Instructions to use alchemist69/08d0111a-99e7-4136-9d9e-6db30b296e21 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use alchemist69/08d0111a-99e7-4136-9d9e-6db30b296e21 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Hermes-2-Pro-Llama-3-8B") model = PeftModel.from_pretrained(base_model, "alchemist69/08d0111a-99e7-4136-9d9e-6db30b296e21") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from alchemist69/08d0111a-99e7-4136-9d9e-6db30b296e21: direct link, hf CLI and curl.
- Browser
- Download file 27.6 kB
-
https://huggingface.co/alchemist69/08d0111a-99e7-4136-9d9e-6db30b296e21/resolve/b3f7c8952897127507da7d40115b540d7b5aa1bc/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://alchemist69/08d0111a-99e7-4136-9d9e-6db30b296e21@b3f7c8952897127507da7d40115b540d7b5aa1bc/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/alchemist69/08d0111a-99e7-4136-9d9e-6db30b296e21/resolve/b3f7c8952897127507da7d40115b540d7b5aa1bc/last-checkpoint/trainer_state.json
27.6 kB
| { | |
| "best_metric": 1.0521574020385742, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.4897959183673469, | |
| "eval_steps": 50, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032653061224489797, | |
| "grad_norm": 1.3490124940872192, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8222, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032653061224489797, | |
| "eval_loss": 1.3359341621398926, | |
| "eval_runtime": 42.9996, | |
| "eval_samples_per_second": 12.0, | |
| "eval_steps_per_second": 3.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006530612244897959, | |
| "grad_norm": 1.4368774890899658, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7242, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009795918367346938, | |
| "grad_norm": 1.437239646911621, | |
| "learning_rate": 3e-05, | |
| "loss": 1.6524, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013061224489795919, | |
| "grad_norm": 0.9052526354789734, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6331, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0163265306122449, | |
| "grad_norm": 0.6831444501876831, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3906, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019591836734693877, | |
| "grad_norm": 0.49962836503982544, | |
| "learning_rate": 6e-05, | |
| "loss": 1.448, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022857142857142857, | |
| "grad_norm": 0.612272322177887, | |
| "learning_rate": 7e-05, | |
| "loss": 1.3516, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026122448979591838, | |
| "grad_norm": 0.7245445251464844, | |
| "learning_rate": 8e-05, | |
| "loss": 1.4017, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029387755102040815, | |
| "grad_norm": 0.7164787650108337, | |
| "learning_rate": 9e-05, | |
| "loss": 1.366, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0326530612244898, | |
| "grad_norm": 0.49317994713783264, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2512, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.035918367346938776, | |
| "grad_norm": 0.4278146028518677, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.2793, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03918367346938775, | |
| "grad_norm": 0.4303657114505768, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.2194, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04244897959183674, | |
| "grad_norm": 0.501557469367981, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.1395, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.045714285714285714, | |
| "grad_norm": 0.4608376920223236, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.1887, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04897959183673469, | |
| "grad_norm": 0.4015524387359619, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.1233, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.052244897959183675, | |
| "grad_norm": 0.38191235065460205, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.1317, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05551020408163265, | |
| "grad_norm": 0.4178871214389801, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.0771, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05877551020408163, | |
| "grad_norm": 0.39849820733070374, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.075, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.062040816326530614, | |
| "grad_norm": 0.39648550748825073, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.0666, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0653061224489796, | |
| "grad_norm": 0.38689857721328735, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.0092, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06857142857142857, | |
| "grad_norm": 0.3697625994682312, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.0626, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07183673469387755, | |
| "grad_norm": 0.377641886472702, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.0963, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07510204081632653, | |
| "grad_norm": 0.4216980040073395, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.1025, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0783673469387755, | |
| "grad_norm": 0.3702249228954315, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.0971, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.37534382939338684, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.0514, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08489795918367347, | |
| "grad_norm": 0.3723922669887543, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.1283, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08816326530612245, | |
| "grad_norm": 0.39508911967277527, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.0027, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09142857142857143, | |
| "grad_norm": 0.38931167125701904, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.0697, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0946938775510204, | |
| "grad_norm": 0.3679940700531006, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.0004, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09795918367346938, | |
| "grad_norm": 0.3660971224308014, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.0879, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10122448979591837, | |
| "grad_norm": 0.3589637279510498, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.0117, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10448979591836735, | |
| "grad_norm": 0.39306482672691345, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.9875, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10775510204081633, | |
| "grad_norm": 0.3901447355747223, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.0339, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1110204081632653, | |
| "grad_norm": 0.3912127912044525, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.0288, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 0.37980273365974426, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.0185, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11755102040816326, | |
| "grad_norm": 0.39466267824172974, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.0441, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12081632653061225, | |
| "grad_norm": 0.40409713983535767, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.0162, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12408163265306123, | |
| "grad_norm": 0.37681710720062256, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.9801, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1273469387755102, | |
| "grad_norm": 0.4067130982875824, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.0325, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1306122448979592, | |
| "grad_norm": 0.4063699543476105, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.0419, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13387755102040816, | |
| "grad_norm": 0.40510568022727966, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.0621, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13714285714285715, | |
| "grad_norm": 0.4200483560562134, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.0322, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1404081632653061, | |
| "grad_norm": 0.42486777901649475, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.9999, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1436734693877551, | |
| "grad_norm": 0.4197094440460205, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.085, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1469387755102041, | |
| "grad_norm": 0.4151225686073303, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.0269, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15020408163265306, | |
| "grad_norm": 0.43390777707099915, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.055, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15346938775510205, | |
| "grad_norm": 0.4523440897464752, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.0183, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.156734693877551, | |
| "grad_norm": 0.45615875720977783, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.0196, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.5123087167739868, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 1.0657, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.7052022218704224, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.1213, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "eval_loss": 1.122199535369873, | |
| "eval_runtime": 43.3342, | |
| "eval_samples_per_second": 11.907, | |
| "eval_steps_per_second": 2.977, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16653061224489796, | |
| "grad_norm": 0.625573456287384, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 1.5952, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.16979591836734695, | |
| "grad_norm": 0.3878016471862793, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 1.5167, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1730612244897959, | |
| "grad_norm": 0.30729126930236816, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 1.4522, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1763265306122449, | |
| "grad_norm": 0.33049070835113525, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 1.4213, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.17959183673469387, | |
| "grad_norm": 0.3417610228061676, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 1.3876, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "grad_norm": 0.33785831928253174, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 1.3355, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.18612244897959185, | |
| "grad_norm": 0.3122543692588806, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 1.38, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1893877551020408, | |
| "grad_norm": 0.28325581550598145, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 1.2459, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1926530612244898, | |
| "grad_norm": 0.27713680267333984, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 1.2945, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.19591836734693877, | |
| "grad_norm": 0.29581400752067566, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.21, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19918367346938776, | |
| "grad_norm": 0.29921674728393555, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 1.1871, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.20244897959183675, | |
| "grad_norm": 0.2888709604740143, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 1.1313, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2057142857142857, | |
| "grad_norm": 0.28377765417099, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 1.0924, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2089795918367347, | |
| "grad_norm": 0.2797093987464905, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 1.041, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.21224489795918366, | |
| "grad_norm": 0.31048381328582764, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 1.0952, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.21551020408163266, | |
| "grad_norm": 0.2931153476238251, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 1.0324, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.21877551020408162, | |
| "grad_norm": 0.3066525161266327, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.0988, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2220408163265306, | |
| "grad_norm": 0.29435673356056213, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 1.0232, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2253061224489796, | |
| "grad_norm": 0.290862113237381, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.9643, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.2951912581920624, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.023, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23183673469387756, | |
| "grad_norm": 0.3182593882083893, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 1.003, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.23510204081632652, | |
| "grad_norm": 0.32849201560020447, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 1.0776, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2383673469387755, | |
| "grad_norm": 0.31729793548583984, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.9929, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2416326530612245, | |
| "grad_norm": 0.31726229190826416, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 1.0441, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 0.3243188261985779, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 1.0261, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24816326530612245, | |
| "grad_norm": 0.31468647718429565, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 1.0167, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.25142857142857145, | |
| "grad_norm": 0.3464677333831787, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 1.0586, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.2546938775510204, | |
| "grad_norm": 0.3374519944190979, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 1.0224, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.25795918367346937, | |
| "grad_norm": 0.34055936336517334, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 1.0422, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2612244897959184, | |
| "grad_norm": 0.3298929035663605, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 1.0183, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26448979591836735, | |
| "grad_norm": 0.3283475637435913, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 1.0105, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2677551020408163, | |
| "grad_norm": 0.34386560320854187, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.9919, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2710204081632653, | |
| "grad_norm": 0.3480358123779297, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 1.0223, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.2742857142857143, | |
| "grad_norm": 0.35029199719429016, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 1.0539, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.27755102040816326, | |
| "grad_norm": 0.34957608580589294, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.9745, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2808163265306122, | |
| "grad_norm": 0.35363855957984924, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.0186, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.28408163265306124, | |
| "grad_norm": 0.35653287172317505, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 1.046, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.2873469387755102, | |
| "grad_norm": 0.35061317682266235, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 1.0133, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.29061224489795917, | |
| "grad_norm": 0.35454726219177246, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 1.0462, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.2938775510204082, | |
| "grad_norm": 0.34342190623283386, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.9128, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29714285714285715, | |
| "grad_norm": 0.36396175622940063, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.9774, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.3004081632653061, | |
| "grad_norm": 0.3561195135116577, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.9924, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3036734693877551, | |
| "grad_norm": 0.36226898431777954, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.9645, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3069387755102041, | |
| "grad_norm": 0.3839600086212158, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.9525, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.31020408163265306, | |
| "grad_norm": 0.4170045852661133, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 1.0206, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.313469387755102, | |
| "grad_norm": 0.3969464898109436, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.9629, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.31673469387755104, | |
| "grad_norm": 0.4268811345100403, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 1.0184, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.44238999485969543, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.9691, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.32326530612244897, | |
| "grad_norm": 0.5090784430503845, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.9984, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.745188295841217, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 1.112, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "eval_loss": 1.080734133720398, | |
| "eval_runtime": 43.594, | |
| "eval_samples_per_second": 11.836, | |
| "eval_steps_per_second": 2.959, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32979591836734695, | |
| "grad_norm": 0.4673844873905182, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 1.5597, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.3330612244897959, | |
| "grad_norm": 0.4106678366661072, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 1.5768, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.3363265306122449, | |
| "grad_norm": 0.32523709535598755, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 1.4829, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.3395918367346939, | |
| "grad_norm": 0.27613213658332825, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 1.2672, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 0.2684955596923828, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3396, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.3461224489795918, | |
| "grad_norm": 0.27828139066696167, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 1.381, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.34938775510204084, | |
| "grad_norm": 0.2876995801925659, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 1.3535, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.3526530612244898, | |
| "grad_norm": 0.28751134872436523, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 1.267, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.35591836734693877, | |
| "grad_norm": 0.2795424461364746, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 1.0994, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.35918367346938773, | |
| "grad_norm": 0.2750096619129181, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 1.1255, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.36244897959183675, | |
| "grad_norm": 0.28660520911216736, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 1.1449, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.3657142857142857, | |
| "grad_norm": 0.2879250943660736, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 1.1128, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.3689795918367347, | |
| "grad_norm": 0.2929372191429138, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 1.0871, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.3722448979591837, | |
| "grad_norm": 0.2932370901107788, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.9774, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.37551020408163266, | |
| "grad_norm": 0.3034680485725403, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 1.0615, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3787755102040816, | |
| "grad_norm": 0.29233381152153015, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 1.0273, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.3820408163265306, | |
| "grad_norm": 0.3026246726512909, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.9679, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.3853061224489796, | |
| "grad_norm": 0.30248984694480896, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 1.0469, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.38857142857142857, | |
| "grad_norm": 0.3062831461429596, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 1.0537, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.39183673469387753, | |
| "grad_norm": 0.29366207122802734, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 1.0142, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39510204081632655, | |
| "grad_norm": 0.3065624535083771, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 1.0233, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3983673469387755, | |
| "grad_norm": 0.3001972734928131, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.9985, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.4016326530612245, | |
| "grad_norm": 0.30375322699546814, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.9795, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.4048979591836735, | |
| "grad_norm": 0.3111690282821655, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.0008, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 0.30732810497283936, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 1.0143, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4114285714285714, | |
| "grad_norm": 0.3141505718231201, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.9801, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.4146938775510204, | |
| "grad_norm": 0.3132982552051544, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 1.0293, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.4179591836734694, | |
| "grad_norm": 0.31532377004623413, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 1.0056, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.42122448979591837, | |
| "grad_norm": 0.34107598662376404, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 1.069, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.42448979591836733, | |
| "grad_norm": 0.33694490790367126, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 1.0271, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.42775510204081635, | |
| "grad_norm": 0.32336458563804626, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.9831, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.4310204081632653, | |
| "grad_norm": 0.3337719440460205, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.9965, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.4342857142857143, | |
| "grad_norm": 0.34013664722442627, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.9897, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.43755102040816324, | |
| "grad_norm": 0.33463314175605774, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.9866, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.44081632653061226, | |
| "grad_norm": 0.3379949927330017, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.9488, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.4440816326530612, | |
| "grad_norm": 0.34378427267074585, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 1.0251, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.4473469387755102, | |
| "grad_norm": 0.34251320362091064, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 1.0149, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.4506122448979592, | |
| "grad_norm": 0.34321892261505127, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 1.0012, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.45387755102040817, | |
| "grad_norm": 0.3566146790981293, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 1.0442, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.34775322675704956, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.9606, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.46040816326530615, | |
| "grad_norm": 0.3511592745780945, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.9832, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.4636734693877551, | |
| "grad_norm": 0.3821600675582886, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 1.0377, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.4669387755102041, | |
| "grad_norm": 0.3769426941871643, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.9492, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.47020408163265304, | |
| "grad_norm": 0.3839811384677887, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 1.0344, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.47346938775510206, | |
| "grad_norm": 0.38504257798194885, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 1.0128, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.476734693877551, | |
| "grad_norm": 0.42816832661628723, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.9911, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.4216458201408386, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 1.0247, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.483265306122449, | |
| "grad_norm": 0.4273131787776947, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 1.0223, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.48653061224489796, | |
| "grad_norm": 0.4991781413555145, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.9789, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 0.6679096817970276, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 1.1044, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "eval_loss": 1.0521574020385742, | |
| "eval_runtime": 43.314, | |
| "eval_samples_per_second": 11.913, | |
| "eval_steps_per_second": 2.978, | |
| "step": 150 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.4136629576794112e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |