Instructions to use aleegis12/e6e6600b-1a23-4227-8804-c69cfc63ce07 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aleegis12/e6e6600b-1a23-4227-8804-c69cfc63ce07 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-2-2b-it") model = PeftModel.from_pretrained(base_model, "aleegis12/e6e6600b-1a23-4227-8804-c69cfc63ce07") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from aleegis12/e6e6600b-1a23-4227-8804-c69cfc63ce07: direct link, hf CLI and curl.
- Browser
- Download file 36.7 kB
-
https://huggingface.co/aleegis12/e6e6600b-1a23-4227-8804-c69cfc63ce07/resolve/main/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://aleegis12/e6e6600b-1a23-4227-8804-c69cfc63ce07/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/aleegis12/e6e6600b-1a23-4227-8804-c69cfc63ce07/resolve/main/last-checkpoint/trainer_state.json
36.7 kB
| { | |
| "best_metric": 0.6336299180984497, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.20110608345902464, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001005530417295123, | |
| "grad_norm": 2.4352548122406006, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6833, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001005530417295123, | |
| "eval_loss": 0.859174907207489, | |
| "eval_runtime": 144.4981, | |
| "eval_samples_per_second": 11.592, | |
| "eval_steps_per_second": 2.9, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002011060834590246, | |
| "grad_norm": 2.3664867877960205, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6703, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030165912518853697, | |
| "grad_norm": 2.0348565578460693, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6261, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004022121669180492, | |
| "grad_norm": 0.7516242265701294, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5305, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005027652086475616, | |
| "grad_norm": 1.6016530990600586, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5401, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006033182503770739, | |
| "grad_norm": 0.9149666428565979, | |
| "learning_rate": 6e-05, | |
| "loss": 0.503, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007038712921065862, | |
| "grad_norm": 0.5540153980255127, | |
| "learning_rate": 7e-05, | |
| "loss": 0.4683, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008044243338360985, | |
| "grad_norm": 0.4465714693069458, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4362, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00904977375565611, | |
| "grad_norm": 0.37307798862457275, | |
| "learning_rate": 9e-05, | |
| "loss": 0.4216, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010055304172951232, | |
| "grad_norm": 0.3346532881259918, | |
| "learning_rate": 0.0001, | |
| "loss": 0.426, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011060834590246356, | |
| "grad_norm": 0.2881012558937073, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.4022, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012066365007541479, | |
| "grad_norm": 0.252236008644104, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.3923, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013071895424836602, | |
| "grad_norm": 0.23015816509723663, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.3805, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014077425842131725, | |
| "grad_norm": 0.34804385900497437, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.4176, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015082956259426848, | |
| "grad_norm": 0.23283986747264862, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.4384, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01608848667672197, | |
| "grad_norm": 3.591134786605835, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.6849, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 0.9220762252807617, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.016, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01809954751131222, | |
| "grad_norm": 1.198287010192871, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.9521, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.019105077928607342, | |
| "grad_norm": 0.5396149158477783, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.8114, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.020110608345902465, | |
| "grad_norm": 0.3927422761917114, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.8306, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021116138763197588, | |
| "grad_norm": 0.35858792066574097, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.7893, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02212166918049271, | |
| "grad_norm": 0.3317579925060272, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.792, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.023127199597787834, | |
| "grad_norm": 0.3556971549987793, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.7937, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.024132730015082957, | |
| "grad_norm": 0.3509909212589264, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.8118, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02513826043237808, | |
| "grad_norm": 0.21706604957580566, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.7938, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026143790849673203, | |
| "grad_norm": 0.3561152219772339, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.8021, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.027149321266968326, | |
| "grad_norm": 0.23132124543190002, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.783, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02815485168426345, | |
| "grad_norm": 0.22269226610660553, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.7959, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.029160382101558573, | |
| "grad_norm": 0.24683009088039398, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.7602, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.030165912518853696, | |
| "grad_norm": 0.25816789269447327, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.797, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03117144293614882, | |
| "grad_norm": 0.2194022387266159, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.7661, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03217697335344394, | |
| "grad_norm": 0.20569732785224915, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.7757, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.033182503770739065, | |
| "grad_norm": 0.26061707735061646, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.8045, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 0.2521941065788269, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.771, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03519356460532931, | |
| "grad_norm": 0.7167894244194031, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.9258, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03619909502262444, | |
| "grad_norm": 0.7023014426231384, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.9272, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03720462543991956, | |
| "grad_norm": 0.7939850091934204, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.8852, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.038210155857214684, | |
| "grad_norm": 0.37145453691482544, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.8617, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 0.36598095297813416, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.8387, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04022121669180493, | |
| "grad_norm": 0.3641310930252075, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.8293, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04122674710910005, | |
| "grad_norm": 0.40900740027427673, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.8166, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.042232277526395176, | |
| "grad_norm": 0.40440893173217773, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.7699, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.043237807943690296, | |
| "grad_norm": 0.4703547954559326, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.789, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04424333836098542, | |
| "grad_norm": 0.3685894012451172, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.7647, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04524886877828054, | |
| "grad_norm": 0.36992567777633667, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.7527, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04625439919557567, | |
| "grad_norm": 0.8148142099380493, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.7516, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04725992961287079, | |
| "grad_norm": 2.1370339393615723, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.7484, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.048265460030165915, | |
| "grad_norm": 0.40228700637817383, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.7357, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.049270990447461034, | |
| "grad_norm": 0.6028892397880554, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.7278, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05027652086475616, | |
| "grad_norm": 0.35520774126052856, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.7097, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05027652086475616, | |
| "eval_loss": 0.7820449471473694, | |
| "eval_runtime": 145.6031, | |
| "eval_samples_per_second": 11.504, | |
| "eval_steps_per_second": 2.878, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 3.0911669731140137, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.7859, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05228758169934641, | |
| "grad_norm": 1.030360221862793, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.6146, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.053293112116641526, | |
| "grad_norm": 0.717653751373291, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.5158, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.05429864253393665, | |
| "grad_norm": 0.537287175655365, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.4709, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.05530417295123177, | |
| "grad_norm": 0.3627510368824005, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.4339, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0563097033685269, | |
| "grad_norm": 0.2506343424320221, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.4205, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05731523378582202, | |
| "grad_norm": 0.24423518776893616, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.4194, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.058320764203117145, | |
| "grad_norm": 0.29906725883483887, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.4156, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.059326294620412265, | |
| "grad_norm": 0.22299951314926147, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.4193, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.06033182503770739, | |
| "grad_norm": 0.20469671487808228, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.3833, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06133735545500251, | |
| "grad_norm": 0.25047266483306885, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.3803, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06234288587229764, | |
| "grad_norm": 0.17370571196079254, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.3761, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.06334841628959276, | |
| "grad_norm": 0.27698203921318054, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.3905, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.06435394670688788, | |
| "grad_norm": 0.14930705726146698, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.3794, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.06535947712418301, | |
| "grad_norm": 0.2859864830970764, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.4343, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06636500754147813, | |
| "grad_norm": 0.3993275761604309, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.2331, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.06737053795877325, | |
| "grad_norm": 2.1870105266571045, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.9635, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.7155138254165649, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.8389, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0693815987933635, | |
| "grad_norm": 0.3495980501174927, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.7636, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.07038712921065862, | |
| "grad_norm": 0.28488680720329285, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.779, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07139265962795374, | |
| "grad_norm": 0.321956068277359, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.7593, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.07239819004524888, | |
| "grad_norm": 0.30106544494628906, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.7582, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.073403720462544, | |
| "grad_norm": 0.2426968514919281, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.7843, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.07440925087983911, | |
| "grad_norm": 0.23462745547294617, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.7782, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.07541478129713423, | |
| "grad_norm": 0.19406434893608093, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.7624, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07642031171442937, | |
| "grad_norm": 0.2184755802154541, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.7927, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.07742584213172449, | |
| "grad_norm": 0.21943315863609314, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.7767, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 0.16851526498794556, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.7379, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.07943690296631473, | |
| "grad_norm": 0.19421535730361938, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.7925, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.08044243338360986, | |
| "grad_norm": 0.17354494333267212, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.7493, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08144796380090498, | |
| "grad_norm": 0.1771775633096695, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.7674, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0824534942182001, | |
| "grad_norm": 0.23186761140823364, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.7458, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.08345902463549522, | |
| "grad_norm": 0.19266724586486816, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.7253, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.08446455505279035, | |
| "grad_norm": 0.22116349637508392, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.7195, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 0.3103989064693451, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.8048, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.08647561588738059, | |
| "grad_norm": 0.443766713142395, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.7976, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.08748114630467571, | |
| "grad_norm": 0.7230583429336548, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.8926, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.08848667672197084, | |
| "grad_norm": 0.30479729175567627, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.8041, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.08949220713926596, | |
| "grad_norm": 0.2751973867416382, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.8375, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.09049773755656108, | |
| "grad_norm": 0.5401359796524048, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.7718, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0915032679738562, | |
| "grad_norm": 0.3586420714855194, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.7999, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.09250879839115134, | |
| "grad_norm": 0.26797112822532654, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.7566, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.09351432880844646, | |
| "grad_norm": 0.2583998739719391, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.7565, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.09451985922574158, | |
| "grad_norm": 0.258475661277771, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.7338, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0955253896430367, | |
| "grad_norm": 0.22778931260108948, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.7501, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.09653092006033183, | |
| "grad_norm": 0.27645596861839294, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.7565, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.09753645047762695, | |
| "grad_norm": 0.28205233812332153, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.7319, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.09854198089492207, | |
| "grad_norm": 0.23500730097293854, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.7307, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.09954751131221719, | |
| "grad_norm": 0.17771759629249573, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.7032, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.10055304172951232, | |
| "grad_norm": 0.36362266540527344, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.6929, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10055304172951232, | |
| "eval_loss": 0.771354079246521, | |
| "eval_runtime": 145.706, | |
| "eval_samples_per_second": 11.496, | |
| "eval_steps_per_second": 2.876, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10155857214680744, | |
| "grad_norm": 4.397695064544678, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 0.6436, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 0.6622849702835083, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.564, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.1035696329813977, | |
| "grad_norm": 0.38446009159088135, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 0.5081, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": 0.3722815215587616, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.4774, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.10558069381598793, | |
| "grad_norm": 0.3972223997116089, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4457, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.10658622423328305, | |
| "grad_norm": 0.3055289387702942, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.4365, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.10759175465057819, | |
| "grad_norm": 0.28584370017051697, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 0.4166, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.1085972850678733, | |
| "grad_norm": 0.30272936820983887, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.3847, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.10960281548516843, | |
| "grad_norm": 0.2166903167963028, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 0.3942, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.11060834590246355, | |
| "grad_norm": 0.22697070240974426, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.3818, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11161387631975868, | |
| "grad_norm": 0.3706066310405731, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.3955, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.1126194067370538, | |
| "grad_norm": 0.24521887302398682, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.3698, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.11362493715434892, | |
| "grad_norm": 0.20502431690692902, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 0.39, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.11463046757164404, | |
| "grad_norm": 0.3430691361427307, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.4146, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.11563599798893917, | |
| "grad_norm": 0.2945917844772339, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.3447, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.11664152840623429, | |
| "grad_norm": 0.8488739132881165, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.9821, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.6183751225471497, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.9052, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.11865258924082453, | |
| "grad_norm": 0.6295905709266663, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.8095, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.11965811965811966, | |
| "grad_norm": 0.658058226108551, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.7223, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.12066365007541478, | |
| "grad_norm": 0.3815332055091858, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.7446, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1216691804927099, | |
| "grad_norm": 0.45176973938941956, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.7509, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.12267471091000502, | |
| "grad_norm": 0.31807297468185425, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.7303, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.12368024132730016, | |
| "grad_norm": 0.20828258991241455, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.7336, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.12468577174459528, | |
| "grad_norm": 0.248319610953331, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.753, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.1256913021618904, | |
| "grad_norm": 0.2716839015483856, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.7684, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.12669683257918551, | |
| "grad_norm": 0.24676644802093506, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.7213, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.12770236299648063, | |
| "grad_norm": 0.21484322845935822, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.7585, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.12870789341377575, | |
| "grad_norm": 0.1997540146112442, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.7374, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.1297134238310709, | |
| "grad_norm": 0.149921715259552, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.749, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.13071895424836602, | |
| "grad_norm": 0.1527470201253891, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.7825, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.13172448466566114, | |
| "grad_norm": 0.19612222909927368, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.7622, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.13273001508295626, | |
| "grad_norm": 0.16798371076583862, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.7769, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.13373554550025138, | |
| "grad_norm": 0.1868869513273239, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.7331, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.1347410759175465, | |
| "grad_norm": 0.24473780393600464, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.7863, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.13574660633484162, | |
| "grad_norm": 1.1770341396331787, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.7561, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.6070170998573303, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.8728, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.13775766716943189, | |
| "grad_norm": 0.35857340693473816, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.7889, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.138763197586727, | |
| "grad_norm": 0.3490099608898163, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.7993, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.13976872800402212, | |
| "grad_norm": 0.3244432210922241, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.8064, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.14077425842131724, | |
| "grad_norm": 0.27973413467407227, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.7832, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14177978883861236, | |
| "grad_norm": 0.2573448717594147, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.7433, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.14278531925590748, | |
| "grad_norm": 0.2445351928472519, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.7559, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.1437908496732026, | |
| "grad_norm": 0.2401212453842163, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.7547, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.14479638009049775, | |
| "grad_norm": 0.2452555149793625, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.746, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.14580191050779287, | |
| "grad_norm": 0.22607146203517914, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.749, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.146807440925088, | |
| "grad_norm": 0.20661811530590057, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.7128, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.1478129713423831, | |
| "grad_norm": 0.20959605276584625, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.7274, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.14881850175967823, | |
| "grad_norm": 0.16401396691799164, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.7214, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.14982403217697335, | |
| "grad_norm": 0.23852993547916412, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.6941, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.15082956259426847, | |
| "grad_norm": 0.18602079153060913, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.6926, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15082956259426847, | |
| "eval_loss": 0.6435860395431519, | |
| "eval_runtime": 145.6929, | |
| "eval_samples_per_second": 11.497, | |
| "eval_steps_per_second": 2.876, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1518350930115636, | |
| "grad_norm": 0.7842530608177185, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 0.4952, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.15284062342885874, | |
| "grad_norm": 0.3953525424003601, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.4712, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 0.34699156880378723, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.4283, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.15485168426344897, | |
| "grad_norm": 0.38496196269989014, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.4285, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.1558572146807441, | |
| "grad_norm": 0.3960326611995697, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.4153, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 0.35928043723106384, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.3961, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.15786827551533433, | |
| "grad_norm": 0.29285934567451477, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 0.3993, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.15887380593262945, | |
| "grad_norm": 0.22251220047473907, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.3851, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.15987933634992457, | |
| "grad_norm": 0.1776050180196762, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.3823, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.16088486676721972, | |
| "grad_norm": 0.17631463706493378, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.3851, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16189039718451484, | |
| "grad_norm": 0.1705498844385147, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 0.3876, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.16289592760180996, | |
| "grad_norm": 0.15294431149959564, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.3824, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.16390145801910508, | |
| "grad_norm": 0.16084668040275574, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 0.3608, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.1649069884364002, | |
| "grad_norm": 0.15742041170597076, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.3634, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.16591251885369532, | |
| "grad_norm": 0.19664114713668823, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.418, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.16691804927099044, | |
| "grad_norm": 0.1666763573884964, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.3098, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.16792357968828556, | |
| "grad_norm": 0.6980152130126953, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.6121, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.1689291101055807, | |
| "grad_norm": 0.8880810737609863, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.8475, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.16993464052287582, | |
| "grad_norm": 0.7049257755279541, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.8096, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 0.8893566727638245, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.7073, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.17194570135746606, | |
| "grad_norm": 0.632365345954895, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.7652, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.17295123177476118, | |
| "grad_norm": 0.4807567894458771, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.7827, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.1739567621920563, | |
| "grad_norm": 0.39152318239212036, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.7443, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.17496229260935142, | |
| "grad_norm": 0.33642587065696716, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.7132, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.17596782302664657, | |
| "grad_norm": 0.2709258496761322, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.7636, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1769733534439417, | |
| "grad_norm": 0.17309905588626862, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.7783, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.1779788838612368, | |
| "grad_norm": 0.16790081560611725, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.7149, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.17898441427853193, | |
| "grad_norm": 0.34023764729499817, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.7298, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.17998994469582705, | |
| "grad_norm": 0.17412666976451874, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.7728, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.18099547511312217, | |
| "grad_norm": 0.20930814743041992, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.7676, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1820010055304173, | |
| "grad_norm": 0.2295064926147461, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.7385, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.1830065359477124, | |
| "grad_norm": 0.2699348032474518, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.7632, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.18401206636500755, | |
| "grad_norm": 0.3166503310203552, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.7743, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.18501759678230267, | |
| "grad_norm": 0.3734043836593628, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.7387, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.1860231271995978, | |
| "grad_norm": 0.45459139347076416, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.742, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.1870286576168929, | |
| "grad_norm": 0.5523736476898193, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.664, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.18803418803418803, | |
| "grad_norm": 0.5295714139938354, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.8219, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.18903971845148315, | |
| "grad_norm": 0.37779638171195984, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.7826, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.19004524886877827, | |
| "grad_norm": 0.7088306546211243, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.777, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.1910507792860734, | |
| "grad_norm": 0.4527333676815033, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.7649, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.19205630970336854, | |
| "grad_norm": 0.3630281686782837, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.7508, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.19306184012066366, | |
| "grad_norm": 0.45705729722976685, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.7721, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.19406737053795878, | |
| "grad_norm": 0.3677905797958374, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.7238, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.1950729009552539, | |
| "grad_norm": 0.2898189425468445, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.7302, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.19607843137254902, | |
| "grad_norm": 0.287230908870697, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.7176, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.19708396178984414, | |
| "grad_norm": 0.2932420074939728, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.7449, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.19808949220713926, | |
| "grad_norm": 0.22437305748462677, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.7201, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.19909502262443438, | |
| "grad_norm": 0.2605840265750885, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.7131, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.20010055304172952, | |
| "grad_norm": 0.22857801616191864, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.7036, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.20110608345902464, | |
| "grad_norm": 0.2576086223125458, | |
| "learning_rate": 0.0, | |
| "loss": 0.6928, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20110608345902464, | |
| "eval_loss": 0.6336299180984497, | |
| "eval_runtime": 145.4313, | |
| "eval_samples_per_second": 11.517, | |
| "eval_steps_per_second": 2.881, | |
| "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": 1.657472104267776e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |