| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.996011396011396, | |
| "eval_steps": 500, | |
| "global_step": 1314, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022792022792022793, | |
| "grad_norm": 0.9521530794194918, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7525, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 0.8119070369194197, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6983, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.9237407530590981, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6785, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 0.8601856015748389, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6787, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 0.7983226648054917, | |
| "learning_rate": 5e-06, | |
| "loss": 0.675, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.6758185377277637, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6548, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 0.4366694519762758, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6518, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 0.36775550977907645, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6548, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.31224824649315924, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6397, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.3002426516351667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 0.34248772148252515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6323, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.3098110517983108, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6406, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.293314757304733, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6415, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 0.314029642796298, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6437, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.3094668637781234, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6362, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 0.31125251870555687, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6414, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 0.35709475039116056, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6332, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.29851001381223125, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6387, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 0.30375221114753276, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6313, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 0.30627109368093075, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6394, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.30766255727916075, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6357, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 0.299639529426904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6394, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 0.3232168108721141, | |
| "learning_rate": 5e-06, | |
| "loss": 0.635, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.29719782420090823, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6309, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 0.3363635940484843, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6358, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.30033818505884713, | |
| "learning_rate": 5e-06, | |
| "loss": 0.634, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.3086405163965774, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6311, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 0.31634207049636615, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6419, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 0.32477215195255127, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6306, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.2907621533490378, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6287, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 0.2954431686558555, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6285, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 0.34977849889475865, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6291, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.30245663078813484, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6258, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 0.32831472647071575, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6316, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 0.3359109219191043, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6387, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.3174626547369431, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6304, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 0.3339423213265321, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6242, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 0.3114302989656154, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6364, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.32415779787778887, | |
| "learning_rate": 5e-06, | |
| "loss": 0.635, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 0.2973232951749668, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6383, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 0.28810939203798974, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6345, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.30207139748619766, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6214, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 0.344169064077701, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6344, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9982905982905983, | |
| "eval_loss": 0.6250722408294678, | |
| "eval_runtime": 443.6075, | |
| "eval_samples_per_second": 26.652, | |
| "eval_steps_per_second": 0.417, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.0034188034188034, | |
| "grad_norm": 0.34946783241847496, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6471, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0262108262108263, | |
| "grad_norm": 0.33013183855519074, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6015, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.049002849002849, | |
| "grad_norm": 0.3103323488559685, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5953, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0717948717948718, | |
| "grad_norm": 0.2945185028376385, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5962, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0945868945868946, | |
| "grad_norm": 0.30641030588405793, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6037, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1173789173789175, | |
| "grad_norm": 0.3267513905977942, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6088, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1401709401709401, | |
| "grad_norm": 0.2935853998446255, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5987, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.162962962962963, | |
| "grad_norm": 0.308464385188772, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5965, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1857549857549858, | |
| "grad_norm": 0.2942132384664065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6021, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2085470085470085, | |
| "grad_norm": 0.3189132017640467, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5952, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2313390313390313, | |
| "grad_norm": 0.2869820262933413, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6054, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2541310541310542, | |
| "grad_norm": 0.3377621778697896, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6021, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2769230769230768, | |
| "grad_norm": 0.2900303332605777, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6036, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2997150997150997, | |
| "grad_norm": 0.30558608540790816, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5976, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3225071225071225, | |
| "grad_norm": 0.2712228991960296, | |
| "learning_rate": 5e-06, | |
| "loss": 0.596, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3452991452991454, | |
| "grad_norm": 0.2985595241937158, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5957, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.368091168091168, | |
| "grad_norm": 0.3460965964967124, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6014, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.390883190883191, | |
| "grad_norm": 0.32067515052052514, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6014, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4136752136752135, | |
| "grad_norm": 0.2886905541324442, | |
| "learning_rate": 5e-06, | |
| "loss": 0.604, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4364672364672364, | |
| "grad_norm": 0.3179972422462899, | |
| "learning_rate": 5e-06, | |
| "loss": 0.602, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4592592592592593, | |
| "grad_norm": 0.3068361438671745, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5969, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4820512820512821, | |
| "grad_norm": 0.2975104191701944, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.504843304843305, | |
| "grad_norm": 0.29302882687174864, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5945, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5276353276353276, | |
| "grad_norm": 0.31187173825236275, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6022, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5504273504273505, | |
| "grad_norm": 0.27548537103558357, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5907, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.573219373219373, | |
| "grad_norm": 0.3238399728974176, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5946, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.596011396011396, | |
| "grad_norm": 0.2888508725955297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6101, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6188034188034188, | |
| "grad_norm": 0.3089362119390452, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5972, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6415954415954417, | |
| "grad_norm": 0.2976327034981006, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6018, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6643874643874645, | |
| "grad_norm": 0.3323839659646312, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5949, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6871794871794872, | |
| "grad_norm": 0.31952825027441906, | |
| "learning_rate": 5e-06, | |
| "loss": 0.596, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7099715099715098, | |
| "grad_norm": 0.3011074921517119, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5934, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7327635327635327, | |
| "grad_norm": 0.3131332658848865, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5973, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7555555555555555, | |
| "grad_norm": 0.29755628566948567, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5938, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7783475783475784, | |
| "grad_norm": 0.31211054710109515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6009, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8011396011396013, | |
| "grad_norm": 0.2978906326724178, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5984, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.823931623931624, | |
| "grad_norm": 0.3102424507970276, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5853, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8467236467236468, | |
| "grad_norm": 0.3124762599590292, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5931, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.8695156695156694, | |
| "grad_norm": 0.30419608665080544, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5908, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8923076923076922, | |
| "grad_norm": 0.3264169715665315, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5946, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.915099715099715, | |
| "grad_norm": 0.31434985279983374, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5991, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.937891737891738, | |
| "grad_norm": 0.29882892452049326, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5972, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9606837606837608, | |
| "grad_norm": 0.3117265825090941, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5985, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9834757834757835, | |
| "grad_norm": 0.34979181120418096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.596, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9994301994301993, | |
| "eval_loss": 0.6186895370483398, | |
| "eval_runtime": 439.9993, | |
| "eval_samples_per_second": 26.87, | |
| "eval_steps_per_second": 0.42, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 2.006837606837607, | |
| "grad_norm": 0.33256368794528257, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6154, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0296296296296297, | |
| "grad_norm": 0.3498663389327836, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5545, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0524216524216525, | |
| "grad_norm": 0.3102992094317097, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5696, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0752136752136754, | |
| "grad_norm": 0.35300604013681036, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5678, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.098005698005698, | |
| "grad_norm": 0.3348846142138304, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5709, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1207977207977207, | |
| "grad_norm": 0.28465315472915964, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1435897435897435, | |
| "grad_norm": 0.29773969488142443, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5636, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.1663817663817664, | |
| "grad_norm": 0.3093469994667971, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5645, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1891737891737892, | |
| "grad_norm": 0.30884393444112174, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5696, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.211965811965812, | |
| "grad_norm": 0.29030383294513096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.234757834757835, | |
| "grad_norm": 0.28643066068803996, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5587, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.2575498575498574, | |
| "grad_norm": 0.31960368373281944, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5677, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2803418803418802, | |
| "grad_norm": 0.3005519444530859, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5681, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.303133903133903, | |
| "grad_norm": 0.32792828711202565, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5655, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.325925925925926, | |
| "grad_norm": 0.3087886259889073, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5686, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.348717948717949, | |
| "grad_norm": 0.3506941453597085, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5699, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3715099715099717, | |
| "grad_norm": 0.29841599509762984, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5678, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.394301994301994, | |
| "grad_norm": 0.3046032681921002, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5672, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.417094017094017, | |
| "grad_norm": 0.29960960913565654, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5755, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.43988603988604, | |
| "grad_norm": 0.30291994610404843, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5784, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4626780626780627, | |
| "grad_norm": 0.3017643197290755, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5736, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.4854700854700855, | |
| "grad_norm": 0.30280589115016937, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5713, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.5082621082621084, | |
| "grad_norm": 0.30504209424147183, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5777, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5310541310541312, | |
| "grad_norm": 0.3148743093639512, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5712, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.5538461538461537, | |
| "grad_norm": 0.3089386225677572, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5693, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.5766381766381765, | |
| "grad_norm": 0.3014166626508354, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5688, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5994301994301994, | |
| "grad_norm": 0.3175814830375422, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5684, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 0.2980766406714121, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5687, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.645014245014245, | |
| "grad_norm": 0.30834863264140017, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5699, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.667806267806268, | |
| "grad_norm": 0.29417025476260483, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5726, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.690598290598291, | |
| "grad_norm": 0.2948129705572315, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5678, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.7133903133903132, | |
| "grad_norm": 0.2922766427891827, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.736182336182336, | |
| "grad_norm": 0.29183424120466955, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5721, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.758974358974359, | |
| "grad_norm": 0.28711979397677007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5755, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.781766381766382, | |
| "grad_norm": 0.28657806547277237, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5653, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.8045584045584047, | |
| "grad_norm": 0.29926178280388954, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5638, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.827350427350427, | |
| "grad_norm": 0.30457249563454525, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5786, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8501424501424504, | |
| "grad_norm": 0.3048971860551261, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5753, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.872934472934473, | |
| "grad_norm": 0.2996336837731426, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5724, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8957264957264957, | |
| "grad_norm": 0.3037595140140286, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5734, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.9185185185185185, | |
| "grad_norm": 0.28775714109325407, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5636, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9413105413105414, | |
| "grad_norm": 0.3009184105687043, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5638, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.9641025641025642, | |
| "grad_norm": 0.35538556844828145, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5649, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9868945868945866, | |
| "grad_norm": 0.3057596140873727, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5748, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "eval_loss": 0.6187015175819397, | |
| "eval_runtime": 445.9084, | |
| "eval_samples_per_second": 26.514, | |
| "eval_steps_per_second": 0.415, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "step": 1314, | |
| "total_flos": 2755219238682624.0, | |
| "train_loss": 0.603826883721025, | |
| "train_runtime": 70509.157, | |
| "train_samples_per_second": 9.557, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1314, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2755219238682624.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |