| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0039058685675227027, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039058685675227026, | |
| "grad_norm": 30.679697036743164, | |
| "learning_rate": 2e-05, | |
| "loss": 38.7076, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039058685675227026, | |
| "eval_loss": 9.116019248962402, | |
| "eval_runtime": 95.3874, | |
| "eval_samples_per_second": 11.301, | |
| "eval_steps_per_second": 5.651, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007811737135045405, | |
| "grad_norm": 43.26640319824219, | |
| "learning_rate": 4e-05, | |
| "loss": 33.6181, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001171760570256811, | |
| "grad_norm": 39.603065490722656, | |
| "learning_rate": 6e-05, | |
| "loss": 35.1822, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001171760570256811, | |
| "eval_loss": 9.003752708435059, | |
| "eval_runtime": 95.4521, | |
| "eval_samples_per_second": 11.294, | |
| "eval_steps_per_second": 5.647, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001562347427009081, | |
| "grad_norm": 32.677711486816406, | |
| "learning_rate": 8e-05, | |
| "loss": 37.3262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019529342837613514, | |
| "grad_norm": 53.797515869140625, | |
| "learning_rate": 0.0001, | |
| "loss": 33.2911, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002343521140513622, | |
| "grad_norm": 50.63685607910156, | |
| "learning_rate": 0.00012, | |
| "loss": 32.4459, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002343521140513622, | |
| "eval_loss": 6.371692180633545, | |
| "eval_runtime": 95.4974, | |
| "eval_samples_per_second": 11.288, | |
| "eval_steps_per_second": 5.644, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002734107997265892, | |
| "grad_norm": 63.162654876708984, | |
| "learning_rate": 0.00014, | |
| "loss": 25.1714, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003124694854018162, | |
| "grad_norm": 55.868839263916016, | |
| "learning_rate": 0.00016, | |
| "loss": 16.4742, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0035152817107704324, | |
| "grad_norm": 20.2382755279541, | |
| "learning_rate": 0.00018, | |
| "loss": 5.0641, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0035152817107704324, | |
| "eval_loss": 2.2086901664733887, | |
| "eval_runtime": 95.646, | |
| "eval_samples_per_second": 11.271, | |
| "eval_steps_per_second": 5.635, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0039058685675227027, | |
| "grad_norm": 4.768134593963623, | |
| "learning_rate": 0.0002, | |
| "loss": 5.6721, | |
| "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": 2239530207805440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |