| { | |
| "best_global_step": 738, | |
| "best_metric": 0.1383887678384781, | |
| "best_model_checkpoint": "/mnt/tank/scratch/rgurtsiev/workflow/ai_models/Oblivion-Adapter-1.5B-v1-demo/checkpoint-738", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 738, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.056960105895996, | |
| "eval_runtime": 568.5606, | |
| "eval_samples_per_second": 3.424, | |
| "eval_steps_per_second": 0.072, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5458435416221619, | |
| "eval_runtime": 564.7929, | |
| "eval_samples_per_second": 3.447, | |
| "eval_steps_per_second": 0.073, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.18356487154960632, | |
| "eval_runtime": 561.3321, | |
| "eval_samples_per_second": 3.469, | |
| "eval_steps_per_second": 0.073, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.1636216789484024, | |
| "eval_runtime": 560.8768, | |
| "eval_samples_per_second": 3.471, | |
| "eval_steps_per_second": 0.073, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.14793169498443604, | |
| "eval_runtime": 562.082, | |
| "eval_samples_per_second": 3.464, | |
| "eval_steps_per_second": 0.073, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.14370538294315338, | |
| "eval_runtime": 559.2463, | |
| "eval_samples_per_second": 3.481, | |
| "eval_steps_per_second": 0.073, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 6.098159509202454, | |
| "grad_norm": 1576.2506103515625, | |
| "learning_rate": 1.0970017636684305e-05, | |
| "loss": 0.1864, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.1408863216638565, | |
| "eval_runtime": 559.9693, | |
| "eval_samples_per_second": 3.477, | |
| "eval_steps_per_second": 0.073, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.13924846053123474, | |
| "eval_runtime": 562.5913, | |
| "eval_samples_per_second": 3.461, | |
| "eval_steps_per_second": 0.073, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.1383887678384781, | |
| "eval_runtime": 559.3973, | |
| "eval_samples_per_second": 3.481, | |
| "eval_steps_per_second": 0.073, | |
| "step": 738 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 810, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.659506773537587e+17, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |