| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 390, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002564102564102564, | |
| "grad_norm": 32.246810828841255, | |
| "learning_rate": 7.692307692307692e-06, | |
| "loss": 2.2691, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01282051282051282, | |
| "grad_norm": 29.537508150180734, | |
| "learning_rate": 3.8461538461538456e-05, | |
| "loss": 2.5015, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "grad_norm": 7.166984360831344, | |
| "learning_rate": 7.692307692307691e-05, | |
| "loss": 1.3116, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 7.358331315050627, | |
| "learning_rate": 0.00011538461538461538, | |
| "loss": 1.2847, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 8.061303504403417, | |
| "learning_rate": 0.00015384615384615382, | |
| "loss": 1.424, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0641025641025641, | |
| "grad_norm": 30.923296803868965, | |
| "learning_rate": 0.0001923076923076923, | |
| "loss": 1.6455, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 35.007464110767536, | |
| "learning_rate": 0.00023076923076923076, | |
| "loss": 1.8041, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08974358974358974, | |
| "grad_norm": 10.894826428758686, | |
| "learning_rate": 0.0002692307692307692, | |
| "loss": 1.6061, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 32.31558367670942, | |
| "learning_rate": 0.0002999939918069778, | |
| "loss": 1.7147, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11538461538461539, | |
| "grad_norm": 408.39746177245365, | |
| "learning_rate": 0.0002997837555846212, | |
| "loss": 3.0391, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1282051282051282, | |
| "grad_norm": 585.894165849368, | |
| "learning_rate": 0.00029927359084964874, | |
| "loss": 7.5436, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14102564102564102, | |
| "grad_norm": 188.43190635567956, | |
| "learning_rate": 0.00029846451916110426, | |
| "loss": 6.3459, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 18.84113658139999, | |
| "learning_rate": 0.00029735816061234965, | |
| "loss": 4.155, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 83.76190854828539, | |
| "learning_rate": 0.00029595673058697357, | |
| "loss": 2.5163, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1794871794871795, | |
| "grad_norm": 8.013185246066367, | |
| "learning_rate": 0.00029426303532268435, | |
| "loss": 1.8248, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 7.809904167784529, | |
| "learning_rate": 0.00029228046629207175, | |
| "loss": 1.6297, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 6.240741545472446, | |
| "learning_rate": 0.00029001299341148754, | |
| "loss": 1.4935, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21794871794871795, | |
| "grad_norm": 56.36582267694748, | |
| "learning_rate": 0.0002874651570916444, | |
| "loss": 1.5049, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 244.98938960556112, | |
| "learning_rate": 0.0002846420591458521, | |
| "loss": 2.0434, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.24358974358974358, | |
| "grad_norm": 15.923002750416765, | |
| "learning_rate": 0.00028154935257409397, | |
| "loss": 1.9592, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 6.887371068354224, | |
| "learning_rate": 0.000278193230243403, | |
| "loss": 1.52, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2692307692307692, | |
| "grad_norm": 2.1953075310025407, | |
| "learning_rate": 0.00027458041248720175, | |
| "loss": 1.4671, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.28205128205128205, | |
| "grad_norm": 5.381841976743356, | |
| "learning_rate": 0.0002707181336484383, | |
| "loss": 1.7707, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2948717948717949, | |
| "grad_norm": 18.048940491315566, | |
| "learning_rate": 0.00026661412759346485, | |
| "loss": 1.4121, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 3.1798969853488384, | |
| "learning_rate": 0.00026227661222566516, | |
| "loss": 1.4291, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.32051282051282054, | |
| "grad_norm": 43.65623626841003, | |
| "learning_rate": 0.00025771427302984107, | |
| "loss": 1.3341, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 26.333557314371472, | |
| "learning_rate": 0.00025293624568031, | |
| "loss": 1.7161, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34615384615384615, | |
| "grad_norm": 2.1036876520568257, | |
| "learning_rate": 0.0002479520977475377, | |
| "loss": 1.4303, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.358974358974359, | |
| "grad_norm": 2.8179883662231773, | |
| "learning_rate": 0.0002427718095399382, | |
| "loss": 1.2882, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3717948717948718, | |
| "grad_norm": 2.0944018050914863, | |
| "learning_rate": 0.00023740575411920265, | |
| "loss": 1.3758, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 32.12093678906791, | |
| "learning_rate": 0.00023186467652917567, | |
| "loss": 1.3851, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3974358974358974, | |
| "grad_norm": 6.163138554388992, | |
| "learning_rate": 0.00022615967227987015, | |
| "loss": 1.3702, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 2.523613373490038, | |
| "learning_rate": 0.00022030216512970553, | |
| "loss": 1.278, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4230769230769231, | |
| "grad_norm": 4.836492744474631, | |
| "learning_rate": 0.0002143038842104581, | |
| "loss": 1.6826, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4358974358974359, | |
| "grad_norm": 35.30106381963297, | |
| "learning_rate": 0.00020817684054072824, | |
| "loss": 1.6584, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.44871794871794873, | |
| "grad_norm": 5.821901622579396, | |
| "learning_rate": 0.0002019333029749549, | |
| "loss": 1.4078, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 1.8515370008819587, | |
| "learning_rate": 0.00019558577363613702, | |
| "loss": 1.1904, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.47435897435897434, | |
| "grad_norm": 1.773287149962229, | |
| "learning_rate": 0.00018914696288145557, | |
| "loss": 1.1222, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.48717948717948717, | |
| "grad_norm": 9.981307604755651, | |
| "learning_rate": 0.0001826297638509251, | |
| "loss": 1.1487, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 3.292661747708301, | |
| "learning_rate": 0.00017604722665003956, | |
| "loss": 1.2224, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 1.5110397540810954, | |
| "learning_rate": 0.00016941253221810829, | |
| "loss": 1.164, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5256410256410257, | |
| "grad_norm": 1.809157946038207, | |
| "learning_rate": 0.0001627389659346097, | |
| "loss": 1.1763, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 1.3191427643036746, | |
| "learning_rate": 0.00015603989101641228, | |
| "loss": 1.2132, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5512820512820513, | |
| "grad_norm": 1.0948738027576763, | |
| "learning_rate": 0.00014932872175913348, | |
| "loss": 1.1136, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5641025641025641, | |
| "grad_norm": 39.38545507943537, | |
| "learning_rate": 0.00014261889667621826, | |
| "loss": 1.1053, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 6.565265116408364, | |
| "learning_rate": 0.0001359238515895231, | |
| "loss": 1.5669, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5897435897435898, | |
| "grad_norm": 4.60069460000724, | |
| "learning_rate": 0.00012925699272529006, | |
| "loss": 1.3127, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6025641025641025, | |
| "grad_norm": 2.5322952556318543, | |
| "learning_rate": 0.0001226316698693831, | |
| "loss": 1.189, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.4722453502945256, | |
| "learning_rate": 0.0001160611496355417, | |
| "loss": 1.1154, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6282051282051282, | |
| "grad_norm": 0.9179752397575098, | |
| "learning_rate": 0.00010955858890017846, | |
| "loss": 1.0788, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.6410256410256411, | |
| "grad_norm": 1.6490754560884426, | |
| "learning_rate": 0.00010313700845691636, | |
| "loss": 1.5551, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6538461538461539, | |
| "grad_norm": 0.9038214719254013, | |
| "learning_rate": 9.680926694361964e-05, | |
| "loss": 1.0483, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.7506946296792257, | |
| "learning_rate": 9.058803509412646e-05, | |
| "loss": 1.0173, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6794871794871795, | |
| "grad_norm": 1.105603168554401, | |
| "learning_rate": 8.448577036624309e-05, | |
| "loss": 1.0209, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 0.7904976226318772, | |
| "learning_rate": 7.851469199680381e-05, | |
| "loss": 1.0113, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7051282051282052, | |
| "grad_norm": 0.8256317535886027, | |
| "learning_rate": 7.268675653374722e-05, | |
| "loss": 1.0168, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 0.9927491874944325, | |
| "learning_rate": 6.701363389420296e-05, | |
| "loss": 0.999, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7307692307692307, | |
| "grad_norm": 0.73183193491982, | |
| "learning_rate": 6.15066839965316e-05, | |
| "loss": 0.9793, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7435897435897436, | |
| "grad_norm": 1.1245402624787457, | |
| "learning_rate": 5.6176934013108364e-05, | |
| "loss": 0.9756, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7564102564102564, | |
| "grad_norm": 0.6697033469064312, | |
| "learning_rate": 5.103505628940178e-05, | |
| "loss": 0.9658, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.7446212713719105, | |
| "learning_rate": 4.609134697356009e-05, | |
| "loss": 0.9734, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.782051282051282, | |
| "grad_norm": 1.0552000330334352, | |
| "learning_rate": 4.135570539930026e-05, | |
| "loss": 0.9496, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.7948717948717948, | |
| "grad_norm": 0.6168006421187829, | |
| "learning_rate": 3.683761426338148e-05, | |
| "loss": 0.9358, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8076923076923077, | |
| "grad_norm": 0.7790438783752558, | |
| "learning_rate": 3.254612063735667e-05, | |
| "loss": 1.0592, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.5966928897383734, | |
| "learning_rate": 2.8489817851625024e-05, | |
| "loss": 0.9039, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 11.644090734466477, | |
| "learning_rate": 2.4676828288059558e-05, | |
| "loss": 0.9481, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 0.676095723656071, | |
| "learning_rate": 2.1114787115667476e-05, | |
| "loss": 0.9089, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8589743589743589, | |
| "grad_norm": 0.7215500519599484, | |
| "learning_rate": 1.7810827001850187e-05, | |
| "loss": 0.9021, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.8717948717948718, | |
| "grad_norm": 0.5589129407190109, | |
| "learning_rate": 1.4771563829877597e-05, | |
| "loss": 0.895, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8846153846153846, | |
| "grad_norm": 0.9293606746960693, | |
| "learning_rate": 1.2003083451176366e-05, | |
| "loss": 0.9188, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.8974358974358975, | |
| "grad_norm": 0.5692953910303316, | |
| "learning_rate": 9.510929498959269e-06, | |
| "loss": 0.8814, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9102564102564102, | |
| "grad_norm": 0.6238210726565123, | |
| "learning_rate": 7.300092287597742e-06, | |
| "loss": 0.8627, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.5072463698927163, | |
| "learning_rate": 5.374998819965653e-06, | |
| "loss": 0.8626, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9358974358974359, | |
| "grad_norm": 0.6124784439233985, | |
| "learning_rate": 3.7395039227639644e-06, | |
| "loss": 0.8568, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.9487179487179487, | |
| "grad_norm": 26.426978867070098, | |
| "learning_rate": 2.3968825275764768e-06, | |
| "loss": 0.8757, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 0.8103195703064432, | |
| "learning_rate": 1.3498231131137293e-06, | |
| "loss": 0.8811, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9743589743589743, | |
| "grad_norm": 0.557003321536524, | |
| "learning_rate": 6.004223217757509e-07, | |
| "loss": 0.8598, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9871794871794872, | |
| "grad_norm": 0.7470834443971104, | |
| "learning_rate": 1.50180761314167e-07, | |
| "loss": 0.8623, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.6929955320341405, | |
| "learning_rate": 0.0, | |
| "loss": 0.9063, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.8606326580047607, | |
| "eval_runtime": 2.3303, | |
| "eval_samples_per_second": 4.291, | |
| "eval_steps_per_second": 0.429, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 390, | |
| "total_flos": 20388343971840.0, | |
| "train_loss": 1.4792061909651144, | |
| "train_runtime": 8464.1713, | |
| "train_samples_per_second": 1.474, | |
| "train_steps_per_second": 0.046 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 390, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 20388343971840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |