| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 39.0, | |
| "eval_steps": 500, | |
| "global_step": 49, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8089030981063843, | |
| "eval_runtime": 3.1842, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.6632791757583618, | |
| "eval_runtime": 3.1852, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.4630075693130493, | |
| "eval_runtime": 3.1841, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.410213589668274, | |
| "eval_runtime": 3.1835, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.348659634590149, | |
| "eval_runtime": 3.1836, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.2120503187179565, | |
| "eval_runtime": 3.184, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.138137936592102, | |
| "eval_runtime": 3.1827, | |
| "eval_samples_per_second": 0.943, | |
| "eval_steps_per_second": 0.943, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.11976298689842224, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4185, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0605453252792358, | |
| "eval_runtime": 3.1835, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.9815027117729187, | |
| "eval_runtime": 3.183, | |
| "eval_samples_per_second": 0.943, | |
| "eval_steps_per_second": 0.943, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.8977057337760925, | |
| "eval_runtime": 3.1827, | |
| "eval_samples_per_second": 0.943, | |
| "eval_steps_per_second": 0.943, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.7791700959205627, | |
| "eval_runtime": 3.1827, | |
| "eval_samples_per_second": 0.943, | |
| "eval_steps_per_second": 0.943, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.6920549273490906, | |
| "eval_runtime": 3.1822, | |
| "eval_samples_per_second": 0.943, | |
| "eval_steps_per_second": 0.943, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.620513916015625, | |
| "eval_runtime": 3.1826, | |
| "eval_samples_per_second": 0.943, | |
| "eval_steps_per_second": 0.943, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.5490264296531677, | |
| "eval_runtime": 3.1827, | |
| "eval_samples_per_second": 0.943, | |
| "eval_steps_per_second": 0.943, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.5206396579742432, | |
| "eval_runtime": 3.1868, | |
| "eval_samples_per_second": 0.941, | |
| "eval_steps_per_second": 0.941, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 0.11907012015581131, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1471, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.515494167804718, | |
| "eval_runtime": 3.1856, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.5170071721076965, | |
| "eval_runtime": 3.1844, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.5145060420036316, | |
| "eval_runtime": 3.184, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.516603946685791, | |
| "eval_runtime": 3.1837, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.502795398235321, | |
| "eval_runtime": 3.1838, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.4955196678638458, | |
| "eval_runtime": 3.184, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.48850372433662415, | |
| "eval_runtime": 3.1843, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.48561426997184753, | |
| "eval_runtime": 3.1846, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.22852468490600586, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0094, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.4888945519924164, | |
| "eval_runtime": 3.1847, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.4937152862548828, | |
| "eval_runtime": 3.184, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.4911680519580841, | |
| "eval_runtime": 3.1847, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.49732208251953125, | |
| "eval_runtime": 3.1841, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.49598249793052673, | |
| "eval_runtime": 3.184, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.4968792200088501, | |
| "eval_runtime": 3.1843, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.4926395118236542, | |
| "eval_runtime": 3.1842, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.48403361439704895, | |
| "eval_runtime": 3.1838, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "grad_norm": 0.024618251249194145, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0014, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.4797053337097168, | |
| "eval_runtime": 3.1844, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.47820767760276794, | |
| "eval_runtime": 3.1841, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.4771677553653717, | |
| "eval_runtime": 3.1849, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.47882938385009766, | |
| "eval_runtime": 3.1847, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.47859469056129456, | |
| "eval_runtime": 3.1839, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.48086562752723694, | |
| "eval_runtime": 3.1846, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.48191726207733154, | |
| "eval_runtime": 3.1843, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.4832973778247833, | |
| "eval_runtime": 3.184, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 49 | |
| } | |
| ], | |
| "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": 1.2045332854603776e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |