| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 218, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.09174311926605505, |
| "grad_norm": 77.97719827296804, |
| "learning_rate": 2.0454545454545457e-06, |
| "loss": 1.3359, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1834862385321101, |
| "grad_norm": 265.24709695837305, |
| "learning_rate": 4.3181818181818185e-06, |
| "loss": 0.5962, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.27522935779816515, |
| "grad_norm": 78.23067497111585, |
| "learning_rate": 4.984280524733107e-06, |
| "loss": 0.5109, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3669724770642202, |
| "grad_norm": 22.475729196588212, |
| "learning_rate": 4.907762682323926e-06, |
| "loss": 0.4847, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.45871559633027525, |
| "grad_norm": 59.756490915636945, |
| "learning_rate": 4.7695183928174804e-06, |
| "loss": 0.4522, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5504587155963303, |
| "grad_norm": 23.110912996719065, |
| "learning_rate": 4.573091746702988e-06, |
| "loss": 0.3365, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.6422018348623854, |
| "grad_norm": 18.715722346382965, |
| "learning_rate": 4.323518422566586e-06, |
| "loss": 0.3215, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.7339449541284404, |
| "grad_norm": 12.25071414423181, |
| "learning_rate": 4.027196590253786e-06, |
| "loss": 0.3522, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.8256880733944955, |
| "grad_norm": 32.268560563433674, |
| "learning_rate": 3.691722884615814e-06, |
| "loss": 0.2965, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.9174311926605505, |
| "grad_norm": 15.37162898982021, |
| "learning_rate": 3.3256976548879183e-06, |
| "loss": 0.2803, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0091743119266054, |
| "grad_norm": 25.86667792331737, |
| "learning_rate": 2.9385044824109544e-06, |
| "loss": 0.3171, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.1009174311926606, |
| "grad_norm": 9.956090203931998, |
| "learning_rate": 2.5400696190754347e-06, |
| "loss": 0.285, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.1926605504587156, |
| "grad_norm": 7.8633473973914985, |
| "learning_rate": 2.140607513628296e-06, |
| "loss": 0.2312, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.2844036697247707, |
| "grad_norm": 185.15386357882502, |
| "learning_rate": 1.750358949640221e-06, |
| "loss": 0.2806, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.3761467889908257, |
| "grad_norm": 7.221204277723146, |
| "learning_rate": 1.3793285083420077e-06, |
| "loss": 0.2754, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.4678899082568808, |
| "grad_norm": 10.193912398664125, |
| "learning_rate": 1.0370280868464405e-06, |
| "loss": 0.2862, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.5596330275229358, |
| "grad_norm": 16.311279963641574, |
| "learning_rate": 7.322330470336314e-07, |
| "loss": 0.1962, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.6513761467889907, |
| "grad_norm": 27.917634703692208, |
| "learning_rate": 4.7275724657262293e-07, |
| "loss": 0.2103, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.7431192660550459, |
| "grad_norm": 13.281134715583004, |
| "learning_rate": 2.652527194814511e-07, |
| "loss": 0.2593, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.834862385321101, |
| "grad_norm": 8.55025910674403, |
| "learning_rate": 1.1503914170159058e-07, |
| "loss": 0.1502, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.926605504587156, |
| "grad_norm": 10.449884704801079, |
| "learning_rate": 2.5967453581185187e-08, |
| "loss": 0.155, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 218, |
| "total_flos": 15650089533440.0, |
| "train_loss": 0.3547171709734365, |
| "train_runtime": 1113.0811, |
| "train_samples_per_second": 1.563, |
| "train_steps_per_second": 0.196 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 218, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 15650089533440.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
