| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.01223540927444023, |
| "eval_steps": 1000, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0006117704637220115, |
| "grad_norm": 1.647070050239563, |
| "learning_rate": 3.671221700999388e-08, |
| "loss": 0.1895, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.001223540927444023, |
| "grad_norm": 1.2862460613250732, |
| "learning_rate": 7.750356924332042e-08, |
| "loss": 0.1824, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0018353113911660345, |
| "grad_norm": 1.6323548555374146, |
| "learning_rate": 1.1829492147664697e-07, |
| "loss": 0.1927, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.002447081854888046, |
| "grad_norm": 1.4893640279769897, |
| "learning_rate": 1.590862737099735e-07, |
| "loss": 0.1911, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0030588523186100575, |
| "grad_norm": 1.0960227251052856, |
| "learning_rate": 1.9987762594330002e-07, |
| "loss": 0.1801, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.003670622782332069, |
| "grad_norm": 0.6325238943099976, |
| "learning_rate": 2.406689781766266e-07, |
| "loss": 0.1818, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.0042823932460540805, |
| "grad_norm": 2.047482490539551, |
| "learning_rate": 2.814603304099531e-07, |
| "loss": 0.192, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.004894163709776092, |
| "grad_norm": 2.4107882976531982, |
| "learning_rate": 3.222516826432796e-07, |
| "loss": 0.1897, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.0055059341734981036, |
| "grad_norm": 0.7147008180618286, |
| "learning_rate": 3.630430348766062e-07, |
| "loss": 0.1833, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.006117704637220115, |
| "grad_norm": 0.7912544012069702, |
| "learning_rate": 4.0383438710993277e-07, |
| "loss": 0.1869, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.006729475100942127, |
| "grad_norm": 1.3714642524719238, |
| "learning_rate": 4.4462573934325923e-07, |
| "loss": 0.1861, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.007341245564664138, |
| "grad_norm": 1.2271082401275635, |
| "learning_rate": 4.854170915765858e-07, |
| "loss": 0.1843, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.00795301602838615, |
| "grad_norm": 0.6724980473518372, |
| "learning_rate": 5.262084438099123e-07, |
| "loss": 0.1819, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.008564786492108161, |
| "grad_norm": 1.4163967370986938, |
| "learning_rate": 5.669997960432388e-07, |
| "loss": 0.182, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.009176556955830173, |
| "grad_norm": 1.1623996496200562, |
| "learning_rate": 6.077911482765654e-07, |
| "loss": 0.1834, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.009788327419552184, |
| "grad_norm": 1.2043864727020264, |
| "learning_rate": 6.48582500509892e-07, |
| "loss": 0.1806, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.010400097883274196, |
| "grad_norm": 0.9487743973731995, |
| "learning_rate": 6.893738527432185e-07, |
| "loss": 0.1806, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.011011868346996207, |
| "grad_norm": 1.135107159614563, |
| "learning_rate": 7.301652049765451e-07, |
| "loss": 0.178, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.011623638810718219, |
| "grad_norm": 1.8040673732757568, |
| "learning_rate": 7.709565572098715e-07, |
| "loss": 0.1776, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.01223540927444023, |
| "grad_norm": 0.6054055690765381, |
| "learning_rate": 8.117479094431981e-07, |
| "loss": 0.1781, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 49038, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1683910754304000.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
