| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03276003276003276, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003276003276003276, | |
| "grad_norm": 6.991154193878174, | |
| "learning_rate": 2e-05, | |
| "loss": 14.3622, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003276003276003276, | |
| "eval_loss": 3.6128365993499756, | |
| "eval_runtime": 1.6665, | |
| "eval_samples_per_second": 77.406, | |
| "eval_steps_per_second": 39.003, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006552006552006552, | |
| "grad_norm": 7.093165397644043, | |
| "learning_rate": 4e-05, | |
| "loss": 13.1498, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "grad_norm": 6.144061088562012, | |
| "learning_rate": 6e-05, | |
| "loss": 14.2222, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "eval_loss": 3.610887050628662, | |
| "eval_runtime": 1.617, | |
| "eval_samples_per_second": 79.776, | |
| "eval_steps_per_second": 40.197, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013104013104013105, | |
| "grad_norm": 7.3027729988098145, | |
| "learning_rate": 8e-05, | |
| "loss": 15.6176, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01638001638001638, | |
| "grad_norm": 7.285496234893799, | |
| "learning_rate": 0.0001, | |
| "loss": 13.8623, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019656019656019656, | |
| "grad_norm": 8.75092887878418, | |
| "learning_rate": 0.00012, | |
| "loss": 14.7874, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019656019656019656, | |
| "eval_loss": 3.4283764362335205, | |
| "eval_runtime": 1.6654, | |
| "eval_samples_per_second": 77.459, | |
| "eval_steps_per_second": 39.03, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02293202293202293, | |
| "grad_norm": 7.491062641143799, | |
| "learning_rate": 0.00014, | |
| "loss": 13.6163, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02620802620802621, | |
| "grad_norm": 7.107450008392334, | |
| "learning_rate": 0.00016, | |
| "loss": 14.2017, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029484029484029485, | |
| "grad_norm": 7.686389446258545, | |
| "learning_rate": 0.00018, | |
| "loss": 12.6007, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.029484029484029485, | |
| "eval_loss": 3.1046876907348633, | |
| "eval_runtime": 1.686, | |
| "eval_samples_per_second": 76.514, | |
| "eval_steps_per_second": 38.554, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03276003276003276, | |
| "grad_norm": 9.958666801452637, | |
| "learning_rate": 0.0002, | |
| "loss": 12.8633, | |
| "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": 75069652992000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |