Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use TabibitoQZP/Qwen3-4B-3Task with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TabibitoQZP/Qwen3-4B-3Task with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TabibitoQZP/Qwen3-4B-3Task") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("TabibitoQZP/Qwen3-4B-3Task") model = AutoModelForMultimodalLM.from_pretrained("TabibitoQZP/Qwen3-4B-3Task") 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 TabibitoQZP/Qwen3-4B-3Task with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TabibitoQZP/Qwen3-4B-3Task" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TabibitoQZP/Qwen3-4B-3Task", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/TabibitoQZP/Qwen3-4B-3Task
- SGLang
How to use TabibitoQZP/Qwen3-4B-3Task 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 "TabibitoQZP/Qwen3-4B-3Task" \ --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": "TabibitoQZP/Qwen3-4B-3Task", "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 "TabibitoQZP/Qwen3-4B-3Task" \ --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": "TabibitoQZP/Qwen3-4B-3Task", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use TabibitoQZP/Qwen3-4B-3Task with Docker Model Runner:
docker model run hf.co/TabibitoQZP/Qwen3-4B-3Task
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1590, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012592475995592633, | |
| "grad_norm": 38.37793731689453, | |
| "learning_rate": 5.660377358490567e-07, | |
| "loss": 1.2378, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025184951991185266, | |
| "grad_norm": 13.752121925354004, | |
| "learning_rate": 1.1949685534591195e-06, | |
| "loss": 0.9875, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0377774279867779, | |
| "grad_norm": 3.883774995803833, | |
| "learning_rate": 1.8238993710691824e-06, | |
| "loss": 0.6558, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05036990398237053, | |
| "grad_norm": 1.039472222328186, | |
| "learning_rate": 2.4528301886792453e-06, | |
| "loss": 0.5882, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06296237997796317, | |
| "grad_norm": 0.9505448937416077, | |
| "learning_rate": 3.0817610062893084e-06, | |
| "loss": 0.5781, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0755548559735558, | |
| "grad_norm": 0.8333441019058228, | |
| "learning_rate": 3.710691823899371e-06, | |
| "loss": 0.5495, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08814733196914844, | |
| "grad_norm": 1.262669324874878, | |
| "learning_rate": 4.339622641509435e-06, | |
| "loss": 0.5535, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.10073980796474107, | |
| "grad_norm": 0.8360942006111145, | |
| "learning_rate": 4.968553459119497e-06, | |
| "loss": 0.5396, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11333228396033371, | |
| "grad_norm": 0.7950102090835571, | |
| "learning_rate": 5.59748427672956e-06, | |
| "loss": 0.5413, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.12592475995592634, | |
| "grad_norm": 0.8145875334739685, | |
| "learning_rate": 6.226415094339623e-06, | |
| "loss": 0.5376, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13851723595151896, | |
| "grad_norm": 0.7814944386482239, | |
| "learning_rate": 6.855345911949685e-06, | |
| "loss": 0.5351, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1511097119471116, | |
| "grad_norm": 0.8993023037910461, | |
| "learning_rate": 7.484276729559748e-06, | |
| "loss": 0.5409, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.16370218794270425, | |
| "grad_norm": 0.866847574710846, | |
| "learning_rate": 8.113207547169812e-06, | |
| "loss": 0.5442, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.17629466393829687, | |
| "grad_norm": 0.7159755229949951, | |
| "learning_rate": 8.742138364779875e-06, | |
| "loss": 0.5365, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1888871399338895, | |
| "grad_norm": 0.7923691272735596, | |
| "learning_rate": 9.371069182389939e-06, | |
| "loss": 0.5382, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.20147961592948213, | |
| "grad_norm": 0.8047380447387695, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5414, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21407209192507476, | |
| "grad_norm": 0.8467481732368469, | |
| "learning_rate": 9.998795122086687e-06, | |
| "loss": 0.5331, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.22666456792066741, | |
| "grad_norm": 0.7700195908546448, | |
| "learning_rate": 9.995181069039055e-06, | |
| "loss": 0.5345, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.23925704391626004, | |
| "grad_norm": 1.2827311754226685, | |
| "learning_rate": 9.989159582654187e-06, | |
| "loss": 0.5302, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.25184951991185267, | |
| "grad_norm": 0.774922251701355, | |
| "learning_rate": 9.98073356499446e-06, | |
| "loss": 0.5337, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2644419959074453, | |
| "grad_norm": 0.7742050290107727, | |
| "learning_rate": 9.969907076988907e-06, | |
| "loss": 0.5229, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2770344719030379, | |
| "grad_norm": 0.7685420513153076, | |
| "learning_rate": 9.956685336476037e-06, | |
| "loss": 0.54, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2896269478986306, | |
| "grad_norm": 0.7166957259178162, | |
| "learning_rate": 9.941074715689097e-06, | |
| "loss": 0.5252, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3022194238942232, | |
| "grad_norm": 0.7183574438095093, | |
| "learning_rate": 9.923082738184969e-06, | |
| "loss": 0.5324, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.31481189988981584, | |
| "grad_norm": 0.7572329044342041, | |
| "learning_rate": 9.902718075218176e-06, | |
| "loss": 0.5213, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3274043758854085, | |
| "grad_norm": 0.7367239594459534, | |
| "learning_rate": 9.879990541561766e-06, | |
| "loss": 0.5221, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3399968518810011, | |
| "grad_norm": 0.7647990584373474, | |
| "learning_rate": 9.854911090777071e-06, | |
| "loss": 0.5116, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.35258932787659375, | |
| "grad_norm": 0.7244531512260437, | |
| "learning_rate": 9.827491809934621e-06, | |
| "loss": 0.5198, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.36518180387218635, | |
| "grad_norm": 0.7534804344177246, | |
| "learning_rate": 9.797745913788772e-06, | |
| "loss": 0.5243, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.377774279867779, | |
| "grad_norm": 0.7589166760444641, | |
| "learning_rate": 9.765687738408834e-06, | |
| "loss": 0.5154, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.39036675586337166, | |
| "grad_norm": 0.755774974822998, | |
| "learning_rate": 9.731332734269791e-06, | |
| "loss": 0.5368, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.40295923185896426, | |
| "grad_norm": 0.7197142243385315, | |
| "learning_rate": 9.69469745880592e-06, | |
| "loss": 0.5257, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.4155517078545569, | |
| "grad_norm": 0.6717684268951416, | |
| "learning_rate": 9.655799568430926e-06, | |
| "loss": 0.5179, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4281441838501495, | |
| "grad_norm": 0.7795198559761047, | |
| "learning_rate": 9.614657810028402e-06, | |
| "loss": 0.5205, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.4407366598457422, | |
| "grad_norm": 0.7759056091308594, | |
| "learning_rate": 9.571292011916753e-06, | |
| "loss": 0.5185, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.45332913584133483, | |
| "grad_norm": 0.7955228090286255, | |
| "learning_rate": 9.525723074292916e-06, | |
| "loss": 0.5193, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.46592161183692743, | |
| "grad_norm": 0.7349282503128052, | |
| "learning_rate": 9.47797295915948e-06, | |
| "loss": 0.5163, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.4785140878325201, | |
| "grad_norm": 0.6859073042869568, | |
| "learning_rate": 9.428064679740081e-06, | |
| "loss": 0.5108, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4911065638281127, | |
| "grad_norm": 0.7050626873970032, | |
| "learning_rate": 9.37602228938814e-06, | |
| "loss": 0.5241, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5036990398237053, | |
| "grad_norm": 0.7306986451148987, | |
| "learning_rate": 9.321870869994336e-06, | |
| "loss": 0.5132, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.516291515819298, | |
| "grad_norm": 0.7835687398910522, | |
| "learning_rate": 9.26563651989835e-06, | |
| "loss": 0.5015, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5288839918148907, | |
| "grad_norm": 0.716162383556366, | |
| "learning_rate": 9.207346341310744e-06, | |
| "loss": 0.5329, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5414764678104832, | |
| "grad_norm": 0.6837930083274841, | |
| "learning_rate": 9.14702842725101e-06, | |
| "loss": 0.5237, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.5540689438060759, | |
| "grad_norm": 0.680153489112854, | |
| "learning_rate": 9.084711848008122e-06, | |
| "loss": 0.5175, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5666614198016685, | |
| "grad_norm": 0.711155891418457, | |
| "learning_rate": 9.020426637130069e-06, | |
| "loss": 0.5048, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5792538957972612, | |
| "grad_norm": 0.7100813388824463, | |
| "learning_rate": 8.954203776949141e-06, | |
| "loss": 0.524, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5918463717928538, | |
| "grad_norm": 0.7131823897361755, | |
| "learning_rate": 8.886075183649976e-06, | |
| "loss": 0.5177, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.6044388477884464, | |
| "grad_norm": 0.6676498651504517, | |
| "learning_rate": 8.816073691887506e-06, | |
| "loss": 0.5089, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.617031323784039, | |
| "grad_norm": 0.6786186099052429, | |
| "learning_rate": 8.744233038962262e-06, | |
| "loss": 0.5006, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.6296237997796317, | |
| "grad_norm": 0.695183515548706, | |
| "learning_rate": 8.670587848560636e-06, | |
| "loss": 0.5069, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6422162757752243, | |
| "grad_norm": 0.6954060792922974, | |
| "learning_rate": 8.595173614067966e-06, | |
| "loss": 0.5083, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.654808751770817, | |
| "grad_norm": 0.7450917959213257, | |
| "learning_rate": 8.518026681462448e-06, | |
| "loss": 0.4996, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6674012277664095, | |
| "grad_norm": 0.7362504005432129, | |
| "learning_rate": 8.43918423179815e-06, | |
| "loss": 0.5071, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6799937037620022, | |
| "grad_norm": 0.7175170183181763, | |
| "learning_rate": 8.358684263285566e-06, | |
| "loss": 0.5038, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6925861797575948, | |
| "grad_norm": 0.7169266939163208, | |
| "learning_rate": 8.27656557297833e-06, | |
| "loss": 0.5136, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.7051786557531875, | |
| "grad_norm": 0.68199223279953, | |
| "learning_rate": 8.192867738074927e-06, | |
| "loss": 0.5087, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.7177711317487802, | |
| "grad_norm": 0.7578943967819214, | |
| "learning_rate": 8.107631096844431e-06, | |
| "loss": 0.5061, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.7303636077443727, | |
| "grad_norm": 0.6680927276611328, | |
| "learning_rate": 8.020896729185406e-06, | |
| "loss": 0.5022, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7429560837399654, | |
| "grad_norm": 0.7082540988922119, | |
| "learning_rate": 7.93270643682742e-06, | |
| "loss": 0.504, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.755548559735558, | |
| "grad_norm": 0.6694560050964355, | |
| "learning_rate": 7.843102723184647e-06, | |
| "loss": 0.5112, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7681410357311507, | |
| "grad_norm": 0.6237286925315857, | |
| "learning_rate": 7.752128772871292e-06, | |
| "loss": 0.5112, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.7807335117267433, | |
| "grad_norm": 0.7196964025497437, | |
| "learning_rate": 7.659828430888726e-06, | |
| "loss": 0.5058, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7933259877223359, | |
| "grad_norm": 0.7414775490760803, | |
| "learning_rate": 7.566246181494325e-06, | |
| "loss": 0.5028, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.8059184637179285, | |
| "grad_norm": 0.7570202350616455, | |
| "learning_rate": 7.4714271267622395e-06, | |
| "loss": 0.5064, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.8185109397135212, | |
| "grad_norm": 0.7066277861595154, | |
| "learning_rate": 7.3754169648463924e-06, | |
| "loss": 0.5032, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.8311034157091138, | |
| "grad_norm": 0.6958999037742615, | |
| "learning_rate": 7.278261967956203e-06, | |
| "loss": 0.5064, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8436958917047065, | |
| "grad_norm": 0.7002361416816711, | |
| "learning_rate": 7.18000896005564e-06, | |
| "loss": 0.5108, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.856288367700299, | |
| "grad_norm": 0.6879448294639587, | |
| "learning_rate": 7.080705294296355e-06, | |
| "loss": 0.498, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8688808436958917, | |
| "grad_norm": 0.6851900219917297, | |
| "learning_rate": 6.980398830195785e-06, | |
| "loss": 0.4974, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.8814733196914843, | |
| "grad_norm": 0.6358043551445007, | |
| "learning_rate": 6.879137910571191e-06, | |
| "loss": 0.4979, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.894065795687077, | |
| "grad_norm": 0.7097135782241821, | |
| "learning_rate": 6.77697133824079e-06, | |
| "loss": 0.5063, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.9066582716826697, | |
| "grad_norm": 0.646121621131897, | |
| "learning_rate": 6.673948352503172e-06, | |
| "loss": 0.5148, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.9192507476782622, | |
| "grad_norm": 0.661415159702301, | |
| "learning_rate": 6.5701186054063704e-06, | |
| "loss": 0.5078, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.9318432236738549, | |
| "grad_norm": 0.7175974249839783, | |
| "learning_rate": 6.4655321378179935e-06, | |
| "loss": 0.505, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.9444356996694475, | |
| "grad_norm": 0.7281399369239807, | |
| "learning_rate": 6.360239355307972e-06, | |
| "loss": 0.5016, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9570281756650402, | |
| "grad_norm": 0.6843705177307129, | |
| "learning_rate": 6.254291003855537e-06, | |
| "loss": 0.5086, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9696206516606328, | |
| "grad_norm": 0.6782203316688538, | |
| "learning_rate": 6.147738145392137e-06, | |
| "loss": 0.4998, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.9822131276562254, | |
| "grad_norm": 0.6951731443405151, | |
| "learning_rate": 6.040632133192074e-06, | |
| "loss": 0.4933, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.994805603651818, | |
| "grad_norm": 0.6784470081329346, | |
| "learning_rate": 5.933024587122745e-06, | |
| "loss": 0.5084, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.0062962379977962, | |
| "grad_norm": 0.7149181962013245, | |
| "learning_rate": 5.824967368766375e-06, | |
| "loss": 0.4699, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.0188887139933889, | |
| "grad_norm": 0.6838890910148621, | |
| "learning_rate": 5.716512556425271e-06, | |
| "loss": 0.4574, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.0314811899889815, | |
| "grad_norm": 0.6297887563705444, | |
| "learning_rate": 5.607712420022627e-06, | |
| "loss": 0.4637, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.0440736659845742, | |
| "grad_norm": 0.6451053619384766, | |
| "learning_rate": 5.4986193959109716e-06, | |
| "loss": 0.464, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.0566661419801668, | |
| "grad_norm": 0.6407359838485718, | |
| "learning_rate": 5.389286061600402e-06, | |
| "loss": 0.4587, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.0692586179757595, | |
| "grad_norm": 0.6714970469474792, | |
| "learning_rate": 5.2797651104187965e-06, | |
| "loss": 0.4615, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.0818510939713522, | |
| "grad_norm": 0.6700007319450378, | |
| "learning_rate": 5.1701093261162095e-06, | |
| "loss": 0.4544, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.0944435699669448, | |
| "grad_norm": 0.721367359161377, | |
| "learning_rate": 5.060371557425669e-06, | |
| "loss": 0.4578, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.1070360459625375, | |
| "grad_norm": 0.6329649090766907, | |
| "learning_rate": 4.9506046925926725e-06, | |
| "loss": 0.4601, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.1196285219581301, | |
| "grad_norm": 0.7482566833496094, | |
| "learning_rate": 4.840861633885642e-06, | |
| "loss": 0.4655, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.1322209979537226, | |
| "grad_norm": 0.6573087573051453, | |
| "learning_rate": 4.7311952720996106e-06, | |
| "loss": 0.4741, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.1448134739493152, | |
| "grad_norm": 0.6579948663711548, | |
| "learning_rate": 4.621658461065435e-06, | |
| "loss": 0.4639, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.1574059499449079, | |
| "grad_norm": 0.702316164970398, | |
| "learning_rate": 4.512303992176841e-06, | |
| "loss": 0.4664, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.1699984259405005, | |
| "grad_norm": 0.6987930536270142, | |
| "learning_rate": 4.4031845689475406e-06, | |
| "loss": 0.466, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.1825909019360932, | |
| "grad_norm": 0.7473271489143372, | |
| "learning_rate": 4.294352781610722e-06, | |
| "loss": 0.4526, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.1951833779316858, | |
| "grad_norm": 0.7382975816726685, | |
| "learning_rate": 4.185861081773115e-06, | |
| "loss": 0.4488, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.2077758539272785, | |
| "grad_norm": 0.7045325040817261, | |
| "learning_rate": 4.077761757135882e-06, | |
| "loss": 0.4572, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.2203683299228711, | |
| "grad_norm": 0.6717881560325623, | |
| "learning_rate": 3.970106906294509e-06, | |
| "loss": 0.4684, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.2329608059184638, | |
| "grad_norm": 0.6612910628318787, | |
| "learning_rate": 3.862948413629806e-06, | |
| "loss": 0.459, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.2455532819140562, | |
| "grad_norm": 0.6803273558616638, | |
| "learning_rate": 3.7563379243021924e-06, | |
| "loss": 0.4509, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.258145757909649, | |
| "grad_norm": 0.6448065638542175, | |
| "learning_rate": 3.6503268193612316e-06, | |
| "loss": 0.4625, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.2707382339052415, | |
| "grad_norm": 0.6815820932388306, | |
| "learning_rate": 3.5449661909824908e-06, | |
| "loss": 0.4638, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.2833307099008342, | |
| "grad_norm": 0.6469627022743225, | |
| "learning_rate": 3.440306817843592e-06, | |
| "loss": 0.4658, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.2959231858964269, | |
| "grad_norm": 0.6718019843101501, | |
| "learning_rate": 3.336399140651385e-06, | |
| "loss": 0.4536, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.3085156618920195, | |
| "grad_norm": 0.7337303161621094, | |
| "learning_rate": 3.2332932378319803e-06, | |
| "loss": 0.4489, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.3211081378876122, | |
| "grad_norm": 0.6914992332458496, | |
| "learning_rate": 3.1310388013953897e-06, | |
| "loss": 0.4627, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.3337006138832048, | |
| "grad_norm": 0.6538123488426208, | |
| "learning_rate": 3.029685112986417e-06, | |
| "loss": 0.4656, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.3462930898787975, | |
| "grad_norm": 0.6971728205680847, | |
| "learning_rate": 2.9292810201332995e-06, | |
| "loss": 0.4591, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.3588855658743901, | |
| "grad_norm": 0.7958908081054688, | |
| "learning_rate": 2.8298749127055914e-06, | |
| "loss": 0.4646, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.3714780418699828, | |
| "grad_norm": 0.6317901015281677, | |
| "learning_rate": 2.7315146995926085e-06, | |
| "loss": 0.452, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.3840705178655752, | |
| "grad_norm": 0.6657803654670715, | |
| "learning_rate": 2.6342477856136806e-06, | |
| "loss": 0.4587, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.3966629938611679, | |
| "grad_norm": 0.6851221323013306, | |
| "learning_rate": 2.53812104867135e-06, | |
| "loss": 0.4623, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.4092554698567605, | |
| "grad_norm": 0.6648300290107727, | |
| "learning_rate": 2.443180817158502e-06, | |
| "loss": 0.463, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.4218479458523532, | |
| "grad_norm": 0.6653546690940857, | |
| "learning_rate": 2.3494728476303547e-06, | |
| "loss": 0.4582, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.4344404218479458, | |
| "grad_norm": 0.6322280168533325, | |
| "learning_rate": 2.2570423027520175e-06, | |
| "loss": 0.4583, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.4470328978435385, | |
| "grad_norm": 0.6664165258407593, | |
| "learning_rate": 2.1659337295323117e-06, | |
| "loss": 0.4675, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.4596253738391312, | |
| "grad_norm": 0.6616364121437073, | |
| "learning_rate": 2.076191037854267e-06, | |
| "loss": 0.4573, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.4722178498347238, | |
| "grad_norm": 0.6122522950172424, | |
| "learning_rate": 1.987857479312721e-06, | |
| "loss": 0.4647, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.4848103258303165, | |
| "grad_norm": 0.7026521563529968, | |
| "learning_rate": 1.9009756263691475e-06, | |
| "loss": 0.4633, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.497402801825909, | |
| "grad_norm": 0.7002488374710083, | |
| "learning_rate": 1.815587351833818e-06, | |
| "loss": 0.4591, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.5099952778215018, | |
| "grad_norm": 0.6730997562408447, | |
| "learning_rate": 1.7317338086851526e-06, | |
| "loss": 0.459, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.5225877538170942, | |
| "grad_norm": 0.6867558360099792, | |
| "learning_rate": 1.649455410235985e-06, | |
| "loss": 0.4538, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.5351802298126869, | |
| "grad_norm": 0.646712064743042, | |
| "learning_rate": 1.5687918106563326e-06, | |
| "loss": 0.4592, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.5477727058082795, | |
| "grad_norm": 0.7295082807540894, | |
| "learning_rate": 1.4897818858620095e-06, | |
| "loss": 0.4549, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.5603651818038722, | |
| "grad_norm": 0.6636416912078857, | |
| "learning_rate": 1.4124637147783431e-06, | |
| "loss": 0.4516, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.5729576577994648, | |
| "grad_norm": 0.7151824831962585, | |
| "learning_rate": 1.3368745609879908e-06, | |
| "loss": 0.4601, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.5855501337950575, | |
| "grad_norm": 0.626083493232727, | |
| "learning_rate": 1.263050854771705e-06, | |
| "loss": 0.4545, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.5981426097906501, | |
| "grad_norm": 0.638517439365387, | |
| "learning_rate": 1.191028175550727e-06, | |
| "loss": 0.4455, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.6107350857862426, | |
| "grad_norm": 0.6936119198799133, | |
| "learning_rate": 1.1208412347392338e-06, | |
| "loss": 0.4445, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.6233275617818355, | |
| "grad_norm": 0.6687029004096985, | |
| "learning_rate": 1.0525238590151442e-06, | |
| "loss": 0.4496, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.635920037777428, | |
| "grad_norm": 0.6389179229736328, | |
| "learning_rate": 9.86108974017298e-07, | |
| "loss": 0.4546, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.6485125137730208, | |
| "grad_norm": 0.615524172782898, | |
| "learning_rate": 9.216285884769172e-07, | |
| "loss": 0.4583, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.6611049897686132, | |
| "grad_norm": 0.6831961274147034, | |
| "learning_rate": 8.591137787909503e-07, | |
| "loss": 0.4555, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.6736974657642059, | |
| "grad_norm": 0.6675463914871216, | |
| "learning_rate": 7.985946740447792e-07, | |
| "loss": 0.4497, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.6862899417597985, | |
| "grad_norm": 0.6614457368850708, | |
| "learning_rate": 7.401004414914586e-07, | |
| "loss": 0.463, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.6988824177553912, | |
| "grad_norm": 0.6566441059112549, | |
| "learning_rate": 6.836592724945323e-07, | |
| "loss": 0.4561, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.7114748937509838, | |
| "grad_norm": 0.6838300228118896, | |
| "learning_rate": 6.292983689411725e-07, | |
| "loss": 0.4624, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.7240673697465763, | |
| "grad_norm": 0.7261980772018433, | |
| "learning_rate": 5.770439301321929e-07, | |
| "loss": 0.4467, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.7366598457421691, | |
| "grad_norm": 0.6649404168128967, | |
| "learning_rate": 5.269211401552721e-07, | |
| "loss": 0.451, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.7492523217377616, | |
| "grad_norm": 0.6621150374412537, | |
| "learning_rate": 4.78954155747448e-07, | |
| "loss": 0.4639, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.7618447977333545, | |
| "grad_norm": 0.71415114402771, | |
| "learning_rate": 4.3316609465275437e-07, | |
| "loss": 0.4518, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.7744372737289469, | |
| "grad_norm": 0.6590133309364319, | |
| "learning_rate": 3.895790244805936e-07, | |
| "loss": 0.4603, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.7870297497245395, | |
| "grad_norm": 0.673554003238678, | |
| "learning_rate": 3.4821395207022767e-07, | |
| "loss": 0.4512, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.7996222257201322, | |
| "grad_norm": 0.6459655165672302, | |
| "learning_rate": 3.0909081336650883e-07, | |
| "loss": 0.4597, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.8122147017157249, | |
| "grad_norm": 0.5669092535972595, | |
| "learning_rate": 2.7222846381172616e-07, | |
| "loss": 0.467, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.8248071777113175, | |
| "grad_norm": 0.6353556513786316, | |
| "learning_rate": 2.3764466925820518e-07, | |
| "loss": 0.4617, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.8373996537069102, | |
| "grad_norm": 0.780803382396698, | |
| "learning_rate": 2.0535609740603092e-07, | |
| "loss": 0.4586, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.8499921297025028, | |
| "grad_norm": 0.6868489980697632, | |
| "learning_rate": 1.7537830977003456e-07, | |
| "loss": 0.4504, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.8625846056980953, | |
| "grad_norm": 0.7090204358100891, | |
| "learning_rate": 1.477257541799032e-07, | |
| "loss": 0.4534, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.8751770816936881, | |
| "grad_norm": 0.6413393616676331, | |
| "learning_rate": 1.2241175781702587e-07, | |
| "loss": 0.4553, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.8877695576892806, | |
| "grad_norm": 0.6809853911399841, | |
| "learning_rate": 9.944852079144862e-08, | |
| "loss": 0.4572, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.9003620336848734, | |
| "grad_norm": 0.6310750842094421, | |
| "learning_rate": 7.884711026201586e-08, | |
| "loss": 0.4589, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.9129545096804659, | |
| "grad_norm": 0.6572443842887878, | |
| "learning_rate": 6.061745510254069e-08, | |
| "loss": 0.4547, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.9255469856760585, | |
| "grad_norm": 0.6803452372550964, | |
| "learning_rate": 4.476834111656891e-08, | |
| "loss": 0.4533, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.9381394616716512, | |
| "grad_norm": 0.7150864005088806, | |
| "learning_rate": 3.130740680305666e-08, | |
| "loss": 0.4503, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.9507319376672438, | |
| "grad_norm": 0.6401649117469788, | |
| "learning_rate": 2.0241139674982424e-08, | |
| "loss": 0.4447, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.9633244136628365, | |
| "grad_norm": 0.635547935962677, | |
| "learning_rate": 1.1574873132684239e-08, | |
| "loss": 0.4649, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.975916889658429, | |
| "grad_norm": 0.6223708391189575, | |
| "learning_rate": 5.31278389342138e-09, | |
| "loss": 0.4572, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.9885093656540218, | |
| "grad_norm": 0.6320503950119019, | |
| "learning_rate": 1.4578899784001288e-09, | |
| "loss": 0.4551, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.6981777548789978, | |
| "learning_rate": 1.2049258235058425e-11, | |
| "loss": 0.4489, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 1590, | |
| "total_flos": 207829311291392.0, | |
| "train_loss": 0.4968748902374843, | |
| "train_runtime": 50004.2557, | |
| "train_samples_per_second": 1.016, | |
| "train_steps_per_second": 0.032 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 207829311291392.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |