| "eval_samples_per_second": 17.675, | |
| "eval_steps_per_second": 8.838, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009169054441260744, | |
| "grad_norm": 7.868908882141113, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4937, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011461318051575931, | |
| "grad_norm": 7.792079925537109, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3419, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013753581661891117, | |
| "grad_norm": 5.8552398681640625, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4592, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013753581661891117, | |
| "eval_loss": 0.5591138601303101, | |
| "eval_runtime": 10.4237, | |
| "eval_samples_per_second": 17.652, | |
| "eval_steps_per_second": 8.826, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016045845272206302, | |
| "grad_norm": 5.96946382522583, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1551, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01833810888252149, | |
| "grad_norm": 4.590500354766846, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9279, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020630372492836675, | |
| "grad_norm": 5.2422919273376465, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0522, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020630372492836675, | |
| "eval_loss": 0.4911685287952423, | |
| "eval_runtime": 10.4201, | |
| "eval_samples_per_second": 17.658, | |
| "eval_steps_per_second": 8.829, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022922636103151862, | |
| "grad_norm": 5.273870468139648, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1747, | |
| "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": 3505343598428160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |