Instructions to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/home/yuxuanzhao/LLaMA-Factory/models/qwen2_5-vl-3B-Instruct") model = PeftModel.from_pretrained(base_model, "AgenticFinLab/PyFi-QwenVL-3B-COT-47K") - Transformers
How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AgenticFinLab/PyFi-QwenVL-3B-COT-47K") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AgenticFinLab/PyFi-QwenVL-3B-COT-47K", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AgenticFinLab/PyFi-QwenVL-3B-COT-47K" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AgenticFinLab/PyFi-QwenVL-3B-COT-47K", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AgenticFinLab/PyFi-QwenVL-3B-COT-47K
- SGLang
How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K 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 "AgenticFinLab/PyFi-QwenVL-3B-COT-47K" \ --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": "AgenticFinLab/PyFi-QwenVL-3B-COT-47K", "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 "AgenticFinLab/PyFi-QwenVL-3B-COT-47K" \ --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": "AgenticFinLab/PyFi-QwenVL-3B-COT-47K", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with Docker Model Runner:
docker model run hf.co/AgenticFinLab/PyFi-QwenVL-3B-COT-47K
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1473, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00679001867255135, | |
| "grad_norm": 0.3240041732788086, | |
| "learning_rate": 6.081081081081082e-06, | |
| "loss": 1.1588, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0135800373451027, | |
| "grad_norm": 0.33118951320648193, | |
| "learning_rate": 1.2837837837837838e-05, | |
| "loss": 1.1753, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02037005601765405, | |
| "grad_norm": 0.31068024039268494, | |
| "learning_rate": 1.9594594594594595e-05, | |
| "loss": 1.1373, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0271600746902054, | |
| "grad_norm": 0.23320411145687103, | |
| "learning_rate": 2.635135135135135e-05, | |
| "loss": 1.0904, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03395009336275675, | |
| "grad_norm": 0.2017011195421219, | |
| "learning_rate": 3.310810810810811e-05, | |
| "loss": 1.0167, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0407401120353081, | |
| "grad_norm": 0.17189085483551025, | |
| "learning_rate": 3.986486486486487e-05, | |
| "loss": 0.9469, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04753013070785945, | |
| "grad_norm": 0.19272379577159882, | |
| "learning_rate": 4.662162162162162e-05, | |
| "loss": 0.8989, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0543201493804108, | |
| "grad_norm": 0.18675033748149872, | |
| "learning_rate": 5.337837837837838e-05, | |
| "loss": 0.8477, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06111016805296215, | |
| "grad_norm": 0.17720773816108704, | |
| "learning_rate": 6.013513513513514e-05, | |
| "loss": 0.8132, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0679001867255135, | |
| "grad_norm": 0.185109943151474, | |
| "learning_rate": 6.68918918918919e-05, | |
| "loss": 0.8234, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07469020539806484, | |
| "grad_norm": 0.1818627268075943, | |
| "learning_rate": 7.364864864864865e-05, | |
| "loss": 0.7957, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0814802240706162, | |
| "grad_norm": 0.21307602524757385, | |
| "learning_rate": 8.040540540540541e-05, | |
| "loss": 0.7972, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08827024274316754, | |
| "grad_norm": 0.2562461793422699, | |
| "learning_rate": 8.716216216216216e-05, | |
| "loss": 0.7792, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0950602614157189, | |
| "grad_norm": 0.20358482003211975, | |
| "learning_rate": 9.391891891891892e-05, | |
| "loss": 0.7592, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.10185028008827024, | |
| "grad_norm": 0.2647990882396698, | |
| "learning_rate": 9.999985945746134e-05, | |
| "loss": 0.7657, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1086402987608216, | |
| "grad_norm": 0.22973226010799408, | |
| "learning_rate": 9.998299530880787e-05, | |
| "loss": 0.7406, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11543031743337294, | |
| "grad_norm": 0.2881716191768646, | |
| "learning_rate": 9.993803351513094e-05, | |
| "loss": 0.7612, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1222203361059243, | |
| "grad_norm": 0.2511983811855316, | |
| "learning_rate": 9.986499935143679e-05, | |
| "loss": 0.723, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12901035477847564, | |
| "grad_norm": 0.25695255398750305, | |
| "learning_rate": 9.976393387344834e-05, | |
| "loss": 0.7439, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.135800373451027, | |
| "grad_norm": 0.2747204005718231, | |
| "learning_rate": 9.963489389452596e-05, | |
| "loss": 0.7484, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14259039212357835, | |
| "grad_norm": 0.2676641345024109, | |
| "learning_rate": 9.947795195373016e-05, | |
| "loss": 0.7454, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14938041079612968, | |
| "grad_norm": 0.30686891078948975, | |
| "learning_rate": 9.92931962750442e-05, | |
| "loss": 0.7232, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15617042946868104, | |
| "grad_norm": 0.28470826148986816, | |
| "learning_rate": 9.908073071777954e-05, | |
| "loss": 0.7269, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.1629604481412324, | |
| "grad_norm": 0.26007500290870667, | |
| "learning_rate": 9.884067471819184e-05, | |
| "loss": 0.7315, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.16975046681378375, | |
| "grad_norm": 0.2531976103782654, | |
| "learning_rate": 9.857316322234067e-05, | |
| "loss": 0.729, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17654048548633508, | |
| "grad_norm": 0.29370632767677307, | |
| "learning_rate": 9.827834661023034e-05, | |
| "loss": 0.7101, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18333050415888644, | |
| "grad_norm": 0.2687228322029114, | |
| "learning_rate": 9.795639061127468e-05, | |
| "loss": 0.7043, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.1901205228314378, | |
| "grad_norm": 0.3212800621986389, | |
| "learning_rate": 9.760747621113325e-05, | |
| "loss": 0.7148, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19691054150398912, | |
| "grad_norm": 0.27572208642959595, | |
| "learning_rate": 9.723179954997125e-05, | |
| "loss": 0.7303, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.20370056017654048, | |
| "grad_norm": 0.30647820234298706, | |
| "learning_rate": 9.682957181220062e-05, | |
| "loss": 0.7171, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21049057884909184, | |
| "grad_norm": 0.31693774461746216, | |
| "learning_rate": 9.640101910776381e-05, | |
| "loss": 0.6952, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2172805975216432, | |
| "grad_norm": 0.30650973320007324, | |
| "learning_rate": 9.594638234502753e-05, | |
| "loss": 0.692, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.22407061619419452, | |
| "grad_norm": 0.2651052176952362, | |
| "learning_rate": 9.546591709535751e-05, | |
| "loss": 0.7064, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.23086063486674588, | |
| "grad_norm": 0.27826765179634094, | |
| "learning_rate": 9.495989344945056e-05, | |
| "loss": 0.6973, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.23765065353929724, | |
| "grad_norm": 0.2882961332798004, | |
| "learning_rate": 9.442859586550468e-05, | |
| "loss": 0.7013, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2444406722118486, | |
| "grad_norm": 0.304463267326355, | |
| "learning_rate": 9.387232300931255e-05, | |
| "loss": 0.6937, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2512306908843999, | |
| "grad_norm": 0.3260940611362457, | |
| "learning_rate": 9.32913875863684e-05, | |
| "loss": 0.7028, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2580207095569513, | |
| "grad_norm": 0.3053944706916809, | |
| "learning_rate": 9.268611616608236e-05, | |
| "loss": 0.7012, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.26481072822950263, | |
| "grad_norm": 0.3119329512119293, | |
| "learning_rate": 9.205684899820147e-05, | |
| "loss": 0.6882, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.271600746902054, | |
| "grad_norm": 0.3281630575656891, | |
| "learning_rate": 9.140393982154026e-05, | |
| "loss": 0.6868, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27839076557460535, | |
| "grad_norm": 0.30837196111679077, | |
| "learning_rate": 9.072775566512863e-05, | |
| "loss": 0.6794, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.2851807842471567, | |
| "grad_norm": 0.3343650698661804, | |
| "learning_rate": 9.002867664188858e-05, | |
| "loss": 0.7032, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 0.31981658935546875, | |
| "learning_rate": 8.930709573495602e-05, | |
| "loss": 0.696, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.29876082159225936, | |
| "grad_norm": 0.2964082956314087, | |
| "learning_rate": 8.856341857676758e-05, | |
| "loss": 0.6868, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3055508402648107, | |
| "grad_norm": 0.2928807735443115, | |
| "learning_rate": 8.779806322103682e-05, | |
| "loss": 0.6892, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3123408589373621, | |
| "grad_norm": 0.37681853771209717, | |
| "learning_rate": 8.701145990774775e-05, | |
| "loss": 0.7025, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.31913087760991343, | |
| "grad_norm": 0.32805585861206055, | |
| "learning_rate": 8.620405082129798e-05, | |
| "loss": 0.6948, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.3259208962824648, | |
| "grad_norm": 0.2930596172809601, | |
| "learning_rate": 8.537628984192736e-05, | |
| "loss": 0.6922, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.33271091495501615, | |
| "grad_norm": 0.3077249228954315, | |
| "learning_rate": 8.452864229057191e-05, | |
| "loss": 0.6869, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3395009336275675, | |
| "grad_norm": 0.3145536482334137, | |
| "learning_rate": 8.366158466728644e-05, | |
| "loss": 0.6634, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3462909523001188, | |
| "grad_norm": 0.30891168117523193, | |
| "learning_rate": 8.277560438338278e-05, | |
| "loss": 0.6735, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.35308097097267016, | |
| "grad_norm": 0.3157874643802643, | |
| "learning_rate": 8.18711994874345e-05, | |
| "loss": 0.6809, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.3598709896452215, | |
| "grad_norm": 0.3254513740539551, | |
| "learning_rate": 8.094887838530174e-05, | |
| "loss": 0.6788, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.3666610083177729, | |
| "grad_norm": 0.30559736490249634, | |
| "learning_rate": 8.000915955433396e-05, | |
| "loss": 0.672, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.37345102699032423, | |
| "grad_norm": 0.3182581067085266, | |
| "learning_rate": 7.905257125191094e-05, | |
| "loss": 0.6726, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3802410456628756, | |
| "grad_norm": 0.2918800115585327, | |
| "learning_rate": 7.807965121848597e-05, | |
| "loss": 0.6748, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.38703106433542694, | |
| "grad_norm": 0.2917610704898834, | |
| "learning_rate": 7.70909463752983e-05, | |
| "loss": 0.6883, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.39382108300797825, | |
| "grad_norm": 0.3264787793159485, | |
| "learning_rate": 7.608701251692457e-05, | |
| "loss": 0.6962, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.4006111016805296, | |
| "grad_norm": 0.31565555930137634, | |
| "learning_rate": 7.506841399884217e-05, | |
| "loss": 0.6652, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.40740112035308096, | |
| "grad_norm": 0.32659557461738586, | |
| "learning_rate": 7.403572342018021e-05, | |
| "loss": 0.6705, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4141911390256323, | |
| "grad_norm": 0.3272686302661896, | |
| "learning_rate": 7.29895213018362e-05, | |
| "loss": 0.6935, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.4209811576981837, | |
| "grad_norm": 0.30826854705810547, | |
| "learning_rate": 7.193039576013976e-05, | |
| "loss": 0.6785, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.42777117637073503, | |
| "grad_norm": 0.3225189745426178, | |
| "learning_rate": 7.085894217624645e-05, | |
| "loss": 0.6852, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.4345611950432864, | |
| "grad_norm": 0.3011186718940735, | |
| "learning_rate": 6.977576286144784e-05, | |
| "loss": 0.6582, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.44135121371583774, | |
| "grad_norm": 0.3189927339553833, | |
| "learning_rate": 6.868146671858567e-05, | |
| "loss": 0.6661, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.44814123238838904, | |
| "grad_norm": 0.3186146318912506, | |
| "learning_rate": 6.757666889976085e-05, | |
| "loss": 0.675, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.4549312510609404, | |
| "grad_norm": 0.32622990012168884, | |
| "learning_rate": 6.646199046052921e-05, | |
| "loss": 0.66, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.46172126973349176, | |
| "grad_norm": 0.3160436451435089, | |
| "learning_rate": 6.533805801077899e-05, | |
| "loss": 0.6583, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.4685112884060431, | |
| "grad_norm": 0.32458364963531494, | |
| "learning_rate": 6.420550336248558e-05, | |
| "loss": 0.6781, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.47530130707859447, | |
| "grad_norm": 0.30644142627716064, | |
| "learning_rate": 6.306496317454227e-05, | |
| "loss": 0.6578, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4820913257511458, | |
| "grad_norm": 0.3288382589817047, | |
| "learning_rate": 6.191707859486622e-05, | |
| "loss": 0.654, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.4888813444236972, | |
| "grad_norm": 0.32884201407432556, | |
| "learning_rate": 6.076249489998097e-05, | |
| "loss": 0.6687, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.49567136309624854, | |
| "grad_norm": 0.31357714533805847, | |
| "learning_rate": 5.9601861132278e-05, | |
| "loss": 0.6676, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.5024613817687998, | |
| "grad_norm": 0.3417271673679352, | |
| "learning_rate": 5.8435829735161416e-05, | |
| "loss": 0.6535, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.5092514004413512, | |
| "grad_norm": 0.3383308947086334, | |
| "learning_rate": 5.7265056186280754e-05, | |
| "loss": 0.6801, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.5160414191139026, | |
| "grad_norm": 0.3183964788913727, | |
| "learning_rate": 5.6090198629058134e-05, | |
| "loss": 0.6623, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.5228314377864539, | |
| "grad_norm": 0.3123168349266052, | |
| "learning_rate": 5.491191750271677e-05, | |
| "loss": 0.6529, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.5296214564590053, | |
| "grad_norm": 0.3268730342388153, | |
| "learning_rate": 5.373087517101899e-05, | |
| "loss": 0.675, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.5364114751315566, | |
| "grad_norm": 0.33710595965385437, | |
| "learning_rate": 5.254773554992242e-05, | |
| "loss": 0.6642, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.543201493804108, | |
| "grad_norm": 0.3158477544784546, | |
| "learning_rate": 5.136316373436343e-05, | |
| "loss": 0.6651, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5499915124766593, | |
| "grad_norm": 0.35006120800971985, | |
| "learning_rate": 5.0177825624378114e-05, | |
| "loss": 0.6677, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.5567815311492107, | |
| "grad_norm": 0.32128673791885376, | |
| "learning_rate": 4.8992387550770373e-05, | |
| "loss": 0.6567, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.563571549821762, | |
| "grad_norm": 0.31521716713905334, | |
| "learning_rate": 4.780751590053813e-05, | |
| "loss": 0.6451, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.5703615684943134, | |
| "grad_norm": 0.35046160221099854, | |
| "learning_rate": 4.662387674226771e-05, | |
| "loss": 0.6516, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.5771515871668647, | |
| "grad_norm": 0.3590330183506012, | |
| "learning_rate": 4.544213545170741e-05, | |
| "loss": 0.6666, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "grad_norm": 0.3667231798171997, | |
| "learning_rate": 4.4262956337730385e-05, | |
| "loss": 0.6769, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.5907316245119674, | |
| "grad_norm": 0.3383621871471405, | |
| "learning_rate": 4.3087002268897434e-05, | |
| "loss": 0.6677, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.5975216431845187, | |
| "grad_norm": 0.32708925008773804, | |
| "learning_rate": 4.191493430082929e-05, | |
| "loss": 0.6631, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.6043116618570701, | |
| "grad_norm": 0.3610892593860626, | |
| "learning_rate": 4.074741130459813e-05, | |
| "loss": 0.6642, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.6111016805296214, | |
| "grad_norm": 0.3324897289276123, | |
| "learning_rate": 3.9585089596347094e-05, | |
| "loss": 0.6759, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6178916992021728, | |
| "grad_norm": 0.35481977462768555, | |
| "learning_rate": 3.842862256834613e-05, | |
| "loss": 0.6746, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.6246817178747242, | |
| "grad_norm": 0.32131439447402954, | |
| "learning_rate": 3.727866032169127e-05, | |
| "loss": 0.6564, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.6314717365472755, | |
| "grad_norm": 0.3492388129234314, | |
| "learning_rate": 3.6135849300854225e-05, | |
| "loss": 0.6598, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.6382617552198269, | |
| "grad_norm": 0.33926454186439514, | |
| "learning_rate": 3.500083193028741e-05, | |
| "loss": 0.6591, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.6450517738923782, | |
| "grad_norm": 0.33176636695861816, | |
| "learning_rate": 3.387424625328892e-05, | |
| "loss": 0.6525, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.6518417925649296, | |
| "grad_norm": 0.36466217041015625, | |
| "learning_rate": 3.275672557333015e-05, | |
| "loss": 0.6622, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.6586318112374809, | |
| "grad_norm": 0.3251396119594574, | |
| "learning_rate": 3.164889809804808e-05, | |
| "loss": 0.6498, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.6654218299100323, | |
| "grad_norm": 0.3163330554962158, | |
| "learning_rate": 3.055138658610202e-05, | |
| "loss": 0.6473, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.6722118485825836, | |
| "grad_norm": 0.35338786244392395, | |
| "learning_rate": 2.946480799709358e-05, | |
| "loss": 0.6565, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.679001867255135, | |
| "grad_norm": 0.35114529728889465, | |
| "learning_rate": 2.83897731447464e-05, | |
| "loss": 0.6464, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6857918859276863, | |
| "grad_norm": 0.32843121886253357, | |
| "learning_rate": 2.7326886353540916e-05, | |
| "loss": 0.6596, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.6925819046002376, | |
| "grad_norm": 0.35616856813430786, | |
| "learning_rate": 2.627674511899678e-05, | |
| "loss": 0.6597, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.699371923272789, | |
| "grad_norm": 0.3362119495868683, | |
| "learning_rate": 2.5239939771794563e-05, | |
| "loss": 0.6595, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.7061619419453403, | |
| "grad_norm": 0.4099394381046295, | |
| "learning_rate": 2.421705314592452e-05, | |
| "loss": 0.657, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.7129519606178917, | |
| "grad_norm": 0.33618077635765076, | |
| "learning_rate": 2.3208660251050158e-05, | |
| "loss": 0.6518, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.719741979290443, | |
| "grad_norm": 0.3896566927433014, | |
| "learning_rate": 2.2215327949269886e-05, | |
| "loss": 0.6576, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.7265319979629944, | |
| "grad_norm": 0.3515529930591583, | |
| "learning_rate": 2.123761463645878e-05, | |
| "loss": 0.6713, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.7333220166355457, | |
| "grad_norm": 0.37407588958740234, | |
| "learning_rate": 2.0276069928369746e-05, | |
| "loss": 0.6517, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.7401120353080971, | |
| "grad_norm": 0.3607807159423828, | |
| "learning_rate": 1.933123435167018e-05, | |
| "loss": 0.662, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.7469020539806485, | |
| "grad_norm": 0.32415834069252014, | |
| "learning_rate": 1.840363904008819e-05, | |
| "loss": 0.6529, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7536920726531998, | |
| "grad_norm": 0.33956629037857056, | |
| "learning_rate": 1.7493805435838874e-05, | |
| "loss": 0.6566, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.7604820913257512, | |
| "grad_norm": 0.3476695716381073, | |
| "learning_rate": 1.660224499649861e-05, | |
| "loss": 0.6623, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.7672721099983025, | |
| "grad_norm": 0.3658044934272766, | |
| "learning_rate": 1.5729458907492327e-05, | |
| "loss": 0.6594, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.7740621286708539, | |
| "grad_norm": 0.3347267508506775, | |
| "learning_rate": 1.4875937800354988e-05, | |
| "loss": 0.6522, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.7808521473434052, | |
| "grad_norm": 0.35682836174964905, | |
| "learning_rate": 1.404216147692598e-05, | |
| "loss": 0.6574, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.7876421660159565, | |
| "grad_norm": 0.3608170747756958, | |
| "learning_rate": 1.3228598639631418e-05, | |
| "loss": 0.6602, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.7944321846885078, | |
| "grad_norm": 0.3760475516319275, | |
| "learning_rate": 1.2435706628005767e-05, | |
| "loss": 0.6485, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.8012222033610592, | |
| "grad_norm": 0.37475037574768066, | |
| "learning_rate": 1.1663931161601188e-05, | |
| "loss": 0.6515, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.8080122220336106, | |
| "grad_norm": 0.35292160511016846, | |
| "learning_rate": 1.0913706089428932e-05, | |
| "loss": 0.6388, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.8148022407061619, | |
| "grad_norm": 0.3781260550022125, | |
| "learning_rate": 1.0185453146073604e-05, | |
| "loss": 0.6589, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8215922593787133, | |
| "grad_norm": 0.4595643877983093, | |
| "learning_rate": 9.479581714617668e-06, | |
| "loss": 0.6547, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.8283822780512646, | |
| "grad_norm": 0.3590555787086487, | |
| "learning_rate": 8.796488596509133e-06, | |
| "loss": 0.6642, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.835172296723816, | |
| "grad_norm": 0.33552083373069763, | |
| "learning_rate": 8.136557788501903e-06, | |
| "loss": 0.6595, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.8419623153963673, | |
| "grad_norm": 0.3614760935306549, | |
| "learning_rate": 7.500160266794371e-06, | |
| "loss": 0.657, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.8487523340689187, | |
| "grad_norm": 0.3503766357898712, | |
| "learning_rate": 6.887653778487307e-06, | |
| "loss": 0.6575, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.8555423527414701, | |
| "grad_norm": 0.35026514530181885, | |
| "learning_rate": 6.2993826404783965e-06, | |
| "loss": 0.6518, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.8623323714140214, | |
| "grad_norm": 0.3700234889984131, | |
| "learning_rate": 5.735677545906626e-06, | |
| "loss": 0.6601, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.8691223900865728, | |
| "grad_norm": 0.36147522926330566, | |
| "learning_rate": 5.196855378254989e-06, | |
| "loss": 0.6495, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.8759124087591241, | |
| "grad_norm": 0.37248465418815613, | |
| "learning_rate": 4.683219033216402e-06, | |
| "loss": 0.6406, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.8827024274316755, | |
| "grad_norm": 0.3341233730316162, | |
| "learning_rate": 4.1950572484226345e-06, | |
| "loss": 0.6531, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.8894924461042268, | |
| "grad_norm": 0.3707130253314972, | |
| "learning_rate": 3.7326444411321547e-06, | |
| "loss": 0.6516, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.8962824647767781, | |
| "grad_norm": 0.34083500504493713, | |
| "learning_rate": 3.2962405539681217e-06, | |
| "loss": 0.6486, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.9030724834493294, | |
| "grad_norm": 0.3688032329082489, | |
| "learning_rate": 2.8860909087931543e-06, | |
| "loss": 0.6551, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.9098625021218808, | |
| "grad_norm": 0.41832467913627625, | |
| "learning_rate": 2.5024260688030987e-06, | |
| "loss": 0.6392, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.9166525207944322, | |
| "grad_norm": 0.3395462930202484, | |
| "learning_rate": 2.145461708917312e-06, | |
| "loss": 0.646, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.9234425394669835, | |
| "grad_norm": 0.3675546944141388, | |
| "learning_rate": 1.8153984945382452e-06, | |
| "loss": 0.6454, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 0.3589598834514618, | |
| "learning_rate": 1.512421968748623e-06, | |
| "loss": 0.636, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.9370225768120862, | |
| "grad_norm": 0.36960166692733765, | |
| "learning_rate": 1.2367024480094691e-06, | |
| "loss": 0.6651, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.9438125954846376, | |
| "grad_norm": 0.354684442281723, | |
| "learning_rate": 9.883949264176962e-07, | |
| "loss": 0.6368, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.9506026141571889, | |
| "grad_norm": 0.4004354178905487, | |
| "learning_rate": 7.676389885771518e-07, | |
| "loss": 0.6499, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9573926328297403, | |
| "grad_norm": 0.3644382059574127, | |
| "learning_rate": 5.745587311318968e-07, | |
| "loss": 0.6436, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.9641826515022917, | |
| "grad_norm": 0.33734816312789917, | |
| "learning_rate": 4.0926269300603503e-07, | |
| "loss": 0.6447, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.970972670174843, | |
| "grad_norm": 0.3564316928386688, | |
| "learning_rate": 2.71843794389226e-07, | |
| "loss": 0.6523, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.9777626888473944, | |
| "grad_norm": 0.3726203739643097, | |
| "learning_rate": 1.623792845020955e-07, | |
| "loss": 0.631, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.9845527075199457, | |
| "grad_norm": 0.3702944219112396, | |
| "learning_rate": 8.093069817109445e-08, | |
| "loss": 0.6347, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.9913427261924971, | |
| "grad_norm": 0.3534630537033081, | |
| "learning_rate": 2.7543821237030475e-08, | |
| "loss": 0.6527, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.9981327448650483, | |
| "grad_norm": 0.3350744843482971, | |
| "learning_rate": 2.2486648168396075e-09, | |
| "loss": 0.6344, | |
| "step": 1470 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1473, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 9.747484099425075e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |