| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005864242779651078, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005864242779651077, | |
| "grad_norm": 2.60758638381958, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6951, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005864242779651077, | |
| "eval_loss": 2.498016834259033, | |
| "eval_runtime": 49.8329, | |
| "eval_samples_per_second": 14.408, | |
| "eval_steps_per_second": 7.204, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011728485559302155, | |
| "grad_norm": 2.1261184215545654, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017592728338953233, | |
| "grad_norm": 2.1857070922851562, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4085, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017592728338953233, | |
| "eval_loss": 2.4860634803771973, | |
| "eval_runtime": 48.3032, | |
| "eval_samples_per_second": 14.864, | |
| "eval_steps_per_second": 7.432, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002345697111860431, | |
| "grad_norm": 2.2904653549194336, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5458, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002932121389825539, | |
| "grad_norm": 2.6547863483428955, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3683, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0035185456677906467, | |
| "grad_norm": 2.743929862976074, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4195, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035185456677906467, | |
| "eval_loss": 2.242464542388916, | |
| "eval_runtime": 48.298, | |
| "eval_samples_per_second": 14.866, | |
| "eval_steps_per_second": 7.433, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004104969945755754, | |
| "grad_norm": 2.964322566986084, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1674, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004691394223720862, | |
| "grad_norm": 5.467318058013916, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1852, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00527781850168597, | |
| "grad_norm": 3.59049916267395, | |
| "learning_rate": 0.00018, | |
| "loss": 1.875, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00527781850168597, | |
| "eval_loss": 1.5978492498397827, | |
| "eval_runtime": 48.3247, | |
| "eval_samples_per_second": 14.858, | |
| "eval_steps_per_second": 7.429, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005864242779651078, | |
| "grad_norm": 3.63289213180542, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7472, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |