| { | |
| "best_global_step": 700, | |
| "best_metric": 0.7608548402786255, | |
| "best_model_checkpoint": "saved_model/stage1-final/Linq-AI-Research/Linq-Embed-Mistral-lora-batch12/checkpoint-640", | |
| "epoch": 7.071246819338422, | |
| "eval_steps": 10, | |
| "global_step": 700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10178117048346055, | |
| "grad_norm": 11.257155418395996, | |
| "learning_rate": 6.122448979591837e-07, | |
| "loss": 6.7388, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10178117048346055, | |
| "eval_loss": 1.6185929775238037, | |
| "eval_runtime": 198.0392, | |
| "eval_samples_per_second": 36.846, | |
| "eval_steps_per_second": 0.439, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2035623409669211, | |
| "grad_norm": 10.305496215820312, | |
| "learning_rate": 1.2925170068027212e-06, | |
| "loss": 6.7492, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2035623409669211, | |
| "eval_loss": 1.6124637126922607, | |
| "eval_runtime": 196.8106, | |
| "eval_samples_per_second": 37.076, | |
| "eval_steps_per_second": 0.442, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3053435114503817, | |
| "grad_norm": 11.446235656738281, | |
| "learning_rate": 1.9727891156462586e-06, | |
| "loss": 6.8035, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3053435114503817, | |
| "eval_loss": 1.597043752670288, | |
| "eval_runtime": 196.884, | |
| "eval_samples_per_second": 37.062, | |
| "eval_steps_per_second": 0.442, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4071246819338422, | |
| "grad_norm": 11.32729721069336, | |
| "learning_rate": 2.6530612244897964e-06, | |
| "loss": 6.6526, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4071246819338422, | |
| "eval_loss": 1.5674270391464233, | |
| "eval_runtime": 196.8025, | |
| "eval_samples_per_second": 37.078, | |
| "eval_steps_per_second": 0.442, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5089058524173028, | |
| "grad_norm": 10.67934513092041, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 6.5743, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5089058524173028, | |
| "eval_loss": 1.52186119556427, | |
| "eval_runtime": 196.7952, | |
| "eval_samples_per_second": 37.079, | |
| "eval_steps_per_second": 0.442, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6106870229007634, | |
| "grad_norm": 12.001185417175293, | |
| "learning_rate": 4.013605442176871e-06, | |
| "loss": 6.2515, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6106870229007634, | |
| "eval_loss": 1.461030125617981, | |
| "eval_runtime": 196.6269, | |
| "eval_samples_per_second": 37.111, | |
| "eval_steps_per_second": 0.442, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.712468193384224, | |
| "grad_norm": 11.75278377532959, | |
| "learning_rate": 4.693877551020409e-06, | |
| "loss": 6.0268, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.712468193384224, | |
| "eval_loss": 1.3867450952529907, | |
| "eval_runtime": 197.067, | |
| "eval_samples_per_second": 37.028, | |
| "eval_steps_per_second": 0.441, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8142493638676844, | |
| "grad_norm": 10.291008949279785, | |
| "learning_rate": 5.374149659863946e-06, | |
| "loss": 5.7487, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8142493638676844, | |
| "eval_loss": 1.301546573638916, | |
| "eval_runtime": 197.2635, | |
| "eval_samples_per_second": 36.991, | |
| "eval_steps_per_second": 0.441, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.916030534351145, | |
| "grad_norm": 10.032578468322754, | |
| "learning_rate": 6.054421768707484e-06, | |
| "loss": 5.3631, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.916030534351145, | |
| "eval_loss": 1.214442491531372, | |
| "eval_runtime": 197.1072, | |
| "eval_samples_per_second": 37.02, | |
| "eval_steps_per_second": 0.441, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0101781170483461, | |
| "grad_norm": 9.304237365722656, | |
| "learning_rate": 6.734693877551021e-06, | |
| "loss": 4.6838, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0101781170483461, | |
| "eval_loss": 1.1307705640792847, | |
| "eval_runtime": 197.1047, | |
| "eval_samples_per_second": 37.021, | |
| "eval_steps_per_second": 0.441, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1119592875318065, | |
| "grad_norm": 8.866251945495605, | |
| "learning_rate": 7.414965986394559e-06, | |
| "loss": 4.6848, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.1119592875318065, | |
| "eval_loss": 1.0552668571472168, | |
| "eval_runtime": 196.9871, | |
| "eval_samples_per_second": 37.043, | |
| "eval_steps_per_second": 0.442, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.213740458015267, | |
| "grad_norm": 8.94212532043457, | |
| "learning_rate": 8.095238095238097e-06, | |
| "loss": 4.3596, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.213740458015267, | |
| "eval_loss": 0.9919796586036682, | |
| "eval_runtime": 196.9676, | |
| "eval_samples_per_second": 37.047, | |
| "eval_steps_per_second": 0.442, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3155216284987277, | |
| "grad_norm": 10.225037574768066, | |
| "learning_rate": 8.775510204081633e-06, | |
| "loss": 4.2959, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3155216284987277, | |
| "eval_loss": 0.9410160779953003, | |
| "eval_runtime": 197.4883, | |
| "eval_samples_per_second": 36.949, | |
| "eval_steps_per_second": 0.441, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4173027989821882, | |
| "grad_norm": 11.060029983520508, | |
| "learning_rate": 9.455782312925171e-06, | |
| "loss": 4.092, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4173027989821882, | |
| "eval_loss": 0.9029314517974854, | |
| "eval_runtime": 198.3793, | |
| "eval_samples_per_second": 36.783, | |
| "eval_steps_per_second": 0.439, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.5190839694656488, | |
| "grad_norm": 10.218499183654785, | |
| "learning_rate": 1.0136054421768708e-05, | |
| "loss": 3.7091, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5190839694656488, | |
| "eval_loss": 0.8802660703659058, | |
| "eval_runtime": 197.2489, | |
| "eval_samples_per_second": 36.994, | |
| "eval_steps_per_second": 0.441, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6208651399491094, | |
| "grad_norm": 12.638457298278809, | |
| "learning_rate": 1.0816326530612246e-05, | |
| "loss": 3.7146, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6208651399491094, | |
| "eval_loss": 0.8618674278259277, | |
| "eval_runtime": 196.6558, | |
| "eval_samples_per_second": 37.105, | |
| "eval_steps_per_second": 0.442, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.72264631043257, | |
| "grad_norm": 12.305733680725098, | |
| "learning_rate": 1.1496598639455783e-05, | |
| "loss": 3.4079, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.72264631043257, | |
| "eval_loss": 0.8440106511116028, | |
| "eval_runtime": 196.8617, | |
| "eval_samples_per_second": 37.067, | |
| "eval_steps_per_second": 0.442, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.8244274809160306, | |
| "grad_norm": 11.612469673156738, | |
| "learning_rate": 1.217687074829932e-05, | |
| "loss": 3.4326, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8244274809160306, | |
| "eval_loss": 0.8307039141654968, | |
| "eval_runtime": 196.7755, | |
| "eval_samples_per_second": 37.083, | |
| "eval_steps_per_second": 0.442, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.9262086513994912, | |
| "grad_norm": 13.059374809265137, | |
| "learning_rate": 1.2857142857142859e-05, | |
| "loss": 3.2776, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.9262086513994912, | |
| "eval_loss": 0.8179739117622375, | |
| "eval_runtime": 196.7605, | |
| "eval_samples_per_second": 37.086, | |
| "eval_steps_per_second": 0.442, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.0203562340966923, | |
| "grad_norm": 14.618268013000488, | |
| "learning_rate": 1.3537414965986395e-05, | |
| "loss": 2.9644, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0203562340966923, | |
| "eval_loss": 0.8075312376022339, | |
| "eval_runtime": 197.2318, | |
| "eval_samples_per_second": 36.997, | |
| "eval_steps_per_second": 0.441, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.122137404580153, | |
| "grad_norm": 32.567684173583984, | |
| "learning_rate": 1.4217687074829934e-05, | |
| "loss": 3.0807, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.122137404580153, | |
| "eval_loss": 0.8039390444755554, | |
| "eval_runtime": 196.5822, | |
| "eval_samples_per_second": 37.119, | |
| "eval_steps_per_second": 0.443, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.223918575063613, | |
| "grad_norm": 16.366945266723633, | |
| "learning_rate": 1.4897959183673472e-05, | |
| "loss": 3.006, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.223918575063613, | |
| "eval_loss": 0.7987977862358093, | |
| "eval_runtime": 196.7919, | |
| "eval_samples_per_second": 37.08, | |
| "eval_steps_per_second": 0.442, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.325699745547074, | |
| "grad_norm": 31.185943603515625, | |
| "learning_rate": 1.557823129251701e-05, | |
| "loss": 2.9497, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.325699745547074, | |
| "eval_loss": 0.806793212890625, | |
| "eval_runtime": 196.8208, | |
| "eval_samples_per_second": 37.074, | |
| "eval_steps_per_second": 0.442, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.427480916030534, | |
| "grad_norm": 25.51577377319336, | |
| "learning_rate": 1.6258503401360547e-05, | |
| "loss": 2.8566, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.427480916030534, | |
| "eval_loss": 0.7805586457252502, | |
| "eval_runtime": 196.7028, | |
| "eval_samples_per_second": 37.097, | |
| "eval_steps_per_second": 0.442, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.5292620865139948, | |
| "grad_norm": 20.69544792175293, | |
| "learning_rate": 1.6938775510204085e-05, | |
| "loss": 2.7469, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.5292620865139948, | |
| "eval_loss": 0.7786166667938232, | |
| "eval_runtime": 196.7575, | |
| "eval_samples_per_second": 37.086, | |
| "eval_steps_per_second": 0.442, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.6310432569974553, | |
| "grad_norm": 17.197845458984375, | |
| "learning_rate": 1.761904761904762e-05, | |
| "loss": 2.7142, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.6310432569974553, | |
| "eval_loss": 0.7945557832717896, | |
| "eval_runtime": 196.7904, | |
| "eval_samples_per_second": 37.08, | |
| "eval_steps_per_second": 0.442, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.732824427480916, | |
| "grad_norm": 21.23394012451172, | |
| "learning_rate": 1.8299319727891158e-05, | |
| "loss": 2.5649, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.732824427480916, | |
| "eval_loss": 0.7873641848564148, | |
| "eval_runtime": 196.7742, | |
| "eval_samples_per_second": 37.083, | |
| "eval_steps_per_second": 0.442, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.8346055979643765, | |
| "grad_norm": 31.057764053344727, | |
| "learning_rate": 1.8979591836734696e-05, | |
| "loss": 2.6656, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.8346055979643765, | |
| "eval_loss": 0.7845763564109802, | |
| "eval_runtime": 196.8253, | |
| "eval_samples_per_second": 37.073, | |
| "eval_steps_per_second": 0.442, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.936386768447837, | |
| "grad_norm": 19.5579833984375, | |
| "learning_rate": 1.965986394557823e-05, | |
| "loss": 2.5469, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.936386768447837, | |
| "eval_loss": 0.7848748564720154, | |
| "eval_runtime": 196.6514, | |
| "eval_samples_per_second": 37.106, | |
| "eval_steps_per_second": 0.442, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.030534351145038, | |
| "grad_norm": 30.564638137817383, | |
| "learning_rate": 1.9962207105064248e-05, | |
| "loss": 2.3555, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.030534351145038, | |
| "eval_loss": 0.7884780168533325, | |
| "eval_runtime": 196.7984, | |
| "eval_samples_per_second": 37.079, | |
| "eval_steps_per_second": 0.442, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.132315521628499, | |
| "grad_norm": 29.762449264526367, | |
| "learning_rate": 1.9886621315192745e-05, | |
| "loss": 2.4069, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.132315521628499, | |
| "eval_loss": 0.7926894426345825, | |
| "eval_runtime": 196.803, | |
| "eval_samples_per_second": 37.078, | |
| "eval_steps_per_second": 0.442, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.2340966921119594, | |
| "grad_norm": 34.85499954223633, | |
| "learning_rate": 1.981103552532124e-05, | |
| "loss": 2.3434, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.2340966921119594, | |
| "eval_loss": 0.793368399143219, | |
| "eval_runtime": 197.3942, | |
| "eval_samples_per_second": 36.967, | |
| "eval_steps_per_second": 0.441, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.33587786259542, | |
| "grad_norm": 24.045879364013672, | |
| "learning_rate": 1.9735449735449738e-05, | |
| "loss": 2.4325, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.33587786259542, | |
| "eval_loss": 0.7951289415359497, | |
| "eval_runtime": 197.6627, | |
| "eval_samples_per_second": 36.916, | |
| "eval_steps_per_second": 0.44, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.4376590330788805, | |
| "grad_norm": 38.132293701171875, | |
| "learning_rate": 1.965986394557823e-05, | |
| "loss": 2.3631, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.4376590330788805, | |
| "eval_loss": 0.7922459244728088, | |
| "eval_runtime": 196.7168, | |
| "eval_samples_per_second": 37.094, | |
| "eval_steps_per_second": 0.442, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.539440203562341, | |
| "grad_norm": 24.430431365966797, | |
| "learning_rate": 1.9584278155706727e-05, | |
| "loss": 2.2495, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.539440203562341, | |
| "eval_loss": 0.7923274040222168, | |
| "eval_runtime": 197.2733, | |
| "eval_samples_per_second": 36.989, | |
| "eval_steps_per_second": 0.441, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.6412213740458013, | |
| "grad_norm": 24.66291618347168, | |
| "learning_rate": 1.9508692365835224e-05, | |
| "loss": 2.2889, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.6412213740458013, | |
| "eval_loss": 0.7891648411750793, | |
| "eval_runtime": 196.712, | |
| "eval_samples_per_second": 37.095, | |
| "eval_steps_per_second": 0.442, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.7430025445292623, | |
| "grad_norm": 22.617324829101562, | |
| "learning_rate": 1.943310657596372e-05, | |
| "loss": 2.4157, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.7430025445292623, | |
| "eval_loss": 0.8096875548362732, | |
| "eval_runtime": 196.8171, | |
| "eval_samples_per_second": 37.075, | |
| "eval_steps_per_second": 0.442, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.8447837150127224, | |
| "grad_norm": 28.949777603149414, | |
| "learning_rate": 1.9357520786092217e-05, | |
| "loss": 2.2913, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.8447837150127224, | |
| "eval_loss": 0.8099191188812256, | |
| "eval_runtime": 196.7661, | |
| "eval_samples_per_second": 37.085, | |
| "eval_steps_per_second": 0.442, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.9465648854961835, | |
| "grad_norm": 26.727798461914062, | |
| "learning_rate": 1.9281934996220713e-05, | |
| "loss": 2.2911, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.9465648854961835, | |
| "eval_loss": 0.7878262400627136, | |
| "eval_runtime": 196.9984, | |
| "eval_samples_per_second": 37.041, | |
| "eval_steps_per_second": 0.442, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.040712468193385, | |
| "grad_norm": 32.30791091918945, | |
| "learning_rate": 1.920634920634921e-05, | |
| "loss": 1.983, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.040712468193385, | |
| "eval_loss": 0.7994019985198975, | |
| "eval_runtime": 196.9221, | |
| "eval_samples_per_second": 37.055, | |
| "eval_steps_per_second": 0.442, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.142493638676845, | |
| "grad_norm": 26.538063049316406, | |
| "learning_rate": 1.9130763416477703e-05, | |
| "loss": 2.1661, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.142493638676845, | |
| "eval_loss": 0.7976495623588562, | |
| "eval_runtime": 196.7158, | |
| "eval_samples_per_second": 37.094, | |
| "eval_steps_per_second": 0.442, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.244274809160306, | |
| "grad_norm": 26.812292098999023, | |
| "learning_rate": 1.90551776266062e-05, | |
| "loss": 2.1431, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.244274809160306, | |
| "eval_loss": 0.7871195673942566, | |
| "eval_runtime": 196.7669, | |
| "eval_samples_per_second": 37.084, | |
| "eval_steps_per_second": 0.442, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.346055979643766, | |
| "grad_norm": 22.95535659790039, | |
| "learning_rate": 1.8979591836734696e-05, | |
| "loss": 2.038, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.346055979643766, | |
| "eval_loss": 0.7978230118751526, | |
| "eval_runtime": 196.8923, | |
| "eval_samples_per_second": 37.061, | |
| "eval_steps_per_second": 0.442, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.447837150127226, | |
| "grad_norm": 59.69046401977539, | |
| "learning_rate": 1.890400604686319e-05, | |
| "loss": 2.1664, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.447837150127226, | |
| "eval_loss": 0.8183807730674744, | |
| "eval_runtime": 196.9222, | |
| "eval_samples_per_second": 37.055, | |
| "eval_steps_per_second": 0.442, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.549618320610687, | |
| "grad_norm": 28.39609718322754, | |
| "learning_rate": 1.8828420256991686e-05, | |
| "loss": 2.1158, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.549618320610687, | |
| "eval_loss": 0.8054695129394531, | |
| "eval_runtime": 196.8454, | |
| "eval_samples_per_second": 37.07, | |
| "eval_steps_per_second": 0.442, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.651399491094148, | |
| "grad_norm": 50.26225280761719, | |
| "learning_rate": 1.8752834467120182e-05, | |
| "loss": 2.0967, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.651399491094148, | |
| "eval_loss": 0.8217968940734863, | |
| "eval_runtime": 196.938, | |
| "eval_samples_per_second": 37.052, | |
| "eval_steps_per_second": 0.442, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.753180661577608, | |
| "grad_norm": 24.08842658996582, | |
| "learning_rate": 1.867724867724868e-05, | |
| "loss": 2.0644, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.753180661577608, | |
| "eval_loss": 0.7928498387336731, | |
| "eval_runtime": 196.8179, | |
| "eval_samples_per_second": 37.075, | |
| "eval_steps_per_second": 0.442, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.854961832061068, | |
| "grad_norm": 28.052635192871094, | |
| "learning_rate": 1.8601662887377175e-05, | |
| "loss": 2.1414, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.854961832061068, | |
| "eval_loss": 0.7986204624176025, | |
| "eval_runtime": 196.8729, | |
| "eval_samples_per_second": 37.065, | |
| "eval_steps_per_second": 0.442, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.956743002544529, | |
| "grad_norm": 25.13821029663086, | |
| "learning_rate": 1.852607709750567e-05, | |
| "loss": 2.1238, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.956743002544529, | |
| "eval_loss": 0.7908161878585815, | |
| "eval_runtime": 196.9443, | |
| "eval_samples_per_second": 37.051, | |
| "eval_steps_per_second": 0.442, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.0508905852417305, | |
| "grad_norm": 26.19794464111328, | |
| "learning_rate": 1.8450491307634165e-05, | |
| "loss": 1.8455, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0508905852417305, | |
| "eval_loss": 0.7990483641624451, | |
| "eval_runtime": 196.7335, | |
| "eval_samples_per_second": 37.091, | |
| "eval_steps_per_second": 0.442, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.152671755725191, | |
| "grad_norm": 30.450307846069336, | |
| "learning_rate": 1.837490551776266e-05, | |
| "loss": 1.9619, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.152671755725191, | |
| "eval_loss": 0.8074842095375061, | |
| "eval_runtime": 196.8517, | |
| "eval_samples_per_second": 37.069, | |
| "eval_steps_per_second": 0.442, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.254452926208652, | |
| "grad_norm": 28.1552677154541, | |
| "learning_rate": 1.8299319727891158e-05, | |
| "loss": 2.0304, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.254452926208652, | |
| "eval_loss": 0.8042052388191223, | |
| "eval_runtime": 196.7101, | |
| "eval_samples_per_second": 37.095, | |
| "eval_steps_per_second": 0.442, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.356234096692112, | |
| "grad_norm": 27.312362670898438, | |
| "learning_rate": 1.8223733938019654e-05, | |
| "loss": 2.0463, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.356234096692112, | |
| "eval_loss": 0.7976890206336975, | |
| "eval_runtime": 196.8133, | |
| "eval_samples_per_second": 37.076, | |
| "eval_steps_per_second": 0.442, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.458015267175573, | |
| "grad_norm": 35.31123733520508, | |
| "learning_rate": 1.814814814814815e-05, | |
| "loss": 2.0223, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.458015267175573, | |
| "eval_loss": 0.8170256614685059, | |
| "eval_runtime": 196.731, | |
| "eval_samples_per_second": 37.091, | |
| "eval_steps_per_second": 0.442, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.559796437659033, | |
| "grad_norm": 20.367048263549805, | |
| "learning_rate": 1.8072562358276647e-05, | |
| "loss": 2.0671, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.559796437659033, | |
| "eval_loss": 0.808813214302063, | |
| "eval_runtime": 197.0705, | |
| "eval_samples_per_second": 37.027, | |
| "eval_steps_per_second": 0.441, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.661577608142494, | |
| "grad_norm": 20.208152770996094, | |
| "learning_rate": 1.7996976568405144e-05, | |
| "loss": 1.9262, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.661577608142494, | |
| "eval_loss": 0.7930235862731934, | |
| "eval_runtime": 196.7715, | |
| "eval_samples_per_second": 37.084, | |
| "eval_steps_per_second": 0.442, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.763358778625954, | |
| "grad_norm": 24.697179794311523, | |
| "learning_rate": 1.7921390778533637e-05, | |
| "loss": 1.9453, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.763358778625954, | |
| "eval_loss": 0.8091068863868713, | |
| "eval_runtime": 196.7083, | |
| "eval_samples_per_second": 37.096, | |
| "eval_steps_per_second": 0.442, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.865139949109414, | |
| "grad_norm": 27.147703170776367, | |
| "learning_rate": 1.7845804988662133e-05, | |
| "loss": 1.9755, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.865139949109414, | |
| "eval_loss": 0.8222293257713318, | |
| "eval_runtime": 196.831, | |
| "eval_samples_per_second": 37.072, | |
| "eval_steps_per_second": 0.442, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.966921119592875, | |
| "grad_norm": 28.390316009521484, | |
| "learning_rate": 1.7770219198790627e-05, | |
| "loss": 1.9713, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.966921119592875, | |
| "eval_loss": 0.7990607023239136, | |
| "eval_runtime": 196.9331, | |
| "eval_samples_per_second": 37.053, | |
| "eval_steps_per_second": 0.442, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.061068702290076, | |
| "grad_norm": 26.295873641967773, | |
| "learning_rate": 1.7694633408919123e-05, | |
| "loss": 1.7896, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.061068702290076, | |
| "eval_loss": 0.7957436442375183, | |
| "eval_runtime": 196.8046, | |
| "eval_samples_per_second": 37.077, | |
| "eval_steps_per_second": 0.442, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.162849872773537, | |
| "grad_norm": 36.52745819091797, | |
| "learning_rate": 1.761904761904762e-05, | |
| "loss": 1.8465, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.162849872773537, | |
| "eval_loss": 0.8197985887527466, | |
| "eval_runtime": 196.6498, | |
| "eval_samples_per_second": 37.107, | |
| "eval_steps_per_second": 0.442, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.264631043256998, | |
| "grad_norm": 25.5435848236084, | |
| "learning_rate": 1.7543461829176116e-05, | |
| "loss": 1.9211, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.264631043256998, | |
| "eval_loss": 0.8007534742355347, | |
| "eval_runtime": 196.7716, | |
| "eval_samples_per_second": 37.084, | |
| "eval_steps_per_second": 0.442, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.366412213740458, | |
| "grad_norm": 27.29486656188965, | |
| "learning_rate": 1.7467876039304613e-05, | |
| "loss": 1.9032, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.366412213740458, | |
| "eval_loss": 0.8093674778938293, | |
| "eval_runtime": 196.6826, | |
| "eval_samples_per_second": 37.1, | |
| "eval_steps_per_second": 0.442, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.468193384223919, | |
| "grad_norm": 27.174612045288086, | |
| "learning_rate": 1.739229024943311e-05, | |
| "loss": 1.9802, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.468193384223919, | |
| "eval_loss": 0.7773081660270691, | |
| "eval_runtime": 196.8476, | |
| "eval_samples_per_second": 37.069, | |
| "eval_steps_per_second": 0.442, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.569974554707379, | |
| "grad_norm": 29.12241554260254, | |
| "learning_rate": 1.7316704459561606e-05, | |
| "loss": 1.9835, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.569974554707379, | |
| "eval_loss": 0.7800359129905701, | |
| "eval_runtime": 196.7774, | |
| "eval_samples_per_second": 37.083, | |
| "eval_steps_per_second": 0.442, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.67175572519084, | |
| "grad_norm": 37.71172332763672, | |
| "learning_rate": 1.72411186696901e-05, | |
| "loss": 1.8889, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.67175572519084, | |
| "eval_loss": 0.7893442511558533, | |
| "eval_runtime": 196.7502, | |
| "eval_samples_per_second": 37.088, | |
| "eval_steps_per_second": 0.442, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.7735368956743, | |
| "grad_norm": 26.940378189086914, | |
| "learning_rate": 1.7165532879818595e-05, | |
| "loss": 1.9965, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.7735368956743, | |
| "eval_loss": 0.7777615785598755, | |
| "eval_runtime": 196.7858, | |
| "eval_samples_per_second": 37.081, | |
| "eval_steps_per_second": 0.442, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.875318066157761, | |
| "grad_norm": 21.455814361572266, | |
| "learning_rate": 1.7089947089947092e-05, | |
| "loss": 1.9188, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.875318066157761, | |
| "eval_loss": 0.7928925156593323, | |
| "eval_runtime": 196.7568, | |
| "eval_samples_per_second": 37.086, | |
| "eval_steps_per_second": 0.442, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.977099236641221, | |
| "grad_norm": 23.221811294555664, | |
| "learning_rate": 1.7014361300075588e-05, | |
| "loss": 1.8648, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.977099236641221, | |
| "eval_loss": 0.761427640914917, | |
| "eval_runtime": 196.7657, | |
| "eval_samples_per_second": 37.085, | |
| "eval_steps_per_second": 0.442, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.071246819338422, | |
| "grad_norm": 23.189342498779297, | |
| "learning_rate": 1.6938775510204085e-05, | |
| "loss": 1.6836, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.071246819338422, | |
| "eval_loss": 0.7608548402786255, | |
| "eval_runtime": 196.989, | |
| "eval_samples_per_second": 37.043, | |
| "eval_steps_per_second": 0.442, | |
| "step": 700 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2940, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4314443763487867e+18, | |
| "train_batch_size": 12, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |