Instructions to use ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA 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, "ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA") - Transformers
How to use ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA
- SGLang
How to use ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA 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 "ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA" \ --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": "ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA", "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 "ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA" \ --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": "ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA with Docker Model Runner:
docker model run hf.co/ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA
Download checkpoint-1450/trainer_state.json from ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA: direct link, hf CLI and curl.
- Browser
- Download file 26 kB
-
https://huggingface.co/ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA/resolve/main/checkpoint-1450/trainer_state.json
- Command line
-
hf download hf://ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA/checkpoint-1450/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/ronantakizawa/Qwen2.5-VL-7B-WebUI-LoRA/resolve/main/checkpoint-1450/trainer_state.json
26 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1450,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013795481979651664,
"grad_norm": 0.3797769546508789,
"learning_rate": 2.4657534246575345e-06,
"loss": 0.7409,
"step": 10
},
{
"epoch": 0.027590963959303327,
"grad_norm": 0.37327441573143005,
"learning_rate": 5.2054794520547945e-06,
"loss": 0.7228,
"step": 20
},
{
"epoch": 0.04138644593895499,
"grad_norm": 0.20207762718200684,
"learning_rate": 7.945205479452055e-06,
"loss": 0.7847,
"step": 30
},
{
"epoch": 0.055181927918606655,
"grad_norm": 0.17325344681739807,
"learning_rate": 1.0684931506849316e-05,
"loss": 0.6964,
"step": 40
},
{
"epoch": 0.06897740989825832,
"grad_norm": 0.19350935518741608,
"learning_rate": 1.3424657534246576e-05,
"loss": 0.6608,
"step": 50
},
{
"epoch": 0.08277289187790998,
"grad_norm": 0.27192795276641846,
"learning_rate": 1.6164383561643838e-05,
"loss": 0.6962,
"step": 60
},
{
"epoch": 0.09656837385756165,
"grad_norm": 0.2818223237991333,
"learning_rate": 1.8904109589041096e-05,
"loss": 0.7059,
"step": 70
},
{
"epoch": 0.11036385583721331,
"grad_norm": 0.17412742972373962,
"learning_rate": 1.999906309061717e-05,
"loss": 0.698,
"step": 80
},
{
"epoch": 0.12415933781686497,
"grad_norm": 0.11162406206130981,
"learning_rate": 1.9993338169037535e-05,
"loss": 0.6718,
"step": 90
},
{
"epoch": 0.13795481979651664,
"grad_norm": 0.3205617070198059,
"learning_rate": 1.9982411807247332e-05,
"loss": 0.6122,
"step": 100
},
{
"epoch": 0.1517503017761683,
"grad_norm": 0.21151131391525269,
"learning_rate": 1.9966289692316944e-05,
"loss": 0.6619,
"step": 110
},
{
"epoch": 0.16554578375581996,
"grad_norm": 0.44795897603034973,
"learning_rate": 1.9944980215658283e-05,
"loss": 0.6537,
"step": 120
},
{
"epoch": 0.17934126573547163,
"grad_norm": 0.2984088957309723,
"learning_rate": 1.9918494468657112e-05,
"loss": 0.6117,
"step": 130
},
{
"epoch": 0.1931367477151233,
"grad_norm": 0.17323806881904602,
"learning_rate": 1.9886846236900102e-05,
"loss": 0.6029,
"step": 140
},
{
"epoch": 0.20693222969477496,
"grad_norm": 0.1392897516489029,
"learning_rate": 1.985005199299956e-05,
"loss": 0.6353,
"step": 150
},
{
"epoch": 0.22072771167442662,
"grad_norm": 0.2399936467409134,
"learning_rate": 1.980813088801957e-05,
"loss": 0.5857,
"step": 160
},
{
"epoch": 0.23452319365407828,
"grad_norm": 0.2649478316307068,
"learning_rate": 1.976110474150806e-05,
"loss": 0.6172,
"step": 170
},
{
"epoch": 0.24831867563372995,
"grad_norm": 0.17964090406894684,
"learning_rate": 1.970899803013991e-05,
"loss": 0.6276,
"step": 180
},
{
"epoch": 0.26211415761338164,
"grad_norm": 0.24538779258728027,
"learning_rate": 1.96518378749771e-05,
"loss": 0.5976,
"step": 190
},
{
"epoch": 0.2759096395930333,
"grad_norm": 0.28566867113113403,
"learning_rate": 1.9589654027352412e-05,
"loss": 0.601,
"step": 200
},
{
"epoch": 0.28970512157268496,
"grad_norm": 0.30197039246559143,
"learning_rate": 1.9522478853384154e-05,
"loss": 0.5974,
"step": 210
},
{
"epoch": 0.3035006035523366,
"grad_norm": 0.1945207715034485,
"learning_rate": 1.9450347317129895e-05,
"loss": 0.6383,
"step": 220
},
{
"epoch": 0.3172960855319883,
"grad_norm": 0.30945831537246704,
"learning_rate": 1.9373296962387988e-05,
"loss": 0.6055,
"step": 230
},
{
"epoch": 0.33109156751163993,
"grad_norm": 0.2356773167848587,
"learning_rate": 1.9291367893156377e-05,
"loss": 0.5739,
"step": 240
},
{
"epoch": 0.3448870494912916,
"grad_norm": 0.39426302909851074,
"learning_rate": 1.920460275275884e-05,
"loss": 0.6058,
"step": 250
},
{
"epoch": 0.35868253147094326,
"grad_norm": 0.160350039601326,
"learning_rate": 1.9113046701649517e-05,
"loss": 0.5651,
"step": 260
},
{
"epoch": 0.37247801345059495,
"grad_norm": 0.39767953753471375,
"learning_rate": 1.9016747393907328e-05,
"loss": 0.5708,
"step": 270
},
{
"epoch": 0.3862734954302466,
"grad_norm": 0.4169345498085022,
"learning_rate": 1.8915754952432456e-05,
"loss": 0.586,
"step": 280
},
{
"epoch": 0.4000689774098983,
"grad_norm": 0.2788037061691284,
"learning_rate": 1.8810121942857848e-05,
"loss": 0.5899,
"step": 290
},
{
"epoch": 0.4138644593895499,
"grad_norm": 0.20818158984184265,
"learning_rate": 1.8699903346189266e-05,
"loss": 0.5636,
"step": 300
},
{
"epoch": 0.4276599413692016,
"grad_norm": 0.24982821941375732,
"learning_rate": 1.8585156530188218e-05,
"loss": 0.6127,
"step": 310
},
{
"epoch": 0.44145542334885324,
"grad_norm": 0.5930744409561157,
"learning_rate": 1.8465941219512533e-05,
"loss": 0.6108,
"step": 320
},
{
"epoch": 0.45525090532850493,
"grad_norm": 0.4836622476577759,
"learning_rate": 1.8342319464630258e-05,
"loss": 0.5814,
"step": 330
},
{
"epoch": 0.46904638730815656,
"grad_norm": 0.6604896187782288,
"learning_rate": 1.8214355609522937e-05,
"loss": 0.544,
"step": 340
},
{
"epoch": 0.48284186928780826,
"grad_norm": 0.42665502429008484,
"learning_rate": 1.8082116258195173e-05,
"loss": 0.5784,
"step": 350
},
{
"epoch": 0.4966373512674599,
"grad_norm": 0.2564467191696167,
"learning_rate": 1.794567024000787e-05,
"loss": 0.5732,
"step": 360
},
{
"epoch": 0.5104328332471115,
"grad_norm": 0.26389172673225403,
"learning_rate": 1.780508857385317e-05,
"loss": 0.5521,
"step": 370
},
{
"epoch": 0.5242283152267633,
"grad_norm": 0.5035005211830139,
"learning_rate": 1.766044443118978e-05,
"loss": 0.6188,
"step": 380
},
{
"epoch": 0.5380237972064149,
"grad_norm": 0.23338013887405396,
"learning_rate": 1.7511813097957913e-05,
"loss": 0.6053,
"step": 390
},
{
"epoch": 0.5518192791860665,
"grad_norm": 0.2688336670398712,
"learning_rate": 1.735927193539363e-05,
"loss": 0.5601,
"step": 400
},
{
"epoch": 0.5656147611657182,
"grad_norm": 0.2981221377849579,
"learning_rate": 1.7202900339763066e-05,
"loss": 0.6365,
"step": 410
},
{
"epoch": 0.5794102431453699,
"grad_norm": 0.3435441851615906,
"learning_rate": 1.7042779701037364e-05,
"loss": 0.5867,
"step": 420
},
{
"epoch": 0.5932057251250216,
"grad_norm": 0.2693606913089752,
"learning_rate": 1.6878993360529985e-05,
"loss": 0.6327,
"step": 430
},
{
"epoch": 0.6070012071046732,
"grad_norm": 0.22722283005714417,
"learning_rate": 1.67116265675183e-05,
"loss": 0.518,
"step": 440
},
{
"epoch": 0.6207966890843248,
"grad_norm": 0.2738974988460541,
"learning_rate": 1.654076643487214e-05,
"loss": 0.5334,
"step": 450
},
{
"epoch": 0.6345921710639766,
"grad_norm": 0.3559092581272125,
"learning_rate": 1.6366501893712346e-05,
"loss": 0.5834,
"step": 460
},
{
"epoch": 0.6483876530436282,
"grad_norm": 0.3664761185646057,
"learning_rate": 1.6188923647122946e-05,
"loss": 0.5931,
"step": 470
},
{
"epoch": 0.6621831350232799,
"grad_norm": 0.7026459574699402,
"learning_rate": 1.6008124122941038e-05,
"loss": 0.5935,
"step": 480
},
{
"epoch": 0.6759786170029315,
"grad_norm": 0.48170900344848633,
"learning_rate": 1.582419742564895e-05,
"loss": 0.5183,
"step": 490
},
{
"epoch": 0.6897740989825832,
"grad_norm": 0.38771921396255493,
"learning_rate": 1.5637239287393725e-05,
"loss": 0.5679,
"step": 500
},
{
"epoch": 0.7035695809622349,
"grad_norm": 0.2537793815135956,
"learning_rate": 1.5447347018159437e-05,
"loss": 0.6055,
"step": 510
},
{
"epoch": 0.7173650629418865,
"grad_norm": 0.21400552988052368,
"learning_rate": 1.5254619455118228e-05,
"loss": 0.5793,
"step": 520
},
{
"epoch": 0.7311605449215381,
"grad_norm": 0.2982640862464905,
"learning_rate": 1.5059156911186465e-05,
"loss": 0.5672,
"step": 530
},
{
"epoch": 0.7449560269011899,
"grad_norm": 0.31989380717277527,
"learning_rate": 1.4861061122812829e-05,
"loss": 0.5452,
"step": 540
},
{
"epoch": 0.7587515088808415,
"grad_norm": 0.3549844026565552,
"learning_rate": 1.4660435197025391e-05,
"loss": 0.5644,
"step": 550
},
{
"epoch": 0.7725469908604932,
"grad_norm": 0.23405125737190247,
"learning_rate": 1.4457383557765385e-05,
"loss": 0.5878,
"step": 560
},
{
"epoch": 0.7863424728401448,
"grad_norm": 0.3422601819038391,
"learning_rate": 1.42520118915355e-05,
"loss": 0.5618,
"step": 570
},
{
"epoch": 0.8001379548197965,
"grad_norm": 0.4048892855644226,
"learning_rate": 1.4044427092391031e-05,
"loss": 0.5636,
"step": 580
},
{
"epoch": 0.8139334367994482,
"grad_norm": 0.3537643253803253,
"learning_rate": 1.3834737206302519e-05,
"loss": 0.5583,
"step": 590
},
{
"epoch": 0.8277289187790998,
"grad_norm": 0.30749791860580444,
"learning_rate": 1.3623051374918803e-05,
"loss": 0.5519,
"step": 600
},
{
"epoch": 0.8415244007587515,
"grad_norm": 0.34683874249458313,
"learning_rate": 1.3409479778759829e-05,
"loss": 0.5549,
"step": 610
},
{
"epoch": 0.8553198827384032,
"grad_norm": 0.3743584156036377,
"learning_rate": 1.3194133579868672e-05,
"loss": 0.5302,
"step": 620
},
{
"epoch": 0.8691153647180548,
"grad_norm": 0.3802427649497986,
"learning_rate": 1.2977124863952753e-05,
"loss": 0.5137,
"step": 630
},
{
"epoch": 0.8829108466977065,
"grad_norm": 0.45509663224220276,
"learning_rate": 1.2758566582044237e-05,
"loss": 0.5579,
"step": 640
},
{
"epoch": 0.8967063286773581,
"grad_norm": 0.4004388153553009,
"learning_rate": 1.2538572491710079e-05,
"loss": 0.548,
"step": 650
},
{
"epoch": 0.9105018106570099,
"grad_norm": 0.3623187243938446,
"learning_rate": 1.2317257097842264e-05,
"loss": 0.5096,
"step": 660
},
{
"epoch": 0.9242972926366615,
"grad_norm": 0.2893803119659424,
"learning_rate": 1.2094735593059046e-05,
"loss": 0.6217,
"step": 670
},
{
"epoch": 0.9380927746163131,
"grad_norm": 0.32819125056266785,
"learning_rate": 1.1871123797748285e-05,
"loss": 0.6465,
"step": 680
},
{
"epoch": 0.9518882565959649,
"grad_norm": 0.32494664192199707,
"learning_rate": 1.1646538099783981e-05,
"loss": 0.5815,
"step": 690
},
{
"epoch": 0.9656837385756165,
"grad_norm": 0.643635094165802,
"learning_rate": 1.142109539394748e-05,
"loss": 0.5417,
"step": 700
},
{
"epoch": 0.9794792205552681,
"grad_norm": 0.38332876563072205,
"learning_rate": 1.119491302108479e-05,
"loss": 0.548,
"step": 710
},
{
"epoch": 0.9932747025349198,
"grad_norm": 0.4323633313179016,
"learning_rate": 1.0968108707031792e-05,
"loss": 0.5093,
"step": 720
},
{
"epoch": 1.0068977409898259,
"grad_norm": 0.3580758571624756,
"learning_rate": 1.0740800501339009e-05,
"loss": 0.5729,
"step": 730
},
{
"epoch": 1.0206932229694774,
"grad_norm": 0.41104599833488464,
"learning_rate": 1.0513106715827897e-05,
"loss": 0.5435,
"step": 740
},
{
"epoch": 1.0344887049491291,
"grad_norm": 0.42808327078819275,
"learning_rate": 1.028514586301066e-05,
"loss": 0.5654,
"step": 750
},
{
"epoch": 1.048284186928781,
"grad_norm": 0.23795004189014435,
"learning_rate": 1.0057036594405563e-05,
"loss": 0.5577,
"step": 760
},
{
"epoch": 1.0620796689084324,
"grad_norm": 0.3503638505935669,
"learning_rate": 9.828897638779909e-06,
"loss": 0.5563,
"step": 770
},
{
"epoch": 1.0758751508880842,
"grad_norm": 0.42293599247932434,
"learning_rate": 9.600847740352834e-06,
"loss": 0.5821,
"step": 780
},
{
"epoch": 1.089670632867736,
"grad_norm": 0.4006507992744446,
"learning_rate": 9.373005596990017e-06,
"loss": 0.5198,
"step": 790
},
{
"epoch": 1.1034661148473874,
"grad_norm": 0.4476047456264496,
"learning_rate": 9.14548979842255e-06,
"loss": 0.562,
"step": 800
},
{
"epoch": 1.1172615968270392,
"grad_norm": 0.27162086963653564,
"learning_rate": 8.918418764522069e-06,
"loss": 0.5608,
"step": 810
},
{
"epoch": 1.1310570788066907,
"grad_norm": 0.4345625638961792,
"learning_rate": 8.691910683664311e-06,
"loss": 0.569,
"step": 820
},
{
"epoch": 1.1448525607863425,
"grad_norm": 0.47795188426971436,
"learning_rate": 8.466083451213145e-06,
"loss": 0.5263,
"step": 830
},
{
"epoch": 1.1586480427659942,
"grad_norm": 0.3844754993915558,
"learning_rate": 8.241054608157158e-06,
"loss": 0.519,
"step": 840
},
{
"epoch": 1.1724435247456457,
"grad_norm": 0.605675220489502,
"learning_rate": 8.016941279930606e-06,
"loss": 0.6201,
"step": 850
},
{
"epoch": 1.1862390067252975,
"grad_norm": 0.4055939018726349,
"learning_rate": 7.793860115450744e-06,
"loss": 0.5269,
"step": 860
},
{
"epoch": 1.2000344887049492,
"grad_norm": 0.4357856810092926,
"learning_rate": 7.5719272264031264e-06,
"loss": 0.5221,
"step": 870
},
{
"epoch": 1.2138299706846007,
"grad_norm": 0.50385981798172,
"learning_rate": 7.351258126806556e-06,
"loss": 0.5446,
"step": 880
},
{
"epoch": 1.2276254526642525,
"grad_norm": 0.299748957157135,
"learning_rate": 7.131967672889101e-06,
"loss": 0.5431,
"step": 890
},
{
"epoch": 1.2414209346439042,
"grad_norm": 0.3890933096408844,
"learning_rate": 6.914170003306477e-06,
"loss": 0.5435,
"step": 900
},
{
"epoch": 1.2552164166235558,
"grad_norm": 0.523298978805542,
"learning_rate": 6.697978479733952e-06,
"loss": 0.5326,
"step": 910
},
{
"epoch": 1.2690118986032075,
"grad_norm": 0.3364376425743103,
"learning_rate": 6.483505627862632e-06,
"loss": 0.5058,
"step": 920
},
{
"epoch": 1.282807380582859,
"grad_norm": 0.3565503656864166,
"learning_rate": 6.2708630788308754e-06,
"loss": 0.5459,
"step": 930
},
{
"epoch": 1.2966028625625108,
"grad_norm": 0.5022204518318176,
"learning_rate": 6.060161511121312e-06,
"loss": 0.5067,
"step": 940
},
{
"epoch": 1.3103983445421625,
"grad_norm": 0.3366709053516388,
"learning_rate": 5.851510592953729e-06,
"loss": 0.5863,
"step": 950
},
{
"epoch": 1.324193826521814,
"grad_norm": 0.28878289461135864,
"learning_rate": 5.645018925203772e-06,
"loss": 0.5089,
"step": 960
},
{
"epoch": 1.3379893085014658,
"grad_norm": 0.33791589736938477,
"learning_rate": 5.440793984877177e-06,
"loss": 0.6144,
"step": 970
},
{
"epoch": 1.3517847904811173,
"grad_norm": 0.2994876503944397,
"learning_rate": 5.238942069169e-06,
"loss": 0.501,
"step": 980
},
{
"epoch": 1.365580272460769,
"grad_norm": 0.3521856665611267,
"learning_rate": 5.039568240136905e-06,
"loss": 0.534,
"step": 990
},
{
"epoch": 1.3793757544404208,
"grad_norm": 0.5321177840232849,
"learning_rate": 4.842776270017332e-06,
"loss": 0.5337,
"step": 1000
},
{
"epoch": 1.3931712364200723,
"grad_norm": 0.4032769799232483,
"learning_rate": 4.648668587212998e-06,
"loss": 0.5389,
"step": 1010
},
{
"epoch": 1.406966718399724,
"grad_norm": 0.5867075324058533,
"learning_rate": 4.4573462229798645e-06,
"loss": 0.5153,
"step": 1020
},
{
"epoch": 1.4207622003793756,
"grad_norm": 0.31274425983428955,
"learning_rate": 4.268908758841318e-06,
"loss": 0.5751,
"step": 1030
},
{
"epoch": 1.4345576823590274,
"grad_norm": 0.33221158385276794,
"learning_rate": 4.083454274756881e-06,
"loss": 0.5634,
"step": 1040
},
{
"epoch": 1.448353164338679,
"grad_norm": 0.5566088557243347,
"learning_rate": 3.90107929807251e-06,
"loss": 0.5289,
"step": 1050
},
{
"epoch": 1.4621486463183309,
"grad_norm": 0.3870019316673279,
"learning_rate": 3.7218787532790167e-06,
"loss": 0.5126,
"step": 1060
},
{
"epoch": 1.4759441282979824,
"grad_norm": 0.4883732497692108,
"learning_rate": 3.5459459126047226e-06,
"loss": 0.6272,
"step": 1070
},
{
"epoch": 1.4897396102776341,
"grad_norm": 0.3769921064376831,
"learning_rate": 3.373372347468141e-06,
"loss": 0.517,
"step": 1080
},
{
"epoch": 1.5035350922572857,
"grad_norm": 0.4440782070159912,
"learning_rate": 3.2042478808159026e-06,
"loss": 0.5357,
"step": 1090
},
{
"epoch": 1.5173305742369374,
"grad_norm": 0.6444796323776245,
"learning_rate": 3.0386605403707347e-06,
"loss": 0.5962,
"step": 1100
},
{
"epoch": 1.5311260562165891,
"grad_norm": 0.30395397543907166,
"learning_rate": 2.876696512813839e-06,
"loss": 0.5804,
"step": 1110
},
{
"epoch": 1.544921538196241,
"grad_norm": 0.26081570982933044,
"learning_rate": 2.7184400989255267e-06,
"loss": 0.4979,
"step": 1120
},
{
"epoch": 1.5587170201758924,
"grad_norm": 0.4978306293487549,
"learning_rate": 2.5639736697074525e-06,
"loss": 0.5222,
"step": 1130
},
{
"epoch": 1.572512502155544,
"grad_norm": 0.439376562833786,
"learning_rate": 2.4133776235092454e-06,
"loss": 0.4971,
"step": 1140
},
{
"epoch": 1.5863079841351957,
"grad_norm": 0.3121717572212219,
"learning_rate": 2.2667303441819243e-06,
"loss": 0.5909,
"step": 1150
},
{
"epoch": 1.6001034661148474,
"grad_norm": 0.6021148562431335,
"learning_rate": 2.124108160279832e-06,
"loss": 0.5091,
"step": 1160
},
{
"epoch": 1.6138989480944992,
"grad_norm": 0.26477521657943726,
"learning_rate": 1.985585305332318e-06,
"loss": 0.4974,
"step": 1170
},
{
"epoch": 1.6276944300741507,
"grad_norm": 0.536442756652832,
"learning_rate": 1.8512338792058749e-06,
"loss": 0.5898,
"step": 1180
},
{
"epoch": 1.6414899120538022,
"grad_norm": 0.44634145498275757,
"learning_rate": 1.7211238105768213e-06,
"loss": 0.5292,
"step": 1190
},
{
"epoch": 1.655285394033454,
"grad_norm": 0.3579349219799042,
"learning_rate": 1.5953228205340843e-06,
"loss": 0.4815,
"step": 1200
},
{
"epoch": 1.6690808760131057,
"grad_norm": 0.28459370136260986,
"learning_rate": 1.4738963873309797e-06,
"loss": 0.5725,
"step": 1210
},
{
"epoch": 1.6828763579927575,
"grad_norm": 0.356793075799942,
"learning_rate": 1.3569077123043973e-06,
"loss": 0.466,
"step": 1220
},
{
"epoch": 1.696671839972409,
"grad_norm": 0.4761062264442444,
"learning_rate": 1.2444176869790925e-06,
"loss": 0.5357,
"step": 1230
},
{
"epoch": 1.7104673219520607,
"grad_norm": 0.3354380130767822,
"learning_rate": 1.1364848613741953e-06,
"loss": 0.5545,
"step": 1240
},
{
"epoch": 1.7242628039317123,
"grad_norm": 0.47991442680358887,
"learning_rate": 1.033165413528483e-06,
"loss": 0.5356,
"step": 1250
},
{
"epoch": 1.738058285911364,
"grad_norm": 0.4192653298377991,
"learning_rate": 9.345131202602164e-07,
"loss": 0.536,
"step": 1260
},
{
"epoch": 1.7518537678910158,
"grad_norm": 0.59385746717453,
"learning_rate": 8.405793291768128e-07,
"loss": 0.5091,
"step": 1270
},
{
"epoch": 1.7656492498706675,
"grad_norm": 0.4526446759700775,
"learning_rate": 7.514129319488839e-07,
"loss": 0.5126,
"step": 1280
},
{
"epoch": 1.779444731850319,
"grad_norm": 0.33946824073791504,
"learning_rate": 6.670603388625729e-07,
"loss": 0.5335,
"step": 1290
},
{
"epoch": 1.7932402138299706,
"grad_norm": 0.5082955956459045,
"learning_rate": 5.875654546634335e-07,
"loss": 0.5252,
"step": 1300
},
{
"epoch": 1.8070356958096223,
"grad_norm": 0.46789219975471497,
"learning_rate": 5.129696557044173e-07,
"loss": 0.5706,
"step": 1310
},
{
"epoch": 1.820831177789274,
"grad_norm": 0.2035694718360901,
"learning_rate": 4.433117684098509e-07,
"loss": 0.528,
"step": 1320
},
{
"epoch": 1.8346266597689258,
"grad_norm": 0.5813590288162231,
"learning_rate": 3.786280490666605e-07,
"loss": 0.5703,
"step": 1330
},
{
"epoch": 1.8484221417485773,
"grad_norm": 0.3720139265060425,
"learning_rate": 3.1895216495329116e-07,
"loss": 0.5764,
"step": 1340
},
{
"epoch": 1.8622176237282289,
"grad_norm": 0.4149673283100128,
"learning_rate": 2.643151768162111e-07,
"loss": 0.5158,
"step": 1350
},
{
"epoch": 1.8760131057078806,
"grad_norm": 0.5767185091972351,
"learning_rate": 2.147455227030748e-07,
"loss": 0.5809,
"step": 1360
},
{
"epoch": 1.8898085876875323,
"grad_norm": 0.3867391049861908,
"learning_rate": 1.7026900316098217e-07,
"loss": 0.5767,
"step": 1370
},
{
"epoch": 1.903604069667184,
"grad_norm": 0.4448705315589905,
"learning_rate": 1.3090876780753715e-07,
"loss": 0.4904,
"step": 1380
},
{
"epoch": 1.9173995516468356,
"grad_norm": 0.3844303786754608,
"learning_rate": 9.668530328167613e-08,
"loss": 0.5501,
"step": 1390
},
{
"epoch": 1.9311950336264874,
"grad_norm": 0.5533041954040527,
"learning_rate": 6.761642258056977e-08,
"loss": 0.5416,
"step": 1400
},
{
"epoch": 1.944990515606139,
"grad_norm": 0.40398353338241577,
"learning_rate": 4.371725578812158e-08,
"loss": 0.5677,
"step": 1410
},
{
"epoch": 1.9587859975857906,
"grad_norm": 0.4691025912761688,
"learning_rate": 2.5000242199895163e-08,
"loss": 0.528,
"step": 1420
},
{
"epoch": 1.9725814795654424,
"grad_norm": 0.32153043150901794,
"learning_rate": 1.147512384857663e-08,
"loss": 0.4928,
"step": 1430
},
{
"epoch": 1.9863769615450941,
"grad_norm": 0.6625865697860718,
"learning_rate": 3.1489404333395756e-09,
"loss": 0.5391,
"step": 1440
},
{
"epoch": 2.0,
"grad_norm": 0.5659023523330688,
"learning_rate": 2.60256557438332e-11,
"loss": 0.4954,
"step": 1450
}
],
"logging_steps": 10,
"max_steps": 1450,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.6346794488779244e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1450,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013795481979651664,
"grad_norm": 0.3797769546508789,
"learning_rate": 2.4657534246575345e-06,
"loss": 0.7409,
"step": 10
},
{
"epoch": 0.027590963959303327,
"grad_norm": 0.37327441573143005,
"learning_rate": 5.2054794520547945e-06,
"loss": 0.7228,
"step": 20
},
{
"epoch": 0.04138644593895499,
"grad_norm": 0.20207762718200684,
"learning_rate": 7.945205479452055e-06,
"loss": 0.7847,
"step": 30
},
{
"epoch": 0.055181927918606655,
"grad_norm": 0.17325344681739807,
"learning_rate": 1.0684931506849316e-05,
"loss": 0.6964,
"step": 40
},
{
"epoch": 0.06897740989825832,
"grad_norm": 0.19350935518741608,
"learning_rate": 1.3424657534246576e-05,
"loss": 0.6608,
"step": 50
},
{
"epoch": 0.08277289187790998,
"grad_norm": 0.27192795276641846,
"learning_rate": 1.6164383561643838e-05,
"loss": 0.6962,
"step": 60
},
{
"epoch": 0.09656837385756165,
"grad_norm": 0.2818223237991333,
"learning_rate": 1.8904109589041096e-05,
"loss": 0.7059,
"step": 70
},
{
"epoch": 0.11036385583721331,
"grad_norm": 0.17412742972373962,
"learning_rate": 1.999906309061717e-05,
"loss": 0.698,
"step": 80
},
{
"epoch": 0.12415933781686497,
"grad_norm": 0.11162406206130981,
"learning_rate": 1.9993338169037535e-05,
"loss": 0.6718,
"step": 90
},
{
"epoch": 0.13795481979651664,
"grad_norm": 0.3205617070198059,
"learning_rate": 1.9982411807247332e-05,
"loss": 0.6122,
"step": 100
},
{
"epoch": 0.1517503017761683,
"grad_norm": 0.21151131391525269,
"learning_rate": 1.9966289692316944e-05,
"loss": 0.6619,
"step": 110
},
{
"epoch": 0.16554578375581996,
"grad_norm": 0.44795897603034973,
"learning_rate": 1.9944980215658283e-05,
"loss": 0.6537,
"step": 120
},
{
"epoch": 0.17934126573547163,
"grad_norm": 0.2984088957309723,
"learning_rate": 1.9918494468657112e-05,
"loss": 0.6117,