| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010778765831312315, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002155753166262463, | |
| "eval_loss": 10.379223823547363, | |
| "eval_runtime": 8.4382, | |
| "eval_samples_per_second": 231.567, | |
| "eval_steps_per_second": 115.783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010778765831312314, | |
| "grad_norm": 0.9546406865119934, | |
| "learning_rate": 5e-05, | |
| "loss": 41.5054, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002155753166262463, | |
| "grad_norm": 1.1193766593933105, | |
| "learning_rate": 0.0001, | |
| "loss": 41.5383, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002155753166262463, | |
| "eval_loss": 10.377625465393066, | |
| "eval_runtime": 8.7272, | |
| "eval_samples_per_second": 223.898, | |
| "eval_steps_per_second": 111.949, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0032336297493936943, | |
| "grad_norm": 1.069719672203064, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 41.5022, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004311506332524926, | |
| "grad_norm": 0.9299646019935608, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 41.482, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004311506332524926, | |
| "eval_loss": 10.374091148376465, | |
| "eval_runtime": 8.7331, | |
| "eval_samples_per_second": 223.746, | |
| "eval_steps_per_second": 111.873, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0053893829156561575, | |
| "grad_norm": 1.0937271118164062, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 41.4792, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0064672594987873885, | |
| "grad_norm": 0.9614943861961365, | |
| "learning_rate": 5e-05, | |
| "loss": 41.5162, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0064672594987873885, | |
| "eval_loss": 10.371255874633789, | |
| "eval_runtime": 8.5479, | |
| "eval_samples_per_second": 228.595, | |
| "eval_steps_per_second": 114.297, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00754513608191862, | |
| "grad_norm": 1.0435622930526733, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 41.4971, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008623012665049851, | |
| "grad_norm": 0.906825065612793, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 41.4963, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008623012665049851, | |
| "eval_loss": 10.369808197021484, | |
| "eval_runtime": 8.8219, | |
| "eval_samples_per_second": 221.493, | |
| "eval_steps_per_second": 110.746, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009700889248181084, | |
| "grad_norm": 0.9356521964073181, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 41.4746, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010778765831312315, | |
| "grad_norm": 0.9362896680831909, | |
| "learning_rate": 0.0, | |
| "loss": 41.4804, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010778765831312315, | |
| "eval_loss": 10.369543075561523, | |
| "eval_runtime": 8.4701, | |
| "eval_samples_per_second": 230.695, | |
| "eval_steps_per_second": 115.347, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1283240755200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |