| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.96, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14814814814814814, |
| "grad_norm": 5.020249366760254, |
| "learning_rate": 4.9000000000000005e-06, |
| "loss": 24.162, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "grad_norm": 5.590981960296631, |
| "learning_rate": 9.900000000000002e-06, |
| "loss": 23.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 7.975481986999512, |
| "learning_rate": 1.49e-05, |
| "loss": 22.6112, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 7.71668004989624, |
| "learning_rate": 1.9900000000000003e-05, |
| "loss": 20.3183, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.7407407407407407, |
| "grad_norm": 7.241501331329346, |
| "learning_rate": 2.4900000000000002e-05, |
| "loss": 16.8563, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 8.053779602050781, |
| "learning_rate": 2.9900000000000002e-05, |
| "loss": 13.3312, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.0355555555555556, |
| "grad_norm": 5.158635139465332, |
| "learning_rate": 3.49e-05, |
| "loss": 7.1556, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.1837037037037037, |
| "grad_norm": 1.008846402168274, |
| "learning_rate": 3.99e-05, |
| "loss": 3.3481, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.3318518518518518, |
| "grad_norm": 0.5116708874702454, |
| "learning_rate": 4.49e-05, |
| "loss": 2.869, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.48, |
| "grad_norm": 0.9101947546005249, |
| "learning_rate": 4.99e-05, |
| "loss": 2.5183, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.6281481481481481, |
| "grad_norm": 0.743137538433075, |
| "learning_rate": 5.4900000000000006e-05, |
| "loss": 1.9262, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.7762962962962963, |
| "grad_norm": 1.1300047636032104, |
| "learning_rate": 5.99e-05, |
| "loss": 1.4028, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.9244444444444444, |
| "grad_norm": 0.6446654200553894, |
| "learning_rate": 6.49e-05, |
| "loss": 1.1013, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.071111111111111, |
| "grad_norm": 0.4343520402908325, |
| "learning_rate": 6.99e-05, |
| "loss": 0.9197, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.2192592592592595, |
| "grad_norm": 0.4966985285282135, |
| "learning_rate": 7.49e-05, |
| "loss": 0.7525, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.3674074074074074, |
| "grad_norm": 0.43477675318717957, |
| "learning_rate": 7.99e-05, |
| "loss": 0.685, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.5155555555555553, |
| "grad_norm": 0.35509243607521057, |
| "learning_rate": 8.49e-05, |
| "loss": 0.645, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.6637037037037037, |
| "grad_norm": 0.3638167679309845, |
| "learning_rate": 8.99e-05, |
| "loss": 0.6012, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.811851851851852, |
| "grad_norm": 0.33944472670555115, |
| "learning_rate": 9.49e-05, |
| "loss": 0.537, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.96, |
| "grad_norm": 0.3524259328842163, |
| "learning_rate": 9.99e-05, |
| "loss": 0.5597, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.96, |
| "step": 1000, |
| "total_flos": 2.197720915771392e+16, |
| "train_loss": 7.265010034561157, |
| "train_runtime": 3207.2808, |
| "train_samples_per_second": 9.977, |
| "train_steps_per_second": 0.312 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.197720915771392e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
