| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0030747943731262973, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00030747943731262973, | |
| "grad_norm": 1.1068464517593384, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2025, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00030747943731262973, | |
| "eval_loss": 3.1388211250305176, | |
| "eval_runtime": 45.8209, | |
| "eval_samples_per_second": 29.899, | |
| "eval_steps_per_second": 14.949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006149588746252595, | |
| "grad_norm": 1.1117780208587646, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4745, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009224383119378892, | |
| "grad_norm": 1.519108533859253, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2771, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009224383119378892, | |
| "eval_loss": 3.1286842823028564, | |
| "eval_runtime": 44.7466, | |
| "eval_samples_per_second": 30.617, | |
| "eval_steps_per_second": 15.308, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001229917749250519, | |
| "grad_norm": 1.700682282447815, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3701, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015373971865631486, | |
| "grad_norm": 1.8919302225112915, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8062, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0018448766238757784, | |
| "grad_norm": 1.9330875873565674, | |
| "learning_rate": 0.00012, | |
| "loss": 2.5166, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018448766238757784, | |
| "eval_loss": 2.944230556488037, | |
| "eval_runtime": 44.8463, | |
| "eval_samples_per_second": 30.549, | |
| "eval_steps_per_second": 15.274, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002152356061188408, | |
| "grad_norm": 2.2040510177612305, | |
| "learning_rate": 0.00014, | |
| "loss": 2.9608, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002459835498501038, | |
| "grad_norm": 1.2488757371902466, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0362, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0027673149358136673, | |
| "grad_norm": 2.463510751724243, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3131, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027673149358136673, | |
| "eval_loss": 2.4527699947357178, | |
| "eval_runtime": 44.8437, | |
| "eval_samples_per_second": 30.551, | |
| "eval_steps_per_second": 15.275, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0030747943731262973, | |
| "grad_norm": 2.1647098064422607, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0647, | |
| "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": 1988281566756864.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |