Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use mingiJ/token_skip-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mingiJ/token_skip-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mingiJ/token_skip-4b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("mingiJ/token_skip-4b") model = AutoModelForCausalLM.from_pretrained("mingiJ/token_skip-4b", 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 mingiJ/token_skip-4b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mingiJ/token_skip-4b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mingiJ/token_skip-4b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/mingiJ/token_skip-4b
- SGLang
How to use mingiJ/token_skip-4b 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 "mingiJ/token_skip-4b" \ --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": "mingiJ/token_skip-4b", "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 "mingiJ/token_skip-4b" \ --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": "mingiJ/token_skip-4b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use mingiJ/token_skip-4b with Docker Model Runner:
docker model run hf.co/mingiJ/token_skip-4b
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.999569151227919, | |
| "eval_steps": 500, | |
| "global_step": 1305, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007659533725884436, | |
| "grad_norm": 4.585542476127782, | |
| "learning_rate": 6.870229007633589e-06, | |
| "loss": 1.5342, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015319067451768873, | |
| "grad_norm": 1.9168528825341193, | |
| "learning_rate": 1.450381679389313e-05, | |
| "loss": 0.8087, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02297860117765331, | |
| "grad_norm": 1.7494595444106944, | |
| "learning_rate": 2.2137404580152673e-05, | |
| "loss": 0.6624, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030638134903537746, | |
| "grad_norm": 2.2498997742937363, | |
| "learning_rate": 2.9770992366412214e-05, | |
| "loss": 0.6558, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03829766862942218, | |
| "grad_norm": 1.8180680448843922, | |
| "learning_rate": 3.7404580152671756e-05, | |
| "loss": 0.6096, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04595720235530662, | |
| "grad_norm": 1.6228088755931114, | |
| "learning_rate": 4.5038167938931294e-05, | |
| "loss": 0.6418, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05361673608119106, | |
| "grad_norm": 1.8008545319562819, | |
| "learning_rate": 5.267175572519084e-05, | |
| "loss": 0.6372, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06127626980707549, | |
| "grad_norm": 1.3828949316057764, | |
| "learning_rate": 6.0305343511450384e-05, | |
| "loss": 0.6454, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06893580353295993, | |
| "grad_norm": 1.5447120083529549, | |
| "learning_rate": 6.793893129770993e-05, | |
| "loss": 0.636, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07659533725884436, | |
| "grad_norm": 4.189206237497925, | |
| "learning_rate": 7.557251908396947e-05, | |
| "loss": 0.6307, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08425487098472881, | |
| "grad_norm": 1.4113919986461227, | |
| "learning_rate": 8.320610687022902e-05, | |
| "loss": 0.683, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09191440471061324, | |
| "grad_norm": 1.2966834984162288, | |
| "learning_rate": 9.083969465648856e-05, | |
| "loss": 0.6656, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09957393843649767, | |
| "grad_norm": 1.2562948634106306, | |
| "learning_rate": 9.84732824427481e-05, | |
| "loss": 0.6729, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.10723347216238212, | |
| "grad_norm": 1.1134314373972036, | |
| "learning_rate": 9.998854310460233e-05, | |
| "loss": 0.6685, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11489300588826655, | |
| "grad_norm": 1.1853742832665686, | |
| "learning_rate": 9.994200846542251e-05, | |
| "loss": 0.6699, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12255253961415098, | |
| "grad_norm": 1.2950541750596993, | |
| "learning_rate": 9.985971332154984e-05, | |
| "loss": 0.6848, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13021207334003543, | |
| "grad_norm": 1.1203368484907543, | |
| "learning_rate": 9.974171659964687e-05, | |
| "loss": 0.7005, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.13787160706591986, | |
| "grad_norm": 1.3142045395841067, | |
| "learning_rate": 9.958810279015473e-05, | |
| "loss": 0.6757, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1455311407918043, | |
| "grad_norm": 1.019650080366063, | |
| "learning_rate": 9.939898188679464e-05, | |
| "loss": 0.6678, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.15319067451768872, | |
| "grad_norm": 0.9168855949375643, | |
| "learning_rate": 9.917448930780786e-05, | |
| "loss": 0.6781, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16085020824357318, | |
| "grad_norm": 1.0530592108443477, | |
| "learning_rate": 9.891478579899079e-05, | |
| "loss": 0.6841, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.16850974196945762, | |
| "grad_norm": 1.0143214926764803, | |
| "learning_rate": 9.862005731859442e-05, | |
| "loss": 0.6841, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.17616927569534205, | |
| "grad_norm": 1.03752898969354, | |
| "learning_rate": 9.829051490417073e-05, | |
| "loss": 0.6667, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.18382880942122648, | |
| "grad_norm": 1.191347331860848, | |
| "learning_rate": 9.792639452146115e-05, | |
| "loss": 0.668, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1914883431471109, | |
| "grad_norm": 1.0429696856251238, | |
| "learning_rate": 9.752795689543564e-05, | |
| "loss": 0.6808, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.19914787687299534, | |
| "grad_norm": 0.9451116935903828, | |
| "learning_rate": 9.709548732360285e-05, | |
| "loss": 0.6701, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2068074105988798, | |
| "grad_norm": 1.0069521463660143, | |
| "learning_rate": 9.662929547172574e-05, | |
| "loss": 0.6764, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.21446694432476424, | |
| "grad_norm": 1.013713779413254, | |
| "learning_rate": 9.61297151520882e-05, | |
| "loss": 0.6653, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.22212647805064867, | |
| "grad_norm": 0.8428712955576788, | |
| "learning_rate": 9.559710408447185e-05, | |
| "loss": 0.6706, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2297860117765331, | |
| "grad_norm": 0.9679286842839989, | |
| "learning_rate": 9.503184364001431e-05, | |
| "loss": 0.6506, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.23744554550241753, | |
| "grad_norm": 0.8636277650595472, | |
| "learning_rate": 9.443433856813197e-05, | |
| "loss": 0.6654, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.24510507922830196, | |
| "grad_norm": 0.9085064112194627, | |
| "learning_rate": 9.38050167067028e-05, | |
| "loss": 0.6489, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.2527646129541864, | |
| "grad_norm": 0.945404545784054, | |
| "learning_rate": 9.314432867571731e-05, | |
| "loss": 0.6762, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.26042414668007086, | |
| "grad_norm": 0.8345456114257215, | |
| "learning_rate": 9.24527475546162e-05, | |
| "loss": 0.6519, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.26808368040595526, | |
| "grad_norm": 1.0600761168334611, | |
| "learning_rate": 9.173076854354634e-05, | |
| "loss": 0.6596, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2757432141318397, | |
| "grad_norm": 0.8045120836973815, | |
| "learning_rate": 9.097890860877732e-05, | |
| "loss": 0.6304, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2834027478577242, | |
| "grad_norm": 0.883297712718, | |
| "learning_rate": 9.01977061125327e-05, | |
| "loss": 0.6487, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2910622815836086, | |
| "grad_norm": 1.1118932234729717, | |
| "learning_rate": 8.938772042750078e-05, | |
| "loss": 0.6551, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.29872181530949304, | |
| "grad_norm": 0.8947188935196859, | |
| "learning_rate": 8.854953153630097e-05, | |
| "loss": 0.6434, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.30638134903537745, | |
| "grad_norm": 0.9133666559350329, | |
| "learning_rate": 8.768373961619283e-05, | |
| "loss": 0.6446, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3140408827612619, | |
| "grad_norm": 0.800135284242025, | |
| "learning_rate": 8.679096460932476e-05, | |
| "loss": 0.6431, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.32170041648714637, | |
| "grad_norm": 0.7667073263249349, | |
| "learning_rate": 8.587184577883018e-05, | |
| "loss": 0.635, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.32935995021303077, | |
| "grad_norm": 0.7446187579392809, | |
| "learning_rate": 8.492704125108932e-05, | |
| "loss": 0.6474, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.33701948393891523, | |
| "grad_norm": 0.8505474486594474, | |
| "learning_rate": 8.395722754448392e-05, | |
| "loss": 0.6435, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.34467901766479964, | |
| "grad_norm": 0.6912136288838342, | |
| "learning_rate": 8.296309908498264e-05, | |
| "loss": 0.6204, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3523385513906841, | |
| "grad_norm": 0.8845907739657766, | |
| "learning_rate": 8.194536770890391e-05, | |
| "loss": 0.6176, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.35999808511656856, | |
| "grad_norm": 0.793300893475574, | |
| "learning_rate": 8.090476215321226e-05, | |
| "loss": 0.6277, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.36765761884245296, | |
| "grad_norm": 0.8491940482226472, | |
| "learning_rate": 7.984202753371299e-05, | |
| "loss": 0.6374, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.3753171525683374, | |
| "grad_norm": 0.7020295330180372, | |
| "learning_rate": 7.875792481151916e-05, | |
| "loss": 0.619, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3829766862942218, | |
| "grad_norm": 0.8353198999548404, | |
| "learning_rate": 7.765323024817237e-05, | |
| "loss": 0.6165, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3906362200201063, | |
| "grad_norm": 0.8682650673639652, | |
| "learning_rate": 7.65287348498082e-05, | |
| "loss": 0.6197, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.3982957537459907, | |
| "grad_norm": 0.8629527743205716, | |
| "learning_rate": 7.538524380076351e-05, | |
| "loss": 0.6371, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.40595528747187515, | |
| "grad_norm": 0.73321971611232, | |
| "learning_rate": 7.422357588703195e-05, | |
| "loss": 0.6122, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.4136148211977596, | |
| "grad_norm": 0.6743735490891473, | |
| "learning_rate": 7.304456290997991e-05, | |
| "loss": 0.6029, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.421274354923644, | |
| "grad_norm": 0.8045206710775962, | |
| "learning_rate": 7.184904909074293e-05, | |
| "loss": 0.6228, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.42893388864952847, | |
| "grad_norm": 0.7878890213701146, | |
| "learning_rate": 7.063789046572916e-05, | |
| "loss": 0.6277, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.4365934223754129, | |
| "grad_norm": 0.7482466270487711, | |
| "learning_rate": 6.941195427366259e-05, | |
| "loss": 0.6037, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.44425295610129734, | |
| "grad_norm": 0.7787316245382442, | |
| "learning_rate": 6.817211833460483e-05, | |
| "loss": 0.5909, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.4519124898271818, | |
| "grad_norm": 0.7516225911350334, | |
| "learning_rate": 6.691927042140044e-05, | |
| "loss": 0.589, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.4595720235530662, | |
| "grad_norm": 0.7479278612486328, | |
| "learning_rate": 6.565430762399546e-05, | |
| "loss": 0.5768, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.46723155727895066, | |
| "grad_norm": 0.7618232755834888, | |
| "learning_rate": 6.437813570708463e-05, | |
| "loss": 0.5912, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.47489109100483506, | |
| "grad_norm": 0.7497540845592845, | |
| "learning_rate": 6.309166846154712e-05, | |
| "loss": 0.5965, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.4825506247307195, | |
| "grad_norm": 0.722941602138503, | |
| "learning_rate": 6.179582705013519e-05, | |
| "loss": 0.6111, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.49021015845660393, | |
| "grad_norm": 0.7215219222437452, | |
| "learning_rate": 6.049153934788429e-05, | |
| "loss": 0.5982, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.4978696921824884, | |
| "grad_norm": 0.7793222397845758, | |
| "learning_rate": 5.9179739277716786e-05, | |
| "loss": 0.603, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5055292259083728, | |
| "grad_norm": 0.7357130962658376, | |
| "learning_rate": 5.7861366141715424e-05, | |
| "loss": 0.6121, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5131887596342573, | |
| "grad_norm": 0.685946141955599, | |
| "learning_rate": 5.653736394854471e-05, | |
| "loss": 0.5825, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.5208482933601417, | |
| "grad_norm": 0.6741723935713323, | |
| "learning_rate": 5.5208680737502606e-05, | |
| "loss": 0.578, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.5285078270860262, | |
| "grad_norm": 0.9915254274904765, | |
| "learning_rate": 5.387626789968574e-05, | |
| "loss": 0.5876, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.5361673608119105, | |
| "grad_norm": 0.7543076820023589, | |
| "learning_rate": 5.2541079496754933e-05, | |
| "loss": 0.5862, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.543826894537795, | |
| "grad_norm": 0.6809288476151739, | |
| "learning_rate": 5.1204071577788204e-05, | |
| "loss": 0.5469, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.5514864282636794, | |
| "grad_norm": 0.6523050317216289, | |
| "learning_rate": 4.986620149471093e-05, | |
| "loss": 0.5787, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.5591459619895639, | |
| "grad_norm": 0.6658435336020647, | |
| "learning_rate": 4.8528427216792935e-05, | |
| "loss": 0.5802, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.5668054957154484, | |
| "grad_norm": 0.7734064939820273, | |
| "learning_rate": 4.7191706644703706e-05, | |
| "loss": 0.5758, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.5744650294413327, | |
| "grad_norm": 0.6696947342532882, | |
| "learning_rate": 4.585699692461655e-05, | |
| "loss": 0.5795, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.5821245631672172, | |
| "grad_norm": 0.737433128812512, | |
| "learning_rate": 4.4525253762853183e-05, | |
| "loss": 0.5653, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.5897840968931016, | |
| "grad_norm": 0.6464215655480927, | |
| "learning_rate": 4.319743074155916e-05, | |
| "loss": 0.5732, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.5974436306189861, | |
| "grad_norm": 0.7611630219437371, | |
| "learning_rate": 4.187447863590039e-05, | |
| "loss": 0.5637, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6051031643448705, | |
| "grad_norm": 0.7139956952893484, | |
| "learning_rate": 4.05573447332695e-05, | |
| "loss": 0.5585, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.6127626980707549, | |
| "grad_norm": 0.7671531182065541, | |
| "learning_rate": 3.924697215498971e-05, | |
| "loss": 0.5663, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6204222317966394, | |
| "grad_norm": 0.7250577559514667, | |
| "learning_rate": 3.794429918100154e-05, | |
| "loss": 0.5631, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.6280817655225238, | |
| "grad_norm": 0.834761848137774, | |
| "learning_rate": 3.665025857801647e-05, | |
| "loss": 0.5688, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.6357412992484083, | |
| "grad_norm": 0.6508555293537424, | |
| "learning_rate": 3.536577693161801e-05, | |
| "loss": 0.5364, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.6434008329742927, | |
| "grad_norm": 0.7426226012698264, | |
| "learning_rate": 3.4091773982788866e-05, | |
| "loss": 0.5324, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.6510603667001771, | |
| "grad_norm": 0.6624694254361643, | |
| "learning_rate": 3.282916196933904e-05, | |
| "loss": 0.5366, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.6587199004260615, | |
| "grad_norm": 0.6822377847021348, | |
| "learning_rate": 3.157884497270658e-05, | |
| "loss": 0.5499, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.666379434151946, | |
| "grad_norm": 0.6606367594029701, | |
| "learning_rate": 3.0341718270598557e-05, | |
| "loss": 0.5415, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.6740389678778305, | |
| "grad_norm": 0.7338327155163575, | |
| "learning_rate": 2.911866769593592e-05, | |
| "loss": 0.5145, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.6816985016037149, | |
| "grad_norm": 0.613013131465413, | |
| "learning_rate": 2.7910569002561138e-05, | |
| "loss": 0.5366, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.6893580353295993, | |
| "grad_norm": 0.6773171037933723, | |
| "learning_rate": 2.6718287238162963e-05, | |
| "loss": 0.5084, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6970175690554837, | |
| "grad_norm": 0.6488882426519923, | |
| "learning_rate": 2.5542676124867103e-05, | |
| "loss": 0.5285, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.7046771027813682, | |
| "grad_norm": 0.653813893870716, | |
| "learning_rate": 2.4384577447936648e-05, | |
| "loss": 0.5088, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.7123366365072527, | |
| "grad_norm": 0.7630538917031888, | |
| "learning_rate": 2.3244820453019566e-05, | |
| "loss": 0.5121, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.7199961702331371, | |
| "grad_norm": 0.7107152117402987, | |
| "learning_rate": 2.2124221252375216e-05, | |
| "loss": 0.531, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.7276557039590215, | |
| "grad_norm": 0.6849386017076563, | |
| "learning_rate": 2.1023582240504835e-05, | |
| "loss": 0.531, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.7353152376849059, | |
| "grad_norm": 0.681713817852427, | |
| "learning_rate": 1.9943691519604524e-05, | |
| "loss": 0.5381, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.7429747714107904, | |
| "grad_norm": 0.6560980468278351, | |
| "learning_rate": 1.8885322335252077e-05, | |
| "loss": 0.5235, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.7506343051366748, | |
| "grad_norm": 0.6387640075811016, | |
| "learning_rate": 1.7849232522731797e-05, | |
| "loss": 0.5228, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.7582938388625592, | |
| "grad_norm": 0.7059290436785569, | |
| "learning_rate": 1.6836163964393664e-05, | |
| "loss": 0.5441, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.7659533725884436, | |
| "grad_norm": 0.6845616969089988, | |
| "learning_rate": 1.5846842058435458e-05, | |
| "loss": 0.5099, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7736129063143281, | |
| "grad_norm": 0.6090491321707817, | |
| "learning_rate": 1.4881975199488245e-05, | |
| "loss": 0.5114, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.7812724400402126, | |
| "grad_norm": 0.6389049963156571, | |
| "learning_rate": 1.3942254271377003e-05, | |
| "loss": 0.5003, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.788931973766097, | |
| "grad_norm": 0.6801436703795579, | |
| "learning_rate": 1.3028352152419876e-05, | |
| "loss": 0.5277, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.7965915074919814, | |
| "grad_norm": 0.6313558029206057, | |
| "learning_rate": 1.21409232336199e-05, | |
| "loss": 0.5194, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.8042510412178658, | |
| "grad_norm": 0.6197855956436422, | |
| "learning_rate": 1.1280602950094531e-05, | |
| "loss": 0.5181, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.8119105749437503, | |
| "grad_norm": 0.6845783637358089, | |
| "learning_rate": 1.0448007326078335e-05, | |
| "loss": 0.5102, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.8195701086696348, | |
| "grad_norm": 0.6480827234715484, | |
| "learning_rate": 9.643732533824546e-06, | |
| "loss": 0.4972, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.8272296423955192, | |
| "grad_norm": 0.6681536341051292, | |
| "learning_rate": 8.868354466721668e-06, | |
| "loss": 0.5208, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.8348891761214036, | |
| "grad_norm": 0.6621991257490283, | |
| "learning_rate": 8.122428326930349e-06, | |
| "loss": 0.5045, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.842548709847288, | |
| "grad_norm": 0.7038914668740155, | |
| "learning_rate": 7.406488227836139e-06, | |
| "loss": 0.4977, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8502082435731725, | |
| "grad_norm": 0.6714452418325616, | |
| "learning_rate": 6.721046811602622e-06, | |
| "loss": 0.5197, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.8578677772990569, | |
| "grad_norm": 0.6728865127826114, | |
| "learning_rate": 6.0665948820988305e-06, | |
| "loss": 0.5012, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.8655273110249414, | |
| "grad_norm": 0.6755473629732173, | |
| "learning_rate": 5.443601053463743e-06, | |
| "loss": 0.4948, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.8731868447508258, | |
| "grad_norm": 0.6718977935317116, | |
| "learning_rate": 4.852511414559574e-06, | |
| "loss": 0.5016, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.8808463784767102, | |
| "grad_norm": 0.6998921635398603, | |
| "learning_rate": 4.293749209554005e-06, | |
| "loss": 0.4983, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.8885059122025947, | |
| "grad_norm": 0.6320217046654734, | |
| "learning_rate": 3.767714534860223e-06, | |
| "loss": 0.4992, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.8961654459284791, | |
| "grad_norm": 0.6455347742794505, | |
| "learning_rate": 3.2747840526516416e-06, | |
| "loss": 0.493, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.9038249796543636, | |
| "grad_norm": 0.5955409045440381, | |
| "learning_rate": 2.8153107211564887e-06, | |
| "loss": 0.4939, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.9114845133802479, | |
| "grad_norm": 0.6352733334971196, | |
| "learning_rate": 2.3896235419254065e-06, | |
| "loss": 0.4849, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.9191440471061324, | |
| "grad_norm": 0.6100416130741432, | |
| "learning_rate": 1.9980273242529823e-06, | |
| "loss": 0.5059, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.9268035808320169, | |
| "grad_norm": 0.6670229788776991, | |
| "learning_rate": 1.6408024669219258e-06, | |
| "loss": 0.489, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.9344631145579013, | |
| "grad_norm": 0.6414138552373387, | |
| "learning_rate": 1.3182047574261558e-06, | |
| "loss": 0.4971, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.9421226482837858, | |
| "grad_norm": 0.61454383407946, | |
| "learning_rate": 1.030465188816604e-06, | |
| "loss": 0.5034, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.9497821820096701, | |
| "grad_norm": 0.6480110228205495, | |
| "learning_rate": 7.777897943007595e-07, | |
| "loss": 0.5032, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.9574417157355546, | |
| "grad_norm": 0.6281167623669748, | |
| "learning_rate": 5.603594997145967e-07, | |
| "loss": 0.4898, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.965101249461439, | |
| "grad_norm": 0.6796483312027185, | |
| "learning_rate": 3.7832999397229843e-07, | |
| "loss": 0.5099, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.9727607831873235, | |
| "grad_norm": 0.6155337842087106, | |
| "learning_rate": 2.318316175866697e-07, | |
| "loss": 0.499, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.9804203169132079, | |
| "grad_norm": 0.5868743351197286, | |
| "learning_rate": 1.2096926934007102e-07, | |
| "loss": 0.5054, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.9880798506390923, | |
| "grad_norm": 0.7031955279741022, | |
| "learning_rate": 4.5822331172606926e-08, | |
| "loss": 0.4933, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.9957393843649768, | |
| "grad_norm": 0.5938630135036446, | |
| "learning_rate": 6.444611341432927e-09, | |
| "loss": 0.4883, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.999569151227919, | |
| "step": 1305, | |
| "total_flos": 184070382419968.0, | |
| "train_loss": 0.5936476859096367, | |
| "train_runtime": 39564.2825, | |
| "train_samples_per_second": 2.112, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1305, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 184070382419968.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |