Instructions to use wonwonn/diversity_base_200 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use wonwonn/diversity_base_200 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct") model = PeftModel.from_pretrained(base_model, "wonwonn/diversity_base_200") - Transformers
How to use wonwonn/diversity_base_200 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wonwonn/diversity_base_200") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("wonwonn/diversity_base_200", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use wonwonn/diversity_base_200 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wonwonn/diversity_base_200" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wonwonn/diversity_base_200", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/wonwonn/diversity_base_200
- SGLang
How to use wonwonn/diversity_base_200 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "wonwonn/diversity_base_200" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wonwonn/diversity_base_200", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "wonwonn/diversity_base_200" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wonwonn/diversity_base_200", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use wonwonn/diversity_base_200 with Docker Model Runner:
docker model run hf.co/wonwonn/diversity_base_200
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5755395683453237, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0028776978417266188, | |
| "grad_norm": 0.4268543749983206, | |
| "learning_rate": 0.0, | |
| "loss": 1.3486042022705078, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0057553956834532375, | |
| "grad_norm": 0.3883090191847927, | |
| "learning_rate": 5.714285714285714e-08, | |
| "loss": 1.2684719562530518, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008633093525179856, | |
| "grad_norm": 0.4433012322855463, | |
| "learning_rate": 1.1428571428571427e-07, | |
| "loss": 1.1761300563812256, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011510791366906475, | |
| "grad_norm": 0.423821859313677, | |
| "learning_rate": 1.7142857142857143e-07, | |
| "loss": 1.1812039613723755, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014388489208633094, | |
| "grad_norm": 0.3726893939340183, | |
| "learning_rate": 2.2857142857142855e-07, | |
| "loss": 1.1689704656600952, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017266187050359712, | |
| "grad_norm": 0.36142045807258394, | |
| "learning_rate": 2.857142857142857e-07, | |
| "loss": 1.1109519004821777, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02014388489208633, | |
| "grad_norm": 0.3827461458540309, | |
| "learning_rate": 3.4285714285714286e-07, | |
| "loss": 1.1866692304611206, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02302158273381295, | |
| "grad_norm": 0.4308096064854969, | |
| "learning_rate": 4e-07, | |
| "loss": 1.184255838394165, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.025899280575539568, | |
| "grad_norm": 0.4132507875975126, | |
| "learning_rate": 4.571428571428571e-07, | |
| "loss": 1.216016173362732, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02877697841726619, | |
| "grad_norm": 0.4227650438538138, | |
| "learning_rate": 5.142857142857142e-07, | |
| "loss": 1.075126051902771, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.031654676258992806, | |
| "grad_norm": 0.4534213697091446, | |
| "learning_rate": 5.714285714285714e-07, | |
| "loss": 1.2043604850769043, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.034532374100719423, | |
| "grad_norm": 0.34013283056384314, | |
| "learning_rate": 6.285714285714286e-07, | |
| "loss": 1.1965858936309814, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03741007194244604, | |
| "grad_norm": 0.38292557373739694, | |
| "learning_rate": 6.857142857142857e-07, | |
| "loss": 1.2496683597564697, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04028776978417266, | |
| "grad_norm": 0.3313065310821612, | |
| "learning_rate": 7.428571428571429e-07, | |
| "loss": 1.1443971395492554, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04316546762589928, | |
| "grad_norm": 0.3491559182363408, | |
| "learning_rate": 8e-07, | |
| "loss": 1.1878836154937744, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0460431654676259, | |
| "grad_norm": 0.3641029856085241, | |
| "learning_rate": 8.57142857142857e-07, | |
| "loss": 1.1661304235458374, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04892086330935252, | |
| "grad_norm": 0.34920739079329194, | |
| "learning_rate": 9.142857142857142e-07, | |
| "loss": 1.136901617050171, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.051798561151079135, | |
| "grad_norm": 0.3247811101333292, | |
| "learning_rate": 9.714285714285715e-07, | |
| "loss": 1.1800942420959473, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05467625899280575, | |
| "grad_norm": 0.3624049468846375, | |
| "learning_rate": 1.0285714285714284e-06, | |
| "loss": 1.2698850631713867, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05755395683453238, | |
| "grad_norm": 0.3795159204565531, | |
| "learning_rate": 1.0857142857142856e-06, | |
| "loss": 1.1252480745315552, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.060431654676258995, | |
| "grad_norm": 0.3919545762127951, | |
| "learning_rate": 1.1428571428571428e-06, | |
| "loss": 1.2633826732635498, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06330935251798561, | |
| "grad_norm": 0.39101333055518667, | |
| "learning_rate": 1.2e-06, | |
| "loss": 1.129035472869873, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06618705035971223, | |
| "grad_norm": 0.35619367974173366, | |
| "learning_rate": 1.2571428571428571e-06, | |
| "loss": 1.2145458459854126, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06906474820143885, | |
| "grad_norm": 0.40015862605747804, | |
| "learning_rate": 1.3142857142857143e-06, | |
| "loss": 1.3340139389038086, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07194244604316546, | |
| "grad_norm": 0.36097464342345337, | |
| "learning_rate": 1.3714285714285715e-06, | |
| "loss": 1.2273904085159302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07482014388489208, | |
| "grad_norm": 0.3889907277644104, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 1.18831467628479, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0776978417266187, | |
| "grad_norm": 0.46087979890923375, | |
| "learning_rate": 1.4857142857142858e-06, | |
| "loss": 1.1542699337005615, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08057553956834532, | |
| "grad_norm": 0.4132863028933459, | |
| "learning_rate": 1.5428571428571428e-06, | |
| "loss": 1.1673165559768677, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08345323741007195, | |
| "grad_norm": 0.4255951689193774, | |
| "learning_rate": 1.6e-06, | |
| "loss": 1.0518189668655396, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08633093525179857, | |
| "grad_norm": 0.40669935687665315, | |
| "learning_rate": 1.657142857142857e-06, | |
| "loss": 1.290560245513916, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08920863309352518, | |
| "grad_norm": 0.42897063247042705, | |
| "learning_rate": 1.714285714285714e-06, | |
| "loss": 1.1954505443572998, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0920863309352518, | |
| "grad_norm": 0.4503515087044223, | |
| "learning_rate": 1.7714285714285712e-06, | |
| "loss": 1.230522632598877, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09496402877697842, | |
| "grad_norm": 0.44106336628597087, | |
| "learning_rate": 1.8285714285714284e-06, | |
| "loss": 1.2302124500274658, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09784172661870504, | |
| "grad_norm": 0.4096595807328641, | |
| "learning_rate": 1.8857142857142856e-06, | |
| "loss": 1.241065263748169, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10071942446043165, | |
| "grad_norm": 0.42763917088656206, | |
| "learning_rate": 1.942857142857143e-06, | |
| "loss": 1.20895254611969, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10359712230215827, | |
| "grad_norm": 0.38403908133420794, | |
| "learning_rate": 2e-06, | |
| "loss": 1.3262802362442017, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10647482014388489, | |
| "grad_norm": 0.390516732544303, | |
| "learning_rate": 1.999988705525916e-06, | |
| "loss": 1.1434489488601685, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1093525179856115, | |
| "grad_norm": 0.39024772430861926, | |
| "learning_rate": 1.9999548223587944e-06, | |
| "loss": 1.0919324159622192, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11223021582733812, | |
| "grad_norm": 0.45604382256971515, | |
| "learning_rate": 1.9998983512640208e-06, | |
| "loss": 1.19603431224823, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11510791366906475, | |
| "grad_norm": 0.4679033197351337, | |
| "learning_rate": 1.9998192935172177e-06, | |
| "loss": 1.267903208732605, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11798561151079137, | |
| "grad_norm": 0.41358258709049733, | |
| "learning_rate": 1.9997176509042157e-06, | |
| "loss": 1.2280285358428955, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12086330935251799, | |
| "grad_norm": 0.42615926425808337, | |
| "learning_rate": 1.9995934257210153e-06, | |
| "loss": 1.161034345626831, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1237410071942446, | |
| "grad_norm": 0.37673217800099756, | |
| "learning_rate": 1.9994466207737324e-06, | |
| "loss": 1.1742950677871704, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12661870503597122, | |
| "grad_norm": 0.36511622795555954, | |
| "learning_rate": 1.9992772393785363e-06, | |
| "loss": 1.0468149185180664, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12949640287769784, | |
| "grad_norm": 0.4130821233225653, | |
| "learning_rate": 1.9990852853615746e-06, | |
| "loss": 1.2955734729766846, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13237410071942446, | |
| "grad_norm": 0.4063317592263896, | |
| "learning_rate": 1.9988707630588874e-06, | |
| "loss": 1.1378052234649658, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13525179856115108, | |
| "grad_norm": 0.41418928467527555, | |
| "learning_rate": 1.9986336773163066e-06, | |
| "loss": 1.1969021558761597, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1381294964028777, | |
| "grad_norm": 0.4518461323768013, | |
| "learning_rate": 1.99837403348935e-06, | |
| "loss": 1.1916333436965942, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1410071942446043, | |
| "grad_norm": 0.48627159448841495, | |
| "learning_rate": 1.9980918374430994e-06, | |
| "loss": 1.1525160074234009, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14388489208633093, | |
| "grad_norm": 0.4661595855455116, | |
| "learning_rate": 1.997787095552066e-06, | |
| "loss": 1.209150791168213, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14676258992805755, | |
| "grad_norm": 0.4486660757069457, | |
| "learning_rate": 1.9974598147000487e-06, | |
| "loss": 1.2794744968414307, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.14964028776978416, | |
| "grad_norm": 0.408265480450518, | |
| "learning_rate": 1.997110002279978e-06, | |
| "loss": 1.2373850345611572, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.15251798561151078, | |
| "grad_norm": 0.4147055013786096, | |
| "learning_rate": 1.9967376661937477e-06, | |
| "loss": 1.1746478080749512, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1553956834532374, | |
| "grad_norm": 0.5423569605141699, | |
| "learning_rate": 1.9963428148520393e-06, | |
| "loss": 1.1579411029815674, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.15827338129496402, | |
| "grad_norm": 0.4260571724263023, | |
| "learning_rate": 1.9959254571741285e-06, | |
| "loss": 1.2749133110046387, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.16115107913669063, | |
| "grad_norm": 0.4509771053826677, | |
| "learning_rate": 1.995485602587687e-06, | |
| "loss": 1.26259183883667, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.16402877697841728, | |
| "grad_norm": 0.5521268337744372, | |
| "learning_rate": 1.995023261028567e-06, | |
| "loss": 1.1529275178909302, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1669064748201439, | |
| "grad_norm": 0.43065407373443115, | |
| "learning_rate": 1.9945384429405776e-06, | |
| "loss": 1.26717209815979, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1697841726618705, | |
| "grad_norm": 0.47792887272228685, | |
| "learning_rate": 1.99403115927525e-06, | |
| "loss": 1.2685507535934448, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.17266187050359713, | |
| "grad_norm": 0.4240112954518359, | |
| "learning_rate": 1.9935014214915883e-06, | |
| "loss": 1.2015361785888672, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17553956834532375, | |
| "grad_norm": 0.4496707820180445, | |
| "learning_rate": 1.992949241555812e-06, | |
| "loss": 1.1896259784698486, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.17841726618705037, | |
| "grad_norm": 0.5453330480067436, | |
| "learning_rate": 1.9923746319410847e-06, | |
| "loss": 1.2229057550430298, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.18129496402877698, | |
| "grad_norm": 0.3998204498071122, | |
| "learning_rate": 1.991777605627234e-06, | |
| "loss": 1.0739102363586426, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1841726618705036, | |
| "grad_norm": 0.4862893749078524, | |
| "learning_rate": 1.9911581761004556e-06, | |
| "loss": 1.2118332386016846, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.18705035971223022, | |
| "grad_norm": 0.5280265302960552, | |
| "learning_rate": 1.990516357353011e-06, | |
| "loss": 1.2767584323883057, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.18992805755395684, | |
| "grad_norm": 0.5303178829072359, | |
| "learning_rate": 1.989852163882911e-06, | |
| "loss": 1.1722222566604614, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.19280575539568345, | |
| "grad_norm": 0.530648491497219, | |
| "learning_rate": 1.9891656106935873e-06, | |
| "loss": 1.1462490558624268, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.19568345323741007, | |
| "grad_norm": 0.4445003702811293, | |
| "learning_rate": 1.988456713293554e-06, | |
| "loss": 1.1741344928741455, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1985611510791367, | |
| "grad_norm": 0.5079121008725791, | |
| "learning_rate": 1.987725487696059e-06, | |
| "loss": 1.300689935684204, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2014388489208633, | |
| "grad_norm": 0.5118265151839159, | |
| "learning_rate": 1.9869719504187175e-06, | |
| "loss": 1.2715141773223877, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.20431654676258992, | |
| "grad_norm": 0.4659364291899321, | |
| "learning_rate": 1.9861961184831453e-06, | |
| "loss": 1.2462115287780762, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.20719424460431654, | |
| "grad_norm": 0.5323278980485148, | |
| "learning_rate": 1.9853980094145696e-06, | |
| "loss": 1.1924316883087158, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.21007194244604316, | |
| "grad_norm": 0.5307636012979421, | |
| "learning_rate": 1.9845776412414346e-06, | |
| "loss": 1.181901216506958, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.21294964028776978, | |
| "grad_norm": 0.39819582395279496, | |
| "learning_rate": 1.9837350324949944e-06, | |
| "loss": 1.055637001991272, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2158273381294964, | |
| "grad_norm": 0.5027833769729672, | |
| "learning_rate": 1.9828702022088942e-06, | |
| "loss": 1.1969636678695679, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.218705035971223, | |
| "grad_norm": 0.5112851149007495, | |
| "learning_rate": 1.9819831699187407e-06, | |
| "loss": 1.2725424766540527, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.22158273381294963, | |
| "grad_norm": 0.5157386153313658, | |
| "learning_rate": 1.9810739556616607e-06, | |
| "loss": 1.1510074138641357, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.22446043165467625, | |
| "grad_norm": 0.4976799100709907, | |
| "learning_rate": 1.980142579975847e-06, | |
| "loss": 1.1272646188735962, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2273381294964029, | |
| "grad_norm": 0.5209100319428271, | |
| "learning_rate": 1.9791890639000973e-06, | |
| "loss": 1.1251168251037598, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2302158273381295, | |
| "grad_norm": 0.5016076184640756, | |
| "learning_rate": 1.9782134289733374e-06, | |
| "loss": 1.259020447731018, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23309352517985613, | |
| "grad_norm": 0.5000696786317257, | |
| "learning_rate": 1.9772156972341326e-06, | |
| "loss": 1.1942812204360962, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.23597122302158274, | |
| "grad_norm": 0.431209395351534, | |
| "learning_rate": 1.9761958912201945e-06, | |
| "loss": 1.1250073909759521, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.23884892086330936, | |
| "grad_norm": 0.49600812252688903, | |
| "learning_rate": 1.9751540339678683e-06, | |
| "loss": 1.0165443420410156, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.24172661870503598, | |
| "grad_norm": 0.6103050780883177, | |
| "learning_rate": 1.9740901490116133e-06, | |
| "loss": 1.1725817918777466, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2446043165467626, | |
| "grad_norm": 0.5153944876109913, | |
| "learning_rate": 1.973004260383471e-06, | |
| "loss": 1.2236909866333008, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2474820143884892, | |
| "grad_norm": 0.5699516336344729, | |
| "learning_rate": 1.9718963926125244e-06, | |
| "loss": 1.0934271812438965, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.2503597122302158, | |
| "grad_norm": 0.6364499492788651, | |
| "learning_rate": 1.9707665707243406e-06, | |
| "loss": 1.2964831590652466, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.25323741007194245, | |
| "grad_norm": 0.5873104786392525, | |
| "learning_rate": 1.969614820240407e-06, | |
| "loss": 1.187952995300293, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.25611510791366904, | |
| "grad_norm": 0.47749017544117933, | |
| "learning_rate": 1.9684411671775568e-06, | |
| "loss": 1.1036763191223145, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.2589928057553957, | |
| "grad_norm": 0.6373304322412259, | |
| "learning_rate": 1.967245638047378e-06, | |
| "loss": 1.128540277481079, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.26187050359712233, | |
| "grad_norm": 0.5390287293852468, | |
| "learning_rate": 1.9660282598556155e-06, | |
| "loss": 1.1319843530654907, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.2647482014388489, | |
| "grad_norm": 0.5759029228083498, | |
| "learning_rate": 1.964789060101563e-06, | |
| "loss": 1.1634244918823242, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.26762589928057556, | |
| "grad_norm": 0.5008926715677038, | |
| "learning_rate": 1.9635280667774385e-06, | |
| "loss": 1.069319486618042, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.27050359712230215, | |
| "grad_norm": 0.4944260632303085, | |
| "learning_rate": 1.9622453083677555e-06, | |
| "loss": 1.0734496116638184, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2733812949640288, | |
| "grad_norm": 0.6343198383253205, | |
| "learning_rate": 1.9609408138486773e-06, | |
| "loss": 1.1902985572814941, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2762589928057554, | |
| "grad_norm": 0.5688350191125725, | |
| "learning_rate": 1.959614612687363e-06, | |
| "loss": 1.1192796230316162, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.27913669064748203, | |
| "grad_norm": 0.5010927783887094, | |
| "learning_rate": 1.9582667348413013e-06, | |
| "loss": 1.18692946434021, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.2820143884892086, | |
| "grad_norm": 0.5632414534697942, | |
| "learning_rate": 1.9568972107576355e-06, | |
| "loss": 1.123215675354004, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.28489208633093527, | |
| "grad_norm": 0.5256142159951962, | |
| "learning_rate": 1.9555060713724737e-06, | |
| "loss": 1.0921350717544556, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.28776978417266186, | |
| "grad_norm": 0.5769884107294132, | |
| "learning_rate": 1.9540933481101923e-06, | |
| "loss": 1.1709322929382324, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2906474820143885, | |
| "grad_norm": 0.5079692506070075, | |
| "learning_rate": 1.952659072882723e-06, | |
| "loss": 1.1703360080718994, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.2935251798561151, | |
| "grad_norm": 0.5075719422001728, | |
| "learning_rate": 1.9512032780888346e-06, | |
| "loss": 1.2004872560501099, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.29640287769784174, | |
| "grad_norm": 0.4618161823401604, | |
| "learning_rate": 1.9497259966134005e-06, | |
| "loss": 1.100082278251648, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.2992805755395683, | |
| "grad_norm": 0.5868224961352833, | |
| "learning_rate": 1.9482272618266554e-06, | |
| "loss": 1.1757385730743408, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.302158273381295, | |
| "grad_norm": 0.565948095750891, | |
| "learning_rate": 1.946707107583442e-06, | |
| "loss": 1.1053205728530884, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.30503597122302156, | |
| "grad_norm": 0.5719871998003366, | |
| "learning_rate": 1.945165568222445e-06, | |
| "loss": 1.2135543823242188, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.3079136690647482, | |
| "grad_norm": 0.5372517039984259, | |
| "learning_rate": 1.9436026785654175e-06, | |
| "loss": 1.092635154724121, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.3107913669064748, | |
| "grad_norm": 0.5351702454729531, | |
| "learning_rate": 1.942018473916393e-06, | |
| "loss": 1.1439979076385498, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.31366906474820144, | |
| "grad_norm": 0.5974563261966084, | |
| "learning_rate": 1.940412990060888e-06, | |
| "loss": 1.2251625061035156, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.31654676258992803, | |
| "grad_norm": 0.46712359174501966, | |
| "learning_rate": 1.9387862632650944e-06, | |
| "loss": 1.162185549736023, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3194244604316547, | |
| "grad_norm": 0.5854527267590803, | |
| "learning_rate": 1.937138330275059e-06, | |
| "loss": 1.1841859817504883, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.32230215827338127, | |
| "grad_norm": 0.5233684999557666, | |
| "learning_rate": 1.9354692283158553e-06, | |
| "loss": 1.123387336730957, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.3251798561151079, | |
| "grad_norm": 0.5492791380155028, | |
| "learning_rate": 1.9337789950907407e-06, | |
| "loss": 1.0858070850372314, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.32805755395683456, | |
| "grad_norm": 0.4557781709412145, | |
| "learning_rate": 1.9320676687803055e-06, | |
| "loss": 1.0631603002548218, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.33093525179856115, | |
| "grad_norm": 0.4162627353186177, | |
| "learning_rate": 1.930335288041612e-06, | |
| "loss": 1.1065043210983276, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3338129496402878, | |
| "grad_norm": 0.48788670081079566, | |
| "learning_rate": 1.928581892007318e-06, | |
| "loss": 1.0199726819992065, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.3366906474820144, | |
| "grad_norm": 0.42019688757208695, | |
| "learning_rate": 1.926807520284796e-06, | |
| "loss": 1.081688404083252, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.339568345323741, | |
| "grad_norm": 0.532979520066663, | |
| "learning_rate": 1.9250122129552364e-06, | |
| "loss": 1.1081211566925049, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.3424460431654676, | |
| "grad_norm": 0.5030802624613613, | |
| "learning_rate": 1.923196010572744e-06, | |
| "loss": 1.1390955448150635, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.34532374100719426, | |
| "grad_norm": 0.44914726964201973, | |
| "learning_rate": 1.92135895416342e-06, | |
| "loss": 1.1776988506317139, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.34820143884892085, | |
| "grad_norm": 0.501909570928216, | |
| "learning_rate": 1.9195010852244366e-06, | |
| "loss": 1.1236053705215454, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3510791366906475, | |
| "grad_norm": 0.36739986646990347, | |
| "learning_rate": 1.917622445723099e-06, | |
| "loss": 0.9320216774940491, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3539568345323741, | |
| "grad_norm": 0.5061126945798536, | |
| "learning_rate": 1.9157230780958975e-06, | |
| "loss": 1.126027226448059, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.35683453237410073, | |
| "grad_norm": 0.4884645880864055, | |
| "learning_rate": 1.9138030252475484e-06, | |
| "loss": 1.081748127937317, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3597122302158273, | |
| "grad_norm": 0.5667653305619992, | |
| "learning_rate": 1.911862330550027e-06, | |
| "loss": 1.1543316841125488, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.36258992805755397, | |
| "grad_norm": 0.4850898662003825, | |
| "learning_rate": 1.9099010378415844e-06, | |
| "loss": 0.9856457710266113, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.36546762589928056, | |
| "grad_norm": 0.5995443403463827, | |
| "learning_rate": 1.90791919142576e-06, | |
| "loss": 1.057324767112732, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.3683453237410072, | |
| "grad_norm": 0.47772823299472444, | |
| "learning_rate": 1.9059168360703803e-06, | |
| "loss": 1.0581177473068237, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.3712230215827338, | |
| "grad_norm": 0.4728036445810035, | |
| "learning_rate": 1.9038940170065466e-06, | |
| "loss": 1.2074534893035889, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.37410071942446044, | |
| "grad_norm": 0.4271600145083479, | |
| "learning_rate": 1.9018507799276131e-06, | |
| "loss": 0.9659124612808228, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.376978417266187, | |
| "grad_norm": 0.48084227705281535, | |
| "learning_rate": 1.8997871709881567e-06, | |
| "loss": 1.0536625385284424, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.37985611510791367, | |
| "grad_norm": 0.4904685471564639, | |
| "learning_rate": 1.8977032368029332e-06, | |
| "loss": 1.0027377605438232, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.38273381294964026, | |
| "grad_norm": 0.5008569796785156, | |
| "learning_rate": 1.8955990244458233e-06, | |
| "loss": 1.11732816696167, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.3856115107913669, | |
| "grad_norm": 0.5573439888206672, | |
| "learning_rate": 1.8934745814487712e-06, | |
| "loss": 1.0723323822021484, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.38848920863309355, | |
| "grad_norm": 0.4998369270086412, | |
| "learning_rate": 1.8913299558007095e-06, | |
| "loss": 1.181422472000122, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.39136690647482014, | |
| "grad_norm": 0.4375775959034456, | |
| "learning_rate": 1.8891651959464758e-06, | |
| "loss": 1.026265025138855, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3942446043165468, | |
| "grad_norm": 0.47392252251172784, | |
| "learning_rate": 1.8869803507857185e-06, | |
| "loss": 1.1072031259536743, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.3971223021582734, | |
| "grad_norm": 0.4615974171855204, | |
| "learning_rate": 1.884775469671791e-06, | |
| "loss": 1.1870160102844238, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.4849662180937002, | |
| "learning_rate": 1.8825506024106396e-06, | |
| "loss": 1.0357952117919922, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.4028776978417266, | |
| "grad_norm": 0.4631538201072282, | |
| "learning_rate": 1.8803057992596747e-06, | |
| "loss": 1.07905912399292, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.40575539568345326, | |
| "grad_norm": 0.4282127435540379, | |
| "learning_rate": 1.8780411109266385e-06, | |
| "loss": 1.1036255359649658, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.40863309352517985, | |
| "grad_norm": 0.4069493219082804, | |
| "learning_rate": 1.8757565885684584e-06, | |
| "loss": 1.0308234691619873, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.4115107913669065, | |
| "grad_norm": 0.3598387804724348, | |
| "learning_rate": 1.8734522837900915e-06, | |
| "loss": 0.9832173585891724, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.4143884892086331, | |
| "grad_norm": 0.48868535540214775, | |
| "learning_rate": 1.8711282486433594e-06, | |
| "loss": 1.1871904134750366, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.4172661870503597, | |
| "grad_norm": 0.39516498249793663, | |
| "learning_rate": 1.8687845356257705e-06, | |
| "loss": 1.00008225440979, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.4201438848920863, | |
| "grad_norm": 0.4351515967198778, | |
| "learning_rate": 1.866421197679338e-06, | |
| "loss": 1.112741231918335, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.42302158273381296, | |
| "grad_norm": 0.42034365587434525, | |
| "learning_rate": 1.8640382881893797e-06, | |
| "loss": 0.932329535484314, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.42589928057553955, | |
| "grad_norm": 0.496792520277127, | |
| "learning_rate": 1.8616358609833144e-06, | |
| "loss": 1.1855289936065674, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.4287769784172662, | |
| "grad_norm": 0.5022145005069215, | |
| "learning_rate": 1.8592139703294456e-06, | |
| "loss": 1.125049352645874, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.4316546762589928, | |
| "grad_norm": 0.4329193295780338, | |
| "learning_rate": 1.8567726709357365e-06, | |
| "loss": 1.0438380241394043, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.43453237410071943, | |
| "grad_norm": 0.42896620295246946, | |
| "learning_rate": 1.854312017948572e-06, | |
| "loss": 1.0002976655960083, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.437410071942446, | |
| "grad_norm": 0.4172511129278549, | |
| "learning_rate": 1.8518320669515145e-06, | |
| "loss": 1.0555000305175781, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.44028776978417267, | |
| "grad_norm": 0.37790831769202976, | |
| "learning_rate": 1.8493328739640494e-06, | |
| "loss": 1.183078408241272, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.44316546762589926, | |
| "grad_norm": 0.4824957472322815, | |
| "learning_rate": 1.8468144954403174e-06, | |
| "loss": 1.0227148532867432, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.4460431654676259, | |
| "grad_norm": 0.4081862560981704, | |
| "learning_rate": 1.8442769882678397e-06, | |
| "loss": 1.064920425415039, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.4489208633093525, | |
| "grad_norm": 0.43104347215658256, | |
| "learning_rate": 1.8417204097662348e-06, | |
| "loss": 0.9629471302032471, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.45179856115107914, | |
| "grad_norm": 0.4260643628313932, | |
| "learning_rate": 1.8391448176859221e-06, | |
| "loss": 0.9961265921592712, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.4546762589928058, | |
| "grad_norm": 0.38706922989312564, | |
| "learning_rate": 1.8365502702068176e-06, | |
| "loss": 0.9955669641494751, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.45755395683453237, | |
| "grad_norm": 0.42253037547232236, | |
| "learning_rate": 1.8339368259370196e-06, | |
| "loss": 1.1107442378997803, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.460431654676259, | |
| "grad_norm": 0.4082948405877952, | |
| "learning_rate": 1.8313045439114854e-06, | |
| "loss": 1.083999752998352, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4633093525179856, | |
| "grad_norm": 0.5086933746905393, | |
| "learning_rate": 1.8286534835906967e-06, | |
| "loss": 0.9459039568901062, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.46618705035971225, | |
| "grad_norm": 0.5290067256195594, | |
| "learning_rate": 1.8259837048593187e-06, | |
| "loss": 1.0736985206604004, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.46906474820143884, | |
| "grad_norm": 0.4473816183394209, | |
| "learning_rate": 1.8232952680248439e-06, | |
| "loss": 1.113641619682312, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.4719424460431655, | |
| "grad_norm": 0.3648549425761286, | |
| "learning_rate": 1.8205882338162333e-06, | |
| "loss": 1.0131745338439941, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.4748201438848921, | |
| "grad_norm": 0.418714277276974, | |
| "learning_rate": 1.8178626633825417e-06, | |
| "loss": 1.0794405937194824, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4776978417266187, | |
| "grad_norm": 0.493363968370368, | |
| "learning_rate": 1.8151186182915383e-06, | |
| "loss": 1.0569260120391846, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.4805755395683453, | |
| "grad_norm": 0.40639014051980893, | |
| "learning_rate": 1.8123561605283163e-06, | |
| "loss": 0.9135780930519104, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.48345323741007196, | |
| "grad_norm": 0.3370540246110779, | |
| "learning_rate": 1.8095753524938903e-06, | |
| "loss": 1.0848565101623535, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.48633093525179855, | |
| "grad_norm": 0.4089743524651253, | |
| "learning_rate": 1.8067762570037885e-06, | |
| "loss": 1.042203664779663, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.4892086330935252, | |
| "grad_norm": 0.3488290801074521, | |
| "learning_rate": 1.8039589372866347e-06, | |
| "loss": 1.0144762992858887, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4920863309352518, | |
| "grad_norm": 0.4415145873981567, | |
| "learning_rate": 1.8011234569827172e-06, | |
| "loss": 1.0598516464233398, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.4949640287769784, | |
| "grad_norm": 0.4086125367839349, | |
| "learning_rate": 1.798269880142554e-06, | |
| "loss": 1.0271472930908203, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.497841726618705, | |
| "grad_norm": 0.4151556739368533, | |
| "learning_rate": 1.7953982712254446e-06, | |
| "loss": 1.144386887550354, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.5007194244604316, | |
| "grad_norm": 0.3557003164456043, | |
| "learning_rate": 1.7925086950980134e-06, | |
| "loss": 1.0051202774047852, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.5035971223021583, | |
| "grad_norm": 0.4674840144255213, | |
| "learning_rate": 1.7896012170327466e-06, | |
| "loss": 1.0651477575302124, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.5064748201438849, | |
| "grad_norm": 0.38157836752138746, | |
| "learning_rate": 1.7866759027065149e-06, | |
| "loss": 1.0956120491027832, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.5093525179856115, | |
| "grad_norm": 0.46192787245391354, | |
| "learning_rate": 1.783732818199092e-06, | |
| "loss": 1.1663614511489868, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.5122302158273381, | |
| "grad_norm": 0.4346365414730697, | |
| "learning_rate": 1.7807720299916613e-06, | |
| "loss": 1.051661729812622, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.5151079136690647, | |
| "grad_norm": 0.45336507778223883, | |
| "learning_rate": 1.7777936049653146e-06, | |
| "loss": 0.9809316396713257, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.5179856115107914, | |
| "grad_norm": 0.3898837595041978, | |
| "learning_rate": 1.77479761039954e-06, | |
| "loss": 1.0009634494781494, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.520863309352518, | |
| "grad_norm": 0.38037522656773876, | |
| "learning_rate": 1.7717841139707038e-06, | |
| "loss": 1.1045811176300049, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.5237410071942447, | |
| "grad_norm": 0.40859760122894645, | |
| "learning_rate": 1.76875318375052e-06, | |
| "loss": 0.9246672987937927, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.5266187050359712, | |
| "grad_norm": 0.39273312912796315, | |
| "learning_rate": 1.7657048882045149e-06, | |
| "loss": 1.0762555599212646, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.5294964028776978, | |
| "grad_norm": 0.4361065191584471, | |
| "learning_rate": 1.7626392961904783e-06, | |
| "loss": 1.1039854288101196, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.5323741007194245, | |
| "grad_norm": 0.42238136460316994, | |
| "learning_rate": 1.7595564769569094e-06, | |
| "loss": 0.9751594066619873, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.5352517985611511, | |
| "grad_norm": 0.34120770103018966, | |
| "learning_rate": 1.7564565001414522e-06, | |
| "loss": 0.8274255990982056, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.5381294964028777, | |
| "grad_norm": 0.3381352803522102, | |
| "learning_rate": 1.753339435769322e-06, | |
| "loss": 1.1029226779937744, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.5410071942446043, | |
| "grad_norm": 0.37871201572790575, | |
| "learning_rate": 1.7502053542517244e-06, | |
| "loss": 1.0747345685958862, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.543884892086331, | |
| "grad_norm": 0.3735857529725458, | |
| "learning_rate": 1.7470543263842642e-06, | |
| "loss": 1.1121901273727417, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.5467625899280576, | |
| "grad_norm": 0.39152871131797023, | |
| "learning_rate": 1.7438864233453473e-06, | |
| "loss": 1.1265859603881836, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5496402877697841, | |
| "grad_norm": 0.3139492113451776, | |
| "learning_rate": 1.7407017166945706e-06, | |
| "loss": 1.0492033958435059, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.5525179856115108, | |
| "grad_norm": 0.31611199876337126, | |
| "learning_rate": 1.7375002783711076e-06, | |
| "loss": 0.9355713725090027, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.5553956834532374, | |
| "grad_norm": 0.33404471627590043, | |
| "learning_rate": 1.7342821806920829e-06, | |
| "loss": 1.0717079639434814, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.5582733812949641, | |
| "grad_norm": 0.34631687569300423, | |
| "learning_rate": 1.7310474963509378e-06, | |
| "loss": 1.0480934381484985, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.5611510791366906, | |
| "grad_norm": 0.3862278493779809, | |
| "learning_rate": 1.72779629841579e-06, | |
| "loss": 0.9718694090843201, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5640287769784172, | |
| "grad_norm": 0.37948630342948375, | |
| "learning_rate": 1.7245286603277803e-06, | |
| "loss": 1.0329382419586182, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.5669064748201439, | |
| "grad_norm": 0.3963495794810709, | |
| "learning_rate": 1.721244655899416e-06, | |
| "loss": 0.9934196472167969, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.5697841726618705, | |
| "grad_norm": 0.34084323412560136, | |
| "learning_rate": 1.717944359312904e-06, | |
| "loss": 1.1339809894561768, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.5726618705035971, | |
| "grad_norm": 0.372793535454918, | |
| "learning_rate": 1.7146278451184717e-06, | |
| "loss": 1.1350829601287842, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.5755395683453237, | |
| "grad_norm": 0.3395541162036473, | |
| "learning_rate": 1.7112951882326869e-06, | |
| "loss": 0.9920399785041809, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 696, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 346421856567296.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |