| { | |
| "best_metric": 1.2696720361709595, | |
| "best_model_checkpoint": "/home/datta0/models/lora_final/Meta-Llama-3-8B_magiccoder_default/checkpoint-152", | |
| "epoch": 0.9846153846153847, | |
| "eval_steps": 4, | |
| "global_step": 152, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006477732793522267, | |
| "grad_norm": 7.975759983062744, | |
| "learning_rate": 7.5e-05, | |
| "loss": 1.3889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012955465587044534, | |
| "grad_norm": 8.645442008972168, | |
| "learning_rate": 0.00015, | |
| "loss": 1.5051, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.025910931174089068, | |
| "grad_norm": 8.133455276489258, | |
| "learning_rate": 0.0003, | |
| "loss": 1.2592, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025910931174089068, | |
| "eval_loss": 1.4263103008270264, | |
| "eval_runtime": 26.5522, | |
| "eval_samples_per_second": 18.643, | |
| "eval_steps_per_second": 2.335, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.038866396761133605, | |
| "grad_norm": 15.554954528808594, | |
| "learning_rate": 0.00029986842451482874, | |
| "loss": 1.4659, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.051821862348178135, | |
| "grad_norm": 11.2620849609375, | |
| "learning_rate": 0.0002994739288874256, | |
| "loss": 1.4281, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.051821862348178135, | |
| "eval_loss": 1.4063184261322021, | |
| "eval_runtime": 26.5276, | |
| "eval_samples_per_second": 18.66, | |
| "eval_steps_per_second": 2.337, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06477732793522267, | |
| "grad_norm": 7.065455913543701, | |
| "learning_rate": 0.0002988172051971717, | |
| "loss": 1.3404, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07773279352226721, | |
| "grad_norm": 9.748723030090332, | |
| "learning_rate": 0.0002978994055605757, | |
| "loss": 1.3795, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07773279352226721, | |
| "eval_loss": 1.382373332977295, | |
| "eval_runtime": 26.5171, | |
| "eval_samples_per_second": 18.667, | |
| "eval_steps_per_second": 2.338, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09068825910931175, | |
| "grad_norm": 12.217620849609375, | |
| "learning_rate": 0.0002967221401100708, | |
| "loss": 1.4444, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10364372469635627, | |
| "grad_norm": 8.278894424438477, | |
| "learning_rate": 0.00029528747416929463, | |
| "loss": 1.3751, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10364372469635627, | |
| "eval_loss": 1.3937216997146606, | |
| "eval_runtime": 26.4559, | |
| "eval_samples_per_second": 18.71, | |
| "eval_steps_per_second": 2.344, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11659919028340081, | |
| "grad_norm": 14.924971580505371, | |
| "learning_rate": 0.00029359792462981004, | |
| "loss": 1.3393, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12955465587044535, | |
| "grad_norm": 7.198514461517334, | |
| "learning_rate": 0.00029165645553562214, | |
| "loss": 1.4053, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12955465587044535, | |
| "eval_loss": 1.3523073196411133, | |
| "eval_runtime": 26.4173, | |
| "eval_samples_per_second": 18.738, | |
| "eval_steps_per_second": 2.347, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14251012145748987, | |
| "grad_norm": 6.342569828033447, | |
| "learning_rate": 0.00028946647288323766, | |
| "loss": 1.3715, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15546558704453442, | |
| "grad_norm": 5.877941131591797, | |
| "learning_rate": 0.0002870318186463901, | |
| "loss": 1.2927, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15546558704453442, | |
| "eval_loss": 1.3473957777023315, | |
| "eval_runtime": 26.2462, | |
| "eval_samples_per_second": 18.86, | |
| "eval_steps_per_second": 2.362, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 4.236348628997803, | |
| "learning_rate": 0.0002843567640359119, | |
| "loss": 1.2866, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1813765182186235, | |
| "grad_norm": 8.370125770568848, | |
| "learning_rate": 0.0002814460020065795, | |
| "loss": 1.3619, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1813765182186235, | |
| "eval_loss": 1.3529084920883179, | |
| "eval_runtime": 58.5577, | |
| "eval_samples_per_second": 8.453, | |
| "eval_steps_per_second": 1.059, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19433198380566802, | |
| "grad_norm": 5.792184352874756, | |
| "learning_rate": 0.000278304639024076, | |
| "loss": 1.3633, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20728744939271254, | |
| "grad_norm": 12.429760932922363, | |
| "learning_rate": 0.00027493818610651487, | |
| "loss": 1.3533, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20728744939271254, | |
| "eval_loss": 1.3628934621810913, | |
| "eval_runtime": 58.1834, | |
| "eval_samples_per_second": 8.508, | |
| "eval_steps_per_second": 1.066, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2202429149797571, | |
| "grad_norm": 8.379545211791992, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 1.4074, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23319838056680162, | |
| "grad_norm": 10.356365203857422, | |
| "learning_rate": 0.00026755401859887595, | |
| "loss": 1.3627, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.23319838056680162, | |
| "eval_loss": 1.3635836839675903, | |
| "eval_runtime": 58.1828, | |
| "eval_samples_per_second": 8.508, | |
| "eval_steps_per_second": 1.066, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24615384615384617, | |
| "grad_norm": 7.12795352935791, | |
| "learning_rate": 0.00026354925834776345, | |
| "loss": 1.2767, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2591093117408907, | |
| "grad_norm": 7.771018981933594, | |
| "learning_rate": 0.0002593452941132117, | |
| "loss": 1.4408, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2591093117408907, | |
| "eval_loss": 1.3530882596969604, | |
| "eval_runtime": 58.4466, | |
| "eval_samples_per_second": 8.469, | |
| "eval_steps_per_second": 1.061, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2720647773279352, | |
| "grad_norm": 4.957456588745117, | |
| "learning_rate": 0.0002549495010770048, | |
| "loss": 1.3767, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.28502024291497974, | |
| "grad_norm": 5.10299825668335, | |
| "learning_rate": 0.0002503695909538287, | |
| "loss": 1.3744, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.28502024291497974, | |
| "eval_loss": 1.3395272493362427, | |
| "eval_runtime": 58.5125, | |
| "eval_samples_per_second": 8.46, | |
| "eval_steps_per_second": 1.06, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2979757085020243, | |
| "grad_norm": 5.048585891723633, | |
| "learning_rate": 0.0002456135984623034, | |
| "loss": 1.3295, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.31093117408906884, | |
| "grad_norm": 3.550816059112549, | |
| "learning_rate": 0.00024068986722935624, | |
| "loss": 1.2658, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.31093117408906884, | |
| "eval_loss": 1.3364324569702148, | |
| "eval_runtime": 58.5182, | |
| "eval_samples_per_second": 8.459, | |
| "eval_steps_per_second": 1.06, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.32388663967611336, | |
| "grad_norm": 9.427572250366211, | |
| "learning_rate": 0.00023560703515266478, | |
| "loss": 1.383, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 6.952998638153076, | |
| "learning_rate": 0.00023037401924684946, | |
| "loss": 1.3364, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "eval_loss": 1.340024709701538, | |
| "eval_runtime": 58.6238, | |
| "eval_samples_per_second": 8.444, | |
| "eval_steps_per_second": 1.058, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3497975708502024, | |
| "grad_norm": 3.620708465576172, | |
| "learning_rate": 0.000225, | |
| "loss": 1.299, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.362753036437247, | |
| "grad_norm": 5.74739408493042, | |
| "learning_rate": 0.00021949440526797926, | |
| "loss": 1.3765, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.362753036437247, | |
| "eval_loss": 1.3390815258026123, | |
| "eval_runtime": 58.1389, | |
| "eval_samples_per_second": 8.514, | |
| "eval_steps_per_second": 1.066, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3757085020242915, | |
| "grad_norm": 3.6690967082977295, | |
| "learning_rate": 0.00021386689373476087, | |
| "loss": 1.2833, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.38866396761133604, | |
| "grad_norm": 4.156944274902344, | |
| "learning_rate": 0.00020812733796781542, | |
| "loss": 1.3427, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38866396761133604, | |
| "eval_loss": 1.3370171785354614, | |
| "eval_runtime": 58.6352, | |
| "eval_samples_per_second": 8.442, | |
| "eval_steps_per_second": 1.057, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.40161943319838056, | |
| "grad_norm": 4.592350959777832, | |
| "learning_rate": 0.00020228580709827227, | |
| "loss": 1.3145, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4145748987854251, | |
| "grad_norm": 3.865915060043335, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 1.3975, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4145748987854251, | |
| "eval_loss": 1.332935094833374, | |
| "eval_runtime": 58.8373, | |
| "eval_samples_per_second": 8.413, | |
| "eval_steps_per_second": 1.054, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.42753036437246966, | |
| "grad_norm": 3.824434757232666, | |
| "learning_rate": 0.00019033797309228983, | |
| "loss": 1.3048, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4404858299595142, | |
| "grad_norm": 4.484032154083252, | |
| "learning_rate": 0.00018425263051659836, | |
| "loss": 1.2595, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4404858299595142, | |
| "eval_loss": 1.3324816226959229, | |
| "eval_runtime": 26.5744, | |
| "eval_samples_per_second": 18.627, | |
| "eval_steps_per_second": 2.333, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4534412955465587, | |
| "grad_norm": 5.382876873016357, | |
| "learning_rate": 0.0001781071971878587, | |
| "loss": 1.3215, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46639676113360323, | |
| "grad_norm": 5.109270095825195, | |
| "learning_rate": 0.00017191245428436173, | |
| "loss": 1.3291, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.46639676113360323, | |
| "eval_loss": 1.3312028646469116, | |
| "eval_runtime": 26.5491, | |
| "eval_samples_per_second": 18.645, | |
| "eval_steps_per_second": 2.335, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.47935222672064776, | |
| "grad_norm": 3.7885613441467285, | |
| "learning_rate": 0.000165679269490148, | |
| "loss": 1.2995, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.49230769230769234, | |
| "grad_norm": 4.146183967590332, | |
| "learning_rate": 0.000159418577929397, | |
| "loss": 1.2702, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.49230769230769234, | |
| "eval_loss": 1.3323029279708862, | |
| "eval_runtime": 26.5527, | |
| "eval_samples_per_second": 18.642, | |
| "eval_steps_per_second": 2.335, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 4.090492248535156, | |
| "learning_rate": 0.00015314136298250354, | |
| "loss": 1.3247, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5182186234817814, | |
| "grad_norm": 4.541670322418213, | |
| "learning_rate": 0.00014685863701749646, | |
| "loss": 1.3527, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5182186234817814, | |
| "eval_loss": 1.321340799331665, | |
| "eval_runtime": 26.4896, | |
| "eval_samples_per_second": 18.687, | |
| "eval_steps_per_second": 2.341, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5311740890688259, | |
| "grad_norm": 3.778151750564575, | |
| "learning_rate": 0.000140581422070603, | |
| "loss": 1.3419, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5441295546558704, | |
| "grad_norm": 3.073720693588257, | |
| "learning_rate": 0.000134320730509852, | |
| "loss": 1.2799, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5441295546558704, | |
| "eval_loss": 1.3154258728027344, | |
| "eval_runtime": 26.4775, | |
| "eval_samples_per_second": 18.695, | |
| "eval_steps_per_second": 2.342, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.557085020242915, | |
| "grad_norm": 3.3625338077545166, | |
| "learning_rate": 0.00012808754571563827, | |
| "loss": 1.2982, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5700404858299595, | |
| "grad_norm": 3.183030605316162, | |
| "learning_rate": 0.00012189280281214126, | |
| "loss": 1.3082, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5700404858299595, | |
| "eval_loss": 1.30991792678833, | |
| "eval_runtime": 26.3464, | |
| "eval_samples_per_second": 18.788, | |
| "eval_steps_per_second": 2.353, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.582995951417004, | |
| "grad_norm": 3.021327257156372, | |
| "learning_rate": 0.00011574736948340163, | |
| "loss": 1.2957, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5959514170040486, | |
| "grad_norm": 3.598100423812866, | |
| "learning_rate": 0.00010966202690771014, | |
| "loss": 1.4042, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.5959514170040486, | |
| "eval_loss": 1.3089451789855957, | |
| "eval_runtime": 26.2013, | |
| "eval_samples_per_second": 18.892, | |
| "eval_steps_per_second": 2.366, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6089068825910932, | |
| "grad_norm": 3.076206922531128, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 1.2443, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6218623481781377, | |
| "grad_norm": 3.216519832611084, | |
| "learning_rate": 9.771419290172773e-05, | |
| "loss": 1.2221, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6218623481781377, | |
| "eval_loss": 1.3048464059829712, | |
| "eval_runtime": 58.5931, | |
| "eval_samples_per_second": 8.448, | |
| "eval_steps_per_second": 1.058, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6348178137651822, | |
| "grad_norm": 3.831418514251709, | |
| "learning_rate": 9.187266203218456e-05, | |
| "loss": 1.3533, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6477732793522267, | |
| "grad_norm": 3.0627291202545166, | |
| "learning_rate": 8.613310626523909e-05, | |
| "loss": 1.3079, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6477732793522267, | |
| "eval_loss": 1.3017206192016602, | |
| "eval_runtime": 58.4051, | |
| "eval_samples_per_second": 8.475, | |
| "eval_steps_per_second": 1.062, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6607287449392713, | |
| "grad_norm": 3.7238402366638184, | |
| "learning_rate": 8.050559473202077e-05, | |
| "loss": 1.3298, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 3.6340792179107666, | |
| "learning_rate": 7.500000000000002e-05, | |
| "loss": 1.2165, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "eval_loss": 1.2970125675201416, | |
| "eval_runtime": 58.3679, | |
| "eval_samples_per_second": 8.481, | |
| "eval_steps_per_second": 1.062, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6866396761133603, | |
| "grad_norm": 3.414825677871704, | |
| "learning_rate": 6.962598075315046e-05, | |
| "loss": 1.3263, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.6995951417004048, | |
| "grad_norm": 3.9352622032165527, | |
| "learning_rate": 6.439296484733525e-05, | |
| "loss": 1.239, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6995951417004048, | |
| "eval_loss": 1.2941410541534424, | |
| "eval_runtime": 58.4064, | |
| "eval_samples_per_second": 8.475, | |
| "eval_steps_per_second": 1.062, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7125506072874493, | |
| "grad_norm": 2.6827166080474854, | |
| "learning_rate": 5.931013277064377e-05, | |
| "loss": 1.2469, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.725506072874494, | |
| "grad_norm": 3.790194034576416, | |
| "learning_rate": 5.4386401537696536e-05, | |
| "loss": 1.2528, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.725506072874494, | |
| "eval_loss": 1.2877105474472046, | |
| "eval_runtime": 58.6006, | |
| "eval_samples_per_second": 8.447, | |
| "eval_steps_per_second": 1.058, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7384615384615385, | |
| "grad_norm": 3.4227898120880127, | |
| "learning_rate": 4.963040904617131e-05, | |
| "loss": 1.2605, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.751417004048583, | |
| "grad_norm": 3.921224355697632, | |
| "learning_rate": 4.5050498922995166e-05, | |
| "loss": 1.2932, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.751417004048583, | |
| "eval_loss": 1.2858980894088745, | |
| "eval_runtime": 58.8103, | |
| "eval_samples_per_second": 8.417, | |
| "eval_steps_per_second": 1.054, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7643724696356275, | |
| "grad_norm": 3.2218077182769775, | |
| "learning_rate": 4.06547058867883e-05, | |
| "loss": 1.2063, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.7773279352226721, | |
| "grad_norm": 2.803480863571167, | |
| "learning_rate": 3.645074165223655e-05, | |
| "loss": 1.2762, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7773279352226721, | |
| "eval_loss": 1.2803733348846436, | |
| "eval_runtime": 58.4885, | |
| "eval_samples_per_second": 8.463, | |
| "eval_steps_per_second": 1.06, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7902834008097166, | |
| "grad_norm": 2.5244181156158447, | |
| "learning_rate": 3.2445981401124035e-05, | |
| "loss": 1.2421, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.8032388663967611, | |
| "grad_norm": 3.004887819290161, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 1.2914, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8032388663967611, | |
| "eval_loss": 1.2790910005569458, | |
| "eval_runtime": 58.6109, | |
| "eval_samples_per_second": 8.446, | |
| "eval_steps_per_second": 1.058, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8161943319838056, | |
| "grad_norm": 3.6300973892211914, | |
| "learning_rate": 2.5061813893485085e-05, | |
| "loss": 1.3242, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8291497975708502, | |
| "grad_norm": 2.6950979232788086, | |
| "learning_rate": 2.169536097592401e-05, | |
| "loss": 1.2835, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8291497975708502, | |
| "eval_loss": 1.2755361795425415, | |
| "eval_runtime": 58.9713, | |
| "eval_samples_per_second": 8.394, | |
| "eval_steps_per_second": 1.051, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 3.0187506675720215, | |
| "learning_rate": 1.8553997993420495e-05, | |
| "loss": 1.2856, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8550607287449393, | |
| "grad_norm": 2.8952746391296387, | |
| "learning_rate": 1.5643235964088064e-05, | |
| "loss": 1.2735, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8550607287449393, | |
| "eval_loss": 1.2730661630630493, | |
| "eval_runtime": 58.4909, | |
| "eval_samples_per_second": 8.463, | |
| "eval_steps_per_second": 1.06, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8680161943319838, | |
| "grad_norm": 2.607783555984497, | |
| "learning_rate": 1.2968181353609852e-05, | |
| "loss": 1.265, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.8809716599190284, | |
| "grad_norm": 3.7643980979919434, | |
| "learning_rate": 1.0533527116762296e-05, | |
| "loss": 1.2264, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8809716599190284, | |
| "eval_loss": 1.272207498550415, | |
| "eval_runtime": 26.5562, | |
| "eval_samples_per_second": 18.64, | |
| "eval_steps_per_second": 2.335, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8939271255060729, | |
| "grad_norm": 2.4194986820220947, | |
| "learning_rate": 8.343544464377849e-06, | |
| "loss": 1.2562, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.9068825910931174, | |
| "grad_norm": 2.965425491333008, | |
| "learning_rate": 6.402075370189913e-06, | |
| "loss": 1.2637, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9068825910931174, | |
| "eval_loss": 1.271282434463501, | |
| "eval_runtime": 26.5644, | |
| "eval_samples_per_second": 18.634, | |
| "eval_steps_per_second": 2.334, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9198380566801619, | |
| "grad_norm": 2.7396891117095947, | |
| "learning_rate": 4.712525830705338e-06, | |
| "loss": 1.2302, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9327935222672065, | |
| "grad_norm": 2.365996837615967, | |
| "learning_rate": 3.2778598899291465e-06, | |
| "loss": 1.2133, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9327935222672065, | |
| "eval_loss": 1.2704302072525024, | |
| "eval_runtime": 26.54, | |
| "eval_samples_per_second": 18.651, | |
| "eval_steps_per_second": 2.336, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.945748987854251, | |
| "grad_norm": 2.8826277256011963, | |
| "learning_rate": 2.100594439424269e-06, | |
| "loss": 1.2561, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.9587044534412955, | |
| "grad_norm": 2.938122034072876, | |
| "learning_rate": 1.1827948028283352e-06, | |
| "loss": 1.2379, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.9587044534412955, | |
| "eval_loss": 1.2698720693588257, | |
| "eval_runtime": 26.5066, | |
| "eval_samples_per_second": 18.675, | |
| "eval_steps_per_second": 2.339, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.97165991902834, | |
| "grad_norm": 3.354945659637451, | |
| "learning_rate": 5.260711125743444e-07, | |
| "loss": 1.216, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9846153846153847, | |
| "grad_norm": 2.604530096054077, | |
| "learning_rate": 1.315754851712425e-07, | |
| "loss": 1.2131, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.9846153846153847, | |
| "eval_loss": 1.2696720361709595, | |
| "eval_runtime": 26.4168, | |
| "eval_samples_per_second": 18.738, | |
| "eval_steps_per_second": 2.347, | |
| "step": 152 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 154, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.140047273385001e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |