| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005295319996187369, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.118127998474948e-05, | |
| "grad_norm": 0.2101120799779892, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.118127998474948e-05, | |
| "eval_loss": 10.403708457946777, | |
| "eval_runtime": 268.1681, | |
| "eval_samples_per_second": 148.258, | |
| "eval_steps_per_second": 74.129, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.236255996949896e-05, | |
| "grad_norm": 0.20717068016529083, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3948, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.354383995424843e-05, | |
| "grad_norm": 0.2090730518102646, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.409, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.472511993899791e-05, | |
| "grad_norm": 0.21802741289138794, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3764, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001059063999237474, | |
| "grad_norm": 0.21404823660850525, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3959, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00012708767990849687, | |
| "grad_norm": 0.20767731964588165, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.376, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014826895989324636, | |
| "grad_norm": 0.22036834061145782, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3979, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00016945023987799583, | |
| "grad_norm": 0.2219642698764801, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3815, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001906315198627453, | |
| "grad_norm": 0.21895252168178558, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3867, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002118127998474948, | |
| "grad_norm": 0.21666066348552704, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.399, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00023299407983224426, | |
| "grad_norm": 0.21962043642997742, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3959, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00025417535981699373, | |
| "grad_norm": 0.27812445163726807, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3602, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002753566398017432, | |
| "grad_norm": 0.22255368530750275, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3785, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0002965379197864927, | |
| "grad_norm": 0.2322796732187271, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3698, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0003177191997712422, | |
| "grad_norm": 0.267484575510025, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00033890047975599166, | |
| "grad_norm": 0.3014521300792694, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.367, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00036008175974074113, | |
| "grad_norm": 0.2773747444152832, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.386, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0003812630397254906, | |
| "grad_norm": 0.23313163220882416, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3712, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00040244431971024006, | |
| "grad_norm": 0.2613055109977722, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3915, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0004236255996949896, | |
| "grad_norm": 0.277883917093277, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3587, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00044480687967973906, | |
| "grad_norm": 0.2852385938167572, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3558, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0004659881596644885, | |
| "grad_norm": 0.3128252625465393, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3685, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.000487169439649238, | |
| "grad_norm": 0.2944328784942627, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3631, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0005083507196339875, | |
| "grad_norm": 0.2717386484146118, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3978, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005295319996187369, | |
| "grad_norm": 0.3077712655067444, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3605, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005295319996187369, | |
| "eval_loss": 10.377364158630371, | |
| "eval_runtime": 268.1587, | |
| "eval_samples_per_second": 148.263, | |
| "eval_steps_per_second": 74.131, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2673003724800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |