| { | |
| "best_metric": 0.2183598130941391, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.26622296173044924, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005324459234608985, | |
| "grad_norm": 4.088531970977783, | |
| "learning_rate": 5e-05, | |
| "loss": 5.1662, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005324459234608985, | |
| "eval_loss": 5.456347465515137, | |
| "eval_runtime": 37.1933, | |
| "eval_samples_per_second": 34.011, | |
| "eval_steps_per_second": 4.275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01064891846921797, | |
| "grad_norm": 4.171426773071289, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9325, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015973377703826955, | |
| "grad_norm": 4.523000717163086, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.6926, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02129783693843594, | |
| "grad_norm": 4.592573642730713, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.1592, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.026622296173044926, | |
| "grad_norm": 4.462768077850342, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.4883, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03194675540765391, | |
| "grad_norm": 3.6760053634643555, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.7529, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03727121464226289, | |
| "grad_norm": 3.266521692276001, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.3894, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04259567387687188, | |
| "grad_norm": 2.4213409423828125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0191, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04792013311148086, | |
| "grad_norm": 2.726236581802368, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9415, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05324459234608985, | |
| "grad_norm": 3.0345311164855957, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8787, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05856905158069883, | |
| "grad_norm": 3.6178336143493652, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0712, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06389351081530782, | |
| "grad_norm": 3.8217687606811523, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.015, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06921797004991681, | |
| "grad_norm": 3.0923008918762207, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.7464, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07454242928452579, | |
| "grad_norm": 3.973829984664917, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3454, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07986688851913477, | |
| "grad_norm": 3.0622823238372803, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2509, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08519134775374376, | |
| "grad_norm": 2.638644218444824, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1201, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09051580698835275, | |
| "grad_norm": 2.270491123199463, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0201, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09584026622296173, | |
| "grad_norm": 2.1647579669952393, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9262, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10116472545757071, | |
| "grad_norm": 1.9108171463012695, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7262, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1064891846921797, | |
| "grad_norm": 1.6335346698760986, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11181364392678869, | |
| "grad_norm": 1.5329469442367554, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6769, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11713810316139767, | |
| "grad_norm": 1.835329532623291, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5839, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12246256239600666, | |
| "grad_norm": 1.8949499130249023, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5463, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12778702163061564, | |
| "grad_norm": 2.221313238143921, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6961, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13311148086522462, | |
| "grad_norm": 3.7558910846710205, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.018, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13311148086522462, | |
| "eval_loss": 0.543145477771759, | |
| "eval_runtime": 37.5153, | |
| "eval_samples_per_second": 33.72, | |
| "eval_steps_per_second": 4.238, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13843594009983362, | |
| "grad_norm": 4.257485866546631, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5404, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1437603993344426, | |
| "grad_norm": 4.45656156539917, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.57, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14908485856905157, | |
| "grad_norm": 3.2174301147460938, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4359, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.15440931780366057, | |
| "grad_norm": 1.8433396816253662, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3289, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.15973377703826955, | |
| "grad_norm": 1.776909589767456, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3473, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16505823627287852, | |
| "grad_norm": 2.0475502014160156, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.338, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.17038269550748752, | |
| "grad_norm": 3.002129316329956, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3206, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1757071547420965, | |
| "grad_norm": 2.487653970718384, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2816, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1810316139767055, | |
| "grad_norm": 2.3512144088745117, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3687, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18635607321131448, | |
| "grad_norm": 1.3423824310302734, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2889, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19168053244592345, | |
| "grad_norm": 2.7216291427612305, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3866, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.19700499168053245, | |
| "grad_norm": 1.77122962474823, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3026, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.20232945091514143, | |
| "grad_norm": 2.95351505279541, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3089, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2076539101497504, | |
| "grad_norm": 1.4593188762664795, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2316, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2129783693843594, | |
| "grad_norm": 1.3390860557556152, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1849, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21830282861896838, | |
| "grad_norm": 1.160514235496521, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1797, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.22362728785357738, | |
| "grad_norm": 1.867867112159729, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2385, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.22895174708818636, | |
| "grad_norm": 1.830309510231018, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1784, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.23427620632279533, | |
| "grad_norm": 1.401082992553711, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1683, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.23960066555740434, | |
| "grad_norm": 1.363930106163025, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1922, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2449251247920133, | |
| "grad_norm": 1.3577070236206055, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1874, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2502495840266223, | |
| "grad_norm": 1.2456406354904175, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.2281, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2555740432612313, | |
| "grad_norm": 1.244443655014038, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2101, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2608985024958403, | |
| "grad_norm": 1.5903034210205078, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2462, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.26622296173044924, | |
| "grad_norm": 3.396489143371582, | |
| "learning_rate": 0.0, | |
| "loss": 0.5009, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.26622296173044924, | |
| "eval_loss": 0.2183598130941391, | |
| "eval_runtime": 37.1668, | |
| "eval_samples_per_second": 34.036, | |
| "eval_steps_per_second": 4.278, | |
| "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": 5.32019209568256e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |