| { | |
| "best_metric": 1.1961991786956787, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.07989134776703682, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015978269553407366, | |
| "eval_loss": 1.6500585079193115, | |
| "eval_runtime": 49.2063, | |
| "eval_samples_per_second": 53.55, | |
| "eval_steps_per_second": 13.393, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015978269553407365, | |
| "grad_norm": 0.31304410099983215, | |
| "learning_rate": 4.24e-05, | |
| "loss": 1.6422, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003195653910681473, | |
| "grad_norm": 0.5056787729263306, | |
| "learning_rate": 8.48e-05, | |
| "loss": 1.6523, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00479348086602221, | |
| "grad_norm": 0.5264449715614319, | |
| "learning_rate": 0.0001272, | |
| "loss": 1.4867, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006391307821362946, | |
| "grad_norm": 0.7551277875900269, | |
| "learning_rate": 0.0001696, | |
| "loss": 1.4439, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007989134776703682, | |
| "grad_norm": 1.3374431133270264, | |
| "learning_rate": 0.000212, | |
| "loss": 1.2566, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007989134776703682, | |
| "eval_loss": 1.3853693008422852, | |
| "eval_runtime": 49.2099, | |
| "eval_samples_per_second": 53.546, | |
| "eval_steps_per_second": 13.392, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00958696173204442, | |
| "grad_norm": 0.36312878131866455, | |
| "learning_rate": 0.00021174178932754136, | |
| "loss": 1.538, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.011184788687385157, | |
| "grad_norm": 0.49091804027557373, | |
| "learning_rate": 0.00021096841528660647, | |
| "loss": 1.4567, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.012782615642725892, | |
| "grad_norm": 0.5926417112350464, | |
| "learning_rate": 0.0002096836456777834, | |
| "loss": 1.2948, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01438044259806663, | |
| "grad_norm": 0.6516161561012268, | |
| "learning_rate": 0.00020789373976946182, | |
| "loss": 1.1847, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.015978269553407365, | |
| "grad_norm": 1.2274402379989624, | |
| "learning_rate": 0.0002056074178033063, | |
| "loss": 1.0668, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.015978269553407365, | |
| "eval_loss": 1.308932900428772, | |
| "eval_runtime": 49.1943, | |
| "eval_samples_per_second": 53.563, | |
| "eval_steps_per_second": 13.396, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.017576096508748102, | |
| "grad_norm": 0.3842248022556305, | |
| "learning_rate": 0.00020283581851011567, | |
| "loss": 1.5373, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01917392346408884, | |
| "grad_norm": 0.4492928981781006, | |
| "learning_rate": 0.00019959244484304625, | |
| "loss": 1.4419, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.020771750419429576, | |
| "grad_norm": 0.5767350196838379, | |
| "learning_rate": 0.00019589309819258114, | |
| "loss": 1.3442, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.022369577374770314, | |
| "grad_norm": 0.6538853049278259, | |
| "learning_rate": 0.00019175580140374444, | |
| "loss": 1.0945, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.023967404330111047, | |
| "grad_norm": 1.4180448055267334, | |
| "learning_rate": 0.00018720071097061167, | |
| "loss": 1.0496, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.023967404330111047, | |
| "eval_loss": 1.282002568244934, | |
| "eval_runtime": 49.137, | |
| "eval_samples_per_second": 53.626, | |
| "eval_steps_per_second": 13.411, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.025565231285451784, | |
| "grad_norm": 0.38757893443107605, | |
| "learning_rate": 0.00018225001883589702, | |
| "loss": 1.4831, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.02716305824079252, | |
| "grad_norm": 0.4853920340538025, | |
| "learning_rate": 0.00017692784427403898, | |
| "loss": 1.4429, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.02876088519613326, | |
| "grad_norm": 0.5605722069740295, | |
| "learning_rate": 0.00017126011638451976, | |
| "loss": 1.2459, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.030358712151473996, | |
| "grad_norm": 0.6170331239700317, | |
| "learning_rate": 0.00016527444776789915, | |
| "loss": 1.009, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03195653910681473, | |
| "grad_norm": 1.6762750148773193, | |
| "learning_rate": 0.00015900000000000002, | |
| "loss": 1.0656, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03195653910681473, | |
| "eval_loss": 1.2561191320419312, | |
| "eval_runtime": 49.3809, | |
| "eval_samples_per_second": 53.361, | |
| "eval_steps_per_second": 13.345, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03355436606215547, | |
| "grad_norm": 0.37146052718162537, | |
| "learning_rate": 0.0001524673415596422, | |
| "loss": 1.4539, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.035152193017496204, | |
| "grad_norm": 0.47493624687194824, | |
| "learning_rate": 0.00014570829890208668, | |
| "loss": 1.3451, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.036750019972836945, | |
| "grad_norm": 0.5821739435195923, | |
| "learning_rate": 0.00013875580140374443, | |
| "loss": 1.3524, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.03834784692817768, | |
| "grad_norm": 0.6922153234481812, | |
| "learning_rate": 0.00013164372093356477, | |
| "loss": 1.1759, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.03994567388351841, | |
| "grad_norm": 1.3326733112335205, | |
| "learning_rate": 0.00012440670683269464, | |
| "loss": 1.0188, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.03994567388351841, | |
| "eval_loss": 1.2323858737945557, | |
| "eval_runtime": 49.4073, | |
| "eval_samples_per_second": 53.332, | |
| "eval_steps_per_second": 13.338, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04154350083885915, | |
| "grad_norm": 0.3916065990924835, | |
| "learning_rate": 0.00011708001710637128, | |
| "loss": 1.4353, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.04314132779419989, | |
| "grad_norm": 0.47572290897369385, | |
| "learning_rate": 0.00010969934665046512, | |
| "loss": 1.3617, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.04473915474954063, | |
| "grad_norm": 0.5964052081108093, | |
| "learning_rate": 0.00010230065334953492, | |
| "loss": 1.2104, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.04633698170488136, | |
| "grad_norm": 0.7098691463470459, | |
| "learning_rate": 9.491998289362875e-05, | |
| "loss": 1.0909, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.047934808660222095, | |
| "grad_norm": 1.1634002923965454, | |
| "learning_rate": 8.759329316730539e-05, | |
| "loss": 0.9742, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.047934808660222095, | |
| "eval_loss": 1.2163466215133667, | |
| "eval_runtime": 49.1098, | |
| "eval_samples_per_second": 53.655, | |
| "eval_steps_per_second": 13.419, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.049532635615562835, | |
| "grad_norm": 0.38519808650016785, | |
| "learning_rate": 8.035627906643523e-05, | |
| "loss": 1.4363, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.05113046257090357, | |
| "grad_norm": 0.4723591208457947, | |
| "learning_rate": 7.324419859625559e-05, | |
| "loss": 1.3084, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05272828952624431, | |
| "grad_norm": 0.6243221163749695, | |
| "learning_rate": 6.629170109791332e-05, | |
| "loss": 1.2501, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.05432611648158504, | |
| "grad_norm": 0.6776363849639893, | |
| "learning_rate": 5.9532658440357784e-05, | |
| "loss": 1.0853, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.055923943436925784, | |
| "grad_norm": 1.2277010679244995, | |
| "learning_rate": 5.300000000000002e-05, | |
| "loss": 1.0173, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.055923943436925784, | |
| "eval_loss": 1.2060250043869019, | |
| "eval_runtime": 49.0653, | |
| "eval_samples_per_second": 53.704, | |
| "eval_steps_per_second": 13.431, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.05752177039226652, | |
| "grad_norm": 0.3953673839569092, | |
| "learning_rate": 4.672555223210085e-05, | |
| "loss": 1.4167, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.05911959734760725, | |
| "grad_norm": 0.5251022577285767, | |
| "learning_rate": 4.073988361548022e-05, | |
| "loss": 1.3159, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.06071742430294799, | |
| "grad_norm": 0.597756564617157, | |
| "learning_rate": 3.507215572596106e-05, | |
| "loss": 1.2607, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.062315251258288726, | |
| "grad_norm": 0.7255125641822815, | |
| "learning_rate": 2.9749981164102997e-05, | |
| "loss": 1.177, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.06391307821362946, | |
| "grad_norm": 1.2851899862289429, | |
| "learning_rate": 2.479928902938834e-05, | |
| "loss": 1.0985, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06391307821362946, | |
| "eval_loss": 1.1991453170776367, | |
| "eval_runtime": 49.1876, | |
| "eval_samples_per_second": 53.57, | |
| "eval_steps_per_second": 13.398, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06551090516897021, | |
| "grad_norm": 0.4205108880996704, | |
| "learning_rate": 2.024419859625558e-05, | |
| "loss": 1.3338, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.06710873212431094, | |
| "grad_norm": 0.5228121280670166, | |
| "learning_rate": 1.610690180741885e-05, | |
| "loss": 1.3194, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.06870655907965167, | |
| "grad_norm": 0.5643351674079895, | |
| "learning_rate": 1.240755515695374e-05, | |
| "loss": 1.1673, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.07030438603499241, | |
| "grad_norm": 0.6846547722816467, | |
| "learning_rate": 9.164181489884296e-06, | |
| "loss": 1.1176, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.07190221299033314, | |
| "grad_norm": 1.4567266702651978, | |
| "learning_rate": 6.392582196693718e-06, | |
| "loss": 0.9772, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07190221299033314, | |
| "eval_loss": 1.1967874765396118, | |
| "eval_runtime": 49.249, | |
| "eval_samples_per_second": 53.504, | |
| "eval_steps_per_second": 13.381, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07350003994567389, | |
| "grad_norm": 0.4065600037574768, | |
| "learning_rate": 4.106260230538197e-06, | |
| "loss": 1.4111, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.07509786690101462, | |
| "grad_norm": 0.4918181002140045, | |
| "learning_rate": 2.316354322216597e-06, | |
| "loss": 1.3486, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.07669569385635536, | |
| "grad_norm": 0.6364920735359192, | |
| "learning_rate": 1.0315847133935416e-06, | |
| "loss": 1.1948, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.07829352081169609, | |
| "grad_norm": 0.657301127910614, | |
| "learning_rate": 2.582106724586351e-07, | |
| "loss": 1.042, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.07989134776703682, | |
| "grad_norm": 1.1757533550262451, | |
| "learning_rate": 0.0, | |
| "loss": 0.9801, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07989134776703682, | |
| "eval_loss": 1.1961991786956787, | |
| "eval_runtime": 49.2155, | |
| "eval_samples_per_second": 53.54, | |
| "eval_steps_per_second": 13.39, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 1.3947946861068288e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |