Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lldois/v13_rec_cot_focus_lr2e5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lldois/v13_rec_cot_focus_lr2e5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lldois/v13_rec_cot_focus_lr2e5") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lldois/v13_rec_cot_focus_lr2e5") model = AutoModelForCausalLM.from_pretrained("lldois/v13_rec_cot_focus_lr2e5", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lldois/v13_rec_cot_focus_lr2e5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lldois/v13_rec_cot_focus_lr2e5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lldois/v13_rec_cot_focus_lr2e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lldois/v13_rec_cot_focus_lr2e5
- SGLang
How to use lldois/v13_rec_cot_focus_lr2e5 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 "lldois/v13_rec_cot_focus_lr2e5" \ --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": "lldois/v13_rec_cot_focus_lr2e5", "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 "lldois/v13_rec_cot_focus_lr2e5" \ --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": "lldois/v13_rec_cot_focus_lr2e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lldois/v13_rec_cot_focus_lr2e5 with Docker Model Runner:
docker model run hf.co/lldois/v13_rec_cot_focus_lr2e5
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 675, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007412898443291327, | |
| "grad_norm": 49.5, | |
| "learning_rate": 3.80952380952381e-06, | |
| "loss": 2.981045722961426, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014825796886582653, | |
| "grad_norm": 13.0, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 2.7763238906860352, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02223869532987398, | |
| "grad_norm": 7.59375, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.5071876525878904, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029651593773165306, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 1.8095238095238097e-05, | |
| "loss": 2.216544532775879, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.037064492216456635, | |
| "grad_norm": 3.453125, | |
| "learning_rate": 1.9998961636899736e-05, | |
| "loss": 2.02364444732666, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04447739065974796, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.9992616865520515e-05, | |
| "loss": 1.8605846405029296, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05189028910303929, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.998050784669941e-05, | |
| "loss": 1.8314769744873047, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05930318754633061, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.9962641565531694e-05, | |
| "loss": 1.7219036102294922, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06671608598962195, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.9939028328193097e-05, | |
| "loss": 1.6877906799316407, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07412898443291327, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.990968175599471e-05, | |
| "loss": 1.6538002014160156, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08154188287620459, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.987461877752552e-05, | |
| "loss": 1.6635187149047852, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08895478131949593, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.983385961888711e-05, | |
| "loss": 1.5999790191650392, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09636767976278725, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.978742779202627e-05, | |
| "loss": 1.572991943359375, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.10378057820607858, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.973535008117207e-05, | |
| "loss": 1.6114467620849608, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1111934766493699, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.9677656527385386e-05, | |
| "loss": 1.5769593238830566, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11860637509266123, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.9614380411229693e-05, | |
| "loss": 1.5900885581970214, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12601927353595255, | |
| "grad_norm": 2.125, | |
| "learning_rate": 1.9545558233573136e-05, | |
| "loss": 1.5888105392456056, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1334321719792439, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.9471229694533003e-05, | |
| "loss": 1.563032054901123, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14084507042253522, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 1.9391437670574656e-05, | |
| "loss": 1.5782450675964355, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.14825796886582654, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 1.9306228189778255e-05, | |
| "loss": 1.5569299697875976, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15567086730911786, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.9215650405287392e-05, | |
| "loss": 1.5072972297668457, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.16308376575240918, | |
| "grad_norm": 2.375, | |
| "learning_rate": 1.9119756566955092e-05, | |
| "loss": 1.4942115783691405, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.17049666419570053, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.901860199120344e-05, | |
| "loss": 1.5515302658081054, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.17790956263899185, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.891224502911428e-05, | |
| "loss": 1.4991122245788575, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18532246108228317, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 1.8800747032769343e-05, | |
| "loss": 1.4753767013549806, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1927353595255745, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.8684172319859258e-05, | |
| "loss": 1.4607695579528808, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.20014825796886582, | |
| "grad_norm": 2.125, | |
| "learning_rate": 1.856258813658188e-05, | |
| "loss": 1.461857509613037, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.20756115641215717, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.8436064618851225e-05, | |
| "loss": 1.530456256866455, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2149740548554485, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.8304674751839583e-05, | |
| "loss": 1.4979378700256347, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.2223869532987398, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 1.8168494327875918e-05, | |
| "loss": 1.4886467933654786, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22979985174203113, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 1.8027601902725065e-05, | |
| "loss": 1.4672227859497071, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.23721275018532245, | |
| "grad_norm": 2.0, | |
| "learning_rate": 1.788207875027274e-05, | |
| "loss": 1.4558910369873046, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2446256486286138, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.77320088156427e-05, | |
| "loss": 1.4654417037963867, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.2520385470719051, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.7577478666772886e-05, | |
| "loss": 1.4390137672424317, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.25945144551519644, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.741857744447869e-05, | |
| "loss": 1.4661806106567383, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2668643439584878, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 1.7255396811032014e-05, | |
| "loss": 1.472686767578125, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2742772424017791, | |
| "grad_norm": 3.328125, | |
| "learning_rate": 1.708803089728583e-05, | |
| "loss": 1.4672610282897949, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.28169014084507044, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.691657624837472e-05, | |
| "loss": 1.4069836616516114, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.28910303928836173, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.6741131768022777e-05, | |
| "loss": 1.471778392791748, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.2965159377316531, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.6561798661490904e-05, | |
| "loss": 1.4518500328063966, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.30392883617494443, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.6378680377196526e-05, | |
| "loss": 1.4200240135192872, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.3113417346182357, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 1.619188254703927e-05, | |
| "loss": 1.4366942405700684, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.31875463306152707, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.6001512925467153e-05, | |
| "loss": 1.4304126739501952, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.32616753150481836, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.5807681327318372e-05, | |
| "loss": 1.4636366844177247, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3335804299481097, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 1.5610499564474512e-05, | |
| "loss": 1.440121841430664, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.34099332839140106, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 1.541008138136183e-05, | |
| "loss": 1.4860041618347168, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.34840622683469236, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 1.520654238933767e-05, | |
| "loss": 1.4189085006713866, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.3558191252779837, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.407963466644287, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.363232023721275, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.4790573357458464e-05, | |
| "loss": 1.4134508132934571, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.37064492216456635, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.4578383269606004e-05, | |
| "loss": 1.425547218322754, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3780578206078577, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 1.4363552138430764e-05, | |
| "loss": 1.402323055267334, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.385470719051149, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.4146203889408418e-05, | |
| "loss": 1.4572528839111327, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.39288361749444034, | |
| "grad_norm": 1.9921875, | |
| "learning_rate": 1.392646390001569e-05, | |
| "loss": 1.3995424270629884, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.40029651593773163, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.3704458927406261e-05, | |
| "loss": 1.4161681175231933, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.407709414381023, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.3480317035290837e-05, | |
| "loss": 1.4083374977111816, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.41512231282431433, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.325416752006351e-05, | |
| "loss": 1.3747909545898438, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4225352112676056, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.302614083621705e-05, | |
| "loss": 1.4275038719177247, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.429948109710897, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.2796368521090143e-05, | |
| "loss": 1.3964252471923828, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.43736100815418827, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.256498311899001e-05, | |
| "loss": 1.401359462738037, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.4447739065974796, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 1.233211810473411e-05, | |
| "loss": 1.4066211700439453, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.45218680504077097, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.2097907806655136e-05, | |
| "loss": 1.3704119682312013, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.45959970348406226, | |
| "grad_norm": 2.125, | |
| "learning_rate": 1.1862487329113606e-05, | |
| "loss": 1.3963244438171387, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.4670126019273536, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.1625992474562846e-05, | |
| "loss": 1.402764892578125, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.4744255003706449, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 1.1388559665211241e-05, | |
| "loss": 1.417808437347412, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.48183839881393625, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.1150325864327003e-05, | |
| "loss": 1.4581987380981445, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.4892512972572276, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.0911428497230834e-05, | |
| "loss": 1.4179252624511718, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4966641957005189, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.0672005372022014e-05, | |
| "loss": 1.4111376762390138, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.5040770941438102, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.043219460008374e-05, | |
| "loss": 1.3600208282470703, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5114899925871016, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.019213451641347e-05, | |
| "loss": 1.3771323204040526, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.5189028910303929, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 9.951963599824294e-06, | |
| "loss": 1.3850160598754884, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 9.711820393063337e-06, | |
| "loss": 1.4168268203735352, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.5337286879169756, | |
| "grad_norm": 2.125, | |
| "learning_rate": 9.471843422893299e-06, | |
| "loss": 1.3890551567077636, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5411415863602669, | |
| "grad_norm": 1.9375, | |
| "learning_rate": 9.232171120183193e-06, | |
| "loss": 1.4085680961608886, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.5485544848035582, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 8.992941740054418e-06, | |
| "loss": 1.3939090728759767, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5559673832468495, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 8.754293282128187e-06, | |
| "loss": 1.4120423316955566, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 8.516363410920376e-06, | |
| "loss": 1.342286968231201, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5707931801334322, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 8.279289376429653e-06, | |
| "loss": 1.3686384201049804, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.5782060785767235, | |
| "grad_norm": 2.25, | |
| "learning_rate": 8.043207934964722e-06, | |
| "loss": 1.4198535919189452, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5856189770200149, | |
| "grad_norm": 1.8515625, | |
| "learning_rate": 7.808255270256368e-06, | |
| "loss": 1.4073737144470215, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.5930318754633062, | |
| "grad_norm": 3.125, | |
| "learning_rate": 7.574566914899779e-06, | |
| "loss": 1.3731096267700196, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6004447739065975, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 7.342277672172483e-06, | |
| "loss": 1.3820195198059082, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.6078576723498889, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 7.111521538272997e-06, | |
| "loss": 1.3672608375549316, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6152705707931801, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 6.882431625025016e-06, | |
| "loss": 1.352785873413086, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.6226834692364714, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 6.655140083091794e-06, | |
| "loss": 1.3680495262145995, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6300963676797627, | |
| "grad_norm": 2.375, | |
| "learning_rate": 6.42977802574494e-06, | |
| "loss": 1.4069809913635254, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.6375092661230541, | |
| "grad_norm": 1.953125, | |
| "learning_rate": 6.206475453231644e-06, | |
| "loss": 1.3522788047790528, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.6449221645663454, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 5.98536117778394e-06, | |
| "loss": 1.3570075035095215, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.6523350630096367, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 5.766562749313309e-06, | |
| "loss": 1.3594365119934082, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6597479614529281, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 5.550206381833409e-06, | |
| "loss": 1.4155049324035645, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.6671608598962194, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 5.336416880653461e-06, | |
| "loss": 1.3647008895874024, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6745737583395107, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 5.125317570384211e-06, | |
| "loss": 1.3679018020629883, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.6819866567828021, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 4.917030223798057e-06, | |
| "loss": 1.4130691528320312, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.6893995552260934, | |
| "grad_norm": 2.25, | |
| "learning_rate": 4.7116749915843356e-06, | |
| "loss": 1.3584203720092773, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.6968124536693847, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 4.5093703330403385e-06, | |
| "loss": 1.348178005218506, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.704225352112676, | |
| "grad_norm": 3.09375, | |
| "learning_rate": 4.310232947737979e-06, | |
| "loss": 1.3591523170471191, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.7116382505559674, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 4.1143777082055715e-06, | |
| "loss": 1.3993351936340332, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7190511489992587, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 3.921917593663538e-06, | |
| "loss": 1.3535401344299316, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.72646404744255, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 3.732963624852275e-06, | |
| "loss": 1.392369556427002, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.7338769458858414, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 3.5476247999897707e-06, | |
| "loss": 1.4015738487243652, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.7412898443291327, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 3.3660080318959043e-06, | |
| "loss": 1.3607392311096191, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.748702742772424, | |
| "grad_norm": 1.9296875, | |
| "learning_rate": 3.1882180863197308e-06, | |
| "loss": 1.3873835563659669, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.7561156412157154, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 3.0143575215052732e-06, | |
| "loss": 1.3514761924743652, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.7635285396590067, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 2.8445266290307515e-06, | |
| "loss": 1.3852715492248535, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.770941438102298, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 2.678823375955314e-06, | |
| "loss": 1.3499971389770509, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7783543365455893, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 2.5173433483066777e-06, | |
| "loss": 1.3455326080322265, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.7857672349888807, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 2.3601796959422585e-06, | |
| "loss": 1.3331590652465821, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.793180133432172, | |
| "grad_norm": 1.9375, | |
| "learning_rate": 2.2074230788156325e-06, | |
| "loss": 1.3671817779541016, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.8005930318754633, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 2.0591616146792705e-06, | |
| "loss": 1.3592339515686036, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8080059303187547, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 1.915480828253763e-06, | |
| "loss": 1.3896028518676757, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.815418828762046, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.7764636018928249e-06, | |
| "loss": 1.3742392539978028, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8228317272053373, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.6421901277725627e-06, | |
| "loss": 1.391466236114502, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.8302446256486287, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.5127378616325606e-06, | |
| "loss": 1.3652151107788086, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.83765752409192, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 1.3881814780954916e-06, | |
| "loss": 1.3537821769714355, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.8450704225352113, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.2685928275910142e-06, | |
| "loss": 1.347853660583496, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.8524833209785025, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 1.1540408949087956e-06, | |
| "loss": 1.3285847663879395, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.859896219421794, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.0445917594046073e-06, | |
| "loss": 1.4402085304260255, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.8673091178650852, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 9.403085568823988e-07, | |
| "loss": 1.4003355979919434, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.8747220163083765, | |
| "grad_norm": 2.25, | |
| "learning_rate": 8.412514431743657e-07, | |
| "loss": 1.3969636917114259, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.8821349147516679, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 7.474775594400252e-07, | |
| "loss": 1.3984580993652345, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.8895478131949592, | |
| "grad_norm": 3.46875, | |
| "learning_rate": 6.590409992042957e-07, | |
| "loss": 1.3271192550659179, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8969607116382505, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 5.759927771536167e-07, | |
| "loss": 1.3371945381164552, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.9043736100815419, | |
| "grad_norm": 1.8515625, | |
| "learning_rate": 4.983807997080925e-07, | |
| "loss": 1.3641469955444336, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.9117865085248332, | |
| "grad_norm": 1.875, | |
| "learning_rate": 4.262498373866486e-07, | |
| "loss": 1.3556190490722657, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.9191994069681245, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 3.5964149898111587e-07, | |
| "loss": 1.3831118583679198, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.9266123054114158, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 2.985942075541848e-07, | |
| "loss": 1.3703168869018554, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.9340252038547072, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 2.4314317827503375e-07, | |
| "loss": 1.3450684547424316, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.9414381022979985, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.9332039810543324e-07, | |
| "loss": 1.3397465705871583, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.9488510007412898, | |
| "grad_norm": 1.8125, | |
| "learning_rate": 1.49154607348051e-07, | |
| "loss": 1.3559181213378906, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.9562638991845812, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.1067128306758267e-07, | |
| "loss": 1.4002655029296875, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.9636767976278725, | |
| "grad_norm": 2.125, | |
| "learning_rate": 7.789262439430012e-08, | |
| "loss": 1.3875154495239257, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9710896960711638, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 5.083753971846239e-08, | |
| "loss": 1.3760144233703613, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.9785025945144552, | |
| "grad_norm": 1.828125, | |
| "learning_rate": 2.9521635783001932e-08, | |
| "loss": 1.3631325721740724, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.9859154929577465, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.3957208680761558e-08, | |
| "loss": 1.3682563781738282, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.9933283914010378, | |
| "grad_norm": 1.953125, | |
| "learning_rate": 4.153236761488266e-09, | |
| "loss": 1.3901843070983886, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.625, | |
| "learning_rate": 1.1537545266726568e-10, | |
| "loss": 1.4335641860961914, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 675, | |
| "total_flos": 3.2515782676161946e+17, | |
| "train_loss": 1.470360949480975, | |
| "train_runtime": 5409.9531, | |
| "train_samples_per_second": 0.499, | |
| "train_steps_per_second": 0.125 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 675, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2515782676161946e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |