| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.3684210526315788, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 52.0, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1736, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 51.75, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.1746, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "eval_loss": 0.1243543028831482, | |
| "eval_runtime": 11.2471, | |
| "eval_samples_per_second": 13.426, | |
| "eval_steps_per_second": 3.379, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0105263157894737, | |
| "grad_norm": 35.5, | |
| "learning_rate": 3e-06, | |
| "loss": 0.1186, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.3473684210526315, | |
| "grad_norm": 7.21875, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0436, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0305, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "eval_loss": 0.03528702259063721, | |
| "eval_runtime": 11.2714, | |
| "eval_samples_per_second": 13.397, | |
| "eval_steps_per_second": 3.371, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0210526315789474, | |
| "grad_norm": 2.625, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0242, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.3578947368421055, | |
| "grad_norm": 1.578125, | |
| "learning_rate": 7e-06, | |
| "loss": 0.0226, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.694736842105263, | |
| "grad_norm": 1.515625, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0138, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.694736842105263, | |
| "eval_loss": 0.026165664196014404, | |
| "eval_runtime": 11.3041, | |
| "eval_samples_per_second": 13.358, | |
| "eval_steps_per_second": 3.362, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.031578947368421, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 9e-06, | |
| "loss": 0.013, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.3684210526315788, | |
| "grad_norm": 0.8515625, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0055, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.3684210526315788, | |
| "eval_loss": 0.03028305061161518, | |
| "eval_runtime": 11.2119, | |
| "eval_samples_per_second": 13.468, | |
| "eval_steps_per_second": 3.389, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.486540608523469e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |