| { | |
| "best_metric": 1.2448393106460571, | |
| "best_model_checkpoint": "./lora_bn/checkpoint-1400", | |
| "epoch": 0.9003215434083601, | |
| "eval_steps": 200, | |
| "global_step": 1400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006430868167202572, | |
| "grad_norm": 1.3939015865325928, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.6079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012861736334405145, | |
| "grad_norm": 1.4347032308578491, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.3531, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01929260450160772, | |
| "grad_norm": 1.10429847240448, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.7805, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02572347266881029, | |
| "grad_norm": 0.6873103976249695, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.3846, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03215434083601286, | |
| "grad_norm": 0.749026894569397, | |
| "learning_rate": 0.00015, | |
| "loss": 2.2196, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03858520900321544, | |
| "grad_norm": 0.6276043057441711, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.0483, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04501607717041801, | |
| "grad_norm": 0.7210396528244019, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.8821, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05144694533762058, | |
| "grad_norm": 0.6538994312286377, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.7903, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05787781350482315, | |
| "grad_norm": 0.7155820727348328, | |
| "learning_rate": 0.00027, | |
| "loss": 1.7298, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06430868167202572, | |
| "grad_norm": 0.6406599283218384, | |
| "learning_rate": 0.0003, | |
| "loss": 1.6995, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0707395498392283, | |
| "grad_norm": 0.5722670555114746, | |
| "learning_rate": 0.00029793814432989686, | |
| "loss": 1.6895, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07717041800643087, | |
| "grad_norm": 0.624355137348175, | |
| "learning_rate": 0.0002958762886597938, | |
| "loss": 1.6073, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08360128617363344, | |
| "grad_norm": 0.5818140506744385, | |
| "learning_rate": 0.0002938144329896907, | |
| "loss": 1.6228, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09003215434083602, | |
| "grad_norm": 0.5287107229232788, | |
| "learning_rate": 0.0002917525773195876, | |
| "loss": 1.6014, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09646302250803858, | |
| "grad_norm": 0.5458894968032837, | |
| "learning_rate": 0.0002896907216494845, | |
| "loss": 1.5688, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10289389067524116, | |
| "grad_norm": 0.5477120876312256, | |
| "learning_rate": 0.0002876288659793814, | |
| "loss": 1.5029, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.10932475884244373, | |
| "grad_norm": 0.5350768566131592, | |
| "learning_rate": 0.0002855670103092783, | |
| "loss": 1.559, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1157556270096463, | |
| "grad_norm": 0.5387317538261414, | |
| "learning_rate": 0.00028350515463917525, | |
| "loss": 1.5013, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12218649517684887, | |
| "grad_norm": 0.5648557543754578, | |
| "learning_rate": 0.00028144329896907214, | |
| "loss": 1.5107, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12861736334405144, | |
| "grad_norm": 0.5028502345085144, | |
| "learning_rate": 0.0002793814432989691, | |
| "loss": 1.525, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12861736334405144, | |
| "eval_loss": 1.4951640367507935, | |
| "eval_runtime": 340.2657, | |
| "eval_samples_per_second": 5.878, | |
| "eval_steps_per_second": 0.735, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13504823151125403, | |
| "grad_norm": 0.520252525806427, | |
| "learning_rate": 0.00027731958762886597, | |
| "loss": 1.5075, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1414790996784566, | |
| "grad_norm": 0.5032276511192322, | |
| "learning_rate": 0.00027525773195876286, | |
| "loss": 1.4617, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.14790996784565916, | |
| "grad_norm": 0.47061678767204285, | |
| "learning_rate": 0.00027319587628865975, | |
| "loss": 1.4809, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.15434083601286175, | |
| "grad_norm": 0.4570547640323639, | |
| "learning_rate": 0.0002711340206185567, | |
| "loss": 1.4195, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1607717041800643, | |
| "grad_norm": 0.49685975909233093, | |
| "learning_rate": 0.0002690721649484536, | |
| "loss": 1.4835, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16720257234726688, | |
| "grad_norm": 0.5451533794403076, | |
| "learning_rate": 0.00026701030927835047, | |
| "loss": 1.4514, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.17363344051446947, | |
| "grad_norm": 0.472751647233963, | |
| "learning_rate": 0.0002649484536082474, | |
| "loss": 1.4538, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.18006430868167203, | |
| "grad_norm": 0.4936389923095703, | |
| "learning_rate": 0.0002628865979381443, | |
| "loss": 1.4562, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.1864951768488746, | |
| "grad_norm": 0.5179173350334167, | |
| "learning_rate": 0.00026082474226804124, | |
| "loss": 1.45, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.19292604501607716, | |
| "grad_norm": 0.48392704129219055, | |
| "learning_rate": 0.00025876288659793813, | |
| "loss": 1.4381, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19935691318327975, | |
| "grad_norm": 0.4685576856136322, | |
| "learning_rate": 0.000256701030927835, | |
| "loss": 1.439, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2057877813504823, | |
| "grad_norm": 0.5039055347442627, | |
| "learning_rate": 0.0002546391752577319, | |
| "loss": 1.3921, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.21221864951768488, | |
| "grad_norm": 0.49153512716293335, | |
| "learning_rate": 0.00025257731958762885, | |
| "loss": 1.4272, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.21864951768488747, | |
| "grad_norm": 0.48751088976860046, | |
| "learning_rate": 0.00025051546391752574, | |
| "loss": 1.3853, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.22508038585209003, | |
| "grad_norm": 0.4660916328430176, | |
| "learning_rate": 0.0002484536082474227, | |
| "loss": 1.3963, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2315112540192926, | |
| "grad_norm": 0.44358980655670166, | |
| "learning_rate": 0.0002463917525773196, | |
| "loss": 1.4165, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2379421221864952, | |
| "grad_norm": 0.49413594603538513, | |
| "learning_rate": 0.00024432989690721646, | |
| "loss": 1.3768, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.24437299035369775, | |
| "grad_norm": 0.44838714599609375, | |
| "learning_rate": 0.00024226804123711338, | |
| "loss": 1.3877, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.2508038585209003, | |
| "grad_norm": 0.46237707138061523, | |
| "learning_rate": 0.0002402061855670103, | |
| "loss": 1.3781, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.2572347266881029, | |
| "grad_norm": 0.49087774753570557, | |
| "learning_rate": 0.00023814432989690718, | |
| "loss": 1.4006, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2572347266881029, | |
| "eval_loss": 1.3819265365600586, | |
| "eval_runtime": 340.2482, | |
| "eval_samples_per_second": 5.878, | |
| "eval_steps_per_second": 0.735, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26366559485530544, | |
| "grad_norm": 0.47525086998939514, | |
| "learning_rate": 0.0002360824742268041, | |
| "loss": 1.3835, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.27009646302250806, | |
| "grad_norm": 0.4709095358848572, | |
| "learning_rate": 0.00023402061855670102, | |
| "loss": 1.4037, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.2765273311897106, | |
| "grad_norm": 0.4556897282600403, | |
| "learning_rate": 0.00023195876288659793, | |
| "loss": 1.4335, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.2829581993569132, | |
| "grad_norm": 0.5150389671325684, | |
| "learning_rate": 0.00022989690721649485, | |
| "loss": 1.3855, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.28938906752411575, | |
| "grad_norm": 0.4785289764404297, | |
| "learning_rate": 0.0002278350515463917, | |
| "loss": 1.3572, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.2958199356913183, | |
| "grad_norm": 0.4818146526813507, | |
| "learning_rate": 0.00022577319587628863, | |
| "loss": 1.4095, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.3022508038585209, | |
| "grad_norm": 0.44462355971336365, | |
| "learning_rate": 0.00022371134020618554, | |
| "loss": 1.3607, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.3086816720257235, | |
| "grad_norm": 0.4708723723888397, | |
| "learning_rate": 0.00022164948453608246, | |
| "loss": 1.3985, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.31511254019292606, | |
| "grad_norm": 0.46771880984306335, | |
| "learning_rate": 0.00021958762886597935, | |
| "loss": 1.364, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3215434083601286, | |
| "grad_norm": 0.4421800971031189, | |
| "learning_rate": 0.00021752577319587626, | |
| "loss": 1.3938, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3279742765273312, | |
| "grad_norm": 0.4229006767272949, | |
| "learning_rate": 0.00021546391752577318, | |
| "loss": 1.3547, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.33440514469453375, | |
| "grad_norm": 0.4854479730129242, | |
| "learning_rate": 0.0002134020618556701, | |
| "loss": 1.3448, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.3408360128617363, | |
| "grad_norm": 0.4800192713737488, | |
| "learning_rate": 0.000211340206185567, | |
| "loss": 1.3716, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.34726688102893893, | |
| "grad_norm": 0.4886428415775299, | |
| "learning_rate": 0.0002092783505154639, | |
| "loss": 1.381, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.3536977491961415, | |
| "grad_norm": 0.4030856788158417, | |
| "learning_rate": 0.0002072164948453608, | |
| "loss": 1.3242, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.36012861736334406, | |
| "grad_norm": 0.5465673208236694, | |
| "learning_rate": 0.0002051546391752577, | |
| "loss": 1.3309, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.3665594855305466, | |
| "grad_norm": 0.47386476397514343, | |
| "learning_rate": 0.00020309278350515462, | |
| "loss": 1.399, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.3729903536977492, | |
| "grad_norm": 0.4967169761657715, | |
| "learning_rate": 0.0002010309278350515, | |
| "loss": 1.3441, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.37942122186495175, | |
| "grad_norm": 0.44418269395828247, | |
| "learning_rate": 0.00019896907216494843, | |
| "loss": 1.3417, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.3858520900321543, | |
| "grad_norm": 0.447294682264328, | |
| "learning_rate": 0.00019690721649484534, | |
| "loss": 1.3011, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3858520900321543, | |
| "eval_loss": 1.331955909729004, | |
| "eval_runtime": 340.7655, | |
| "eval_samples_per_second": 5.869, | |
| "eval_steps_per_second": 0.734, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.39228295819935693, | |
| "grad_norm": 0.46866482496261597, | |
| "learning_rate": 0.00019484536082474226, | |
| "loss": 1.3152, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.3987138263665595, | |
| "grad_norm": 0.4665449857711792, | |
| "learning_rate": 0.00019278350515463918, | |
| "loss": 1.3253, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.40514469453376206, | |
| "grad_norm": 0.4765641391277313, | |
| "learning_rate": 0.00019072164948453606, | |
| "loss": 1.3493, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.4115755627009646, | |
| "grad_norm": 0.49187275767326355, | |
| "learning_rate": 0.00018865979381443298, | |
| "loss": 1.3454, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.4180064308681672, | |
| "grad_norm": 0.4786391258239746, | |
| "learning_rate": 0.0001865979381443299, | |
| "loss": 1.3464, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.42443729903536975, | |
| "grad_norm": 0.5260841846466064, | |
| "learning_rate": 0.00018453608247422679, | |
| "loss": 1.3165, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.43086816720257237, | |
| "grad_norm": 0.47295427322387695, | |
| "learning_rate": 0.00018247422680412367, | |
| "loss": 1.3064, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.43729903536977494, | |
| "grad_norm": 0.49421828985214233, | |
| "learning_rate": 0.0001804123711340206, | |
| "loss": 1.3315, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.4437299035369775, | |
| "grad_norm": 0.4635757505893707, | |
| "learning_rate": 0.0001783505154639175, | |
| "loss": 1.3549, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.45016077170418006, | |
| "grad_norm": 0.47637075185775757, | |
| "learning_rate": 0.00017628865979381442, | |
| "loss": 1.3124, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4565916398713826, | |
| "grad_norm": 0.442953884601593, | |
| "learning_rate": 0.00017422680412371134, | |
| "loss": 1.3702, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.4630225080385852, | |
| "grad_norm": 0.49394121766090393, | |
| "learning_rate": 0.00017216494845360823, | |
| "loss": 1.3104, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.4694533762057878, | |
| "grad_norm": 0.4604041576385498, | |
| "learning_rate": 0.00017010309278350514, | |
| "loss": 1.2666, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.4758842443729904, | |
| "grad_norm": 0.45597556233406067, | |
| "learning_rate": 0.00016804123711340206, | |
| "loss": 1.3049, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.48231511254019294, | |
| "grad_norm": 0.4338426887989044, | |
| "learning_rate": 0.00016597938144329898, | |
| "loss": 1.3581, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.4887459807073955, | |
| "grad_norm": 0.4623814821243286, | |
| "learning_rate": 0.00016391752577319584, | |
| "loss": 1.2777, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.49517684887459806, | |
| "grad_norm": 0.4995267689228058, | |
| "learning_rate": 0.00016185567010309275, | |
| "loss": 1.3087, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.5016077170418006, | |
| "grad_norm": 0.4469720721244812, | |
| "learning_rate": 0.00015979381443298967, | |
| "loss": 1.2893, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.5080385852090032, | |
| "grad_norm": 0.4728144407272339, | |
| "learning_rate": 0.00015773195876288659, | |
| "loss": 1.2496, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.5144694533762058, | |
| "grad_norm": 0.4181075096130371, | |
| "learning_rate": 0.0001556701030927835, | |
| "loss": 1.2912, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5144694533762058, | |
| "eval_loss": 1.2991915941238403, | |
| "eval_runtime": 340.7607, | |
| "eval_samples_per_second": 5.869, | |
| "eval_steps_per_second": 0.734, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5209003215434084, | |
| "grad_norm": 0.46053722500801086, | |
| "learning_rate": 0.0001536082474226804, | |
| "loss": 1.2695, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.5273311897106109, | |
| "grad_norm": 0.5585050582885742, | |
| "learning_rate": 0.0001515463917525773, | |
| "loss": 1.2968, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.5337620578778135, | |
| "grad_norm": 0.4734201431274414, | |
| "learning_rate": 0.00014948453608247422, | |
| "loss": 1.2478, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.5401929260450161, | |
| "grad_norm": 0.45543360710144043, | |
| "learning_rate": 0.0001474226804123711, | |
| "loss": 1.3217, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.5466237942122186, | |
| "grad_norm": 0.5416027903556824, | |
| "learning_rate": 0.00014536082474226803, | |
| "loss": 1.2522, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.5530546623794212, | |
| "grad_norm": 0.42681366205215454, | |
| "learning_rate": 0.00014329896907216494, | |
| "loss": 1.3112, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.5594855305466238, | |
| "grad_norm": 0.45384252071380615, | |
| "learning_rate": 0.00014123711340206183, | |
| "loss": 1.2793, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.5659163987138264, | |
| "grad_norm": 0.450888454914093, | |
| "learning_rate": 0.00013917525773195875, | |
| "loss": 1.3204, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.572347266881029, | |
| "grad_norm": 0.4524657428264618, | |
| "learning_rate": 0.00013711340206185566, | |
| "loss": 1.272, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.5787781350482315, | |
| "grad_norm": 0.46384352445602417, | |
| "learning_rate": 0.00013505154639175258, | |
| "loss": 1.2948, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.5852090032154341, | |
| "grad_norm": 0.4582608938217163, | |
| "learning_rate": 0.00013298969072164947, | |
| "loss": 1.3027, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.5916398713826366, | |
| "grad_norm": 0.4848160147666931, | |
| "learning_rate": 0.00013092783505154639, | |
| "loss": 1.3172, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.5980707395498392, | |
| "grad_norm": 0.484418660402298, | |
| "learning_rate": 0.00012886597938144327, | |
| "loss": 1.3117, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.6045016077170418, | |
| "grad_norm": 0.39582470059394836, | |
| "learning_rate": 0.0001268041237113402, | |
| "loss": 1.2813, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.6109324758842444, | |
| "grad_norm": 0.4482058882713318, | |
| "learning_rate": 0.0001247422680412371, | |
| "loss": 1.2639, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.617363344051447, | |
| "grad_norm": 0.49503323435783386, | |
| "learning_rate": 0.000122680412371134, | |
| "loss": 1.302, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.6237942122186495, | |
| "grad_norm": 0.42037469148635864, | |
| "learning_rate": 0.00012061855670103093, | |
| "loss": 1.2943, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.6302250803858521, | |
| "grad_norm": 0.449434757232666, | |
| "learning_rate": 0.00011855670103092781, | |
| "loss": 1.2941, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.6366559485530546, | |
| "grad_norm": 0.44711926579475403, | |
| "learning_rate": 0.00011649484536082473, | |
| "loss": 1.2906, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.6430868167202572, | |
| "grad_norm": 0.43769001960754395, | |
| "learning_rate": 0.00011443298969072163, | |
| "loss": 1.3039, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6430868167202572, | |
| "eval_loss": 1.2755881547927856, | |
| "eval_runtime": 341.9539, | |
| "eval_samples_per_second": 5.849, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6495176848874598, | |
| "grad_norm": 0.4710148870944977, | |
| "learning_rate": 0.00011237113402061855, | |
| "loss": 1.2645, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.6559485530546624, | |
| "grad_norm": 0.44989457726478577, | |
| "learning_rate": 0.00011030927835051547, | |
| "loss": 1.282, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.662379421221865, | |
| "grad_norm": 0.4453730285167694, | |
| "learning_rate": 0.00010824742268041235, | |
| "loss": 1.256, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.6688102893890675, | |
| "grad_norm": 0.5148506164550781, | |
| "learning_rate": 0.00010618556701030927, | |
| "loss": 1.2541, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.6752411575562701, | |
| "grad_norm": 0.43415772914886475, | |
| "learning_rate": 0.00010412371134020617, | |
| "loss": 1.2902, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.6816720257234726, | |
| "grad_norm": 0.4594573974609375, | |
| "learning_rate": 0.00010206185567010309, | |
| "loss": 1.2425, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.6881028938906752, | |
| "grad_norm": 0.4503769278526306, | |
| "learning_rate": 9.999999999999999e-05, | |
| "loss": 1.2896, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.6945337620578779, | |
| "grad_norm": 0.4645858407020569, | |
| "learning_rate": 9.79381443298969e-05, | |
| "loss": 1.2735, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.7009646302250804, | |
| "grad_norm": 0.48965829610824585, | |
| "learning_rate": 9.58762886597938e-05, | |
| "loss": 1.3047, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.707395498392283, | |
| "grad_norm": 0.46829336881637573, | |
| "learning_rate": 9.381443298969071e-05, | |
| "loss": 1.2751, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7138263665594855, | |
| "grad_norm": 0.4561706483364105, | |
| "learning_rate": 9.175257731958763e-05, | |
| "loss": 1.2858, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.7202572347266881, | |
| "grad_norm": 0.4418432414531708, | |
| "learning_rate": 8.969072164948453e-05, | |
| "loss": 1.2254, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.7266881028938906, | |
| "grad_norm": 0.46051761507987976, | |
| "learning_rate": 8.762886597938145e-05, | |
| "loss": 1.2198, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.7331189710610932, | |
| "grad_norm": 0.48182615637779236, | |
| "learning_rate": 8.556701030927834e-05, | |
| "loss": 1.2631, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.7395498392282959, | |
| "grad_norm": 0.42658165097236633, | |
| "learning_rate": 8.350515463917525e-05, | |
| "loss": 1.2667, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.7459807073954984, | |
| "grad_norm": 0.48048514127731323, | |
| "learning_rate": 8.144329896907215e-05, | |
| "loss": 1.27, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.752411575562701, | |
| "grad_norm": 0.4658808410167694, | |
| "learning_rate": 7.938144329896907e-05, | |
| "loss": 1.2778, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.7588424437299035, | |
| "grad_norm": 0.47830724716186523, | |
| "learning_rate": 7.731958762886596e-05, | |
| "loss": 1.2327, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.7652733118971061, | |
| "grad_norm": 0.4181123971939087, | |
| "learning_rate": 7.525773195876288e-05, | |
| "loss": 1.2559, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.7717041800643086, | |
| "grad_norm": 0.46117720007896423, | |
| "learning_rate": 7.319587628865979e-05, | |
| "loss": 1.2572, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7717041800643086, | |
| "eval_loss": 1.2570642232894897, | |
| "eval_runtime": 340.7404, | |
| "eval_samples_per_second": 5.87, | |
| "eval_steps_per_second": 0.734, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7781350482315113, | |
| "grad_norm": 0.4613102078437805, | |
| "learning_rate": 7.11340206185567e-05, | |
| "loss": 1.2659, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.7845659163987139, | |
| "grad_norm": 0.4278354346752167, | |
| "learning_rate": 6.90721649484536e-05, | |
| "loss": 1.2858, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.7909967845659164, | |
| "grad_norm": 0.4664517343044281, | |
| "learning_rate": 6.701030927835051e-05, | |
| "loss": 1.293, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.797427652733119, | |
| "grad_norm": 0.44390469789505005, | |
| "learning_rate": 6.494845360824742e-05, | |
| "loss": 1.2234, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.8038585209003215, | |
| "grad_norm": 0.4815686345100403, | |
| "learning_rate": 6.288659793814433e-05, | |
| "loss": 1.2891, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.8102893890675241, | |
| "grad_norm": 0.43138524889945984, | |
| "learning_rate": 6.0824742268041234e-05, | |
| "loss": 1.2344, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.8167202572347267, | |
| "grad_norm": 0.49563485383987427, | |
| "learning_rate": 5.8762886597938136e-05, | |
| "loss": 1.2214, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.8231511254019293, | |
| "grad_norm": 0.4346306324005127, | |
| "learning_rate": 5.6701030927835046e-05, | |
| "loss": 1.2804, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.8295819935691319, | |
| "grad_norm": 0.4574083685874939, | |
| "learning_rate": 5.463917525773195e-05, | |
| "loss": 1.237, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.8360128617363344, | |
| "grad_norm": 0.43636971712112427, | |
| "learning_rate": 5.257731958762886e-05, | |
| "loss": 1.218, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.842443729903537, | |
| "grad_norm": 0.411658376455307, | |
| "learning_rate": 5.051546391752577e-05, | |
| "loss": 1.2383, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.8488745980707395, | |
| "grad_norm": 0.4198724627494812, | |
| "learning_rate": 4.8453608247422676e-05, | |
| "loss": 1.2599, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.8553054662379421, | |
| "grad_norm": 0.4522201418876648, | |
| "learning_rate": 4.6391752577319585e-05, | |
| "loss": 1.2277, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.8617363344051447, | |
| "grad_norm": 0.4966380298137665, | |
| "learning_rate": 4.4329896907216494e-05, | |
| "loss": 1.2268, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.8681672025723473, | |
| "grad_norm": 0.4492814838886261, | |
| "learning_rate": 4.22680412371134e-05, | |
| "loss": 1.2589, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.8745980707395499, | |
| "grad_norm": 0.4740350544452667, | |
| "learning_rate": 4.0206185567010306e-05, | |
| "loss": 1.2196, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.8810289389067524, | |
| "grad_norm": 0.46403658390045166, | |
| "learning_rate": 3.814432989690721e-05, | |
| "loss": 1.2811, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.887459807073955, | |
| "grad_norm": 0.46236127614974976, | |
| "learning_rate": 3.608247422680412e-05, | |
| "loss": 1.2403, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.8938906752411575, | |
| "grad_norm": 0.44528549909591675, | |
| "learning_rate": 3.402061855670103e-05, | |
| "loss": 1.2374, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.9003215434083601, | |
| "grad_norm": 0.4524483382701874, | |
| "learning_rate": 3.1958762886597937e-05, | |
| "loss": 1.2833, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9003215434083601, | |
| "eval_loss": 1.2448393106460571, | |
| "eval_runtime": 340.581, | |
| "eval_samples_per_second": 5.872, | |
| "eval_steps_per_second": 0.734, | |
| "step": 1400 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1555, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1406337433445335e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |