Instructions to use hai2131/vi-lo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use hai2131/vi-lo with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("sail/Sailor2-1B-Chat") model = PeftModel.from_pretrained(base_model, "hai2131/vi-lo") - Transformers
How to use hai2131/vi-lo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hai2131/vi-lo") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hai2131/vi-lo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hai2131/vi-lo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hai2131/vi-lo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hai2131/vi-lo", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/hai2131/vi-lo
- SGLang
How to use hai2131/vi-lo 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 "hai2131/vi-lo" \ --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": "hai2131/vi-lo", "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 "hai2131/vi-lo" \ --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": "hai2131/vi-lo", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use hai2131/vi-lo with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for hai2131/vi-lo to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for hai2131/vi-lo to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for hai2131/vi-lo to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="hai2131/vi-lo", max_seq_length=2048, ) - Docker Model Runner
How to use hai2131/vi-lo with Docker Model Runner:
docker model run hf.co/hai2131/vi-lo
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1189, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008413967185527976, | |
| "grad_norm": 5.52308988571167, | |
| "learning_rate": 3.7815126050420167e-06, | |
| "loss": 2.3433109283447267, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016827934371055953, | |
| "grad_norm": 2.464683771133423, | |
| "learning_rate": 7.983193277310924e-06, | |
| "loss": 1.652139663696289, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02524190155658393, | |
| "grad_norm": 2.0469274520874023, | |
| "learning_rate": 1.2184873949579832e-05, | |
| "loss": 1.1116899490356444, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.033655868742111905, | |
| "grad_norm": 0.7639474868774414, | |
| "learning_rate": 1.638655462184874e-05, | |
| "loss": 0.7363139629364014, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04206983592763988, | |
| "grad_norm": 0.5862300992012024, | |
| "learning_rate": 2.058823529411765e-05, | |
| "loss": 0.6817426681518555, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05048380311316786, | |
| "grad_norm": 0.5755972266197205, | |
| "learning_rate": 2.4789915966386556e-05, | |
| "loss": 0.6467609405517578, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.058897770298695834, | |
| "grad_norm": 0.6070194840431213, | |
| "learning_rate": 2.8991596638655467e-05, | |
| "loss": 0.6276434898376465, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06731173748422381, | |
| "grad_norm": 0.5020004510879517, | |
| "learning_rate": 3.319327731092437e-05, | |
| "loss": 0.6195865154266358, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07572570466975179, | |
| "grad_norm": 0.6197963953018188, | |
| "learning_rate": 3.739495798319328e-05, | |
| "loss": 0.6030911445617676, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08413967185527976, | |
| "grad_norm": 0.5069003105163574, | |
| "learning_rate": 4.159663865546219e-05, | |
| "loss": 0.6262809276580811, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09255363904080774, | |
| "grad_norm": 0.5204105377197266, | |
| "learning_rate": 4.579831932773109e-05, | |
| "loss": 0.6028512954711914, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10096760622633572, | |
| "grad_norm": 0.5738821625709534, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5683792114257813, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10938157341186369, | |
| "grad_norm": 0.49655693769454956, | |
| "learning_rate": 4.998922515567496e-05, | |
| "loss": 0.5995708465576172, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11779554059739167, | |
| "grad_norm": 0.5619757771492004, | |
| "learning_rate": 4.995690991048146e-05, | |
| "loss": 0.564251708984375, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12620950778291964, | |
| "grad_norm": 0.4584529399871826, | |
| "learning_rate": 4.99030821197584e-05, | |
| "loss": 0.5650043487548828, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13462347496844762, | |
| "grad_norm": 0.4953455626964569, | |
| "learning_rate": 4.982778818239101e-05, | |
| "loss": 0.5550412178039551, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1430374421539756, | |
| "grad_norm": 0.4682803750038147, | |
| "learning_rate": 4.97310930008156e-05, | |
| "loss": 0.5843101024627686, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15145140933950357, | |
| "grad_norm": 0.4659602642059326, | |
| "learning_rate": 4.961307992507443e-05, | |
| "loss": 0.5531447410583497, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.15986537652503155, | |
| "grad_norm": 0.4590919315814972, | |
| "learning_rate": 4.947385068096907e-05, | |
| "loss": 0.5672853469848633, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.16827934371055953, | |
| "grad_norm": 0.45025721192359924, | |
| "learning_rate": 4.9313525282373974e-05, | |
| "loss": 0.5719799041748047, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1766933108960875, | |
| "grad_norm": 0.403734415769577, | |
| "learning_rate": 4.9132241927786035e-05, | |
| "loss": 0.5558256149291992, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.18510727808161548, | |
| "grad_norm": 0.4194377064704895, | |
| "learning_rate": 4.893015688119921e-05, | |
| "loss": 0.5472552299499511, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.19352124526714345, | |
| "grad_norm": 0.4364999234676361, | |
| "learning_rate": 4.870744433740688e-05, | |
| "loss": 0.5540333747863769, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.20193521245267143, | |
| "grad_norm": 0.4469076097011566, | |
| "learning_rate": 4.8464296271848155e-05, | |
| "loss": 0.5611124038696289, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2103491796381994, | |
| "grad_norm": 0.4727751314640045, | |
| "learning_rate": 4.8200922275127355e-05, | |
| "loss": 0.5728967189788818, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21876314682372738, | |
| "grad_norm": 0.44017159938812256, | |
| "learning_rate": 4.7917549372349616e-05, | |
| "loss": 0.5312878131866455, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.22717711400925536, | |
| "grad_norm": 0.4599165618419647, | |
| "learning_rate": 4.761442182742799e-05, | |
| "loss": 0.5565039634704589, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.23559108119478334, | |
| "grad_norm": 0.4193755090236664, | |
| "learning_rate": 4.7291800932531064e-05, | |
| "loss": 0.540295934677124, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2440050483803113, | |
| "grad_norm": 0.45968326926231384, | |
| "learning_rate": 4.694996478285231e-05, | |
| "loss": 0.5284191131591797, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2524190155658393, | |
| "grad_norm": 0.3882873058319092, | |
| "learning_rate": 4.6589208036895535e-05, | |
| "loss": 0.5438860416412353, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2608329827513673, | |
| "grad_norm": 0.4749172329902649, | |
| "learning_rate": 4.620984166248288e-05, | |
| "loss": 0.5341141700744629, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.26924694993689524, | |
| "grad_norm": 0.433540403842926, | |
| "learning_rate": 4.581219266870446e-05, | |
| "loss": 0.5331087112426758, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.27766091712242325, | |
| "grad_norm": 0.4713405668735504, | |
| "learning_rate": 4.53966038240406e-05, | |
| "loss": 0.5343032836914062, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.2860748843079512, | |
| "grad_norm": 0.3954574465751648, | |
| "learning_rate": 4.496343336089965e-05, | |
| "loss": 0.5209596633911133, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2944888514934792, | |
| "grad_norm": 0.41449224948883057, | |
| "learning_rate": 4.4513054666826146e-05, | |
| "loss": 0.5443466663360595, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.30290281867900715, | |
| "grad_norm": 0.4463038742542267, | |
| "learning_rate": 4.4045855962645363e-05, | |
| "loss": 0.5250945091247559, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.31131678586453515, | |
| "grad_norm": 0.38618430495262146, | |
| "learning_rate": 4.3562239967821805e-05, | |
| "loss": 0.5211163997650147, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3197307530500631, | |
| "grad_norm": 0.39523622393608093, | |
| "learning_rate": 4.306262355332006e-05, | |
| "loss": 0.5420632362365723, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3281447202355911, | |
| "grad_norm": 0.3752327263355255, | |
| "learning_rate": 4.254743738226721e-05, | |
| "loss": 0.5398785591125488, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.33655868742111905, | |
| "grad_norm": 0.42189350724220276, | |
| "learning_rate": 4.201712553872658e-05, | |
| "loss": 0.5390230655670166, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34497265460664706, | |
| "grad_norm": 0.3766239583492279, | |
| "learning_rate": 4.147214514490278e-05, | |
| "loss": 0.518889045715332, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.353386621792175, | |
| "grad_norm": 0.38176998496055603, | |
| "learning_rate": 4.0912965967108125e-05, | |
| "loss": 0.5434842109680176, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.361800588977703, | |
| "grad_norm": 0.43197810649871826, | |
| "learning_rate": 4.034007001082985e-05, | |
| "loss": 0.5342769145965576, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.37021455616323096, | |
| "grad_norm": 0.4258919060230255, | |
| "learning_rate": 3.975395110524742e-05, | |
| "loss": 0.511136817932129, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.37862852334875896, | |
| "grad_norm": 0.42476603388786316, | |
| "learning_rate": 3.9155114477557933e-05, | |
| "loss": 0.5225476264953614, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3870424905342869, | |
| "grad_norm": 0.38390135765075684, | |
| "learning_rate": 3.854407631747654e-05, | |
| "loss": 0.5341035842895507, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.3954564577198149, | |
| "grad_norm": 0.3868181109428406, | |
| "learning_rate": 3.792136333228735e-05, | |
| "loss": 0.5320357799530029, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.40387042490534286, | |
| "grad_norm": 0.4116423726081848, | |
| "learning_rate": 3.728751229282836e-05, | |
| "loss": 0.523101806640625, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.41228439209087087, | |
| "grad_norm": 0.37969765067100525, | |
| "learning_rate": 3.664306957080159e-05, | |
| "loss": 0.5135246753692627, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.4206983592763988, | |
| "grad_norm": 0.4192858934402466, | |
| "learning_rate": 3.598859066780754e-05, | |
| "loss": 0.5182962417602539, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4291123264619268, | |
| "grad_norm": 0.3658738136291504, | |
| "learning_rate": 3.5324639736509714e-05, | |
| "loss": 0.5355247020721435, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.43752629364745477, | |
| "grad_norm": 0.4016229808330536, | |
| "learning_rate": 3.4651789094342044e-05, | |
| "loss": 0.513187026977539, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.44594026083298277, | |
| "grad_norm": 0.367687463760376, | |
| "learning_rate": 3.39706187301784e-05, | |
| "loss": 0.5053876876831055, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.4543542280185107, | |
| "grad_norm": 0.36950457096099854, | |
| "learning_rate": 3.3281715804389403e-05, | |
| "loss": 0.5256223201751709, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.4627681952040387, | |
| "grad_norm": 0.4080349802970886, | |
| "learning_rate": 3.258567414271748e-05, | |
| "loss": 0.5013936519622803, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.47118216238956667, | |
| "grad_norm": 0.4254259765148163, | |
| "learning_rate": 3.18830937244065e-05, | |
| "loss": 0.5354822635650635, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.4795961295750947, | |
| "grad_norm": 0.3755163252353668, | |
| "learning_rate": 3.117458016502711e-05, | |
| "loss": 0.5031180381774902, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.4880100967606226, | |
| "grad_norm": 0.36723464727401733, | |
| "learning_rate": 3.046074419444366e-05, | |
| "loss": 0.5144643783569336, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.49642406394615063, | |
| "grad_norm": 0.3998170495033264, | |
| "learning_rate": 2.9742201130372693e-05, | |
| "loss": 0.5088897705078125, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.5048380311316786, | |
| "grad_norm": 0.3749750554561615, | |
| "learning_rate": 2.901957034798671e-05, | |
| "loss": 0.4881998062133789, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5132519983172066, | |
| "grad_norm": 0.36973705887794495, | |
| "learning_rate": 2.8293474746020472e-05, | |
| "loss": 0.49605550765991213, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.5216659655027346, | |
| "grad_norm": 0.34159213304519653, | |
| "learning_rate": 2.756454020984009e-05, | |
| "loss": 0.516224479675293, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.5300799326882625, | |
| "grad_norm": 0.37420156598091125, | |
| "learning_rate": 2.68333950719376e-05, | |
| "loss": 0.5166028022766114, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.5384938998737905, | |
| "grad_norm": 0.40217989683151245, | |
| "learning_rate": 2.6100669570316195e-05, | |
| "loss": 0.5076315879821778, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.5469078670593185, | |
| "grad_norm": 0.40898215770721436, | |
| "learning_rate": 2.5366995305232916e-05, | |
| "loss": 0.5209317207336426, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5553218342448465, | |
| "grad_norm": 0.35764551162719727, | |
| "learning_rate": 2.463300469476709e-05, | |
| "loss": 0.4946465492248535, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5637358014303744, | |
| "grad_norm": 0.3629818558692932, | |
| "learning_rate": 2.3899330429683807e-05, | |
| "loss": 0.5308743476867676, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.5721497686159024, | |
| "grad_norm": 0.405501127243042, | |
| "learning_rate": 2.3166604928062406e-05, | |
| "loss": 0.498077392578125, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.5805637358014304, | |
| "grad_norm": 0.3686980903148651, | |
| "learning_rate": 2.243545979015992e-05, | |
| "loss": 0.4924039840698242, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.5889777029869584, | |
| "grad_norm": 0.37260791659355164, | |
| "learning_rate": 2.1706525253979534e-05, | |
| "loss": 0.49569120407104494, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5973916701724863, | |
| "grad_norm": 0.33350419998168945, | |
| "learning_rate": 2.0980429652013297e-05, | |
| "loss": 0.5090860843658447, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.6058056373580143, | |
| "grad_norm": 0.34768742322921753, | |
| "learning_rate": 2.025779886962731e-05, | |
| "loss": 0.5070259094238281, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.6142196045435423, | |
| "grad_norm": 0.420901894569397, | |
| "learning_rate": 1.9539255805556344e-05, | |
| "loss": 0.5386468887329101, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.6226335717290703, | |
| "grad_norm": 0.3629691004753113, | |
| "learning_rate": 1.8825419834972902e-05, | |
| "loss": 0.5100968360900879, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.6310475389145982, | |
| "grad_norm": 0.37897151708602905, | |
| "learning_rate": 1.811690627559351e-05, | |
| "loss": 0.4982123374938965, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6394615061001262, | |
| "grad_norm": 0.41103869676589966, | |
| "learning_rate": 1.7414325857282526e-05, | |
| "loss": 0.49430279731750487, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6478754732856542, | |
| "grad_norm": 0.419221967458725, | |
| "learning_rate": 1.6718284195610606e-05, | |
| "loss": 0.5015609741210938, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.6562894404711822, | |
| "grad_norm": 0.4170032739639282, | |
| "learning_rate": 1.6029381269821604e-05, | |
| "loss": 0.5064301490783691, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6647034076567101, | |
| "grad_norm": 0.3627830147743225, | |
| "learning_rate": 1.534821090565796e-05, | |
| "loss": 0.5212658882141114, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.6731173748422381, | |
| "grad_norm": 0.3786025941371918, | |
| "learning_rate": 1.4675360263490295e-05, | |
| "loss": 0.5047730445861817, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6815313420277661, | |
| "grad_norm": 0.35577592253685, | |
| "learning_rate": 1.4011409332192472e-05, | |
| "loss": 0.507427167892456, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.6899453092132941, | |
| "grad_norm": 0.4018078148365021, | |
| "learning_rate": 1.335693042919841e-05, | |
| "loss": 0.5077090740203858, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.698359276398822, | |
| "grad_norm": 0.42130208015441895, | |
| "learning_rate": 1.2712487707171645e-05, | |
| "loss": 0.5090289115905762, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.70677324358435, | |
| "grad_norm": 0.36082717776298523, | |
| "learning_rate": 1.2078636667712649e-05, | |
| "loss": 0.5091034889221191, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.715187210769878, | |
| "grad_norm": 0.4265519678592682, | |
| "learning_rate": 1.1455923682523475e-05, | |
| "loss": 0.517885971069336, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.723601177955406, | |
| "grad_norm": 0.34974387288093567, | |
| "learning_rate": 1.0844885522442074e-05, | |
| "loss": 0.5208765029907226, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.7320151451409339, | |
| "grad_norm": 0.35048907995224, | |
| "learning_rate": 1.0246048894752589e-05, | |
| "loss": 0.49442739486694337, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.7404291123264619, | |
| "grad_norm": 0.42127740383148193, | |
| "learning_rate": 9.659929989170154e-06, | |
| "loss": 0.4968879699707031, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.7488430795119899, | |
| "grad_norm": 0.39883238077163696, | |
| "learning_rate": 9.087034032891883e-06, | |
| "loss": 0.5004133224487305, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.7572570466975179, | |
| "grad_norm": 0.35957688093185425, | |
| "learning_rate": 8.527854855097225e-06, | |
| "loss": 0.47731876373291016, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.7656710138830458, | |
| "grad_norm": 0.3513461947441101, | |
| "learning_rate": 7.982874461273438e-06, | |
| "loss": 0.4781493186950684, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.7740849810685738, | |
| "grad_norm": 0.3396323323249817, | |
| "learning_rate": 7.452562617732794e-06, | |
| "loss": 0.48314857482910156, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.7824989482541018, | |
| "grad_norm": 0.35780707001686096, | |
| "learning_rate": 6.93737644667995e-06, | |
| "loss": 0.5017595291137695, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.7909129154396298, | |
| "grad_norm": 0.38778507709503174, | |
| "learning_rate": 6.4377600321782e-06, | |
| "loss": 0.507000732421875, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.7993268826251577, | |
| "grad_norm": 0.3847760856151581, | |
| "learning_rate": 5.954144037354645e-06, | |
| "loss": 0.5197389602661133, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.8077408498106857, | |
| "grad_norm": 0.45024698972702026, | |
| "learning_rate": 5.486945333173851e-06, | |
| "loss": 0.4876283645629883, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.8161548169962137, | |
| "grad_norm": 0.39939478039741516, | |
| "learning_rate": 5.036566639100351e-06, | |
| "loss": 0.5140261173248291, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.8245687841817417, | |
| "grad_norm": 0.35428670048713684, | |
| "learning_rate": 4.603396175959404e-06, | |
| "loss": 0.49584507942199707, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.8329827513672696, | |
| "grad_norm": 0.3984188139438629, | |
| "learning_rate": 4.187807331295549e-06, | |
| "loss": 0.5067983627319336, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.8413967185527976, | |
| "grad_norm": 0.3336002230644226, | |
| "learning_rate": 3.7901583375171273e-06, | |
| "loss": 0.48990588188171386, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8498106857383256, | |
| "grad_norm": 0.36534884572029114, | |
| "learning_rate": 3.4107919631044732e-06, | |
| "loss": 0.4993289947509766, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.8582246529238536, | |
| "grad_norm": 0.3818396031856537, | |
| "learning_rate": 3.0500352171476897e-06, | |
| "loss": 0.5111321449279785, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.8666386201093815, | |
| "grad_norm": 0.34951460361480713, | |
| "learning_rate": 2.708199067468939e-06, | |
| "loss": 0.5004692077636719, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.8750525872949095, | |
| "grad_norm": 0.34865912795066833, | |
| "learning_rate": 2.385578172572009e-06, | |
| "loss": 0.48421926498413087, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.8834665544804375, | |
| "grad_norm": 0.3657017648220062, | |
| "learning_rate": 2.0824506276503897e-06, | |
| "loss": 0.49608964920043946, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.8918805216659655, | |
| "grad_norm": 0.36945363879203796, | |
| "learning_rate": 1.7990777248726442e-06, | |
| "loss": 0.49359979629516604, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.9002944888514934, | |
| "grad_norm": 0.40284156799316406, | |
| "learning_rate": 1.5357037281518522e-06, | |
| "loss": 0.5033816337585449, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.9087084560370214, | |
| "grad_norm": 0.37313589453697205, | |
| "learning_rate": 1.2925556625931173e-06, | |
| "loss": 0.4955038547515869, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.9171224232225494, | |
| "grad_norm": 0.37710103392601013, | |
| "learning_rate": 1.0698431188007952e-06, | |
| "loss": 0.505764389038086, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.9255363904080774, | |
| "grad_norm": 0.36644142866134644, | |
| "learning_rate": 8.677580722139672e-07, | |
| "loss": 0.4921365737915039, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.9339503575936053, | |
| "grad_norm": 0.3648861050605774, | |
| "learning_rate": 6.864747176260289e-07, | |
| "loss": 0.5047013759613037, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.9423643247791333, | |
| "grad_norm": 0.34883520007133484, | |
| "learning_rate": 5.261493190309303e-07, | |
| "loss": 0.4873218536376953, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.9507782919646613, | |
| "grad_norm": 0.35124751925468445, | |
| "learning_rate": 3.8692007492557024e-07, | |
| "loss": 0.5037882804870606, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.9591922591501894, | |
| "grad_norm": 0.39010515809059143, | |
| "learning_rate": 2.6890699918440676e-07, | |
| "loss": 0.512601661682129, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.9676062263357172, | |
| "grad_norm": 0.3450499176979065, | |
| "learning_rate": 1.7221181760899152e-07, | |
| "loss": 0.49816131591796875, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.9760201935212452, | |
| "grad_norm": 0.3444308340549469, | |
| "learning_rate": 9.691788024160376e-08, | |
| "loss": 0.5218628883361817, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.9844341607067733, | |
| "grad_norm": 0.37698882818222046, | |
| "learning_rate": 4.3090089518540987e-08, | |
| "loss": 0.5030824661254882, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.9928481278923013, | |
| "grad_norm": 0.36695829033851624, | |
| "learning_rate": 1.0774844325039946e-08, | |
| "loss": 0.48960113525390625, | |
| "step": 1180 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1189, | |
| "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": 5.558831689184051e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |