Image-Text-to-Text
Transformers
Safetensors
English
qwen3_vl
llama-factory
full
Generated from Trainer
conversational
Instructions to use Jaew00Lee/HiViG-critic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jaew00Lee/HiViG-critic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Jaew00Lee/HiViG-critic") 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("Jaew00Lee/HiViG-critic") model = AutoModelForMultimodalLM.from_pretrained("Jaew00Lee/HiViG-critic") 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 Jaew00Lee/HiViG-critic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jaew00Lee/HiViG-critic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jaew00Lee/HiViG-critic", "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/Jaew00Lee/HiViG-critic
- SGLang
How to use Jaew00Lee/HiViG-critic 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 "Jaew00Lee/HiViG-critic" \ --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": "Jaew00Lee/HiViG-critic", "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 "Jaew00Lee/HiViG-critic" \ --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": "Jaew00Lee/HiViG-critic", "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 Jaew00Lee/HiViG-critic with Docker Model Runner:
docker model run hf.co/Jaew00Lee/HiViG-critic
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 192, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00522875816993464, | |
| "grad_norm": 6.347966857947682, | |
| "learning_rate": 0.0, | |
| "loss": 0.9481360912322998, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01045751633986928, | |
| "grad_norm": 6.494536397572297, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.984634280204773, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01568627450980392, | |
| "grad_norm": 6.289502266193006, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.969107449054718, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02091503267973856, | |
| "grad_norm": 6.29776928567881, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.9729210734367371, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.026143790849673203, | |
| "grad_norm": 6.079050292624905, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.957334041595459, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03137254901960784, | |
| "grad_norm": 5.206607922464983, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.9323782324790955, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.036601307189542485, | |
| "grad_norm": 4.810000840095693, | |
| "learning_rate": 3e-06, | |
| "loss": 0.9412962198257446, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04183006535947712, | |
| "grad_norm": 2.5660008448589346, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.8515911102294922, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.047058823529411764, | |
| "grad_norm": 2.2824469364216737, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.8457263708114624, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05228758169934641, | |
| "grad_norm": 3.3736759059530814, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.8140297532081604, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05751633986928104, | |
| "grad_norm": 3.0995176628277736, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8191126585006714, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06274509803921569, | |
| "grad_norm": 2.5895398622981927, | |
| "learning_rate": 4.999627560102124e-06, | |
| "loss": 0.7870434522628784, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06797385620915032, | |
| "grad_norm": 1.8974304445402854, | |
| "learning_rate": 4.998510351377676e-06, | |
| "loss": 0.7835123538970947, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07320261437908497, | |
| "grad_norm": 1.956193988467153, | |
| "learning_rate": 4.996648706701141e-06, | |
| "loss": 0.762599527835846, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 1.6501330069020888, | |
| "learning_rate": 4.99404318075312e-06, | |
| "loss": 0.7699071168899536, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08366013071895424, | |
| "grad_norm": 1.3191510260737256, | |
| "learning_rate": 4.990694549855066e-06, | |
| "loss": 0.7532117962837219, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 1.0728054038541968, | |
| "learning_rate": 4.986603811737982e-06, | |
| "loss": 0.7490524053573608, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 0.911602085668756, | |
| "learning_rate": 4.981772185245135e-06, | |
| "loss": 0.7236852645874023, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09934640522875816, | |
| "grad_norm": 0.921971864311516, | |
| "learning_rate": 4.976201109968909e-06, | |
| "loss": 0.7044740915298462, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": 1.0278227255206556, | |
| "learning_rate": 4.969892245821867e-06, | |
| "loss": 0.684246838092804, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10980392156862745, | |
| "grad_norm": 1.0505320545862888, | |
| "learning_rate": 4.9628474725421845e-06, | |
| "loss": 0.6957111358642578, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11503267973856209, | |
| "grad_norm": 0.9718522726959984, | |
| "learning_rate": 4.955068889133577e-06, | |
| "loss": 0.6782320141792297, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12026143790849673, | |
| "grad_norm": 0.8985769871307081, | |
| "learning_rate": 4.946558813239889e-06, | |
| "loss": 0.6832859516143799, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12549019607843137, | |
| "grad_norm": 0.7625829683264522, | |
| "learning_rate": 4.937319780454559e-06, | |
| "loss": 0.6632767915725708, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13071895424836602, | |
| "grad_norm": 0.7153335787803188, | |
| "learning_rate": 4.927354543565131e-06, | |
| "loss": 0.6677097082138062, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13594771241830064, | |
| "grad_norm": 0.7832405880278965, | |
| "learning_rate": 4.9166660717330496e-06, | |
| "loss": 0.6688209772109985, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1411764705882353, | |
| "grad_norm": 0.8081012579571756, | |
| "learning_rate": 4.905257549609002e-06, | |
| "loss": 0.6523228883743286, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14640522875816994, | |
| "grad_norm": 0.7232667052601495, | |
| "learning_rate": 4.89313237638404e-06, | |
| "loss": 0.6514331102371216, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.15163398692810456, | |
| "grad_norm": 0.7364919902342735, | |
| "learning_rate": 4.880294164776785e-06, | |
| "loss": 0.6719018220901489, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 0.7402087352191463, | |
| "learning_rate": 4.866746739957016e-06, | |
| "loss": 0.6616781949996948, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16209150326797386, | |
| "grad_norm": 0.6548663554771319, | |
| "learning_rate": 4.852494138405942e-06, | |
| "loss": 0.6498498916625977, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.16732026143790849, | |
| "grad_norm": 0.6462896054284554, | |
| "learning_rate": 4.837540606713538e-06, | |
| "loss": 0.6334521770477295, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.17254901960784313, | |
| "grad_norm": 0.6601443083080514, | |
| "learning_rate": 4.821890600313256e-06, | |
| "loss": 0.6329904794692993, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.6361024237274734, | |
| "learning_rate": 4.805548782154527e-06, | |
| "loss": 0.6358813643455505, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1830065359477124, | |
| "grad_norm": 0.6370767401843039, | |
| "learning_rate": 4.788520021313416e-06, | |
| "loss": 0.6412982940673828, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 0.6160492611377754, | |
| "learning_rate": 4.770809391541885e-06, | |
| "loss": 0.6219744682312012, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1934640522875817, | |
| "grad_norm": 0.5891892411318342, | |
| "learning_rate": 4.752422169756048e-06, | |
| "loss": 0.6276743412017822, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19869281045751633, | |
| "grad_norm": 0.593118371908844, | |
| "learning_rate": 4.733363834463908e-06, | |
| "loss": 0.6285060048103333, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.20392156862745098, | |
| "grad_norm": 0.575270106297829, | |
| "learning_rate": 4.7136400641330245e-06, | |
| "loss": 0.6261259317398071, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20915032679738563, | |
| "grad_norm": 0.5713198483443941, | |
| "learning_rate": 4.693256735498605e-06, | |
| "loss": 0.6043239831924438, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21437908496732025, | |
| "grad_norm": 0.6125225644788509, | |
| "learning_rate": 4.672219921812517e-06, | |
| "loss": 0.6216004490852356, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2196078431372549, | |
| "grad_norm": 0.5732437092230873, | |
| "learning_rate": 4.650535891033752e-06, | |
| "loss": 0.6183825731277466, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.22483660130718955, | |
| "grad_norm": 0.5893871794916001, | |
| "learning_rate": 4.6282111039608786e-06, | |
| "loss": 0.6294577717781067, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.23006535947712417, | |
| "grad_norm": 0.5883118590404731, | |
| "learning_rate": 4.60525221230703e-06, | |
| "loss": 0.5969547033309937, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5645900134186553, | |
| "learning_rate": 4.581666056718016e-06, | |
| "loss": 0.6152564287185669, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.24052287581699347, | |
| "grad_norm": 0.5538864743605434, | |
| "learning_rate": 4.5574596647341414e-06, | |
| "loss": 0.6116839647293091, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2457516339869281, | |
| "grad_norm": 0.5876321390392742, | |
| "learning_rate": 4.532640248696331e-06, | |
| "loss": 0.5973551273345947, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.25098039215686274, | |
| "grad_norm": 0.5667126105497471, | |
| "learning_rate": 4.5072152035972065e-06, | |
| "loss": 0.6084102392196655, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.25620915032679736, | |
| "grad_norm": 0.5779618428834822, | |
| "learning_rate": 4.481192104877727e-06, | |
| "loss": 0.6000851988792419, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.26143790849673204, | |
| "grad_norm": 0.595872790475092, | |
| "learning_rate": 4.454578706170075e-06, | |
| "loss": 0.6287335157394409, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.6135449402557597, | |
| "learning_rate": 4.427382936987449e-06, | |
| "loss": 0.6047977209091187, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2718954248366013, | |
| "grad_norm": 0.5654402206393638, | |
| "learning_rate": 4.3996129003614476e-06, | |
| "loss": 0.6092298626899719, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.27712418300653596, | |
| "grad_norm": 0.588720660819845, | |
| "learning_rate": 4.3712768704277535e-06, | |
| "loss": 0.6106082797050476, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": 0.5625841118179689, | |
| "learning_rate": 4.342383289960842e-06, | |
| "loss": 0.5951759219169617, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2875816993464052, | |
| "grad_norm": 0.6385157703007635, | |
| "learning_rate": 4.312940767858442e-06, | |
| "loss": 0.5925623178482056, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2928104575163399, | |
| "grad_norm": 0.5450004755809773, | |
| "learning_rate": 4.282958076576491e-06, | |
| "loss": 0.5999478697776794, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2980392156862745, | |
| "grad_norm": 0.5441923776730769, | |
| "learning_rate": 4.252444149515374e-06, | |
| "loss": 0.5923868417739868, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3032679738562091, | |
| "grad_norm": 0.5820233623448337, | |
| "learning_rate": 4.221408078358193e-06, | |
| "loss": 0.6029752492904663, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.3084967320261438, | |
| "grad_norm": 0.5892415536138577, | |
| "learning_rate": 4.189859110361886e-06, | |
| "loss": 0.5926511287689209, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 0.5599877647664481, | |
| "learning_rate": 4.1578066456019885e-06, | |
| "loss": 0.589052677154541, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.31895424836601305, | |
| "grad_norm": 0.541734586591236, | |
| "learning_rate": 4.125260234171861e-06, | |
| "loss": 0.5972912311553955, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3241830065359477, | |
| "grad_norm": 0.5582144979942749, | |
| "learning_rate": 4.092229573337223e-06, | |
| "loss": 0.5824427604675293, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.32941176470588235, | |
| "grad_norm": 0.5789574351764452, | |
| "learning_rate": 4.058724504646834e-06, | |
| "loss": 0.5841062068939209, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.33464052287581697, | |
| "grad_norm": 0.5627250980341298, | |
| "learning_rate": 4.0247550110001825e-06, | |
| "loss": 0.5932133197784424, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.33986928104575165, | |
| "grad_norm": 0.5602690396228506, | |
| "learning_rate": 3.990331213673064e-06, | |
| "loss": 0.5924372673034668, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.34509803921568627, | |
| "grad_norm": 0.6235146146565055, | |
| "learning_rate": 3.9554633693019275e-06, | |
| "loss": 0.5912005305290222, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3503267973856209, | |
| "grad_norm": 0.5807352926165517, | |
| "learning_rate": 3.92016186682789e-06, | |
| "loss": 0.5893465876579285, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.5644905720493231, | |
| "learning_rate": 3.884437224401333e-06, | |
| "loss": 0.581815242767334, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3607843137254902, | |
| "grad_norm": 0.6126080456576034, | |
| "learning_rate": 3.848300086247998e-06, | |
| "loss": 0.5809829831123352, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3660130718954248, | |
| "grad_norm": 0.5703279895399361, | |
| "learning_rate": 3.81176121949752e-06, | |
| "loss": 0.5824570655822754, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3712418300653595, | |
| "grad_norm": 0.5608014055042397, | |
| "learning_rate": 3.7748315109753402e-06, | |
| "loss": 0.5795037746429443, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 0.6129777799452483, | |
| "learning_rate": 3.737521963958954e-06, | |
| "loss": 0.592901349067688, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.38169934640522873, | |
| "grad_norm": 0.6064170242930988, | |
| "learning_rate": 3.6998436948994664e-06, | |
| "loss": 0.5877245664596558, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3869281045751634, | |
| "grad_norm": 0.5258060101465157, | |
| "learning_rate": 3.661807930109422e-06, | |
| "loss": 0.5766226649284363, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.39215686274509803, | |
| "grad_norm": 0.5532641087151743, | |
| "learning_rate": 3.6234260024179036e-06, | |
| "loss": 0.5878047943115234, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.39738562091503266, | |
| "grad_norm": 0.5753178152704953, | |
| "learning_rate": 3.5847093477938955e-06, | |
| "loss": 0.5693782567977905, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.40261437908496733, | |
| "grad_norm": 0.57261888823084, | |
| "learning_rate": 3.545669501938913e-06, | |
| "loss": 0.5842486619949341, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.40784313725490196, | |
| "grad_norm": 0.5711955538919853, | |
| "learning_rate": 3.506318096849919e-06, | |
| "loss": 0.5750635862350464, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.4130718954248366, | |
| "grad_norm": 0.5621104350357707, | |
| "learning_rate": 3.466666857353547e-06, | |
| "loss": 0.5776480436325073, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.41830065359477125, | |
| "grad_norm": 0.5733622981347513, | |
| "learning_rate": 3.4267275976126697e-06, | |
| "loss": 0.5773502588272095, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4235294117647059, | |
| "grad_norm": 0.5784229314497759, | |
| "learning_rate": 3.386512217606339e-06, | |
| "loss": 0.5791910886764526, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.4287581699346405, | |
| "grad_norm": 0.5603923512105482, | |
| "learning_rate": 3.346032699584176e-06, | |
| "loss": 0.5744297504425049, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.4339869281045752, | |
| "grad_norm": 0.5476863889079238, | |
| "learning_rate": 3.3053011044962268e-06, | |
| "loss": 0.5794825553894043, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.4392156862745098, | |
| "grad_norm": 0.5465150807879586, | |
| "learning_rate": 3.2643295683993827e-06, | |
| "loss": 0.5800514221191406, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.5190947807026538, | |
| "learning_rate": 3.2231302988414198e-06, | |
| "loss": 0.5898442268371582, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4496732026143791, | |
| "grad_norm": 0.5452710234094856, | |
| "learning_rate": 3.1817155712237347e-06, | |
| "loss": 0.5779276490211487, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.4549019607843137, | |
| "grad_norm": 0.5508881891925463, | |
| "learning_rate": 3.140097725143868e-06, | |
| "loss": 0.5735259652137756, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.46013071895424834, | |
| "grad_norm": 0.5164501716677642, | |
| "learning_rate": 3.0982891607188948e-06, | |
| "loss": 0.573521077632904, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.465359477124183, | |
| "grad_norm": 0.5314892359327341, | |
| "learning_rate": 3.056302334890786e-06, | |
| "loss": 0.5799280405044556, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.5554410893740324, | |
| "learning_rate": 3.0141497577148416e-06, | |
| "loss": 0.5816221833229065, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.47581699346405226, | |
| "grad_norm": 0.5674238841107639, | |
| "learning_rate": 2.971843988632292e-06, | |
| "loss": 0.5861309766769409, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.48104575163398694, | |
| "grad_norm": 0.5383333102829588, | |
| "learning_rate": 2.929397632728191e-06, | |
| "loss": 0.5848875641822815, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.48627450980392156, | |
| "grad_norm": 0.5281164661452042, | |
| "learning_rate": 2.886823336975703e-06, | |
| "loss": 0.5784912109375, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4915032679738562, | |
| "grad_norm": 0.5185162243520675, | |
| "learning_rate": 2.8441337864679213e-06, | |
| "loss": 0.5753432512283325, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.49673202614379086, | |
| "grad_norm": 0.5681437863408695, | |
| "learning_rate": 2.8013417006383078e-06, | |
| "loss": 0.5733731985092163, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5019607843137255, | |
| "grad_norm": 0.5397128007436308, | |
| "learning_rate": 2.758459829470925e-06, | |
| "loss": 0.5713093280792236, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.5071895424836601, | |
| "grad_norm": 0.5286420212232708, | |
| "learning_rate": 2.7155009497015487e-06, | |
| "loss": 0.5599273443222046, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.5124183006535947, | |
| "grad_norm": 0.5332061382995414, | |
| "learning_rate": 2.6724778610108123e-06, | |
| "loss": 0.5773267149925232, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.5176470588235295, | |
| "grad_norm": 0.5719742771192323, | |
| "learning_rate": 2.629403382210524e-06, | |
| "loss": 0.5814815163612366, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5228758169934641, | |
| "grad_norm": 0.5632680640869598, | |
| "learning_rate": 2.5862903474242707e-06, | |
| "loss": 0.5715689659118652, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5228758169934641, | |
| "eval_loss": 0.5673182606697083, | |
| "eval_runtime": 358.5243, | |
| "eval_samples_per_second": 7.188, | |
| "eval_steps_per_second": 0.901, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5281045751633987, | |
| "grad_norm": 0.5335986189868693, | |
| "learning_rate": 2.5431516022634718e-06, | |
| "loss": 0.5701637864112854, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.5447359969374349, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.5731196403503418, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.538562091503268, | |
| "grad_norm": 0.5452628034951653, | |
| "learning_rate": 2.456848397736529e-06, | |
| "loss": 0.570784866809845, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.5437908496732026, | |
| "grad_norm": 0.5214059077677813, | |
| "learning_rate": 2.4137096525757306e-06, | |
| "loss": 0.5641082525253296, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.5490196078431373, | |
| "grad_norm": 0.5338181878638509, | |
| "learning_rate": 2.3705966177894763e-06, | |
| "loss": 0.5622221231460571, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.5542483660130719, | |
| "grad_norm": 0.5417133865959133, | |
| "learning_rate": 2.3275221389891877e-06, | |
| "loss": 0.5729820132255554, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.5594771241830065, | |
| "grad_norm": 0.5788688379436328, | |
| "learning_rate": 2.2844990502984517e-06, | |
| "loss": 0.5598784685134888, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.5647058823529412, | |
| "grad_norm": 0.527902900147592, | |
| "learning_rate": 2.2415401705290753e-06, | |
| "loss": 0.5576006174087524, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.5699346405228758, | |
| "grad_norm": 0.5421982725166127, | |
| "learning_rate": 2.1986582993616926e-06, | |
| "loss": 0.5639731884002686, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.5751633986928104, | |
| "grad_norm": 0.5726654841184247, | |
| "learning_rate": 2.15586621353208e-06, | |
| "loss": 0.581594705581665, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5803921568627451, | |
| "grad_norm": 0.52327011841633, | |
| "learning_rate": 2.113176663024297e-06, | |
| "loss": 0.5771512985229492, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.5856209150326798, | |
| "grad_norm": 0.5199682658397303, | |
| "learning_rate": 2.07060236727181e-06, | |
| "loss": 0.5710991621017456, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.5908496732026144, | |
| "grad_norm": 0.5520241920459973, | |
| "learning_rate": 2.0281560113677085e-06, | |
| "loss": 0.538283109664917, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.596078431372549, | |
| "grad_norm": 0.5257419472887066, | |
| "learning_rate": 1.9858502422851588e-06, | |
| "loss": 0.5497515201568604, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.6013071895424836, | |
| "grad_norm": 0.5119991697476447, | |
| "learning_rate": 1.9436976651092143e-06, | |
| "loss": 0.5641146898269653, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.6065359477124183, | |
| "grad_norm": 0.5446106545142635, | |
| "learning_rate": 1.9017108392811065e-06, | |
| "loss": 0.5670981407165527, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.611764705882353, | |
| "grad_norm": 0.5259369530730766, | |
| "learning_rate": 1.8599022748561324e-06, | |
| "loss": 0.5728137493133545, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.6169934640522876, | |
| "grad_norm": 0.5034903035804525, | |
| "learning_rate": 1.8182844287762657e-06, | |
| "loss": 0.560348391532898, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.5325668868834296, | |
| "learning_rate": 1.776869701158581e-06, | |
| "loss": 0.560174822807312, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": 0.5467877432708195, | |
| "learning_rate": 1.7356704316006185e-06, | |
| "loss": 0.5621490478515625, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6326797385620915, | |
| "grad_norm": 0.528568337591619, | |
| "learning_rate": 1.694698895503774e-06, | |
| "loss": 0.5659476518630981, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.6379084967320261, | |
| "grad_norm": 0.5089558928097043, | |
| "learning_rate": 1.653967300415824e-06, | |
| "loss": 0.569420576095581, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.6431372549019608, | |
| "grad_norm": 0.5024462543910206, | |
| "learning_rate": 1.613487782393661e-06, | |
| "loss": 0.5675485134124756, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.6483660130718955, | |
| "grad_norm": 0.5193556626496942, | |
| "learning_rate": 1.5732724023873313e-06, | |
| "loss": 0.5646683573722839, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.6535947712418301, | |
| "grad_norm": 0.5167777438862812, | |
| "learning_rate": 1.5333331426464532e-06, | |
| "loss": 0.5609128475189209, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.6588235294117647, | |
| "grad_norm": 0.5214328685096735, | |
| "learning_rate": 1.4936819031500816e-06, | |
| "loss": 0.5676463842391968, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.6640522875816993, | |
| "grad_norm": 0.5147327036840245, | |
| "learning_rate": 1.4543304980610879e-06, | |
| "loss": 0.5723596811294556, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.6692810457516339, | |
| "grad_norm": 0.5053173120160722, | |
| "learning_rate": 1.415290652206105e-06, | |
| "loss": 0.5553067922592163, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.6745098039215687, | |
| "grad_norm": 0.532609302888491, | |
| "learning_rate": 1.3765739975820964e-06, | |
| "loss": 0.5784270763397217, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.6797385620915033, | |
| "grad_norm": 0.5186651032522405, | |
| "learning_rate": 1.3381920698905788e-06, | |
| "loss": 0.558042049407959, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6849673202614379, | |
| "grad_norm": 0.495557755541781, | |
| "learning_rate": 1.3001563051005348e-06, | |
| "loss": 0.5508121252059937, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.6901960784313725, | |
| "grad_norm": 0.5131732718876296, | |
| "learning_rate": 1.2624780360410465e-06, | |
| "loss": 0.5609950423240662, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.6954248366013072, | |
| "grad_norm": 0.5803152168243949, | |
| "learning_rate": 1.225168489024661e-06, | |
| "loss": 0.5562149286270142, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.7006535947712418, | |
| "grad_norm": 0.5170427589265535, | |
| "learning_rate": 1.18823878050248e-06, | |
| "loss": 0.5500751733779907, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.5024022320857018, | |
| "learning_rate": 1.1516999137520023e-06, | |
| "loss": 0.5647166967391968, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.5649509800380527, | |
| "learning_rate": 1.1155627755986673e-06, | |
| "loss": 0.5671936273574829, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.7163398692810458, | |
| "grad_norm": 0.5177084345458365, | |
| "learning_rate": 1.079838133172111e-06, | |
| "loss": 0.5641372203826904, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.7215686274509804, | |
| "grad_norm": 0.5137945415106975, | |
| "learning_rate": 1.044536630698074e-06, | |
| "loss": 0.5575729012489319, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.726797385620915, | |
| "grad_norm": 0.5211634393198903, | |
| "learning_rate": 1.0096687863269368e-06, | |
| "loss": 0.5538100004196167, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.7320261437908496, | |
| "grad_norm": 0.5224412702400191, | |
| "learning_rate": 9.752449889998177e-07, | |
| "loss": 0.5602108240127563, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7372549019607844, | |
| "grad_norm": 0.498873761813189, | |
| "learning_rate": 9.412754953531664e-07, | |
| "loss": 0.5666385293006897, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.742483660130719, | |
| "grad_norm": 0.5495549304431346, | |
| "learning_rate": 9.077704266627777e-07, | |
| "loss": 0.5576941967010498, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.7477124183006536, | |
| "grad_norm": 0.4971585112051998, | |
| "learning_rate": 8.747397658281396e-07, | |
| "loss": 0.560312032699585, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.7529411764705882, | |
| "grad_norm": 0.4988535210920422, | |
| "learning_rate": 8.421933543980126e-07, | |
| "loss": 0.5632399320602417, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.7581699346405228, | |
| "grad_norm": 0.5201536305985685, | |
| "learning_rate": 8.101408896381141e-07, | |
| "loss": 0.5657294988632202, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.7633986928104575, | |
| "grad_norm": 0.5143498110980177, | |
| "learning_rate": 7.78591921641807e-07, | |
| "loss": 0.5454354286193848, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.7686274509803922, | |
| "grad_norm": 0.748375404324366, | |
| "learning_rate": 7.475558504846264e-07, | |
| "loss": 0.5555028915405273, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.7738562091503268, | |
| "grad_norm": 0.5338879723386315, | |
| "learning_rate": 7.170419234235099e-07, | |
| "loss": 0.5638636946678162, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.7790849673202614, | |
| "grad_norm": 0.5458700295815662, | |
| "learning_rate": 6.870592321415595e-07, | |
| "loss": 0.5679295063018799, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": 0.49974904279732546, | |
| "learning_rate": 6.576167100391583e-07, | |
| "loss": 0.5531324148178101, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7895424836601307, | |
| "grad_norm": 0.48725698658480215, | |
| "learning_rate": 6.28723129572247e-07, | |
| "loss": 0.5494948625564575, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.7947712418300653, | |
| "grad_norm": 0.4936709993021908, | |
| "learning_rate": 6.003870996385533e-07, | |
| "loss": 0.557604193687439, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.4785500324707629, | |
| "learning_rate": 5.72617063012551e-07, | |
| "loss": 0.5621477365493774, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.8052287581699347, | |
| "grad_norm": 0.51265153178198, | |
| "learning_rate": 5.454212938299256e-07, | |
| "loss": 0.5555800199508667, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.8104575163398693, | |
| "grad_norm": 0.5929400138865342, | |
| "learning_rate": 5.188078951222745e-07, | |
| "loss": 0.5754239559173584, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.8156862745098039, | |
| "grad_norm": 0.5151264092726617, | |
| "learning_rate": 4.92784796402794e-07, | |
| "loss": 0.5659595727920532, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.8209150326797385, | |
| "grad_norm": 0.48683381113142116, | |
| "learning_rate": 4.673597513036684e-07, | |
| "loss": 0.5688292384147644, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.8261437908496732, | |
| "grad_norm": 0.49956835275891054, | |
| "learning_rate": 4.4254033526585917e-07, | |
| "loss": 0.5485458970069885, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.8313725490196079, | |
| "grad_norm": 0.5053069611704939, | |
| "learning_rate": 4.183339432819844e-07, | |
| "loss": 0.560895562171936, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.8366013071895425, | |
| "grad_norm": 0.4987215316301059, | |
| "learning_rate": 3.947477876929706e-07, | |
| "loss": 0.5563021302223206, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8418300653594771, | |
| "grad_norm": 0.4909410145974737, | |
| "learning_rate": 3.717888960391222e-07, | |
| "loss": 0.5633970499038696, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.8470588235294118, | |
| "grad_norm": 0.482251665763075, | |
| "learning_rate": 3.4946410896624816e-07, | |
| "loss": 0.5483416318893433, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.8522875816993464, | |
| "grad_norm": 0.503006037783509, | |
| "learning_rate": 3.2778007818748376e-07, | |
| "loss": 0.5658166408538818, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.857516339869281, | |
| "grad_norm": 0.5036055628183839, | |
| "learning_rate": 3.0674326450139516e-07, | |
| "loss": 0.5492104291915894, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.8627450980392157, | |
| "grad_norm": 0.5026032251221639, | |
| "learning_rate": 2.8635993586697555e-07, | |
| "loss": 0.55476975440979, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.8679738562091504, | |
| "grad_norm": 0.49878849351164134, | |
| "learning_rate": 2.6663616553609273e-07, | |
| "loss": 0.5482717752456665, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.873202614379085, | |
| "grad_norm": 0.4993322700673657, | |
| "learning_rate": 2.4757783024395244e-07, | |
| "loss": 0.553543210029602, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.8784313725490196, | |
| "grad_norm": 0.4891186370831776, | |
| "learning_rate": 2.2919060845811498e-07, | |
| "loss": 0.5653778314590454, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.8836601307189542, | |
| "grad_norm": 0.5104384613452125, | |
| "learning_rate": 2.1147997868658427e-07, | |
| "loss": 0.5473053455352783, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.5565094294303261, | |
| "learning_rate": 1.9445121784547437e-07, | |
| "loss": 0.5555562376976013, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8941176470588236, | |
| "grad_norm": 0.4868919535614007, | |
| "learning_rate": 1.7810939968674418e-07, | |
| "loss": 0.5629611015319824, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.8993464052287582, | |
| "grad_norm": 0.49051351012766137, | |
| "learning_rate": 1.6245939328646322e-07, | |
| "loss": 0.569056510925293, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.9045751633986928, | |
| "grad_norm": 0.5065131508836102, | |
| "learning_rate": 1.4750586159405917e-07, | |
| "loss": 0.5600336790084839, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.9098039215686274, | |
| "grad_norm": 0.5093368159571033, | |
| "learning_rate": 1.3325326004298533e-07, | |
| "loss": 0.5577600598335266, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.9150326797385621, | |
| "grad_norm": 0.5012778907296466, | |
| "learning_rate": 1.197058352232147e-07, | |
| "loss": 0.5549207925796509, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.9202614379084967, | |
| "grad_norm": 0.494297148988845, | |
| "learning_rate": 1.0686762361596075e-07, | |
| "loss": 0.5604888200759888, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.9254901960784314, | |
| "grad_norm": 0.4908336081620801, | |
| "learning_rate": 9.474245039099883e-08, | |
| "loss": 0.5673908591270447, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.930718954248366, | |
| "grad_norm": 0.5156383296582215, | |
| "learning_rate": 8.333392826695125e-08, | |
| "loss": 0.5623798370361328, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.9359477124183007, | |
| "grad_norm": 0.511017006136213, | |
| "learning_rate": 7.264545643486997e-08, | |
| "loss": 0.5695925354957581, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.5246694637251323, | |
| "learning_rate": 6.268021954544095e-08, | |
| "loss": 0.5567260384559631, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9464052287581699, | |
| "grad_norm": 0.48564624001478096, | |
| "learning_rate": 5.344118676011173e-08, | |
| "loss": 0.5637162923812866, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.9516339869281045, | |
| "grad_norm": 0.4816986249713747, | |
| "learning_rate": 4.493111086642438e-08, | |
| "loss": 0.568381130695343, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.9568627450980393, | |
| "grad_norm": 0.5152957786140409, | |
| "learning_rate": 3.7152527457815504e-08, | |
| "loss": 0.5643942356109619, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.9620915032679739, | |
| "grad_norm": 0.5009014081483334, | |
| "learning_rate": 3.010775417813388e-08, | |
| "loss": 0.5601834058761597, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.9673202614379085, | |
| "grad_norm": 0.49981156598749754, | |
| "learning_rate": 2.3798890031092037e-08, | |
| "loss": 0.5571467876434326, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.9725490196078431, | |
| "grad_norm": 0.4756602024624245, | |
| "learning_rate": 1.822781475486507e-08, | |
| "loss": 0.5563821792602539, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.4808447389705439, | |
| "learning_rate": 1.3396188262018439e-08, | |
| "loss": 0.5627793073654175, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.9830065359477124, | |
| "grad_norm": 0.5075203531092929, | |
| "learning_rate": 9.305450144933836e-09, | |
| "loss": 0.5584004521369934, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.9882352941176471, | |
| "grad_norm": 0.4991385105933137, | |
| "learning_rate": 5.9568192468811844e-09, | |
| "loss": 0.5592875480651855, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.9934640522875817, | |
| "grad_norm": 0.4819552321388971, | |
| "learning_rate": 3.3512932988596924e-09, | |
| "loss": 0.5583007335662842, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.9986928104575163, | |
| "grad_norm": 0.5013592427400733, | |
| "learning_rate": 1.4896486223239802e-09, | |
| "loss": 0.5680533051490784, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9891674873290996, | |
| "learning_rate": 3.7243989787633106e-10, | |
| "loss": 0.5837845802307129, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 192, | |
| "total_flos": 989914169868288.0, | |
| "train_loss": 0.6082294903074702, | |
| "train_runtime": 18395.1691, | |
| "train_samples_per_second": 2.661, | |
| "train_steps_per_second": 0.01 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 192, | |
| "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": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 989914169868288.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |