Instructions to use aleegis12/0713cc3c-6719-4484-90c8-17d434503f79 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aleegis12/0713cc3c-6719-4484-90c8-17d434503f79 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Hermes-3-Llama-3.1-8B") model = PeftModel.from_pretrained(base_model, "aleegis12/0713cc3c-6719-4484-90c8-17d434503f79") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from aleegis12/0713cc3c-6719-4484-90c8-17d434503f79: direct link, hf CLI and curl.
- Browser
- Download file 36.6 kB
-
https://huggingface.co/aleegis12/0713cc3c-6719-4484-90c8-17d434503f79/resolve/main/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://aleegis12/0713cc3c-6719-4484-90c8-17d434503f79/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/aleegis12/0713cc3c-6719-4484-90c8-17d434503f79/resolve/main/last-checkpoint/trainer_state.json
36.6 kB
| { | |
| "best_metric": 0.12536098062992096, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.922722029988466, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00461361014994233, | |
| "grad_norm": 0.3045492470264435, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2108, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00461361014994233, | |
| "eval_loss": 0.27964168787002563, | |
| "eval_runtime": 47.6217, | |
| "eval_samples_per_second": 7.665, | |
| "eval_steps_per_second": 1.932, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00922722029988466, | |
| "grad_norm": 0.30339309573173523, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2196, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01384083044982699, | |
| "grad_norm": 0.3432806432247162, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2236, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01845444059976932, | |
| "grad_norm": 0.3780440092086792, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2372, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02306805074971165, | |
| "grad_norm": 0.3281646966934204, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2254, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02768166089965398, | |
| "grad_norm": 0.32049763202667236, | |
| "learning_rate": 6e-05, | |
| "loss": 0.2416, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03229527104959631, | |
| "grad_norm": 0.24442344903945923, | |
| "learning_rate": 7e-05, | |
| "loss": 0.1857, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03690888119953864, | |
| "grad_norm": 0.24097011983394623, | |
| "learning_rate": 8e-05, | |
| "loss": 0.2117, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04152249134948097, | |
| "grad_norm": 0.2817794680595398, | |
| "learning_rate": 9e-05, | |
| "loss": 0.2382, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0461361014994233, | |
| "grad_norm": 0.2251605987548828, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05074971164936563, | |
| "grad_norm": 0.2191903442144394, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.1893, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05536332179930796, | |
| "grad_norm": 0.24539101123809814, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.2197, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05997693194925029, | |
| "grad_norm": 0.22205574810504913, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.1785, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06459054209919261, | |
| "grad_norm": 0.2609347105026245, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.1984, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06920415224913495, | |
| "grad_norm": 0.20046018064022064, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.1492, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07381776239907728, | |
| "grad_norm": 0.21731822192668915, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.1632, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 0.23892828822135925, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.1945, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08304498269896193, | |
| "grad_norm": 0.20451225340366364, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.1589, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08765859284890427, | |
| "grad_norm": 0.20716607570648193, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.1713, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0922722029988466, | |
| "grad_norm": 0.21056786179542542, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.1573, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09688581314878893, | |
| "grad_norm": 0.23277905583381653, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.1845, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10149942329873125, | |
| "grad_norm": 0.2355295568704605, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.1934, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1061130334486736, | |
| "grad_norm": 0.2014722377061844, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.1453, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11072664359861592, | |
| "grad_norm": 0.2323940247297287, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.1861, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11534025374855825, | |
| "grad_norm": 0.227676123380661, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.1841, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11995386389850057, | |
| "grad_norm": 0.2341572642326355, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.1767, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1245674740484429, | |
| "grad_norm": 0.21418996155261993, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.118, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12918108419838523, | |
| "grad_norm": 0.17156128585338593, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.1089, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13379469434832755, | |
| "grad_norm": 0.19603177905082703, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.1193, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1384083044982699, | |
| "grad_norm": 0.19700869917869568, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.1422, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14302191464821223, | |
| "grad_norm": 0.20202751457691193, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.1281, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14763552479815456, | |
| "grad_norm": 0.2103014439344406, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.1305, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1522491349480969, | |
| "grad_norm": 0.2085191011428833, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.1446, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 0.20140966773033142, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.1338, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16147635524798154, | |
| "grad_norm": 0.19825860857963562, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.1324, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16608996539792387, | |
| "grad_norm": 0.21896785497665405, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.1505, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1707035755478662, | |
| "grad_norm": 0.18379439413547516, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.1013, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17531718569780855, | |
| "grad_norm": 0.1981578916311264, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.1158, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17993079584775087, | |
| "grad_norm": 0.22546447813510895, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.1583, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1845444059976932, | |
| "grad_norm": 0.1885482370853424, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.1014, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18915801614763553, | |
| "grad_norm": 0.20522329211235046, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.1208, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19377162629757785, | |
| "grad_norm": 0.22759485244750977, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.1567, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19838523644752018, | |
| "grad_norm": 0.2325202226638794, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.1757, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2029988465974625, | |
| "grad_norm": 0.2388521432876587, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.1314, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.20761245674740483, | |
| "grad_norm": 0.28926414251327515, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.1608, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2122260668973472, | |
| "grad_norm": 0.2602057456970215, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.1689, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21683967704728951, | |
| "grad_norm": 0.23124495148658752, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.1374, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22145328719723184, | |
| "grad_norm": 0.24282653629779816, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.1321, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22606689734717417, | |
| "grad_norm": 0.28385406732559204, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.1372, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2306805074971165, | |
| "grad_norm": 0.30819329619407654, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.1338, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2306805074971165, | |
| "eval_loss": 0.14867614209651947, | |
| "eval_runtime": 48.222, | |
| "eval_samples_per_second": 7.569, | |
| "eval_steps_per_second": 1.908, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.1632201224565506, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.1716, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.23990772779700115, | |
| "grad_norm": 0.19273817539215088, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.1704, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.24452133794694347, | |
| "grad_norm": 0.14002658426761627, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.1394, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.2491349480968858, | |
| "grad_norm": 0.13335628807544708, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.1303, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2537485582468281, | |
| "grad_norm": 0.14133335649967194, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.1656, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.25836216839677045, | |
| "grad_norm": 0.2346196323633194, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.1598, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2629757785467128, | |
| "grad_norm": 0.17851288616657257, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.1726, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2675893886966551, | |
| "grad_norm": 0.1496780514717102, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.1431, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2722029988465975, | |
| "grad_norm": 0.15850284695625305, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.1457, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2768166089965398, | |
| "grad_norm": 0.15871545672416687, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.1371, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28143021914648214, | |
| "grad_norm": 0.146070197224617, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.118, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.28604382929642447, | |
| "grad_norm": 0.14819538593292236, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.1166, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2906574394463668, | |
| "grad_norm": 0.19428430497646332, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.1572, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2952710495963091, | |
| "grad_norm": 0.15656042098999023, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.1364, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.29988465974625145, | |
| "grad_norm": 0.20241779088974, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.1594, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3044982698961938, | |
| "grad_norm": 0.15743836760520935, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.1345, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3091118800461361, | |
| "grad_norm": 0.35860782861709595, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.1605, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 0.18126502633094788, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.1169, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.31833910034602075, | |
| "grad_norm": 0.1790701299905777, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.127, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3229527104959631, | |
| "grad_norm": 0.16510623693466187, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.1194, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3275663206459054, | |
| "grad_norm": 0.16934818029403687, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.1305, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.33217993079584773, | |
| "grad_norm": 0.23819081485271454, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.1846, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.33679354094579006, | |
| "grad_norm": 0.18752993643283844, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.1455, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3414071510957324, | |
| "grad_norm": 0.21817506849765778, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.1476, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3460207612456747, | |
| "grad_norm": 0.17927341163158417, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.1292, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3506343713956171, | |
| "grad_norm": 0.17165836691856384, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.1188, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3552479815455594, | |
| "grad_norm": 0.18539024889469147, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.1475, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.35986159169550175, | |
| "grad_norm": 0.16444933414459229, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.1128, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3644752018454441, | |
| "grad_norm": 0.15929977595806122, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.0969, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.3690888119953864, | |
| "grad_norm": 0.18575657904148102, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.1059, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3737024221453287, | |
| "grad_norm": 0.18567027151584625, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.1247, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.37831603229527105, | |
| "grad_norm": 0.1998375505208969, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.1476, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.3829296424452134, | |
| "grad_norm": 0.21210910379886627, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.1332, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.3875432525951557, | |
| "grad_norm": 0.19910669326782227, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.1241, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.39215686274509803, | |
| "grad_norm": 0.20645062625408173, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.1255, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.39677047289504036, | |
| "grad_norm": 0.2057769000530243, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.134, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.4013840830449827, | |
| "grad_norm": 0.20311889052391052, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.1367, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.405997693194925, | |
| "grad_norm": 0.2152274250984192, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.1495, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.41061130334486734, | |
| "grad_norm": 0.19864894449710846, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.1386, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.41522491349480967, | |
| "grad_norm": 0.19807681441307068, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.1241, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.419838523644752, | |
| "grad_norm": 0.19944807887077332, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.1215, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.4244521337946944, | |
| "grad_norm": 0.18852022290229797, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.1025, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4290657439446367, | |
| "grad_norm": 0.2149016410112381, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.1276, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.43367935409457903, | |
| "grad_norm": 0.20780391991138458, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.1063, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.43829296424452135, | |
| "grad_norm": 0.20517082512378693, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.1052, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4429065743944637, | |
| "grad_norm": 0.30427610874176025, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.1841, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.447520184544406, | |
| "grad_norm": 0.22177459299564362, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.1205, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.45213379469434833, | |
| "grad_norm": 0.2582891583442688, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.1276, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.45674740484429066, | |
| "grad_norm": 0.24995219707489014, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.137, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.461361014994233, | |
| "grad_norm": 0.21583551168441772, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.0826, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.461361014994233, | |
| "eval_loss": 0.13724249601364136, | |
| "eval_runtime": 48.2111, | |
| "eval_samples_per_second": 7.571, | |
| "eval_steps_per_second": 1.908, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4659746251441753, | |
| "grad_norm": 0.16693854331970215, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 0.1229, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.14586929976940155, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.1424, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.47520184544405997, | |
| "grad_norm": 0.13790450990200043, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 0.1256, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.4798154555940023, | |
| "grad_norm": 0.1593526005744934, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.1509, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.4844290657439446, | |
| "grad_norm": 0.16184355318546295, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1738, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.48904267589388695, | |
| "grad_norm": 0.14446185529232025, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.1207, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.4936562860438293, | |
| "grad_norm": 0.132633239030838, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 0.1295, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.4982698961937716, | |
| "grad_norm": 0.16127470135688782, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.1467, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.5028835063437139, | |
| "grad_norm": 1.3746932744979858, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 0.1863, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.5074971164936563, | |
| "grad_norm": 0.14423397183418274, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.1279, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5121107266435986, | |
| "grad_norm": 0.1783188432455063, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.1185, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.5167243367935409, | |
| "grad_norm": 0.17310823500156403, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.1193, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.5213379469434832, | |
| "grad_norm": 0.19535663723945618, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 0.1534, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.5259515570934256, | |
| "grad_norm": 0.1580890715122223, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.1332, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.5305651672433679, | |
| "grad_norm": 0.23308928310871124, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.1442, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5351787773933102, | |
| "grad_norm": 0.18780064582824707, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.1733, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5397923875432526, | |
| "grad_norm": 0.19831004738807678, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.1674, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.544405997693195, | |
| "grad_norm": 0.17428018152713776, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.1362, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5490196078431373, | |
| "grad_norm": 0.17842572927474976, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.1655, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.5536332179930796, | |
| "grad_norm": 0.1584247648715973, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.1181, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.558246828143022, | |
| "grad_norm": 0.19633540511131287, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.1525, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.5628604382929643, | |
| "grad_norm": 0.18967780470848083, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.1785, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5674740484429066, | |
| "grad_norm": 0.15900085866451263, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.1272, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5720876585928489, | |
| "grad_norm": 0.16912361979484558, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.1254, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5767012687427913, | |
| "grad_norm": 0.16823305189609528, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.1373, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5813148788927336, | |
| "grad_norm": 0.1765795350074768, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.1494, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5859284890426759, | |
| "grad_norm": 0.16386839747428894, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.1139, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5905420991926182, | |
| "grad_norm": 0.1809309720993042, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.1226, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5951557093425606, | |
| "grad_norm": 0.18641479313373566, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.1223, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5997693194925029, | |
| "grad_norm": 0.17032507061958313, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.11, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6043829296424452, | |
| "grad_norm": 0.18085092306137085, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.1342, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.6089965397923875, | |
| "grad_norm": 0.2097395807504654, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.1622, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.6136101499423299, | |
| "grad_norm": 0.20478329062461853, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.1495, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.6182237600922722, | |
| "grad_norm": 0.16314689815044403, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.0896, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.6228373702422145, | |
| "grad_norm": 0.20483306050300598, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.1435, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": 0.18159297108650208, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.111, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.6320645905420992, | |
| "grad_norm": 0.18506605923175812, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.1047, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.6366782006920415, | |
| "grad_norm": 0.16207557916641235, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.0933, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6412918108419838, | |
| "grad_norm": 0.21236790716648102, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.143, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.6459054209919262, | |
| "grad_norm": 0.18207381665706635, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.1129, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6505190311418685, | |
| "grad_norm": 0.17932240664958954, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.0879, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.6551326412918108, | |
| "grad_norm": 0.2707701325416565, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.1214, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.6597462514417531, | |
| "grad_norm": 0.24743866920471191, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.1767, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.6643598615916955, | |
| "grad_norm": 0.19047924876213074, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.0967, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6689734717416378, | |
| "grad_norm": 0.21621400117874146, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.1347, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6735870818915801, | |
| "grad_norm": 0.1867235153913498, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.0892, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.6782006920415224, | |
| "grad_norm": 0.22504442930221558, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.1389, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6828143021914648, | |
| "grad_norm": 0.20804926753044128, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.0777, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.6874279123414071, | |
| "grad_norm": 0.21870160102844238, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.1019, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.6920415224913494, | |
| "grad_norm": 0.26978006958961487, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.1173, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6920415224913494, | |
| "eval_loss": 0.12923087179660797, | |
| "eval_runtime": 47.9945, | |
| "eval_samples_per_second": 7.605, | |
| "eval_steps_per_second": 1.917, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6966551326412919, | |
| "grad_norm": 0.3860698640346527, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 0.1393, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.7012687427912342, | |
| "grad_norm": 0.22779765725135803, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.1388, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.14972583949565887, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.143, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.7104959630911188, | |
| "grad_norm": 0.14631463587284088, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.1503, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.7151095732410612, | |
| "grad_norm": 0.14756916463375092, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.1397, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7197231833910035, | |
| "grad_norm": 0.14130614697933197, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.1369, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.7243367935409458, | |
| "grad_norm": 0.12575864791870117, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 0.1135, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.7289504036908881, | |
| "grad_norm": 0.138638436794281, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.1263, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.7335640138408305, | |
| "grad_norm": 0.16222459077835083, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.1356, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.7381776239907728, | |
| "grad_norm": 0.1442897468805313, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.1176, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7427912341407151, | |
| "grad_norm": 0.1275886446237564, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 0.1061, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.7474048442906575, | |
| "grad_norm": 0.15764059126377106, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.1551, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.7520184544405998, | |
| "grad_norm": 0.139136403799057, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 0.1001, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.7566320645905421, | |
| "grad_norm": 0.17154617607593536, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.1654, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.7612456747404844, | |
| "grad_norm": 0.1845884770154953, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.1488, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7658592848904268, | |
| "grad_norm": 0.171508327126503, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.1425, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.7704728950403691, | |
| "grad_norm": 0.16210150718688965, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.1287, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.7750865051903114, | |
| "grad_norm": 0.15348601341247559, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.132, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.7797001153402537, | |
| "grad_norm": 0.1609523743391037, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.1341, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": 0.1901412159204483, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.1527, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7889273356401384, | |
| "grad_norm": 0.1699613481760025, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.1402, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.7935409457900807, | |
| "grad_norm": 0.17142589390277863, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.1245, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.798154555940023, | |
| "grad_norm": 0.17896845936775208, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.1338, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.8027681660899654, | |
| "grad_norm": 0.16168656945228577, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.1221, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.8073817762399077, | |
| "grad_norm": 0.1705646514892578, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.1217, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.81199538638985, | |
| "grad_norm": 0.14521192014217377, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.0977, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.8166089965397924, | |
| "grad_norm": 0.15054786205291748, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.1027, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.8212226066897347, | |
| "grad_norm": 0.17648428678512573, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.1147, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.825836216839677, | |
| "grad_norm": 0.16229428350925446, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.1131, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.8304498269896193, | |
| "grad_norm": 0.21467943489551544, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.1204, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8350634371395617, | |
| "grad_norm": 0.18471477925777435, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.1374, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.839677047289504, | |
| "grad_norm": 0.17805612087249756, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.1221, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.8442906574394463, | |
| "grad_norm": 0.18708768486976624, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.1254, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.8489042675893888, | |
| "grad_norm": 0.17021335661411285, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.1095, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.8535178777393311, | |
| "grad_norm": 0.15688352286815643, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.0949, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8581314878892734, | |
| "grad_norm": 0.1738876849412918, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.1182, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.8627450980392157, | |
| "grad_norm": 0.17870713770389557, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.1103, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.8673587081891581, | |
| "grad_norm": 0.17221105098724365, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.1044, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.8719723183391004, | |
| "grad_norm": 0.19080223143100739, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.1221, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.8765859284890427, | |
| "grad_norm": 0.164084792137146, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.0931, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.881199538638985, | |
| "grad_norm": 0.1871854066848755, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.1195, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.8858131487889274, | |
| "grad_norm": 0.18558648228645325, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.1118, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.8904267589388697, | |
| "grad_norm": 0.19379585981369019, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.1167, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.895040369088812, | |
| "grad_norm": 0.1844157725572586, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.0854, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.8996539792387543, | |
| "grad_norm": 0.1929725706577301, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.112, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.9042675893886967, | |
| "grad_norm": 0.21881221234798431, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.1224, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.908881199538639, | |
| "grad_norm": 0.20187975466251373, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.1076, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.9134948096885813, | |
| "grad_norm": 0.229701966047287, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.128, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.9181084198385236, | |
| "grad_norm": 0.2651047110557556, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.1212, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.922722029988466, | |
| "grad_norm": 0.2499540001153946, | |
| "learning_rate": 0.0, | |
| "loss": 0.1077, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.922722029988466, | |
| "eval_loss": 0.12536098062992096, | |
| "eval_runtime": 48.2363, | |
| "eval_samples_per_second": 7.567, | |
| "eval_steps_per_second": 1.907, | |
| "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": 5.260941105876173e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |