| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.030534351145038167, | |
| "eval_steps": 6, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002544529262086514, | |
| "grad_norm": 2.992696523666382, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1826, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002544529262086514, | |
| "eval_loss": 1.6133360862731934, | |
| "eval_runtime": 7.5869, | |
| "eval_samples_per_second": 21.88, | |
| "eval_steps_per_second": 10.94, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005089058524173028, | |
| "grad_norm": 3.473165512084961, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "grad_norm": 2.82555890083313, | |
| "learning_rate": 6e-05, | |
| "loss": 1.175, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010178117048346057, | |
| "grad_norm": 2.444389581680298, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8444, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01272264631043257, | |
| "grad_norm": 2.6523401737213135, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0504, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "grad_norm": 2.7490906715393066, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0024, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "eval_loss": 0.9683742523193359, | |
| "eval_runtime": 7.6156, | |
| "eval_samples_per_second": 21.797, | |
| "eval_steps_per_second": 10.899, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017811704834605598, | |
| "grad_norm": 2.5362422466278076, | |
| "learning_rate": 0.00014, | |
| "loss": 0.8316, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020356234096692113, | |
| "grad_norm": 2.6198008060455322, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6159, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022900763358778626, | |
| "grad_norm": 2.256551742553711, | |
| "learning_rate": 0.00018, | |
| "loss": 0.4382, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02544529262086514, | |
| "grad_norm": 2.475969076156616, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3562, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027989821882951654, | |
| "grad_norm": 3.510289192199707, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 0.3165, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030534351145038167, | |
| "grad_norm": 1.8848199844360352, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.2195, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030534351145038167, | |
| "eval_loss": 0.1976952999830246, | |
| "eval_runtime": 7.5845, | |
| "eval_samples_per_second": 21.887, | |
| "eval_steps_per_second": 10.943, | |
| "step": 12 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 24, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 6, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 600116796850176.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |