Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lldois/v11_item_cot_focus_lr2e5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lldois/v11_item_cot_focus_lr2e5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lldois/v11_item_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/v11_item_cot_focus_lr2e5") model = AutoModelForCausalLM.from_pretrained("lldois/v11_item_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/v11_item_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/v11_item_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/v11_item_cot_focus_lr2e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lldois/v11_item_cot_focus_lr2e5
- SGLang
How to use lldois/v11_item_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/v11_item_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/v11_item_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/v11_item_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/v11_item_cot_focus_lr2e5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lldois/v11_item_cot_focus_lr2e5 with Docker Model Runner:
docker model run hf.co/lldois/v11_item_cot_focus_lr2e5
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 458, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01092896174863388, | |
| "grad_norm": 32.75, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 3.0794925689697266, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02185792349726776, | |
| "grad_norm": 7.53125, | |
| "learning_rate": 1.2857142857142859e-05, | |
| "loss": 2.721632385253906, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03278688524590164, | |
| "grad_norm": 7.03125, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3995603561401366, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04371584699453552, | |
| "grad_norm": 3.359375, | |
| "learning_rate": 1.999374253369202e-05, | |
| "loss": 2.0898674011230467, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0546448087431694, | |
| "grad_norm": 3.3125, | |
| "learning_rate": 1.9974977965945e-05, | |
| "loss": 2.0346654891967773, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 2.625, | |
| "learning_rate": 1.994372978048903e-05, | |
| "loss": 1.8668981552124024, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07650273224043716, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.9900037084217637e-05, | |
| "loss": 1.8034637451171875, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08743169398907104, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 1.98439545582458e-05, | |
| "loss": 1.7929542541503907, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09836065573770492, | |
| "grad_norm": 2.125, | |
| "learning_rate": 1.9775552389476865e-05, | |
| "loss": 1.7653799057006836, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1092896174863388, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.9694916182764113e-05, | |
| "loss": 1.8002981185913085, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12021857923497267, | |
| "grad_norm": 1.828125, | |
| "learning_rate": 1.9602146853776894e-05, | |
| "loss": 1.7515642166137695, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.13114754098360656, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.949736050270532e-05, | |
| "loss": 1.6643417358398438, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14207650273224043, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 1.938068826896166e-05, | |
| "loss": 1.7326908111572266, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.15300546448087432, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.925227616706026e-05, | |
| "loss": 1.6682777404785156, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16393442622950818, | |
| "grad_norm": 1.921875, | |
| "learning_rate": 1.911228490388136e-05, | |
| "loss": 1.6137102127075196, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.17486338797814208, | |
| "grad_norm": 2.125, | |
| "learning_rate": 1.8960889677547506e-05, | |
| "loss": 1.6803092956542969, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18579234972677597, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.8798279958164295e-05, | |
| "loss": 1.594618320465088, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.19672131147540983, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 1.8624659250699807e-05, | |
| "loss": 1.6478633880615234, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20765027322404372, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.8440244840299507e-05, | |
| "loss": 1.5899643898010254, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2185792349726776, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.8245267520355348e-05, | |
| "loss": 1.7294490814208985, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22950819672131148, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.8039971303669407e-05, | |
| "loss": 1.587702465057373, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.24043715846994534, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 1.78246131170735e-05, | |
| "loss": 1.6548728942871094, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.25136612021857924, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 1.7599462479886976e-05, | |
| "loss": 1.6343778610229491, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 1.7364801166615124e-05, | |
| "loss": 1.5680456161499023, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.273224043715847, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.712092285431026e-05, | |
| "loss": 1.624847984313965, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.28415300546448086, | |
| "grad_norm": 1.796875, | |
| "learning_rate": 1.6868132755036875e-05, | |
| "loss": 1.6338729858398438, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.29508196721311475, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.6606747233900816e-05, | |
| "loss": 1.6267793655395508, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.30601092896174864, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 1.6337093413120463e-05, | |
| "loss": 1.6020263671875, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.31693989071038253, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.6059508762635482e-05, | |
| "loss": 1.5867203712463378, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 1.9765625, | |
| "learning_rate": 1.5774340677765483e-05, | |
| "loss": 1.6130403518676757, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.33879781420765026, | |
| "grad_norm": 1.859375, | |
| "learning_rate": 1.54819460444471e-05, | |
| "loss": 1.529791259765625, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.34972677595628415, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.5182690792593659e-05, | |
| "loss": 1.5679257392883301, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.36065573770491804, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.4876949438136348e-05, | |
| "loss": 1.5688570976257323, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.37158469945355194, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.4565104614320065e-05, | |
| "loss": 1.606216812133789, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3825136612021858, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.424754659284048e-05, | |
| "loss": 1.489095973968506, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.39344262295081966, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.3924672795421638e-05, | |
| "loss": 1.4960175514221192, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.40437158469945356, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 1.359688729644536e-05, | |
| "loss": 1.5484750747680665, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.41530054644808745, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 1.3264600317254854e-05, | |
| "loss": 1.5497447967529296, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4262295081967213, | |
| "grad_norm": 1.9921875, | |
| "learning_rate": 1.2928227712765504e-05, | |
| "loss": 1.5531758308410644, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.4371584699453552, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.2588190451025209e-05, | |
| "loss": 1.5273221969604491, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.44808743169398907, | |
| "grad_norm": 2.875, | |
| "learning_rate": 1.2244914086375726e-05, | |
| "loss": 1.5461650848388673, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.45901639344262296, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.1898828226874284e-05, | |
| "loss": 1.5468520164489745, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.46994535519125685, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 1.155036599664198e-05, | |
| "loss": 1.5714691162109375, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.4808743169398907, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.119996349381187e-05, | |
| "loss": 1.5547896385192872, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4918032786885246, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.0848059244755093e-05, | |
| "loss": 1.5582594871520996, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5027322404371585, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 1.049509365526807e-05, | |
| "loss": 1.5906845092773438, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5136612021857924, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 1.0141508459407622e-05, | |
| "loss": 1.5457923889160157, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 9.787746166663765e-06, | |
| "loss": 1.5068846702575684, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5355191256830601, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 9.434249508162076e-06, | |
| "loss": 1.587421703338623, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.546448087431694, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 9.081460882588668e-06, | |
| "loss": 1.5227561950683595, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5573770491803278, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 8.729821802531213e-06, | |
| "loss": 1.5408030509948731, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.5683060109289617, | |
| "grad_norm": 2.0, | |
| "learning_rate": 8.379772341928916e-06, | |
| "loss": 1.539006233215332, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5792349726775956, | |
| "grad_norm": 1.890625, | |
| "learning_rate": 8.031750585322948e-06, | |
| "loss": 1.5504417419433594, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.5901639344262295, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 7.686192079596586e-06, | |
| "loss": 1.4833337783813476, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6010928961748634, | |
| "grad_norm": 2.125, | |
| "learning_rate": 7.343529288891239e-06, | |
| "loss": 1.5717066764831542, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6120218579234973, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 7.004191053380469e-06, | |
| "loss": 1.5402889251708984, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6229508196721312, | |
| "grad_norm": 2.125, | |
| "learning_rate": 6.668602052579425e-06, | |
| "loss": 1.556431198120117, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.6338797814207651, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 6.337182273861273e-06, | |
| "loss": 1.6031099319458009, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.644808743169399, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 6.010346486845837e-06, | |
| "loss": 1.5742233276367188, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 5.688503724318217e-06, | |
| "loss": 1.4503952026367188, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 1.8984375, | |
| "learning_rate": 5.3720567703270135e-06, | |
| "loss": 1.5349412918090821, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.6775956284153005, | |
| "grad_norm": 2.25, | |
| "learning_rate": 5.061401656102791e-06, | |
| "loss": 1.5250138282775878, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6885245901639344, | |
| "grad_norm": 2.0, | |
| "learning_rate": 4.756927164427685e-06, | |
| "loss": 1.5778297424316405, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.6994535519125683, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 4.459014343076356e-06, | |
| "loss": 1.4995346069335938, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7103825136612022, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 4.168036027937267e-06, | |
| "loss": 1.5108715057373048, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7213114754098361, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 3.884356376411089e-06, | |
| "loss": 1.5526594161987304, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.73224043715847, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 3.6083304116701535e-06, | |
| "loss": 1.4732019424438476, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.7431693989071039, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 3.340303578349361e-06, | |
| "loss": 1.5316784858703614, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7540983606557377, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 3.0806113102245395e-06, | |
| "loss": 1.529658317565918, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.7650273224043715, | |
| "grad_norm": 2.25, | |
| "learning_rate": 2.829578610419337e-06, | |
| "loss": 1.4984872817993165, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7759562841530054, | |
| "grad_norm": 1.8046875, | |
| "learning_rate": 2.587519644666001e-06, | |
| "loss": 1.5388754844665526, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 1.90625, | |
| "learning_rate": 2.354737348129077e-06, | |
| "loss": 1.523587131500244, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7978142076502732, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 2.1315230462840985e-06, | |
| "loss": 1.5976734161376953, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.8087431693989071, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 1.9181560903257234e-06, | |
| "loss": 1.488864803314209, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.7149035075615795e-06, | |
| "loss": 1.5337986946105957, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8306010928961749, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 1.522019667229393e-06, | |
| "loss": 1.5084647178649901, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8415300546448088, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 1.5753061294555664, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.8524590163934426, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 1.1683105066539068e-06, | |
| "loss": 1.5077287673950195, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8633879781420765, | |
| "grad_norm": 1.78125, | |
| "learning_rate": 1.0079278510416313e-06, | |
| "loss": 1.4942996978759766, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.8743169398907104, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 8.587987131315656e-07, | |
| "loss": 1.5271930694580078, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8852459016393442, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 7.211097270349065e-07, | |
| "loss": 1.493248176574707, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.8961748633879781, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 5.950332095899547e-07, | |
| "loss": 1.6621942520141602, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.907103825136612, | |
| "grad_norm": 1.953125, | |
| "learning_rate": 4.807269447087348e-07, | |
| "loss": 1.6068300247192382, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.9180327868852459, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 3.783339859115065e-07, | |
| "loss": 1.5068284034729005, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9289617486338798, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 2.879824772962381e-07, | |
| "loss": 1.45760498046875, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9398907103825137, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 2.0978549316713615e-07, | |
| "loss": 1.5096138000488282, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9508196721311475, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.4384089652291544e-07, | |
| "loss": 1.5121006965637207, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.9617486338797814, | |
| "grad_norm": 1.8671875, | |
| "learning_rate": 9.023121658191636e-08, | |
| "loss": 1.4845489501953124, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9726775956284153, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 4.902354549733979e-08, | |
| "loss": 1.5319786071777344, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 2.0269454391874665e-08, | |
| "loss": 1.4230306625366211, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.994535519125683, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 4.00492881678427e-09, | |
| "loss": 1.528977870941162, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 458, | |
| "total_flos": 2.1822581284723507e+17, | |
| "train_loss": 1.623693225685686, | |
| "train_runtime": 3645.8723, | |
| "train_samples_per_second": 0.502, | |
| "train_steps_per_second": 0.126 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 458, | |
| "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": 2.1822581284723507e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |