Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
decor
baseline
conversational
text-generation-inference
Instructions to use Ciaranshu/decor-qwen3-4b-original with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ciaranshu/decor-qwen3-4b-original with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ciaranshu/decor-qwen3-4b-original") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ciaranshu/decor-qwen3-4b-original") model = AutoModelForCausalLM.from_pretrained("Ciaranshu/decor-qwen3-4b-original", 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 Ciaranshu/decor-qwen3-4b-original with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ciaranshu/decor-qwen3-4b-original" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ciaranshu/decor-qwen3-4b-original", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ciaranshu/decor-qwen3-4b-original
- SGLang
How to use Ciaranshu/decor-qwen3-4b-original 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 "Ciaranshu/decor-qwen3-4b-original" \ --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": "Ciaranshu/decor-qwen3-4b-original", "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 "Ciaranshu/decor-qwen3-4b-original" \ --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": "Ciaranshu/decor-qwen3-4b-original", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Ciaranshu/decor-qwen3-4b-original with Docker Model Runner:
docker model run hf.co/Ciaranshu/decor-qwen3-4b-original
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 1545, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.097799511002445, | |
| "grad_norm": 8.912188529968262, | |
| "learning_rate": 2.9032258064516134e-07, | |
| "loss": 0.5864, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19559902200489, | |
| "grad_norm": 4.516577243804932, | |
| "learning_rate": 6.129032258064516e-07, | |
| "loss": 0.5922, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.293398533007335, | |
| "grad_norm": 1.903780221939087, | |
| "learning_rate": 9.35483870967742e-07, | |
| "loss": 0.6003, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.39119804400978, | |
| "grad_norm": 2.3196961879730225, | |
| "learning_rate": 1.2580645161290322e-06, | |
| "loss": 0.5621, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4889975550122249, | |
| "grad_norm": 0.8394497632980347, | |
| "learning_rate": 1.5806451612903226e-06, | |
| "loss": 0.4849, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.58679706601467, | |
| "grad_norm": 0.7316912412643433, | |
| "learning_rate": 1.9032258064516128e-06, | |
| "loss": 0.4989, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.684596577017115, | |
| "grad_norm": 0.8046264052391052, | |
| "learning_rate": 2.2258064516129034e-06, | |
| "loss": 0.5522, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.78239608801956, | |
| "grad_norm": 0.886458694934845, | |
| "learning_rate": 2.5483870967741934e-06, | |
| "loss": 0.5153, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8801955990220048, | |
| "grad_norm": 0.6029126644134521, | |
| "learning_rate": 2.8709677419354843e-06, | |
| "loss": 0.5107, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9779951100244498, | |
| "grad_norm": 0.7654699683189392, | |
| "learning_rate": 3.1935483870967742e-06, | |
| "loss": 0.4748, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0684596577017116, | |
| "grad_norm": 0.7337806224822998, | |
| "learning_rate": 3.516129032258065e-06, | |
| "loss": 0.5089, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.1662591687041566, | |
| "grad_norm": 0.6805911660194397, | |
| "learning_rate": 3.838709677419355e-06, | |
| "loss": 0.4771, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2640586797066016, | |
| "grad_norm": 3.876692771911621, | |
| "learning_rate": 4.161290322580646e-06, | |
| "loss": 0.5139, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3618581907090466, | |
| "grad_norm": 0.8315966725349426, | |
| "learning_rate": 4.4838709677419354e-06, | |
| "loss": 0.5066, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4596577017114916, | |
| "grad_norm": 0.7394840717315674, | |
| "learning_rate": 4.806451612903227e-06, | |
| "loss": 0.4487, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5574572127139366, | |
| "grad_norm": 0.9246750473976135, | |
| "learning_rate": 4.999897836166041e-06, | |
| "loss": 0.5024, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6552567237163816, | |
| "grad_norm": 0.5809449553489685, | |
| "learning_rate": 4.998748588925897e-06, | |
| "loss": 0.4334, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.7530562347188265, | |
| "grad_norm": 0.8815693259239197, | |
| "learning_rate": 4.996322978646722e-06, | |
| "loss": 0.4537, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8508557457212715, | |
| "grad_norm": 0.7594463229179382, | |
| "learning_rate": 4.992622244332439e-06, | |
| "loss": 0.4834, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.9486552567237165, | |
| "grad_norm": 0.5691333413124084, | |
| "learning_rate": 4.987648276321482e-06, | |
| "loss": 0.4625, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.039119804400978, | |
| "grad_norm": 0.8171164393424988, | |
| "learning_rate": 4.98140361532121e-06, | |
| "loss": 0.4874, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.136919315403423, | |
| "grad_norm": 0.5794939398765564, | |
| "learning_rate": 4.973891451110109e-06, | |
| "loss": 0.4522, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.234718826405868, | |
| "grad_norm": 0.6122840046882629, | |
| "learning_rate": 4.965115620908453e-06, | |
| "loss": 0.426, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.332518337408313, | |
| "grad_norm": 0.6676702499389648, | |
| "learning_rate": 4.955080607418244e-06, | |
| "loss": 0.4313, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.430317848410758, | |
| "grad_norm": 0.6127225160598755, | |
| "learning_rate": 4.94379153653345e-06, | |
| "loss": 0.4153, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.528117359413203, | |
| "grad_norm": 0.7623103857040405, | |
| "learning_rate": 4.931254174721687e-06, | |
| "loss": 0.444, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.625916870415648, | |
| "grad_norm": 0.6758006811141968, | |
| "learning_rate": 4.917474926078707e-06, | |
| "loss": 0.4533, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.723716381418093, | |
| "grad_norm": 0.6232055425643921, | |
| "learning_rate": 4.90246082905718e-06, | |
| "loss": 0.464, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.821515892420538, | |
| "grad_norm": 0.9327264428138733, | |
| "learning_rate": 4.886219552871441e-06, | |
| "loss": 0.4561, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.919315403422983, | |
| "grad_norm": 0.6441056728363037, | |
| "learning_rate": 4.868759393580054e-06, | |
| "loss": 0.3988, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0097799511002443, | |
| "grad_norm": 1.5844961404800415, | |
| "learning_rate": 4.8500892698481784e-06, | |
| "loss": 0.3743, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.1075794621026893, | |
| "grad_norm": 0.6993974447250366, | |
| "learning_rate": 4.8302187183918996e-06, | |
| "loss": 0.3315, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.2053789731051343, | |
| "grad_norm": 1.0430474281311035, | |
| "learning_rate": 4.80915788910687e-06, | |
| "loss": 0.3977, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.3031784841075793, | |
| "grad_norm": 0.9191403985023499, | |
| "learning_rate": 4.786917539883738e-06, | |
| "loss": 0.3425, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.4009779951100243, | |
| "grad_norm": 0.9135327935218811, | |
| "learning_rate": 4.763509031113e-06, | |
| "loss": 0.4444, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.4987775061124693, | |
| "grad_norm": 0.7067691087722778, | |
| "learning_rate": 4.7389443198821035e-06, | |
| "loss": 0.3602, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.5965770171149143, | |
| "grad_norm": 0.727276623249054, | |
| "learning_rate": 4.713235953867764e-06, | |
| "loss": 0.4589, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.6943765281173593, | |
| "grad_norm": 0.6709797382354736, | |
| "learning_rate": 4.6863970649265914e-06, | |
| "loss": 0.3539, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.7921760391198043, | |
| "grad_norm": 3.665849208831787, | |
| "learning_rate": 4.658441362387328e-06, | |
| "loss": 0.4394, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.8899755501222493, | |
| "grad_norm": 0.7635933756828308, | |
| "learning_rate": 4.629383126048114e-06, | |
| "loss": 0.3618, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.9877750611246943, | |
| "grad_norm": 0.7998107075691223, | |
| "learning_rate": 4.599237198882351e-06, | |
| "loss": 0.4151, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.078239608801956, | |
| "grad_norm": 0.795903742313385, | |
| "learning_rate": 4.568018979456899e-06, | |
| "loss": 0.3637, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.176039119804401, | |
| "grad_norm": 1.0807809829711914, | |
| "learning_rate": 4.535744414066473e-06, | |
| "loss": 0.3681, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.273838630806846, | |
| "grad_norm": 0.7779868245124817, | |
| "learning_rate": 4.502429988588263e-06, | |
| "loss": 0.3101, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.371638141809291, | |
| "grad_norm": 0.7853298187255859, | |
| "learning_rate": 4.46809272006093e-06, | |
| "loss": 0.3308, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.469437652811736, | |
| "grad_norm": 0.819804310798645, | |
| "learning_rate": 4.4327501479922955e-06, | |
| "loss": 0.3409, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.56723716381418, | |
| "grad_norm": 0.7861034870147705, | |
| "learning_rate": 4.396420325400132e-06, | |
| "loss": 0.352, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.665036674816626, | |
| "grad_norm": 3.1795172691345215, | |
| "learning_rate": 4.359121809590678e-06, | |
| "loss": 0.3618, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.76283618581907, | |
| "grad_norm": 0.7519227266311646, | |
| "learning_rate": 4.320873652679538e-06, | |
| "loss": 0.3023, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.860635696821516, | |
| "grad_norm": 0.8518574237823486, | |
| "learning_rate": 4.281695391859854e-06, | |
| "loss": 0.3818, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.95843520782396, | |
| "grad_norm": 0.9220756888389587, | |
| "learning_rate": 4.241607039422687e-06, | |
| "loss": 0.3814, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.048899755501223, | |
| "grad_norm": 0.7876546382904053, | |
| "learning_rate": 4.200629072534713e-06, | |
| "loss": 0.3522, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.146699266503667, | |
| "grad_norm": 1.0232821702957153, | |
| "learning_rate": 4.15878242277848e-06, | |
| "loss": 0.3883, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.244498777506112, | |
| "grad_norm": 1.0325844287872314, | |
| "learning_rate": 4.116088465460529e-06, | |
| "loss": 0.3062, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.342298288508557, | |
| "grad_norm": 1.2710373401641846, | |
| "learning_rate": 4.072569008692868e-06, | |
| "loss": 0.286, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.440097799511002, | |
| "grad_norm": 0.8699069023132324, | |
| "learning_rate": 4.028246282253373e-06, | |
| "loss": 0.3079, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.537897310513447, | |
| "grad_norm": 1.0510350465774536, | |
| "learning_rate": 3.983142926230792e-06, | |
| "loss": 0.3319, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.635696821515893, | |
| "grad_norm": 1.7061210870742798, | |
| "learning_rate": 3.937281979460175e-06, | |
| "loss": 0.2772, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.733496332518337, | |
| "grad_norm": 0.9135501384735107, | |
| "learning_rate": 3.890686867754604e-06, | |
| "loss": 0.2705, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.831295843520783, | |
| "grad_norm": 1.255777359008789, | |
| "learning_rate": 3.843381391939281e-06, | |
| "loss": 0.2754, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.929095354523227, | |
| "grad_norm": 0.759937047958374, | |
| "learning_rate": 3.7953897156940323e-06, | |
| "loss": 0.3659, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.019559902200489, | |
| "grad_norm": 1.0174964666366577, | |
| "learning_rate": 3.7467363532104874e-06, | |
| "loss": 0.2745, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.117359413202934, | |
| "grad_norm": 1.0734614133834839, | |
| "learning_rate": 3.6974461566702048e-06, | |
| "loss": 0.2563, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.215158924205379, | |
| "grad_norm": 1.0012364387512207, | |
| "learning_rate": 3.6475443035501522e-06, | |
| "loss": 0.3063, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.312958435207824, | |
| "grad_norm": 0.9189195036888123, | |
| "learning_rate": 3.597056283762034e-06, | |
| "loss": 0.2535, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.410757946210269, | |
| "grad_norm": 1.4923477172851562, | |
| "learning_rate": 3.546007886632019e-06, | |
| "loss": 0.2611, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.508557457212714, | |
| "grad_norm": 1.1967344284057617, | |
| "learning_rate": 3.494425187727528e-06, | |
| "loss": 0.2894, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.606356968215159, | |
| "grad_norm": 1.1267250776290894, | |
| "learning_rate": 3.4423345355378114e-06, | |
| "loss": 0.2608, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.704156479217604, | |
| "grad_norm": 1.003569483757019, | |
| "learning_rate": 3.389762538015116e-06, | |
| "loss": 0.2444, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.801955990220049, | |
| "grad_norm": 1.534313678741455, | |
| "learning_rate": 3.3367360489833236e-06, | |
| "loss": 0.302, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.899755501222494, | |
| "grad_norm": 1.1240261793136597, | |
| "learning_rate": 3.283282154420985e-06, | |
| "loss": 0.2934, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.997555012224939, | |
| "grad_norm": 0.8965175747871399, | |
| "learning_rate": 3.229428158625787e-06, | |
| "loss": 0.2663, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.0880195599022, | |
| "grad_norm": 0.9263703227043152, | |
| "learning_rate": 3.1752015702674855e-06, | |
| "loss": 0.269, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 7.185819070904645, | |
| "grad_norm": 0.9905564188957214, | |
| "learning_rate": 3.1206300883364547e-06, | |
| "loss": 0.2574, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.28361858190709, | |
| "grad_norm": 1.090330958366394, | |
| "learning_rate": 3.065741587995019e-06, | |
| "loss": 0.2318, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.381418092909535, | |
| "grad_norm": 1.1688711643218994, | |
| "learning_rate": 3.010564106338791e-06, | |
| "loss": 0.2038, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.47921760391198, | |
| "grad_norm": 0.8666380643844604, | |
| "learning_rate": 2.9551258280753046e-06, | |
| "loss": 0.2288, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.577017114914425, | |
| "grad_norm": 1.0252586603164673, | |
| "learning_rate": 2.8994550711272317e-06, | |
| "loss": 0.2134, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.67481662591687, | |
| "grad_norm": 0.9690338969230652, | |
| "learning_rate": 2.843580272167569e-06, | |
| "loss": 0.279, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.772616136919315, | |
| "grad_norm": 1.1712546348571777, | |
| "learning_rate": 2.7875299720941577e-06, | |
| "loss": 0.2097, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.87041564792176, | |
| "grad_norm": 1.1309782266616821, | |
| "learning_rate": 2.7313328014509653e-06, | |
| "loss": 0.2459, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.968215158924205, | |
| "grad_norm": 1.1082842350006104, | |
| "learning_rate": 2.6750174658035793e-06, | |
| "loss": 0.2212, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.058679706601467, | |
| "grad_norm": 1.0827865600585938, | |
| "learning_rate": 2.61861273107638e-06, | |
| "loss": 0.199, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 8.156479217603913, | |
| "grad_norm": 1.197373390197754, | |
| "learning_rate": 2.562147408858876e-06, | |
| "loss": 0.2406, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 8.254278728606357, | |
| "grad_norm": 1.0432353019714355, | |
| "learning_rate": 2.5056503416887222e-06, | |
| "loss": 0.1658, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 8.352078239608803, | |
| "grad_norm": 1.2802042961120605, | |
| "learning_rate": 2.4491503883189242e-06, | |
| "loss": 0.1798, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.449877750611247, | |
| "grad_norm": 0.8931949138641357, | |
| "learning_rate": 2.3926764089767594e-06, | |
| "loss": 0.2049, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.547677261613693, | |
| "grad_norm": 0.8885977268218994, | |
| "learning_rate": 2.33625725062195e-06, | |
| "loss": 0.2322, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.645476772616137, | |
| "grad_norm": 1.109119176864624, | |
| "learning_rate": 2.279921732211609e-06, | |
| "loss": 0.2116, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 8.743276283618583, | |
| "grad_norm": 0.9827072024345398, | |
| "learning_rate": 2.223698629979487e-06, | |
| "loss": 0.1712, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.841075794621027, | |
| "grad_norm": 1.128921389579773, | |
| "learning_rate": 2.167616662737052e-06, | |
| "loss": 0.2061, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.938875305623473, | |
| "grad_norm": 1.2514700889587402, | |
| "learning_rate": 2.1117044772038915e-06, | |
| "loss": 0.2161, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 9.029339853300733, | |
| "grad_norm": 0.8430796265602112, | |
| "learning_rate": 2.0559906333749392e-06, | |
| "loss": 0.1981, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 9.12713936430318, | |
| "grad_norm": 1.307217001914978, | |
| "learning_rate": 2.0005035899320115e-06, | |
| "loss": 0.1937, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 9.224938875305623, | |
| "grad_norm": 1.5007126331329346, | |
| "learning_rate": 1.9452716897070785e-06, | |
| "loss": 0.2305, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 9.32273838630807, | |
| "grad_norm": 1.3814022541046143, | |
| "learning_rate": 1.8903231452047265e-06, | |
| "loss": 0.1532, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 9.420537897310513, | |
| "grad_norm": 0.9845283031463623, | |
| "learning_rate": 1.8356860241911817e-06, | |
| "loss": 0.157, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.51833740831296, | |
| "grad_norm": 1.5370829105377197, | |
| "learning_rate": 1.7813882353572692e-06, | |
| "loss": 0.1356, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.616136919315403, | |
| "grad_norm": 1.1557724475860596, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.2167, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.713936430317847, | |
| "grad_norm": 0.9717232584953308, | |
| "learning_rate": 1.6739214081684799e-06, | |
| "loss": 0.15, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.811735941320293, | |
| "grad_norm": 0.7423869371414185, | |
| "learning_rate": 1.6208072639661226e-06, | |
| "loss": 0.1998, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 9.90953545232274, | |
| "grad_norm": 1.5157626867294312, | |
| "learning_rate": 1.5681422122084522e-06, | |
| "loss": 0.1945, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.3885276317596436, | |
| "learning_rate": 1.515953154251535e-06, | |
| "loss": 0.1699, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 10.097799511002446, | |
| "grad_norm": 1.2888805866241455, | |
| "learning_rate": 1.4642667483133753e-06, | |
| "loss": 0.1818, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 10.19559902200489, | |
| "grad_norm": 0.960208535194397, | |
| "learning_rate": 1.4131093958568695e-06, | |
| "loss": 0.1315, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 10.293398533007334, | |
| "grad_norm": 1.0998454093933105, | |
| "learning_rate": 1.362507228103918e-06, | |
| "loss": 0.172, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 10.39119804400978, | |
| "grad_norm": 1.3192960023880005, | |
| "learning_rate": 1.3124860926875732e-06, | |
| "loss": 0.1373, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 10.488997555012224, | |
| "grad_norm": 1.2738300561904907, | |
| "learning_rate": 1.2630715404490424e-06, | |
| "loss": 0.1417, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 10.58679706601467, | |
| "grad_norm": 0.9237063527107239, | |
| "learning_rate": 1.2142888123862992e-06, | |
| "loss": 0.1719, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 10.684596577017114, | |
| "grad_norm": 1.303916335105896, | |
| "learning_rate": 1.166162826760955e-06, | |
| "loss": 0.1758, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.78239608801956, | |
| "grad_norm": 1.209743857383728, | |
| "learning_rate": 1.1187181663699935e-06, | |
| "loss": 0.1466, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 10.880195599022004, | |
| "grad_norm": 1.196293830871582, | |
| "learning_rate": 1.0719790659888481e-06, | |
| "loss": 0.1712, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 10.97799511002445, | |
| "grad_norm": 1.413644552230835, | |
| "learning_rate": 1.025969399992264e-06, | |
| "loss": 0.1632, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 11.06845965770171, | |
| "grad_norm": 1.725104570388794, | |
| "learning_rate": 9.80712670159242e-07, | |
| "loss": 0.1282, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 11.166259168704157, | |
| "grad_norm": 1.0897539854049683, | |
| "learning_rate": 9.362319936683092e-07, | |
| "loss": 0.1218, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 11.2640586797066, | |
| "grad_norm": 2.127143621444702, | |
| "learning_rate": 8.925500912892471e-07, | |
| "loss": 0.1411, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 11.361858190709047, | |
| "grad_norm": 1.7445807456970215, | |
| "learning_rate": 8.496892757772934e-07, | |
| "loss": 0.1295, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 11.45965770171149, | |
| "grad_norm": 0.8322131633758545, | |
| "learning_rate": 8.076714404757735e-07, | |
| "loss": 0.1172, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 11.557457212713937, | |
| "grad_norm": 1.07593834400177, | |
| "learning_rate": 7.665180481329621e-07, | |
| "loss": 0.1489, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 11.65525672371638, | |
| "grad_norm": 1.582017183303833, | |
| "learning_rate": 7.262501199388827e-07, | |
| "loss": 0.1578, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.753056234718827, | |
| "grad_norm": 1.4432977437973022, | |
| "learning_rate": 6.868882247876776e-07, | |
| "loss": 0.1528, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 11.85085574572127, | |
| "grad_norm": 0.8151497840881348, | |
| "learning_rate": 6.484524687709853e-07, | |
| "loss": 0.1781, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 11.948655256723717, | |
| "grad_norm": 1.1070584058761597, | |
| "learning_rate": 6.109624849077397e-07, | |
| "loss": 0.1415, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 12.039119804400977, | |
| "grad_norm": 1.0976202487945557, | |
| "learning_rate": 5.744374231156056e-07, | |
| "loss": 0.1478, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 12.136919315403423, | |
| "grad_norm": 0.9782683849334717, | |
| "learning_rate": 5.388959404291757e-07, | |
| "loss": 0.095, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 12.234718826405867, | |
| "grad_norm": 0.5222208499908447, | |
| "learning_rate": 5.043561914699513e-07, | |
| "loss": 0.1311, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 12.332518337408313, | |
| "grad_norm": 0.9819530248641968, | |
| "learning_rate": 4.7083581917293784e-07, | |
| "loss": 0.1396, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 12.430317848410757, | |
| "grad_norm": 1.1775444746017456, | |
| "learning_rate": 4.383519457746174e-07, | |
| "loss": 0.1782, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 12.528117359413203, | |
| "grad_norm": 1.0930062532424927, | |
| "learning_rate": 4.0692116406690214e-07, | |
| "loss": 0.1533, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 12.625916870415647, | |
| "grad_norm": 1.134692668914795, | |
| "learning_rate": 3.76559528921511e-07, | |
| "loss": 0.1133, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 12.723716381418093, | |
| "grad_norm": 0.5726219415664673, | |
| "learning_rate": 3.4728254908913683e-07, | |
| "loss": 0.0765, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 12.821515892420537, | |
| "grad_norm": 0.970542848110199, | |
| "learning_rate": 3.1910517927755516e-07, | |
| "loss": 0.1332, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 12.919315403422983, | |
| "grad_norm": 0.9467713832855225, | |
| "learning_rate": 2.9204181251274665e-07, | |
| "loss": 0.1099, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 13.009779951100244, | |
| "grad_norm": 2.8466508388519287, | |
| "learning_rate": 2.6610627278693265e-07, | |
| "loss": 0.1719, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 13.10757946210269, | |
| "grad_norm": 1.2875152826309204, | |
| "learning_rate": 2.413118079972593e-07, | |
| "loss": 0.1242, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 13.205378973105134, | |
| "grad_norm": 0.6140391826629639, | |
| "learning_rate": 2.176710831787651e-07, | |
| "loss": 0.1131, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 13.30317848410758, | |
| "grad_norm": 0.704987645149231, | |
| "learning_rate": 1.9519617403506747e-07, | |
| "loss": 0.1386, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 13.400977995110024, | |
| "grad_norm": 0.8624230027198792, | |
| "learning_rate": 1.7389856077008245e-07, | |
| "loss": 0.1493, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 13.49877750611247, | |
| "grad_norm": 0.8811519742012024, | |
| "learning_rate": 1.537891222239271e-07, | |
| "loss": 0.109, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 13.596577017114914, | |
| "grad_norm": 1.3603438138961792, | |
| "learning_rate": 1.348781303159974e-07, | |
| "loss": 0.1029, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 13.69437652811736, | |
| "grad_norm": 1.362648606300354, | |
| "learning_rate": 1.1717524479806231e-07, | |
| "loss": 0.1352, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 13.792176039119804, | |
| "grad_norm": 1.3594386577606201, | |
| "learning_rate": 1.0068950832005487e-07, | |
| "loss": 0.1075, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 13.88997555012225, | |
| "grad_norm": 1.763226866722107, | |
| "learning_rate": 8.542934181107687e-08, | |
| "loss": 0.1168, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 13.987775061124694, | |
| "grad_norm": 1.506229043006897, | |
| "learning_rate": 7.140254017798221e-08, | |
| "loss": 0.1278, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 14.078239608801956, | |
| "grad_norm": 1.131917119026184, | |
| "learning_rate": 5.8616268323730685e-08, | |
| "loss": 0.1638, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 14.1760391198044, | |
| "grad_norm": 1.120328664779663, | |
| "learning_rate": 4.707705748754898e-08, | |
| "loss": 0.1162, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 14.273838630806846, | |
| "grad_norm": 1.1553229093551636, | |
| "learning_rate": 3.679080190876788e-08, | |
| "loss": 0.1287, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 14.37163814180929, | |
| "grad_norm": 0.5191317200660706, | |
| "learning_rate": 2.7762755816039823e-08, | |
| "loss": 0.1055, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 14.469437652811736, | |
| "grad_norm": 0.8353264331817627, | |
| "learning_rate": 1.9997530743473548e-08, | |
| "loss": 0.1077, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 14.56723716381418, | |
| "grad_norm": 1.1898248195648193, | |
| "learning_rate": 1.3499093175059208e-08, | |
| "loss": 0.1465, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.665036674816626, | |
| "grad_norm": 0.7969550490379333, | |
| "learning_rate": 8.270762518583498e-09, | |
| "loss": 0.1433, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 14.76283618581907, | |
| "grad_norm": 1.4807196855545044, | |
| "learning_rate": 4.3152094100740175e-09, | |
| "loss": 0.1005, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 14.860635696821516, | |
| "grad_norm": 0.7831215858459473, | |
| "learning_rate": 1.6344543496360499e-09, | |
| "loss": 0.1021, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 14.95843520782396, | |
| "grad_norm": 0.8250207304954529, | |
| "learning_rate": 2.2986666937896418e-10, | |
| "loss": 0.097, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 1545, | |
| "total_flos": 1.858545542842286e+18, | |
| "train_loss": 0.2710213578248873, | |
| "train_runtime": 32230.4648, | |
| "train_samples_per_second": 0.38, | |
| "train_steps_per_second": 0.048 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1545, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "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": 1.858545542842286e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |