Instructions to use OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("huihui-ai/Huihui-LFM2-2.6B-Exp-abliterated") model = PeftModel.from_pretrained(base_model, "OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter") - Transformers
How to use OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter
- SGLang
How to use OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter 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 "OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter" \ --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": "OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter", "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 "OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter" \ --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": "OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter 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 OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter 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 OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter", max_seq_length=2048, ) - Docker Model Runner
How to use OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter with Docker Model Runner:
docker model run hf.co/OpenIntelligenceNet/liquid-2.6B-QAT-LoRA-Adapter
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10958153551126636, | |
| "eval_steps": 500, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013697691938908295, | |
| "grad_norm": 0.36237362027168274, | |
| "learning_rate": 3.5e-06, | |
| "loss": 2.435038375854492, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002739538387781659, | |
| "grad_norm": 0.36249515414237976, | |
| "learning_rate": 8.5e-06, | |
| "loss": 2.2692413330078125, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004109307581672488, | |
| "grad_norm": 0.3869870603084564, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 2.338268280029297, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005479076775563318, | |
| "grad_norm": 0.43124574422836304, | |
| "learning_rate": 1.8500000000000002e-05, | |
| "loss": 2.3821529388427733, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006848845969454147, | |
| "grad_norm": 0.4636060893535614, | |
| "learning_rate": 1.9815789473684213e-05, | |
| "loss": 2.3642246246337892, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008218615163344977, | |
| "grad_norm": 0.4747641980648041, | |
| "learning_rate": 1.955263157894737e-05, | |
| "loss": 2.3556377410888674, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009588384357235805, | |
| "grad_norm": 0.6179090738296509, | |
| "learning_rate": 1.9289473684210526e-05, | |
| "loss": 2.3772085189819334, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.010958153551126636, | |
| "grad_norm": 0.6049761772155762, | |
| "learning_rate": 1.9026315789473686e-05, | |
| "loss": 2.2972381591796873, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.012327922745017464, | |
| "grad_norm": 0.6118033528327942, | |
| "learning_rate": 1.8763157894736843e-05, | |
| "loss": 2.352596473693848, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.013697691938908295, | |
| "grad_norm": 0.6712182760238647, | |
| "learning_rate": 1.8500000000000002e-05, | |
| "loss": 2.2117843627929688, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.015067461132799123, | |
| "grad_norm": 0.6315696239471436, | |
| "learning_rate": 1.823684210526316e-05, | |
| "loss": 2.239790344238281, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.016437230326689953, | |
| "grad_norm": 0.5321571230888367, | |
| "learning_rate": 1.7973684210526315e-05, | |
| "loss": 2.1258014678955077, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.017806999520580784, | |
| "grad_norm": 0.5182818174362183, | |
| "learning_rate": 1.7710526315789475e-05, | |
| "loss": 2.2043216705322264, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01917676871447161, | |
| "grad_norm": 0.5181311964988708, | |
| "learning_rate": 1.7447368421052632e-05, | |
| "loss": 2.166463088989258, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02054653790836244, | |
| "grad_norm": 0.48421230912208557, | |
| "learning_rate": 1.7184210526315788e-05, | |
| "loss": 2.1357837677001954, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02191630710225327, | |
| "grad_norm": 0.4353867769241333, | |
| "learning_rate": 1.6921052631578948e-05, | |
| "loss": 2.0161502838134764, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.023286076296144098, | |
| "grad_norm": 0.4691782593727112, | |
| "learning_rate": 1.6657894736842105e-05, | |
| "loss": 2.0219562530517576, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.02465584549003493, | |
| "grad_norm": 0.49481505155563354, | |
| "learning_rate": 1.6394736842105265e-05, | |
| "loss": 2.0304351806640626, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02602561468392576, | |
| "grad_norm": 0.3865645229816437, | |
| "learning_rate": 1.613157894736842e-05, | |
| "loss": 1.9581424713134765, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02739538387781659, | |
| "grad_norm": 0.43848446011543274, | |
| "learning_rate": 1.586842105263158e-05, | |
| "loss": 1.981527328491211, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.028765153071707416, | |
| "grad_norm": 0.39352574944496155, | |
| "learning_rate": 1.5605263157894737e-05, | |
| "loss": 2.059296798706055, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.030134922265598246, | |
| "grad_norm": 0.46410003304481506, | |
| "learning_rate": 1.5342105263157897e-05, | |
| "loss": 1.913700485229492, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.03150469145948907, | |
| "grad_norm": 0.3708699345588684, | |
| "learning_rate": 1.5078947368421054e-05, | |
| "loss": 1.9376255035400392, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.03287446065337991, | |
| "grad_norm": 0.410113126039505, | |
| "learning_rate": 1.4815789473684212e-05, | |
| "loss": 1.9357620239257813, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.034244229847270734, | |
| "grad_norm": 0.34002822637557983, | |
| "learning_rate": 1.455263157894737e-05, | |
| "loss": 1.855245590209961, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.03561399904116157, | |
| "grad_norm": 0.38149112462997437, | |
| "learning_rate": 1.4289473684210527e-05, | |
| "loss": 1.8379920959472655, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.036983768235052394, | |
| "grad_norm": 0.3515079915523529, | |
| "learning_rate": 1.4026315789473685e-05, | |
| "loss": 1.9092113494873046, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.03835353742894322, | |
| "grad_norm": 0.34938475489616394, | |
| "learning_rate": 1.3763157894736843e-05, | |
| "loss": 1.83590087890625, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.039723306622834055, | |
| "grad_norm": 0.3297061324119568, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 1.9256158828735352, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.04109307581672488, | |
| "grad_norm": 0.36877989768981934, | |
| "learning_rate": 1.323684210526316e-05, | |
| "loss": 1.8834123611450195, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.04246284501061571, | |
| "grad_norm": 0.29596567153930664, | |
| "learning_rate": 1.2973684210526316e-05, | |
| "loss": 1.7876396179199219, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.04383261420450654, | |
| "grad_norm": 0.31500086188316345, | |
| "learning_rate": 1.2710526315789476e-05, | |
| "loss": 1.8464454650878905, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.04520238339839737, | |
| "grad_norm": 0.3053838610649109, | |
| "learning_rate": 1.2447368421052632e-05, | |
| "loss": 1.8393360137939454, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.046572152592288196, | |
| "grad_norm": 0.3389897346496582, | |
| "learning_rate": 1.2184210526315789e-05, | |
| "loss": 1.8508255004882812, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.04794192178617903, | |
| "grad_norm": 0.27679404616355896, | |
| "learning_rate": 1.1921052631578949e-05, | |
| "loss": 1.8790317535400392, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04931169098006986, | |
| "grad_norm": 0.29857176542282104, | |
| "learning_rate": 1.1657894736842105e-05, | |
| "loss": 1.8166206359863282, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.05068146017396069, | |
| "grad_norm": 0.307064950466156, | |
| "learning_rate": 1.1394736842105265e-05, | |
| "loss": 1.740498161315918, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.05205122936785152, | |
| "grad_norm": 0.2849220931529999, | |
| "learning_rate": 1.1131578947368421e-05, | |
| "loss": 1.86405029296875, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.053420998561742344, | |
| "grad_norm": 0.2507258653640747, | |
| "learning_rate": 1.086842105263158e-05, | |
| "loss": 1.8203811645507812, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.05479076775563318, | |
| "grad_norm": 0.32056924700737, | |
| "learning_rate": 1.0605263157894738e-05, | |
| "loss": 1.8383829116821289, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.056160536949524005, | |
| "grad_norm": 0.3862442374229431, | |
| "learning_rate": 1.0342105263157896e-05, | |
| "loss": 1.7965122222900392, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.05753030614341483, | |
| "grad_norm": 0.2158074676990509, | |
| "learning_rate": 1.0078947368421053e-05, | |
| "loss": 1.7655912399291993, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.058900075337305666, | |
| "grad_norm": 0.27215778827667236, | |
| "learning_rate": 9.815789473684212e-06, | |
| "loss": 1.7762609481811524, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.06026984453119649, | |
| "grad_norm": 0.2439756989479065, | |
| "learning_rate": 9.552631578947369e-06, | |
| "loss": 1.7678848266601563, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.06163961372508732, | |
| "grad_norm": 0.3162086009979248, | |
| "learning_rate": 9.289473684210527e-06, | |
| "loss": 1.8514827728271483, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.06300938291897815, | |
| "grad_norm": 0.280586838722229, | |
| "learning_rate": 9.026315789473685e-06, | |
| "loss": 1.8047622680664062, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.06437915211286899, | |
| "grad_norm": 0.22920483350753784, | |
| "learning_rate": 8.763157894736842e-06, | |
| "loss": 1.7634853363037108, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.06574892130675981, | |
| "grad_norm": 0.2582913637161255, | |
| "learning_rate": 8.5e-06, | |
| "loss": 1.8084178924560548, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.06711869050065064, | |
| "grad_norm": 0.22125154733657837, | |
| "learning_rate": 8.236842105263158e-06, | |
| "loss": 1.7368389129638673, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.06848845969454147, | |
| "grad_norm": 0.22868144512176514, | |
| "learning_rate": 7.973684210526316e-06, | |
| "loss": 1.7524850845336915, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0698582288884323, | |
| "grad_norm": 0.42042723298072815, | |
| "learning_rate": 7.710526315789474e-06, | |
| "loss": 1.7123191833496094, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.07122799808232314, | |
| "grad_norm": 0.2862432599067688, | |
| "learning_rate": 7.447368421052632e-06, | |
| "loss": 1.729414939880371, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.07259776727621396, | |
| "grad_norm": 0.2237967550754547, | |
| "learning_rate": 7.18421052631579e-06, | |
| "loss": 1.7572792053222657, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.07396753647010479, | |
| "grad_norm": 0.2615198493003845, | |
| "learning_rate": 6.921052631578948e-06, | |
| "loss": 1.78935546875, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.07533730566399562, | |
| "grad_norm": 0.215779110789299, | |
| "learning_rate": 6.6578947368421055e-06, | |
| "loss": 1.753053855895996, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.07670707485788644, | |
| "grad_norm": 0.20498128235340118, | |
| "learning_rate": 6.394736842105264e-06, | |
| "loss": 1.6631881713867187, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.07807684405177727, | |
| "grad_norm": 0.216533824801445, | |
| "learning_rate": 6.131578947368422e-06, | |
| "loss": 1.7446210861206055, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.07944661324566811, | |
| "grad_norm": 0.25069892406463623, | |
| "learning_rate": 5.86842105263158e-06, | |
| "loss": 1.805841064453125, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.08081638243955894, | |
| "grad_norm": 0.2501865327358246, | |
| "learning_rate": 5.605263157894737e-06, | |
| "loss": 1.7990594863891602, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.08218615163344976, | |
| "grad_norm": 0.23411990702152252, | |
| "learning_rate": 5.342105263157895e-06, | |
| "loss": 1.72657470703125, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.08355592082734059, | |
| "grad_norm": 0.25468888878822327, | |
| "learning_rate": 5.078947368421053e-06, | |
| "loss": 1.6869335174560547, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.08492569002123142, | |
| "grad_norm": 0.20213402807712555, | |
| "learning_rate": 4.815789473684211e-06, | |
| "loss": 1.6238441467285156, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.08629545921512226, | |
| "grad_norm": 0.22670616209506989, | |
| "learning_rate": 4.552631578947369e-06, | |
| "loss": 1.7246341705322266, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.08766522840901309, | |
| "grad_norm": 0.27973708510398865, | |
| "learning_rate": 4.289473684210527e-06, | |
| "loss": 1.7155805587768556, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.08903499760290391, | |
| "grad_norm": 0.24762506783008575, | |
| "learning_rate": 4.026315789473684e-06, | |
| "loss": 1.706759262084961, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.09040476679679474, | |
| "grad_norm": 0.3544348478317261, | |
| "learning_rate": 3.7631578947368426e-06, | |
| "loss": 1.676065444946289, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.09177453599068557, | |
| "grad_norm": 0.213600754737854, | |
| "learning_rate": 3.5e-06, | |
| "loss": 1.7575370788574218, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.09314430518457639, | |
| "grad_norm": 0.20907212793827057, | |
| "learning_rate": 3.236842105263158e-06, | |
| "loss": 1.681616973876953, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.09451407437846723, | |
| "grad_norm": 0.2494778037071228, | |
| "learning_rate": 2.973684210526316e-06, | |
| "loss": 1.7092714309692383, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.09588384357235806, | |
| "grad_norm": 0.2179274708032608, | |
| "learning_rate": 2.710526315789474e-06, | |
| "loss": 1.7354896545410157, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.09725361276624889, | |
| "grad_norm": 0.24646683037281036, | |
| "learning_rate": 2.447368421052632e-06, | |
| "loss": 1.723104476928711, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.09862338196013971, | |
| "grad_norm": 0.21943680942058563, | |
| "learning_rate": 2.1842105263157896e-06, | |
| "loss": 1.8309019088745118, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.09999315115403054, | |
| "grad_norm": 0.2424953579902649, | |
| "learning_rate": 1.9210526315789474e-06, | |
| "loss": 1.703164291381836, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.10136292034792138, | |
| "grad_norm": 0.2525971531867981, | |
| "learning_rate": 1.6578947368421053e-06, | |
| "loss": 1.7882774353027344, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.10273268954181221, | |
| "grad_norm": 0.2217267006635666, | |
| "learning_rate": 1.394736842105263e-06, | |
| "loss": 1.7480182647705078, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.10410245873570304, | |
| "grad_norm": 0.2686385214328766, | |
| "learning_rate": 1.1315789473684213e-06, | |
| "loss": 1.712969970703125, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.10547222792959386, | |
| "grad_norm": 0.23270924389362335, | |
| "learning_rate": 8.68421052631579e-07, | |
| "loss": 1.727523422241211, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.10684199712348469, | |
| "grad_norm": 0.21745167672634125, | |
| "learning_rate": 6.052631578947369e-07, | |
| "loss": 1.7345813751220702, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.10821176631737552, | |
| "grad_norm": 0.24494187533855438, | |
| "learning_rate": 3.421052631578948e-07, | |
| "loss": 1.7722370147705078, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.10958153551126636, | |
| "grad_norm": 0.19390442967414856, | |
| "learning_rate": 7.894736842105264e-08, | |
| "loss": 1.760666275024414, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9111174457838797e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |