| { | |
| "best_metric": 1.1700222492218018, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6872852233676976, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013745704467353952, | |
| "grad_norm": 8.521697044372559, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013745704467353952, | |
| "eval_loss": 1.69869065284729, | |
| "eval_runtime": 23.7639, | |
| "eval_samples_per_second": 20.62, | |
| "eval_steps_per_second": 2.609, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027491408934707903, | |
| "grad_norm": 8.721661567687988, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5639, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 9.311981201171875, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.6337, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.054982817869415807, | |
| "grad_norm": 7.9015936851501465, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.4346, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06872852233676977, | |
| "grad_norm": 7.836700439453125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.4628, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 5.524428844451904, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3585, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09621993127147767, | |
| "grad_norm": 5.041913032531738, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3979, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10996563573883161, | |
| "grad_norm": 5.0521440505981445, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4176, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 5.009284019470215, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.3873, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13745704467353953, | |
| "grad_norm": 5.2991719245910645, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3692, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15120274914089346, | |
| "grad_norm": 6.43788480758667, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.421, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 6.886988639831543, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3988, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17869415807560138, | |
| "grad_norm": 8.61909294128418, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5297, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19243986254295534, | |
| "grad_norm": 9.367788314819336, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3699, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20618556701030927, | |
| "grad_norm": 6.352292060852051, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.1778, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21993127147766323, | |
| "grad_norm": 4.758786201477051, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.161, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23367697594501718, | |
| "grad_norm": 4.461093425750732, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1936, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 4.39322566986084, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1752, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2611683848797251, | |
| "grad_norm": 3.388389825820923, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1414, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.27491408934707906, | |
| "grad_norm": 3.6625843048095703, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2274, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28865979381443296, | |
| "grad_norm": 3.5239598751068115, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2471, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3024054982817869, | |
| "grad_norm": 4.69722318649292, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2665, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3161512027491409, | |
| "grad_norm": 3.7608370780944824, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2757, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": 5.575406551361084, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3511, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3436426116838488, | |
| "grad_norm": 8.046637535095215, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3011, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3436426116838488, | |
| "eval_loss": 1.222367763519287, | |
| "eval_runtime": 23.7465, | |
| "eval_samples_per_second": 20.635, | |
| "eval_steps_per_second": 2.611, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35738831615120276, | |
| "grad_norm": 8.447471618652344, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3699, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3711340206185567, | |
| "grad_norm": 6.330043315887451, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.2511, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3848797250859107, | |
| "grad_norm": 4.982043266296387, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1805, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.39862542955326463, | |
| "grad_norm": 5.331606864929199, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.1521, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 3.5054099559783936, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1404, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4261168384879725, | |
| "grad_norm": 4.3697614669799805, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1858, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43986254295532645, | |
| "grad_norm": 3.5054900646209717, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1712, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4536082474226804, | |
| "grad_norm": 2.989226818084717, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0911, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.46735395189003437, | |
| "grad_norm": 3.1136281490325928, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1126, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.48109965635738833, | |
| "grad_norm": 3.8040785789489746, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.2245, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4948453608247423, | |
| "grad_norm": 4.323892116546631, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.111, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5085910652920962, | |
| "grad_norm": 4.997296333312988, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1923, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5223367697594502, | |
| "grad_norm": 5.276499271392822, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4023, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5360824742268041, | |
| "grad_norm": 3.8192012310028076, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2573, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5498281786941581, | |
| "grad_norm": 3.393066883087158, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.2258, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.563573883161512, | |
| "grad_norm": 2.6232097148895264, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.0416, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5773195876288659, | |
| "grad_norm": 2.9142274856567383, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9755, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5910652920962199, | |
| "grad_norm": 3.119406223297119, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.1864, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6048109965635738, | |
| "grad_norm": 2.5969648361206055, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.132, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6185567010309279, | |
| "grad_norm": 2.6044764518737793, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1857, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6323024054982818, | |
| "grad_norm": 2.9976484775543213, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1866, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6460481099656358, | |
| "grad_norm": 3.2721643447875977, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.1646, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6597938144329897, | |
| "grad_norm": 4.761203289031982, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.2401, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6735395189003437, | |
| "grad_norm": 4.534084796905518, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.129, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6872852233676976, | |
| "grad_norm": 8.279170036315918, | |
| "learning_rate": 0.0, | |
| "loss": 1.2175, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6872852233676976, | |
| "eval_loss": 1.1700222492218018, | |
| "eval_runtime": 23.7368, | |
| "eval_samples_per_second": 20.643, | |
| "eval_steps_per_second": 2.612, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.975488880578396e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |