| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 44.0, | |
| "eval_steps": 500, | |
| "global_step": 55, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.7059780359268188, | |
| "eval_runtime": 3.184, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.552927017211914, | |
| "eval_runtime": 3.1846, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.338813304901123, | |
| "eval_runtime": 3.1854, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.2230206727981567, | |
| "eval_runtime": 3.1854, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.1060389280319214, | |
| "eval_runtime": 3.185, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.9127510190010071, | |
| "eval_runtime": 3.1854, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.8066120147705078, | |
| "eval_runtime": 3.1857, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.31343773007392883, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3573, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.713127076625824, | |
| "eval_runtime": 3.1868, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.6134043335914612, | |
| "eval_runtime": 3.1858, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.5432830452919006, | |
| "eval_runtime": 3.1857, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.5256462693214417, | |
| "eval_runtime": 3.1867, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.4858134686946869, | |
| "eval_runtime": 3.1872, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.4822380840778351, | |
| "eval_runtime": 3.1868, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.4799506664276123, | |
| "eval_runtime": 3.1861, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.46334752440452576, | |
| "eval_runtime": 3.1859, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 0.19768336415290833, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0472, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.4545087516307831, | |
| "eval_runtime": 3.1863, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.4524390995502472, | |
| "eval_runtime": 3.1865, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.4537128210067749, | |
| "eval_runtime": 3.1865, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.4678395688533783, | |
| "eval_runtime": 3.1865, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.46853116154670715, | |
| "eval_runtime": 3.1871, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.47128668427467346, | |
| "eval_runtime": 3.1866, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.4789499044418335, | |
| "eval_runtime": 3.1865, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.4797506630420685, | |
| "eval_runtime": 3.1863, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.13670594990253448, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0021, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.47982195019721985, | |
| "eval_runtime": 3.1868, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.47853362560272217, | |
| "eval_runtime": 3.1877, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.47531822323799133, | |
| "eval_runtime": 3.187, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.47337570786476135, | |
| "eval_runtime": 3.1886, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.4755137860774994, | |
| "eval_runtime": 3.1857, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.4671432077884674, | |
| "eval_runtime": 3.1861, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.4592552185058594, | |
| "eval_runtime": 3.1858, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.45515766739845276, | |
| "eval_runtime": 3.1858, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "grad_norm": 0.039176054298877716, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0011, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.45262205600738525, | |
| "eval_runtime": 3.1866, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.4497206211090088, | |
| "eval_runtime": 3.1848, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.4475771188735962, | |
| "eval_runtime": 3.1852, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.44721055030822754, | |
| "eval_runtime": 3.185, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.44510793685913086, | |
| "eval_runtime": 3.1857, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.4454095661640167, | |
| "eval_runtime": 3.1854, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.44539403915405273, | |
| "eval_runtime": 3.1873, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.44641730189323425, | |
| "eval_runtime": 3.1861, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.0032469367142766714, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0001, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.44554126262664795, | |
| "eval_runtime": 3.187, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 0.4454215466976166, | |
| "eval_runtime": 3.1853, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 0.4468770921230316, | |
| "eval_runtime": 3.1853, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 0.44626128673553467, | |
| "eval_runtime": 3.187, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 0.4460159242153168, | |
| "eval_runtime": 3.1857, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 55 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 60, | |
| "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": 1.3545797228429312e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |