Image-Text-to-Text
Transformers
Safetensors
qwen3_5
llama-factory
full
Generated from Trainer
conversational
🇪🇺 Region: EU
Instructions to use eth-sri/kodcode-v1-qwen36 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eth-sri/kodcode-v1-qwen36 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="eth-sri/kodcode-v1-qwen36") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("eth-sri/kodcode-v1-qwen36") model = AutoModelForMultimodalLM.from_pretrained("eth-sri/kodcode-v1-qwen36") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use eth-sri/kodcode-v1-qwen36 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "eth-sri/kodcode-v1-qwen36" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "eth-sri/kodcode-v1-qwen36", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/eth-sri/kodcode-v1-qwen36
- SGLang
How to use eth-sri/kodcode-v1-qwen36 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 "eth-sri/kodcode-v1-qwen36" \ --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": "eth-sri/kodcode-v1-qwen36", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "eth-sri/kodcode-v1-qwen36" \ --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": "eth-sri/kodcode-v1-qwen36", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use eth-sri/kodcode-v1-qwen36 with Docker Model Runner:
docker model run hf.co/eth-sri/kodcode-v1-qwen36
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 84, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03614457831325301, | |
| "grad_norm": 2.243542194366455, | |
| "learning_rate": 0.0, | |
| "loss": 0.6798985004425049, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "grad_norm": 2.272136926651001, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.6897931098937988, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10843373493975904, | |
| "grad_norm": 2.009799003601074, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.6687372326850891, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 1.5434411764144897, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.6511715054512024, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18072289156626506, | |
| "grad_norm": 1.2117929458618164, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.6404632329940796, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21686746987951808, | |
| "grad_norm": 1.288975477218628, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.6380958557128906, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25301204819277107, | |
| "grad_norm": 1.1806610822677612, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.624602735042572, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 1.2804715633392334, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.6305320858955383, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3253012048192771, | |
| "grad_norm": 1.0711824893951416, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.6563503742218018, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 1.0959501266479492, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6455645561218262, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39759036144578314, | |
| "grad_norm": 1.0095149278640747, | |
| "learning_rate": 9.995614150494293e-06, | |
| "loss": 0.628766655921936, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": 1.5699474811553955, | |
| "learning_rate": 9.982464296247523e-06, | |
| "loss": 0.6071541905403137, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46987951807228917, | |
| "grad_norm": 0.7985743284225464, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.6209861636161804, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5060240963855421, | |
| "grad_norm": 0.714244544506073, | |
| "learning_rate": 9.929980185352525e-06, | |
| "loss": 0.6150267124176025, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5421686746987951, | |
| "grad_norm": 0.6876276135444641, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 0.6164926290512085, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 0.6876976490020752, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 0.6059902906417847, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6144578313253012, | |
| "grad_norm": 0.6507225036621094, | |
| "learning_rate": 9.786597487660336e-06, | |
| "loss": 0.6016689538955688, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6506024096385542, | |
| "grad_norm": 0.5742944478988647, | |
| "learning_rate": 9.721881851187406e-06, | |
| "loss": 0.5898147821426392, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6867469879518072, | |
| "grad_norm": 0.5965182185173035, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.5911672115325928, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 0.6031558513641357, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 0.5862749814987183, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7590361445783133, | |
| "grad_norm": 0.5991913080215454, | |
| "learning_rate": 9.478558801197065e-06, | |
| "loss": 0.5881009101867676, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7951807228915663, | |
| "grad_norm": 0.5532190203666687, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 0.5938855409622192, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8313253012048193, | |
| "grad_norm": 0.5534331202507019, | |
| "learning_rate": 9.276821300802535e-06, | |
| "loss": 0.580564558506012, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": 0.635610044002533, | |
| "learning_rate": 9.164606203550498e-06, | |
| "loss": 0.6000862121582031, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "grad_norm": 0.5146282315254211, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.5746794939041138, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9397590361445783, | |
| "grad_norm": 0.543429970741272, | |
| "learning_rate": 8.9184672866292e-06, | |
| "loss": 0.577430784702301, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9759036144578314, | |
| "grad_norm": 0.4730767011642456, | |
| "learning_rate": 8.784975278258783e-06, | |
| "loss": 0.5721206068992615, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.578737735748291, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 0.5727310180664062, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.036144578313253, | |
| "grad_norm": 0.5965927243232727, | |
| "learning_rate": 8.498316702566828e-06, | |
| "loss": 0.5036242008209229, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.072289156626506, | |
| "grad_norm": 0.533427894115448, | |
| "learning_rate": 8.345653031794292e-06, | |
| "loss": 0.5078785419464111, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.108433734939759, | |
| "grad_norm": 0.51552814245224, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.4693022668361664, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.144578313253012, | |
| "grad_norm": 0.5974420309066772, | |
| "learning_rate": 8.022995574311876e-06, | |
| "loss": 0.4865715503692627, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.180722891566265, | |
| "grad_norm": 0.5751659274101257, | |
| "learning_rate": 7.85356783842216e-06, | |
| "loss": 0.49929895997047424, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.216867469879518, | |
| "grad_norm": 0.5281147956848145, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 0.49614834785461426, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2530120481927711, | |
| "grad_norm": 0.5489075183868408, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.49161770939826965, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2891566265060241, | |
| "grad_norm": 0.6569790244102478, | |
| "learning_rate": 7.31648017559931e-06, | |
| "loss": 0.48665398359298706, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3253012048192772, | |
| "grad_norm": 0.5829439163208008, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 0.4777125120162964, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3614457831325302, | |
| "grad_norm": 0.49731743335723877, | |
| "learning_rate": 6.9375779322605154e-06, | |
| "loss": 0.4852375388145447, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3975903614457832, | |
| "grad_norm": 0.5951570868492126, | |
| "learning_rate": 6.7428602366090764e-06, | |
| "loss": 0.46885544061660767, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4337349397590362, | |
| "grad_norm": 0.5189629793167114, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.4777418375015259, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4698795180722892, | |
| "grad_norm": 0.5602889060974121, | |
| "learning_rate": 6.344599103076329e-06, | |
| "loss": 0.4813598096370697, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5060240963855422, | |
| "grad_norm": 0.5076647996902466, | |
| "learning_rate": 6.141754350553279e-06, | |
| "loss": 0.4753226637840271, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5421686746987953, | |
| "grad_norm": 0.4632566571235657, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 0.497364342212677, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5783132530120483, | |
| "grad_norm": 0.489469438791275, | |
| "learning_rate": 5.730415142812059e-06, | |
| "loss": 0.4533390402793884, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6144578313253013, | |
| "grad_norm": 0.5627046227455139, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 0.47720852494239807, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6506024096385543, | |
| "grad_norm": 0.615321934223175, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 0.4630257785320282, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6867469879518073, | |
| "grad_norm": 0.7377497553825378, | |
| "learning_rate": 5.1047120994167855e-06, | |
| "loss": 0.4707484245300293, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7228915662650603, | |
| "grad_norm": 0.44864723086357117, | |
| "learning_rate": 4.895287900583216e-06, | |
| "loss": 0.5026432871818542, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7590361445783134, | |
| "grad_norm": 0.48998555541038513, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 0.4894215762615204, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7951807228915664, | |
| "grad_norm": 0.4500783383846283, | |
| "learning_rate": 4.477357683661734e-06, | |
| "loss": 0.48538342118263245, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8313253012048194, | |
| "grad_norm": 0.4918319880962372, | |
| "learning_rate": 4.269584857187942e-06, | |
| "loss": 0.45954716205596924, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.8674698795180724, | |
| "grad_norm": 0.5150398015975952, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 0.4566912055015564, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.9036144578313254, | |
| "grad_norm": 0.44811761379241943, | |
| "learning_rate": 3.8582456494467214e-06, | |
| "loss": 0.48027291893959045, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.9397590361445785, | |
| "grad_norm": 0.609320342540741, | |
| "learning_rate": 3.655400896923672e-06, | |
| "loss": 0.49082323908805847, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9759036144578315, | |
| "grad_norm": 0.46881070733070374, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.47446680068969727, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.5909848213195801, | |
| "learning_rate": 3.2571397633909252e-06, | |
| "loss": 0.47039300203323364, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.036144578313253, | |
| "grad_norm": 0.709743857383728, | |
| "learning_rate": 3.0624220677394854e-06, | |
| "loss": 0.3891071379184723, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.072289156626506, | |
| "grad_norm": 0.5000724792480469, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 0.43356871604919434, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.108433734939759, | |
| "grad_norm": 0.5290446877479553, | |
| "learning_rate": 2.683519824400693e-06, | |
| "loss": 0.40094226598739624, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.144578313253012, | |
| "grad_norm": 0.5125427842140198, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.4142378270626068, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.180722891566265, | |
| "grad_norm": 0.6648615002632141, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.3956088721752167, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.216867469879518, | |
| "grad_norm": 0.8099228739738464, | |
| "learning_rate": 2.146432161577842e-06, | |
| "loss": 0.38991785049438477, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.253012048192771, | |
| "grad_norm": 0.53780198097229, | |
| "learning_rate": 1.977004425688126e-06, | |
| "loss": 0.3925628364086151, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.289156626506024, | |
| "grad_norm": 0.6565864086151123, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 0.39590010046958923, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.325301204819277, | |
| "grad_norm": 0.48299795389175415, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 0.4138052761554718, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.36144578313253, | |
| "grad_norm": 0.5652570128440857, | |
| "learning_rate": 1.5016832974331725e-06, | |
| "loss": 0.40755337476730347, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.397590361445783, | |
| "grad_norm": 1.1212197542190552, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 0.4035053253173828, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.433734939759036, | |
| "grad_norm": 0.5047882795333862, | |
| "learning_rate": 1.2150247217412186e-06, | |
| "loss": 0.41533365845680237, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.4698795180722892, | |
| "grad_norm": 0.5447006821632385, | |
| "learning_rate": 1.0815327133708015e-06, | |
| "loss": 0.36712491512298584, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.5060240963855422, | |
| "grad_norm": 0.5147467851638794, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.3851737380027771, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.5421686746987953, | |
| "grad_norm": 0.47967737913131714, | |
| "learning_rate": 8.353937964495029e-07, | |
| "loss": 0.4188123345375061, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.5783132530120483, | |
| "grad_norm": 0.5074743628501892, | |
| "learning_rate": 7.23178699197467e-07, | |
| "loss": 0.40590065717697144, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.6144578313253013, | |
| "grad_norm": 0.46036818623542786, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 0.38054245710372925, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.6506024096385543, | |
| "grad_norm": 1.1342926025390625, | |
| "learning_rate": 5.214411988029355e-07, | |
| "loss": 0.4026598334312439, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.6867469879518073, | |
| "grad_norm": 0.46817532181739807, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 0.4054795503616333, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.7228915662650603, | |
| "grad_norm": 0.7104460597038269, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 0.37800586223602295, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.7590361445783134, | |
| "grad_norm": 0.5266546010971069, | |
| "learning_rate": 2.7811814881259503e-07, | |
| "loss": 0.3979753255844116, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.7951807228915664, | |
| "grad_norm": 0.4721384644508362, | |
| "learning_rate": 2.134025123396638e-07, | |
| "loss": 0.3682253956794739, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.8313253012048194, | |
| "grad_norm": 0.426792174577713, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 0.4290738105773926, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.8674698795180724, | |
| "grad_norm": 0.4718446433544159, | |
| "learning_rate": 1.0926199633097156e-07, | |
| "loss": 0.3954327702522278, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.9036144578313254, | |
| "grad_norm": 0.4800931215286255, | |
| "learning_rate": 7.001981464747565e-08, | |
| "loss": 0.4111490845680237, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.9397590361445785, | |
| "grad_norm": 0.5462878346443176, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 0.38509202003479004, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.9759036144578315, | |
| "grad_norm": 0.44628024101257324, | |
| "learning_rate": 1.753570375247815e-08, | |
| "loss": 0.4102988541126251, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.5103145837783813, | |
| "learning_rate": 4.385849505708084e-09, | |
| "loss": 0.42839542031288147, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 84, | |
| "total_flos": 305241727172608.0, | |
| "train_loss": 0.4993832171672866, | |
| "train_runtime": 16221.4591, | |
| "train_samples_per_second": 0.245, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 84, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 305241727172608.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |