Instructions to use aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-3b") model = PeftModel.from_pretrained(base_model, "aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 0.5150178074836731, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.6235385814497272, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003117692907248636, | |
| "grad_norm": 11.655372619628906, | |
| "learning_rate": 1e-05, | |
| "loss": 9.4725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003117692907248636, | |
| "eval_loss": 2.0170581340789795, | |
| "eval_runtime": 19.8075, | |
| "eval_samples_per_second": 27.262, | |
| "eval_steps_per_second": 6.816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006235385814497272, | |
| "grad_norm": 13.125012397766113, | |
| "learning_rate": 2e-05, | |
| "loss": 11.8029, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009353078721745909, | |
| "grad_norm": 12.141226768493652, | |
| "learning_rate": 3e-05, | |
| "loss": 11.4664, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012470771628994544, | |
| "grad_norm": 14.667614936828613, | |
| "learning_rate": 4e-05, | |
| "loss": 12.0023, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01558846453624318, | |
| "grad_norm": 12.08423137664795, | |
| "learning_rate": 5e-05, | |
| "loss": 10.5206, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018706157443491817, | |
| "grad_norm": 11.249734878540039, | |
| "learning_rate": 6e-05, | |
| "loss": 9.5772, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021823850350740453, | |
| "grad_norm": 22.513164520263672, | |
| "learning_rate": 7e-05, | |
| "loss": 9.5923, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02494154325798909, | |
| "grad_norm": 18.979618072509766, | |
| "learning_rate": 8e-05, | |
| "loss": 9.3301, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028059236165237724, | |
| "grad_norm": 29.20528221130371, | |
| "learning_rate": 9e-05, | |
| "loss": 10.607, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03117692907248636, | |
| "grad_norm": 25.135574340820312, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5226, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.034294621979735, | |
| "grad_norm": 15.285947799682617, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 8.4817, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.037412314886983634, | |
| "grad_norm": 15.414291381835938, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 7.4645, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04053000779423227, | |
| "grad_norm": 13.062957763671875, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 5.7704, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.043647700701480906, | |
| "grad_norm": 13.44833755493164, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 6.9123, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04676539360872954, | |
| "grad_norm": 12.443500518798828, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 5.7389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04988308651597818, | |
| "grad_norm": 12.959155082702637, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 5.9033, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05300077942322681, | |
| "grad_norm": 9.476544380187988, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 5.9961, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05611847233047545, | |
| "grad_norm": 11.186797142028809, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 5.6498, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.059236165237724084, | |
| "grad_norm": 11.144340515136719, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 5.4165, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06235385814497272, | |
| "grad_norm": 12.207180976867676, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 6.3502, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06547155105222136, | |
| "grad_norm": 12.063061714172363, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 5.482, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06858924395947, | |
| "grad_norm": 13.639694213867188, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 5.8621, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07170693686671863, | |
| "grad_norm": 10.871453285217285, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 5.3057, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07482462977396727, | |
| "grad_norm": 11.467005729675293, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 4.4601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0779423226812159, | |
| "grad_norm": 11.330914497375488, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 4.9252, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08106001558846454, | |
| "grad_norm": 11.97061538696289, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 4.8823, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08417770849571317, | |
| "grad_norm": 13.585055351257324, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 5.3709, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08729540140296181, | |
| "grad_norm": 13.680033683776855, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 5.6623, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09041309431021044, | |
| "grad_norm": 14.604742050170898, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 5.3659, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09353078721745908, | |
| "grad_norm": 13.014104843139648, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 5.0338, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09664848012470771, | |
| "grad_norm": 13.416587829589844, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 4.5345, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09976617303195635, | |
| "grad_norm": 13.330890655517578, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 4.7284, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10288386593920498, | |
| "grad_norm": 14.181489944458008, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 5.1683, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10600155884645363, | |
| "grad_norm": 14.32101058959961, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 4.4735, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10911925175370225, | |
| "grad_norm": 11.41262435913086, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 4.555, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1122369446609509, | |
| "grad_norm": 11.651115417480469, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 4.3732, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11535463756819954, | |
| "grad_norm": 10.54432487487793, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 4.2542, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11847233047544817, | |
| "grad_norm": 13.021109580993652, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 4.5108, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12159002338269681, | |
| "grad_norm": 13.503449440002441, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 4.2284, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12470771628994544, | |
| "grad_norm": 13.191174507141113, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 4.2834, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12782540919719407, | |
| "grad_norm": 12.584697723388672, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 3.8461, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1309431021044427, | |
| "grad_norm": 14.472663879394531, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 3.8354, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13406079501169135, | |
| "grad_norm": 12.175851821899414, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 3.9488, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13717848791894, | |
| "grad_norm": 28.482507705688477, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 3.8271, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1402961808261886, | |
| "grad_norm": 18.594249725341797, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 4.1931, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14341387373343725, | |
| "grad_norm": 15.749979019165039, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 3.1982, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1465315666406859, | |
| "grad_norm": 20.301923751831055, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 4.3817, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14964925954793454, | |
| "grad_norm": 13.996861457824707, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 4.1606, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15276695245518315, | |
| "grad_norm": 19.21599006652832, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 4.6406, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1558846453624318, | |
| "grad_norm": 19.336666107177734, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 4.3495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1558846453624318, | |
| "eval_loss": 0.745703935623169, | |
| "eval_runtime": 20.391, | |
| "eval_samples_per_second": 26.482, | |
| "eval_steps_per_second": 6.621, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15900233826968044, | |
| "grad_norm": 16.644689559936523, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 3.5753, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.16212003117692908, | |
| "grad_norm": 13.698346138000488, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 3.5221, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1652377240841777, | |
| "grad_norm": 10.113664627075195, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 3.4487, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.16835541699142634, | |
| "grad_norm": 9.818008422851562, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 2.9978, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.17147310989867498, | |
| "grad_norm": 7.929912090301514, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 2.7355, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.17459080280592362, | |
| "grad_norm": 9.08836555480957, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 3.0724, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.17770849571317227, | |
| "grad_norm": 8.289327621459961, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 3.1148, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.18082618862042088, | |
| "grad_norm": 8.683759689331055, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 2.7112, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.18394388152766952, | |
| "grad_norm": 8.794864654541016, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 3.2929, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.18706157443491817, | |
| "grad_norm": 7.364131927490234, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 2.63, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1901792673421668, | |
| "grad_norm": 7.907564163208008, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 3.0691, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.19329696024941542, | |
| "grad_norm": 9.792932510375977, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 3.1184, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.19641465315666407, | |
| "grad_norm": 7.965488910675049, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 3.3138, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1995323460639127, | |
| "grad_norm": 9.244006156921387, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 2.995, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.20265003897116135, | |
| "grad_norm": 6.818788051605225, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 2.6801, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.20576773187840997, | |
| "grad_norm": 8.18008804321289, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 2.8639, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2088854247856586, | |
| "grad_norm": 8.462689399719238, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 3.3518, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.21200311769290725, | |
| "grad_norm": 9.65335464477539, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 3.0363, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2151208106001559, | |
| "grad_norm": 9.894681930541992, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 3.6108, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2182385035074045, | |
| "grad_norm": 10.462113380432129, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 3.4783, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22135619641465315, | |
| "grad_norm": 8.34600830078125, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 3.0312, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2244738893219018, | |
| "grad_norm": 8.083913803100586, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 3.1196, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.22759158222915044, | |
| "grad_norm": 9.153026580810547, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 3.2304, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.23070927513639908, | |
| "grad_norm": 18.286788940429688, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 3.3481, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2338269680436477, | |
| "grad_norm": 12.73767375946045, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 3.5366, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.23694466095089634, | |
| "grad_norm": 11.967613220214844, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 3.4847, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.24006235385814498, | |
| "grad_norm": 9.898238182067871, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 3.4925, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.24318004676539362, | |
| "grad_norm": 13.920319557189941, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 3.8911, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.24629773967264224, | |
| "grad_norm": 14.240066528320312, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 3.9988, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.24941543257989088, | |
| "grad_norm": 12.303492546081543, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 4.0639, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2525331254871395, | |
| "grad_norm": 11.494243621826172, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 3.8558, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.25565081839438814, | |
| "grad_norm": 11.226067543029785, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 3.3342, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2587685113016368, | |
| "grad_norm": 11.755266189575195, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 4.2033, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.2618862042088854, | |
| "grad_norm": 8.904754638671875, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 3.4204, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.26500389711613404, | |
| "grad_norm": 11.56294059753418, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 3.26, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2681215900233827, | |
| "grad_norm": 10.843947410583496, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 3.6785, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.2712392829306313, | |
| "grad_norm": 9.812710762023926, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 3.1796, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.27435697583788, | |
| "grad_norm": 12.650871276855469, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 3.7719, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2774746687451286, | |
| "grad_norm": 9.260048866271973, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 3.3953, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.2805923616523772, | |
| "grad_norm": 10.217822074890137, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 3.2167, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2837100545596259, | |
| "grad_norm": 11.022683143615723, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 3.2912, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.2868277474668745, | |
| "grad_norm": 12.414704322814941, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 3.328, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2899454403741232, | |
| "grad_norm": 11.644399642944336, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 3.1574, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.2930631332813718, | |
| "grad_norm": 19.45965003967285, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 2.4187, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2961808261886204, | |
| "grad_norm": 9.440485000610352, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 2.7639, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2992985190958691, | |
| "grad_norm": 10.892629623413086, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 2.6128, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3024162120031177, | |
| "grad_norm": 11.69962215423584, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 3.0135, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.3055339049103663, | |
| "grad_norm": 16.776004791259766, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 3.2701, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.308651597817615, | |
| "grad_norm": 10.856680870056152, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 3.1861, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3117692907248636, | |
| "grad_norm": 23.68087387084961, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 4.1984, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3117692907248636, | |
| "eval_loss": 0.6143662333488464, | |
| "eval_runtime": 20.4247, | |
| "eval_samples_per_second": 26.439, | |
| "eval_steps_per_second": 6.61, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31488698363211226, | |
| "grad_norm": 6.1397271156311035, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 2.3444, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.3180046765393609, | |
| "grad_norm": 7.607326030731201, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 2.9072, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.3211223694466095, | |
| "grad_norm": 6.6434407234191895, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 2.3472, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.32424006235385816, | |
| "grad_norm": 7.280537128448486, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 2.4164, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.3273577552611068, | |
| "grad_norm": 6.675552845001221, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3209, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.3304754481683554, | |
| "grad_norm": 6.807125568389893, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 2.3718, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.33359314107560406, | |
| "grad_norm": 6.205484867095947, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 2.4963, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.3367108339828527, | |
| "grad_norm": 6.572414875030518, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 2.6112, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.33982852689010135, | |
| "grad_norm": 6.466701984405518, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 2.1945, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.34294621979734996, | |
| "grad_norm": 5.984310150146484, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 2.8097, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3460639127045986, | |
| "grad_norm": 10.94200325012207, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 2.4516, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.34918160561184725, | |
| "grad_norm": 11.749654769897461, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 2.4898, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.35229929851909586, | |
| "grad_norm": 7.231618881225586, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 2.5991, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.35541699142634453, | |
| "grad_norm": 8.064313888549805, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 2.6607, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.35853468433359315, | |
| "grad_norm": 14.305150032043457, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 2.7776, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.36165237724084176, | |
| "grad_norm": 7.72219705581665, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 2.4705, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.36477007014809043, | |
| "grad_norm": 7.625950813293457, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 2.4539, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.36788776305533905, | |
| "grad_norm": 8.687618255615234, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 3.2093, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.37100545596258766, | |
| "grad_norm": 7.8179826736450195, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 3.1214, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.37412314886983633, | |
| "grad_norm": 11.393646240234375, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 3.2904, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37724084177708495, | |
| "grad_norm": 9.927339553833008, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 3.8075, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3803585346843336, | |
| "grad_norm": 7.990683555603027, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 2.7959, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.38347622759158223, | |
| "grad_norm": 7.790266513824463, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 2.7875, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.38659392049883085, | |
| "grad_norm": 8.719717025756836, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 3.7968, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3897116134060795, | |
| "grad_norm": 10.316503524780273, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 3.2443, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.39282930631332813, | |
| "grad_norm": 8.768962860107422, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 3.6746, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3959469992205768, | |
| "grad_norm": 9.664812088012695, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 3.1677, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.3990646921278254, | |
| "grad_norm": 9.670389175415039, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 3.4062, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.40218238503507403, | |
| "grad_norm": 9.162301063537598, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 3.6435, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.4053000779423227, | |
| "grad_norm": 7.748847961425781, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 3.178, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4084177708495713, | |
| "grad_norm": 9.13791561126709, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 3.3075, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.41153546375681993, | |
| "grad_norm": 9.217190742492676, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 3.5296, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.4146531566640686, | |
| "grad_norm": 10.093830108642578, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 3.282, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.4177708495713172, | |
| "grad_norm": 11.196274757385254, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 3.1394, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.4208885424785659, | |
| "grad_norm": 9.726496696472168, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 3.7191, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.4240062353858145, | |
| "grad_norm": 10.877890586853027, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 3.2328, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.4271239282930631, | |
| "grad_norm": 10.798422813415527, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 3.3357, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.4302416212003118, | |
| "grad_norm": 9.386134147644043, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 3.3181, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.4333593141075604, | |
| "grad_norm": 12.355273246765137, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 2.9209, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.436477007014809, | |
| "grad_norm": 10.783023834228516, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 3.6177, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4395946999220577, | |
| "grad_norm": 16.665035247802734, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 2.9883, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.4427123928293063, | |
| "grad_norm": 10.434625625610352, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 2.5966, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.44583008573655497, | |
| "grad_norm": 9.988262176513672, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.3265, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.4489477786438036, | |
| "grad_norm": 10.1835355758667, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 2.6702, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.4520654715510522, | |
| "grad_norm": 12.877456665039062, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 3.1513, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.45518316445830087, | |
| "grad_norm": 11.23567008972168, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 2.9379, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.4583008573655495, | |
| "grad_norm": 11.280649185180664, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 2.5896, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.46141855027279816, | |
| "grad_norm": 12.652727127075195, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 3.0991, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.46453624318004677, | |
| "grad_norm": 12.5499906539917, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 2.7149, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.4676539360872954, | |
| "grad_norm": 22.550954818725586, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 3.8598, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4676539360872954, | |
| "eval_loss": 0.5526705980300903, | |
| "eval_runtime": 20.4183, | |
| "eval_samples_per_second": 26.447, | |
| "eval_steps_per_second": 6.612, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.47077162899454406, | |
| "grad_norm": 5.510451316833496, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 1.7517, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.47388932190179267, | |
| "grad_norm": 5.776265621185303, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 2.2235, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.4770070148090413, | |
| "grad_norm": 5.69129753112793, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 2.0681, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.48012470771628996, | |
| "grad_norm": 7.5511956214904785, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 2.3379, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.48324240062353857, | |
| "grad_norm": 6.128115177154541, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 1.9243, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.48636009353078724, | |
| "grad_norm": 5.709255218505859, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 2.0376, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.48947778643803586, | |
| "grad_norm": 6.6855950355529785, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 2.2901, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.49259547934528447, | |
| "grad_norm": 6.084838390350342, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 2.2606, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.49571317225253314, | |
| "grad_norm": 6.58294677734375, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 2.2749, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.49883086515978176, | |
| "grad_norm": 7.350609302520752, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 2.2602, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5019485580670304, | |
| "grad_norm": 6.449454307556152, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 2.0813, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.505066250974279, | |
| "grad_norm": 10.626570701599121, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.2476, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.5081839438815277, | |
| "grad_norm": 5.894722938537598, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 2.2141, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.5113016367887763, | |
| "grad_norm": 8.111690521240234, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 2.0128, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.514419329696025, | |
| "grad_norm": 6.200974464416504, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 2.2972, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.5175370226032736, | |
| "grad_norm": 7.870783805847168, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 2.4488, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.5206547155105222, | |
| "grad_norm": 7.808360576629639, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 2.2896, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.5237724084177708, | |
| "grad_norm": 7.943413257598877, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 2.3406, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.5268901013250195, | |
| "grad_norm": 9.041855812072754, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 2.8324, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.5300077942322681, | |
| "grad_norm": 8.971168518066406, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 3.0823, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5331254871395168, | |
| "grad_norm": 7.470766544342041, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 2.7118, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.5362431800467654, | |
| "grad_norm": 9.016336441040039, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 2.9919, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.539360872954014, | |
| "grad_norm": 8.753948211669922, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 3.1282, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.5424785658612626, | |
| "grad_norm": 9.623739242553711, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 2.9055, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.5455962587685113, | |
| "grad_norm": 9.623494148254395, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 3.3859, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.54871395167576, | |
| "grad_norm": 11.163936614990234, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 2.9277, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.5518316445830086, | |
| "grad_norm": 8.889883995056152, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 3.0582, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.5549493374902572, | |
| "grad_norm": 14.302506446838379, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 3.8435, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.5580670303975058, | |
| "grad_norm": 9.2825345993042, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 3.2624, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.5611847233047544, | |
| "grad_norm": 9.157449722290039, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 3.5069, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5643024162120032, | |
| "grad_norm": 7.781318187713623, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 3.0756, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.5674201091192518, | |
| "grad_norm": 10.207369804382324, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 3.7111, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.5705378020265004, | |
| "grad_norm": 8.891037940979004, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 3.7993, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.573655494933749, | |
| "grad_norm": 9.740682601928711, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 3.6118, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.5767731878409976, | |
| "grad_norm": 12.479891777038574, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 3.3783, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.5798908807482464, | |
| "grad_norm": 16.013286590576172, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 2.8446, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.583008573655495, | |
| "grad_norm": 9.353748321533203, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 3.1683, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.5861262665627436, | |
| "grad_norm": 9.315102577209473, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 3.1097, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.5892439594699922, | |
| "grad_norm": 14.705044746398926, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 2.7454, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.5923616523772408, | |
| "grad_norm": 8.641880989074707, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 2.7142, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5954793452844894, | |
| "grad_norm": 11.792092323303223, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 2.6724, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.5985970381917382, | |
| "grad_norm": 10.994759559631348, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 2.4745, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.6017147310989868, | |
| "grad_norm": 13.135787010192871, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 2.7174, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.6048324240062354, | |
| "grad_norm": 10.710105895996094, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 3.0424, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.607950116913484, | |
| "grad_norm": 11.313312530517578, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 2.7834, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.6110678098207326, | |
| "grad_norm": 12.285223007202148, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 2.9568, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.6141855027279813, | |
| "grad_norm": 11.848814964294434, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 2.5463, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.61730319563523, | |
| "grad_norm": 13.349742889404297, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 3.4006, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.6204208885424786, | |
| "grad_norm": 16.632017135620117, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 3.4796, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.6235385814497272, | |
| "grad_norm": 19.081388473510742, | |
| "learning_rate": 0.0, | |
| "loss": 3.6177, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6235385814497272, | |
| "eval_loss": 0.5150178074836731, | |
| "eval_runtime": 20.4207, | |
| "eval_samples_per_second": 26.444, | |
| "eval_steps_per_second": 6.611, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.169711928705024e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |