Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lldois/v12_user_cot_focus_lr15e6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lldois/v12_user_cot_focus_lr15e6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lldois/v12_user_cot_focus_lr15e6") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lldois/v12_user_cot_focus_lr15e6") model = AutoModelForCausalLM.from_pretrained("lldois/v12_user_cot_focus_lr15e6", 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/v12_user_cot_focus_lr15e6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lldois/v12_user_cot_focus_lr15e6" # 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/v12_user_cot_focus_lr15e6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lldois/v12_user_cot_focus_lr15e6
- SGLang
How to use lldois/v12_user_cot_focus_lr15e6 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/v12_user_cot_focus_lr15e6" \ --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/v12_user_cot_focus_lr15e6", "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/v12_user_cot_focus_lr15e6" \ --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/v12_user_cot_focus_lr15e6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lldois/v12_user_cot_focus_lr15e6 with Docker Model Runner:
docker model run hf.co/lldois/v12_user_cot_focus_lr15e6
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 927, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005398110661268556, | |
| "grad_norm": 46.5, | |
| "learning_rate": 2.1428571428571427e-06, | |
| "loss": 2.6865272521972656, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010796221322537112, | |
| "grad_norm": 25.5, | |
| "learning_rate": 4.821428571428572e-06, | |
| "loss": 2.7759025573730467, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016194331983805668, | |
| "grad_norm": 9.625, | |
| "learning_rate": 7.5e-06, | |
| "loss": 2.3364213943481444, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021592442645074223, | |
| "grad_norm": 10.0625, | |
| "learning_rate": 1.0178571428571429e-05, | |
| "loss": 2.357875442504883, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02699055330634278, | |
| "grad_norm": 7.125, | |
| "learning_rate": 1.2857142857142857e-05, | |
| "loss": 2.113478088378906, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032388663967611336, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.4999954205725012e-05, | |
| "loss": 2.0126585006713866, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.037786774628879895, | |
| "grad_norm": 3.546875, | |
| "learning_rate": 1.4998351464818896e-05, | |
| "loss": 1.952888298034668, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.043184885290148446, | |
| "grad_norm": 3.875, | |
| "learning_rate": 1.4994459569363502e-05, | |
| "loss": 1.7912431716918946, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.048582995951417005, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.4988279707506684e-05, | |
| "loss": 1.7172063827514648, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05398110661268556, | |
| "grad_norm": 3.828125, | |
| "learning_rate": 1.4979813765884318e-05, | |
| "loss": 1.6440818786621094, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.059379217273954114, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.4969064329044335e-05, | |
| "loss": 1.691044235229492, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06477732793522267, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 1.4956034678657697e-05, | |
| "loss": 1.6486940383911133, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 1.4940728792516532e-05, | |
| "loss": 1.621745491027832, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07557354925775979, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 1.492315134331978e-05, | |
| "loss": 1.7037588119506837, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08097165991902834, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.490330769724665e-05, | |
| "loss": 1.5873713493347168, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08636977058029689, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 1.4881203912318417e-05, | |
| "loss": 1.5764989852905273, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09176788124156546, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.4856846736548972e-05, | |
| "loss": 1.6242074966430664, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.09716599190283401, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 1.4830243605884732e-05, | |
| "loss": 1.5501031875610352, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 1.4801402641934543e-05, | |
| "loss": 1.7399942398071289, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.10796221322537113, | |
| "grad_norm": 3.46875, | |
| "learning_rate": 1.4770332649490248e-05, | |
| "loss": 1.5935526847839356, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11336032388663968, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.4737043113838703e-05, | |
| "loss": 1.6135421752929688, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.11875843454790823, | |
| "grad_norm": 3.734375, | |
| "learning_rate": 1.4701544197866017e-05, | |
| "loss": 1.4750379562377929, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1241565452091768, | |
| "grad_norm": 3.421875, | |
| "learning_rate": 1.4663846738954966e-05, | |
| "loss": 1.5500977516174317, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.12955465587044535, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 1.4623962245676462e-05, | |
| "loss": 1.4977538108825683, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1349527665317139, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.4581902894276133e-05, | |
| "loss": 1.5538610458374023, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 3.515625, | |
| "learning_rate": 1.4537681524957061e-05, | |
| "loss": 1.5750856399536133, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.145748987854251, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.4491311637959828e-05, | |
| "loss": 1.5172950744628906, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.15114709851551958, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.4442807389441062e-05, | |
| "loss": 1.4594326972961427, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15654520917678813, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 1.439218358715173e-05, | |
| "loss": 1.5347204208374023, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.16194331983805668, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.4339455685916516e-05, | |
| "loss": 1.490595531463623, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16734143049932523, | |
| "grad_norm": 3.421875, | |
| "learning_rate": 1.4284639782915652e-05, | |
| "loss": 1.4158689498901367, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.17273954116059378, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 1.4227752612770654e-05, | |
| "loss": 1.4857367515563964, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17813765182186234, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.4168811542435435e-05, | |
| "loss": 1.5408924102783204, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.18353576248313092, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 1.4107834565894396e-05, | |
| "loss": 1.6404100418090821, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.18893387314439947, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.4044840298669085e-05, | |
| "loss": 1.5440165519714355, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.19433198380566802, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 1.3979847972135099e-05, | |
| "loss": 1.4469735145568847, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.19973009446693657, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.391287742765099e-05, | |
| "loss": 1.4575271606445312, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.3843949110500939e-05, | |
| "loss": 1.468193817138672, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 1.3773084063653057e-05, | |
| "loss": 1.380112075805664, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.21592442645074225, | |
| "grad_norm": 3.71875, | |
| "learning_rate": 1.3700303921335235e-05, | |
| "loss": 1.4284241676330567, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2213225371120108, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.3625630902430466e-05, | |
| "loss": 1.4978090286254884, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.22672064777327935, | |
| "grad_norm": 3.3125, | |
| "learning_rate": 1.3549087803693715e-05, | |
| "loss": 1.4717984199523926, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2321187584345479, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 1.3470697992792328e-05, | |
| "loss": 1.5032032966613769, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.23751686909581646, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 1.339048540117218e-05, | |
| "loss": 1.539174461364746, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.242914979757085, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.3308474516751701e-05, | |
| "loss": 1.4706098556518554, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.2483130904183536, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 1.322469037644601e-05, | |
| "loss": 1.4873103141784667, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.25371120107962214, | |
| "grad_norm": 3.046875, | |
| "learning_rate": 1.3139158558523457e-05, | |
| "loss": 1.4533129692077638, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2591093117408907, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.3051905174796882e-05, | |
| "loss": 1.5055602073669434, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.26450742240215924, | |
| "grad_norm": 2.375, | |
| "learning_rate": 1.296295686265202e-05, | |
| "loss": 1.4806604385375977, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.2699055330634278, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.2872340776915414e-05, | |
| "loss": 1.463977336883545, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.27530364372469635, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.2780084581564391e-05, | |
| "loss": 1.445403480529785, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 1.2686216441281581e-05, | |
| "loss": 1.4426302909851074, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.28609986504723345, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.2590765012856599e-05, | |
| "loss": 1.4424419403076172, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.291497975708502, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.2493759436437467e-05, | |
| "loss": 1.3920962333679199, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.2968960863697706, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 1.2395229326634489e-05, | |
| "loss": 1.481032943725586, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.30229419703103916, | |
| "grad_norm": 3.171875, | |
| "learning_rate": 1.2295204763479281e-05, | |
| "loss": 1.3904236793518066, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 3.34375, | |
| "learning_rate": 1.2193716283241692e-05, | |
| "loss": 1.4106941223144531, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.31309041835357626, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 1.2090794869107473e-05, | |
| "loss": 1.4160966873168945, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.3184885290148448, | |
| "grad_norm": 4.375, | |
| "learning_rate": 1.1986471941719478e-05, | |
| "loss": 1.392179298400879, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.32388663967611336, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 1.1880779349585331e-05, | |
| "loss": 1.4000489234924316, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3292847503373819, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.1773749359354481e-05, | |
| "loss": 1.482375717163086, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.33468286099865047, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.166541464596757e-05, | |
| "loss": 1.5753582000732422, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.340080971659919, | |
| "grad_norm": 3.59375, | |
| "learning_rate": 1.1555808282681187e-05, | |
| "loss": 1.3877858161926269, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.34547908232118757, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.1444963730971009e-05, | |
| "loss": 1.3945396423339844, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 3.125, | |
| "learning_rate": 1.1332914830316416e-05, | |
| "loss": 1.3506329536437989, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.3562753036437247, | |
| "grad_norm": 3.296875, | |
| "learning_rate": 1.121969578786973e-05, | |
| "loss": 1.4695911407470703, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.3616734143049933, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.1105341168013172e-05, | |
| "loss": 1.350149440765381, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.36707152496626183, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 1.098988588180679e-05, | |
| "loss": 1.4387104034423828, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3724696356275304, | |
| "grad_norm": 3.421875, | |
| "learning_rate": 1.0873365176330553e-05, | |
| "loss": 1.3866162300109863, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.37786774628879893, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.0755814623923825e-05, | |
| "loss": 1.4232500076293946, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3832658569500675, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 1.0637270111325591e-05, | |
| "loss": 1.483820629119873, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.38866396761133604, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.0517767828718664e-05, | |
| "loss": 1.429130458831787, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3940620782726046, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 1.0397344258681267e-05, | |
| "loss": 1.435228157043457, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.39946018893387314, | |
| "grad_norm": 3.328125, | |
| "learning_rate": 1.027603616504936e-05, | |
| "loss": 1.508815097808838, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.4048582995951417, | |
| "grad_norm": 3.625, | |
| "learning_rate": 1.0153880581693075e-05, | |
| "loss": 1.486521339416504, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 1.0030914801210753e-05, | |
| "loss": 1.3994467735290528, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4156545209176788, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 9.907176363543956e-06, | |
| "loss": 1.417519474029541, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 9.782703044516986e-06, | |
| "loss": 1.485072708129883, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.42645074224021595, | |
| "grad_norm": 3.984375, | |
| "learning_rate": 9.657532844304396e-06, | |
| "loss": 1.4095831871032716, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.4318488529014845, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 9.531703975829994e-06, | |
| "loss": 1.5393587112426759, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.43724696356275305, | |
| "grad_norm": 3.3125, | |
| "learning_rate": 9.405254853100927e-06, | |
| "loss": 1.4214500427246093, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.4426450742240216, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 9.278224079480331e-06, | |
| "loss": 1.3928979873657226, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.44804318488529016, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 9.150650435902215e-06, | |
| "loss": 1.4364460945129394, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.4534412955465587, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 9.022572869032115e-06, | |
| "loss": 1.3835034370422363, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.45883940620782726, | |
| "grad_norm": 2.75, | |
| "learning_rate": 8.894030479377152e-06, | |
| "loss": 1.4032472610473632, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.4642375168690958, | |
| "grad_norm": 3.84375, | |
| "learning_rate": 8.765062509349134e-06, | |
| "loss": 1.3748113632202148, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.46963562753036436, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 8.635708331284326e-06, | |
| "loss": 1.4337423324584961, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.4750337381916329, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 8.506007435423558e-06, | |
| "loss": 1.4276753425598145, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.48043184885290147, | |
| "grad_norm": 2.375, | |
| "learning_rate": 8.375999417856343e-06, | |
| "loss": 1.3890512466430665, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.48582995951417, | |
| "grad_norm": 2.875, | |
| "learning_rate": 8.24572396843268e-06, | |
| "loss": 1.4220175743103027, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 8.11522085864622e-06, | |
| "loss": 1.4079001426696778, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.4966261808367072, | |
| "grad_norm": 3.765625, | |
| "learning_rate": 7.984529929492535e-06, | |
| "loss": 1.369932270050049, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5020242914979757, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 7.853691079306129e-06, | |
| "loss": 1.269005298614502, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.5074224021592443, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 7.722744251579988e-06, | |
| "loss": 1.3606270790100097, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 7.591729422771317e-06, | |
| "loss": 1.4284911155700684, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5182186234817814, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 7.460686590097202e-06, | |
| "loss": 1.449836254119873, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5236167341430499, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 7.3296557593239795e-06, | |
| "loss": 1.3596923828125, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.5290148448043185, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 7.1986769325539485e-06, | |
| "loss": 1.3217558860778809, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5344129554655871, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 7.067790096013219e-06, | |
| "loss": 1.4159544944763183, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.5398110661268556, | |
| "grad_norm": 2.75, | |
| "learning_rate": 6.93703520784442e-06, | |
| "loss": 1.4698023796081543, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5452091767881242, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 6.806452185907963e-06, | |
| "loss": 1.4592896461486817, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.5506072874493927, | |
| "grad_norm": 2.578125, | |
| "learning_rate": 6.676080895595617e-06, | |
| "loss": 1.440026092529297, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5560053981106613, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 6.545961137660077e-06, | |
| "loss": 1.4954944610595704, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 3.453125, | |
| "learning_rate": 6.416132636064301e-06, | |
| "loss": 1.4568126678466797, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5668016194331984, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 6.2866350258542645e-06, | |
| "loss": 1.4184711456298829, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5721997300944669, | |
| "grad_norm": 2.890625, | |
| "learning_rate": 6.157507841058874e-06, | |
| "loss": 1.4063173294067384, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5775978407557355, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 6.028790502620701e-06, | |
| "loss": 1.3004539489746094, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.582995951417004, | |
| "grad_norm": 3.296875, | |
| "learning_rate": 5.900522306361271e-06, | |
| "loss": 1.3872806549072265, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5883940620782726, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 5.772742410984511e-06, | |
| "loss": 1.3209671020507812, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.5937921727395412, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 5.645489826122098e-06, | |
| "loss": 1.5138866424560546, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5991902834008097, | |
| "grad_norm": 3.75, | |
| "learning_rate": 5.518803400424286e-06, | |
| "loss": 1.383652400970459, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.6045883940620783, | |
| "grad_norm": 3.625, | |
| "learning_rate": 5.392721809699897e-06, | |
| "loss": 1.4016658782958984, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6099865047233468, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 5.267283545109068e-06, | |
| "loss": 1.3988656997680664, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 5.142526901412366e-06, | |
| "loss": 1.4131988525390624, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.6207827260458839, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 5.018489965279887e-06, | |
| "loss": 1.3934114456176758, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6261808367071525, | |
| "grad_norm": 3.09375, | |
| "learning_rate": 4.895210603663849e-06, | |
| "loss": 1.3578675270080567, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 4.772726452238277e-06, | |
| "loss": 1.4002360343933105, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.6369770580296896, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 4.651074903909303e-06, | |
| "loss": 1.2647083282470704, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6423751686909581, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 4.5302930973995636e-06, | |
| "loss": 1.402871036529541, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.6477732793522267, | |
| "grad_norm": 2.25, | |
| "learning_rate": 4.4104179059102066e-06, | |
| "loss": 1.3439860343933105, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6531713900134952, | |
| "grad_norm": 3.796875, | |
| "learning_rate": 4.291485925863952e-06, | |
| "loss": 1.3316984176635742, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.6585695006747638, | |
| "grad_norm": 2.875, | |
| "learning_rate": 4.173533465732669e-06, | |
| "loss": 1.4628570556640625, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6639676113360324, | |
| "grad_norm": 3.390625, | |
| "learning_rate": 4.056596534952823e-06, | |
| "loss": 1.3681221961975099, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.6693657219973009, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 3.940710832932262e-06, | |
| "loss": 1.4698673248291017, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6747638326585695, | |
| "grad_norm": 3.09375, | |
| "learning_rate": 3.8259117381516e-06, | |
| "loss": 1.3489319801330566, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.680161943319838, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 3.712234297363618e-06, | |
| "loss": 1.3783289909362793, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6855600539811066, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 3.5997132148939237e-06, | |
| "loss": 1.5137944221496582, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.6909581646423751, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 3.488382842046137e-06, | |
| "loss": 1.2776326179504394, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6963562753036437, | |
| "grad_norm": 3.953125, | |
| "learning_rate": 3.3782771666148696e-06, | |
| "loss": 1.3425775527954102, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 3.26942980250965e-06, | |
| "loss": 1.3643362998962403, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7071524966261808, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 3.1618739794930366e-06, | |
| "loss": 1.4447607040405273, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.7125506072874493, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 3.055642533035964e-06, | |
| "loss": 1.406121826171875, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 3.765625, | |
| "learning_rate": 2.9507678942934702e-06, | |
| "loss": 1.2962283134460448, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.7233468286099866, | |
| "grad_norm": 3.859375, | |
| "learning_rate": 2.8472820802038847e-06, | |
| "loss": 1.3783414840698243, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.728744939271255, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 2.745216683714428e-06, | |
| "loss": 1.3261849403381347, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.7341430499325237, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 2.6446028641362934e-06, | |
| "loss": 1.5042543411254883, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7395411605937922, | |
| "grad_norm": 3.875, | |
| "learning_rate": 2.5454713376320764e-06, | |
| "loss": 1.3572941780090333, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.7449392712550608, | |
| "grad_norm": 3.046875, | |
| "learning_rate": 2.4478523678385194e-06, | |
| "loss": 1.3866613388061524, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7503373819163293, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 2.3517757566273827e-06, | |
| "loss": 1.4149866104125977, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.7557354925775979, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 2.257270835007314e-06, | |
| "loss": 1.3730114936828612, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7611336032388664, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 2.1643664541694376e-06, | |
| "loss": 1.2785679817199707, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.766531713900135, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 2.073090976679452e-06, | |
| "loss": 1.229942226409912, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7719298245614035, | |
| "grad_norm": 2.375, | |
| "learning_rate": 1.983472267818883e-06, | |
| "loss": 1.3718143463134767, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.7773279352226721, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 1.8955376870781552e-06, | |
| "loss": 1.402730655670166, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.7827260458839406, | |
| "grad_norm": 3.390625, | |
| "learning_rate": 1.8093140798040686e-06, | |
| "loss": 1.3430524826049806, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.7881241565452092, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.7248277690042604e-06, | |
| "loss": 1.4013592720031738, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.7935222672064778, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.642104547311099e-06, | |
| "loss": 1.407256507873535, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.7989203778677463, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.5611696691075208e-06, | |
| "loss": 1.4018988609313965, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.8043184885290149, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.4820478428171713e-06, | |
| "loss": 1.3888368606567383, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.8097165991902834, | |
| "grad_norm": 2.125, | |
| "learning_rate": 1.4047632233612263e-06, | |
| "loss": 1.444268035888672, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.815114709851552, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 1.3293394047841987e-06, | |
| "loss": 1.4442663192749023, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.2557994130509583e-06, | |
| "loss": 1.4278512001037598, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.8259109311740891, | |
| "grad_norm": 3.421875, | |
| "learning_rate": 1.184165699017195e-06, | |
| "loss": 1.4104692459106445, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.8313090418353576, | |
| "grad_norm": 3.96875, | |
| "learning_rate": 1.1144601315754397e-06, | |
| "loss": 1.3686716079711914, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.8367071524966262, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.0467039909787668e-06, | |
| "loss": 1.4443007469177247, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 4.125, | |
| "learning_rate": 9.809179623441958e-07, | |
| "loss": 1.411851978302002, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8475033738191633, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 9.171221293377735e-07, | |
| "loss": 1.491429901123047, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.8529014844804319, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 8.553359680432815e-07, | |
| "loss": 1.3643847465515138, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.8582995951417004, | |
| "grad_norm": 3.5, | |
| "learning_rate": 7.95578341016428e-07, | |
| "loss": 1.3733964920043946, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.863697705802969, | |
| "grad_norm": 4.375, | |
| "learning_rate": 7.378674915263359e-07, | |
| "loss": 1.270117950439453, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8690958164642375, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 6.822210379861002e-07, | |
| "loss": 1.4278650283813477, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.8744939271255061, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 6.286559685741076e-07, | |
| "loss": 1.388138484954834, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.8798920377867746, | |
| "grad_norm": 3.5, | |
| "learning_rate": 5.77188636047746e-07, | |
| "loss": 1.5160203933715821, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.8852901484480432, | |
| "grad_norm": 3.21875, | |
| "learning_rate": 5.278347527511174e-07, | |
| "loss": 1.3769659042358398, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.8906882591093117, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 4.806093858182428e-07, | |
| "loss": 1.4992185592651368, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.8960863697705803, | |
| "grad_norm": 3.21875, | |
| "learning_rate": 4.3552695257325775e-07, | |
| "loss": 1.3635730743408203, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.9014844804318488, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 3.9260121612898244e-07, | |
| "loss": 1.4149579048156737, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.9068825910931174, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 3.5184528118520296e-07, | |
| "loss": 1.4671350479125977, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.9122807017543859, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 3.132715900279809e-07, | |
| "loss": 1.413409423828125, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.9176788124156545, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 2.768919187311614e-07, | |
| "loss": 1.399053192138672, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 2.125, | |
| "learning_rate": 2.4271737356129585e-07, | |
| "loss": 1.3476950645446777, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.9284750337381916, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 2.107583875870267e-07, | |
| "loss": 1.3789938926696776, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.9338731443994602, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 1.810247174940058e-07, | |
| "loss": 1.3317445755004882, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.9392712550607287, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.5352544060629136e-07, | |
| "loss": 1.4837261199951173, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.9446693657219973, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.282689521151581e-07, | |
| "loss": 1.2977308273315429, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.9500674763832658, | |
| "grad_norm": 3.6875, | |
| "learning_rate": 1.0526296251614554e-07, | |
| "loss": 1.3634986877441406, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.9554655870445344, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 8.451449525514021e-08, | |
| "loss": 1.5160835266113282, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.9608636977058029, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 6.602988458420417e-08, | |
| "loss": 1.5019266128540039, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.9662618083670715, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 4.981477362780429e-08, | |
| "loss": 1.4313615798950194, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.97165991902834, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 3.587411266003371e-08, | |
| "loss": 1.4134346008300782, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9770580296896086, | |
| "grad_norm": 2.75, | |
| "learning_rate": 2.4212157593359873e-08, | |
| "loss": 1.3511739730834962, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 2.921875, | |
| "learning_rate": 1.4832468679341348e-08, | |
| "loss": 1.348922061920166, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.9878542510121457, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 7.737909421730583e-09, | |
| "loss": 1.4228689193725585, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.9932523616734144, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 2.930645702277357e-09, | |
| "loss": 1.319122886657715, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.9986504723346828, | |
| "grad_norm": 2.5, | |
| "learning_rate": 4.1214511951603864e-10, | |
| "loss": 1.3635743141174317, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 927, | |
| "total_flos": 4.491836313357128e+17, | |
| "train_loss": 1.4709593629888476, | |
| "train_runtime": 8039.0159, | |
| "train_samples_per_second": 0.461, | |
| "train_steps_per_second": 0.115 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 927, | |
| "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": 4.491836313357128e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |