Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use Nevamind-AI/0115_intents with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Nevamind-AI/0115_intents with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Nevamind-AI/0115_intents") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Nevamind-AI/0115_intents") model = AutoModelForCausalLM.from_pretrained("Nevamind-AI/0115_intents", 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 Nevamind-AI/0115_intents with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Nevamind-AI/0115_intents" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Nevamind-AI/0115_intents", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Nevamind-AI/0115_intents
- SGLang
How to use Nevamind-AI/0115_intents 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 "Nevamind-AI/0115_intents" \ --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": "Nevamind-AI/0115_intents", "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 "Nevamind-AI/0115_intents" \ --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": "Nevamind-AI/0115_intents", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Nevamind-AI/0115_intents with Docker Model Runner:
docker model run hf.co/Nevamind-AI/0115_intents
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1230, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04069175991861648, | |
| "grad_norm": 92.81427001953125, | |
| "learning_rate": 7.317073170731707e-07, | |
| "loss": 2.6701, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08138351983723296, | |
| "grad_norm": 79.43732452392578, | |
| "learning_rate": 1.5447154471544717e-06, | |
| "loss": 2.4541, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12207527975584945, | |
| "grad_norm": 43.05386734008789, | |
| "learning_rate": 2.3577235772357727e-06, | |
| "loss": 1.3936, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16276703967446593, | |
| "grad_norm": 16.605979919433594, | |
| "learning_rate": 3.1707317073170736e-06, | |
| "loss": 0.8148, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2034587995930824, | |
| "grad_norm": 22.727693557739258, | |
| "learning_rate": 3.983739837398374e-06, | |
| "loss": 0.6495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2441505595116989, | |
| "grad_norm": 30.917770385742188, | |
| "learning_rate": 4.796747967479675e-06, | |
| "loss": 0.7512, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28484231943031535, | |
| "grad_norm": 22.059432983398438, | |
| "learning_rate": 5.609756097560977e-06, | |
| "loss": 0.7512, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32553407934893186, | |
| "grad_norm": 17.015850067138672, | |
| "learning_rate": 6.422764227642278e-06, | |
| "loss": 0.589, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3662258392675483, | |
| "grad_norm": 20.26092529296875, | |
| "learning_rate": 7.2357723577235786e-06, | |
| "loss": 0.6861, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4069175991861648, | |
| "grad_norm": 15.508604049682617, | |
| "learning_rate": 8.048780487804879e-06, | |
| "loss": 0.614, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4476093591047813, | |
| "grad_norm": 19.158126831054688, | |
| "learning_rate": 8.86178861788618e-06, | |
| "loss": 0.6005, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4883011190233978, | |
| "grad_norm": 11.933234214782715, | |
| "learning_rate": 9.67479674796748e-06, | |
| "loss": 0.7188, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5289928789420142, | |
| "grad_norm": 16.164588928222656, | |
| "learning_rate": 9.999275169399614e-06, | |
| "loss": 0.6161, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5696846388606307, | |
| "grad_norm": 18.435869216918945, | |
| "learning_rate": 9.994846410084447e-06, | |
| "loss": 0.6543, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6103763987792472, | |
| "grad_norm": 12.114426612854004, | |
| "learning_rate": 9.986395137421607e-06, | |
| "loss": 0.6622, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6510681586978637, | |
| "grad_norm": 15.55136775970459, | |
| "learning_rate": 9.973928157497675e-06, | |
| "loss": 0.7225, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6917599186164801, | |
| "grad_norm": 16.748210906982422, | |
| "learning_rate": 9.957455510379753e-06, | |
| "loss": 0.6754, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7324516785350966, | |
| "grad_norm": 9.66128921508789, | |
| "learning_rate": 9.93699046202989e-06, | |
| "loss": 0.5801, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7731434384537131, | |
| "grad_norm": 19.142738342285156, | |
| "learning_rate": 9.912549493621555e-06, | |
| "loss": 0.6912, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8138351983723296, | |
| "grad_norm": 17.11036491394043, | |
| "learning_rate": 9.88415228826682e-06, | |
| "loss": 0.5697, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.854526958290946, | |
| "grad_norm": 22.85980224609375, | |
| "learning_rate": 9.851821715164891e-06, | |
| "loss": 0.5947, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8952187182095626, | |
| "grad_norm": 13.296561241149902, | |
| "learning_rate": 9.815583811184809e-06, | |
| "loss": 0.6648, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9359104781281791, | |
| "grad_norm": 12.144593238830566, | |
| "learning_rate": 9.775467759897092e-06, | |
| "loss": 0.6594, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9766022380467956, | |
| "grad_norm": 15.691839218139648, | |
| "learning_rate": 9.731505868071262e-06, | |
| "loss": 0.6727, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0162767039674465, | |
| "grad_norm": 14.279473304748535, | |
| "learning_rate": 9.68373353965814e-06, | |
| "loss": 0.4631, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.056968463886063, | |
| "grad_norm": 12.410947799682617, | |
| "learning_rate": 9.632189247277885e-06, | |
| "loss": 0.251, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0976602238046795, | |
| "grad_norm": 15.906357765197754, | |
| "learning_rate": 9.576914501236734e-06, | |
| "loss": 0.3202, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.138351983723296, | |
| "grad_norm": 12.009112358093262, | |
| "learning_rate": 9.517953816097396e-06, | |
| "loss": 0.2484, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1790437436419126, | |
| "grad_norm": 11.677927017211914, | |
| "learning_rate": 9.455354674830016e-06, | |
| "loss": 0.3739, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.219735503560529, | |
| "grad_norm": 14.100173950195312, | |
| "learning_rate": 9.38916749057258e-06, | |
| "loss": 0.3099, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2604272634791456, | |
| "grad_norm": 15.457694053649902, | |
| "learning_rate": 9.31944556603157e-06, | |
| "loss": 0.2975, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.3011190233977619, | |
| "grad_norm": 15.466636657714844, | |
| "learning_rate": 9.24624505055555e-06, | |
| "loss": 0.2417, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.3418107833163784, | |
| "grad_norm": 15.553060531616211, | |
| "learning_rate": 9.169624894916252e-06, | |
| "loss": 0.4207, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3825025432349949, | |
| "grad_norm": 12.042600631713867, | |
| "learning_rate": 9.089646803833589e-06, | |
| "loss": 0.3039, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.4231943031536114, | |
| "grad_norm": 13.659996032714844, | |
| "learning_rate": 9.006375186282832e-06, | |
| "loss": 0.3429, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.463886063072228, | |
| "grad_norm": 9.686576843261719, | |
| "learning_rate": 8.919877103623949e-06, | |
| "loss": 0.2936, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.5045778229908442, | |
| "grad_norm": 16.189590454101562, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.3392, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.545269582909461, | |
| "grad_norm": 10.429255485534668, | |
| "learning_rate": 8.737482724212331e-06, | |
| "loss": 0.3809, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.5859613428280772, | |
| "grad_norm": 10.174290657043457, | |
| "learning_rate": 8.641733315625014e-06, | |
| "loss": 0.3951, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.626653102746694, | |
| "grad_norm": 13.610822677612305, | |
| "learning_rate": 8.543051099966558e-06, | |
| "loss": 0.3753, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6673448626653102, | |
| "grad_norm": 11.966940879821777, | |
| "learning_rate": 8.441515549256134e-06, | |
| "loss": 0.3865, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.7080366225839267, | |
| "grad_norm": 13.420720100402832, | |
| "learning_rate": 8.337208433397051e-06, | |
| "loss": 0.3145, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.7487283825025433, | |
| "grad_norm": 12.261284828186035, | |
| "learning_rate": 8.230213754324773e-06, | |
| "loss": 0.3274, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.7894201424211598, | |
| "grad_norm": 23.362167358398438, | |
| "learning_rate": 8.120617678357415e-06, | |
| "loss": 0.3265, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.8301119023397763, | |
| "grad_norm": 16.948017120361328, | |
| "learning_rate": 8.00850846680318e-06, | |
| "loss": 0.3069, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8708036622583926, | |
| "grad_norm": 10.656729698181152, | |
| "learning_rate": 7.893976404880643e-06, | |
| "loss": 0.3134, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.9114954221770093, | |
| "grad_norm": 8.87990951538086, | |
| "learning_rate": 7.7771137290091e-06, | |
| "loss": 0.3279, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.9521871820956256, | |
| "grad_norm": 11.63674259185791, | |
| "learning_rate": 7.658014552527572e-06, | |
| "loss": 0.2968, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.992878942014242, | |
| "grad_norm": 13.58907699584961, | |
| "learning_rate": 7.536774789902246e-06, | |
| "loss": 0.3326, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.032553407934893, | |
| "grad_norm": 8.482688903808594, | |
| "learning_rate": 7.413492079483405e-06, | |
| "loss": 0.1491, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0732451678535098, | |
| "grad_norm": 13.235920906066895, | |
| "learning_rate": 7.288265704874089e-06, | |
| "loss": 0.0931, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.113936927772126, | |
| "grad_norm": 12.441973686218262, | |
| "learning_rate": 7.161196514973735e-06, | |
| "loss": 0.1267, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.154628687690743, | |
| "grad_norm": 7.682718753814697, | |
| "learning_rate": 7.032386842761282e-06, | |
| "loss": 0.1007, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.195320447609359, | |
| "grad_norm": 10.622251510620117, | |
| "learning_rate": 6.9019404228830465e-06, | |
| "loss": 0.1438, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.236012207527976, | |
| "grad_norm": 16.89317512512207, | |
| "learning_rate": 6.769962308111839e-06, | |
| "loss": 0.1238, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.276703967446592, | |
| "grad_norm": 17.99605941772461, | |
| "learning_rate": 6.636558784744507e-06, | |
| "loss": 0.0905, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.3173957273652084, | |
| "grad_norm": 7.3495988845825195, | |
| "learning_rate": 6.501837287006112e-06, | |
| "loss": 0.1337, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.358087487283825, | |
| "grad_norm": 19.655866622924805, | |
| "learning_rate": 6.365906310529631e-06, | |
| "loss": 0.1201, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.3987792472024414, | |
| "grad_norm": 10.437213897705078, | |
| "learning_rate": 6.228875324980862e-06, | |
| "loss": 0.1224, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.439471007121058, | |
| "grad_norm": 5.903636932373047, | |
| "learning_rate": 6.090854685898928e-06, | |
| "loss": 0.1338, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.4801627670396744, | |
| "grad_norm": 15.597542762756348, | |
| "learning_rate": 5.951955545823342e-06, | |
| "loss": 0.1131, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.520854526958291, | |
| "grad_norm": 14.72775650024414, | |
| "learning_rate": 5.812289764779232e-06, | |
| "loss": 0.0968, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.5615462868769074, | |
| "grad_norm": 15.866310119628906, | |
| "learning_rate": 5.671969820192794e-06, | |
| "loss": 0.111, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.6022380467955237, | |
| "grad_norm": 7.502605438232422, | |
| "learning_rate": 5.5311087163095475e-06, | |
| "loss": 0.0841, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.6429298067141405, | |
| "grad_norm": 18.2998104095459, | |
| "learning_rate": 5.389819893188304e-06, | |
| "loss": 0.1383, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.6836215666327567, | |
| "grad_norm": 15.197412490844727, | |
| "learning_rate": 5.248217135344191e-06, | |
| "loss": 0.0884, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.7243133265513735, | |
| "grad_norm": 17.366880416870117, | |
| "learning_rate": 5.106414480114238e-06, | |
| "loss": 0.1403, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.7650050864699898, | |
| "grad_norm": 9.119755744934082, | |
| "learning_rate": 4.96452612581939e-06, | |
| "loss": 0.0814, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.8056968463886065, | |
| "grad_norm": 12.41996955871582, | |
| "learning_rate": 4.82266633979685e-06, | |
| "loss": 0.1237, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.846388606307223, | |
| "grad_norm": 7.5573272705078125, | |
| "learning_rate": 4.680949366376858e-06, | |
| "loss": 0.1266, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.887080366225839, | |
| "grad_norm": 15.844888687133789, | |
| "learning_rate": 4.539489334877992e-06, | |
| "loss": 0.1148, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.927772126144456, | |
| "grad_norm": 14.323039054870605, | |
| "learning_rate": 4.3984001676950875e-06, | |
| "loss": 0.1393, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.968463886063072, | |
| "grad_norm": 10.77807331085205, | |
| "learning_rate": 4.2577954885537985e-06, | |
| "loss": 0.1149, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.0081383519837233, | |
| "grad_norm": 6.736983776092529, | |
| "learning_rate": 4.1177885310057045e-06, | |
| "loss": 0.0954, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.04883011190234, | |
| "grad_norm": 1.4531277418136597, | |
| "learning_rate": 3.978492047237608e-06, | |
| "loss": 0.0553, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.0895218718209563, | |
| "grad_norm": 3.5012948513031006, | |
| "learning_rate": 3.840018217268527e-06, | |
| "loss": 0.0372, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.1302136317395726, | |
| "grad_norm": 8.241860389709473, | |
| "learning_rate": 3.702478558607429e-06, | |
| "loss": 0.029, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.1709053916581893, | |
| "grad_norm": 11.57922077178955, | |
| "learning_rate": 3.5659838364445505e-06, | |
| "loss": 0.0457, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.2115971515768056, | |
| "grad_norm": 2.174631118774414, | |
| "learning_rate": 3.4306439744485453e-06, | |
| "loss": 0.0441, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.2522889114954223, | |
| "grad_norm": 18.824871063232422, | |
| "learning_rate": 3.2965679662413772e-06, | |
| "loss": 0.0353, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.2929806714140386, | |
| "grad_norm": 0.8748295307159424, | |
| "learning_rate": 3.163863787622162e-06, | |
| "loss": 0.0217, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.333672431332655, | |
| "grad_norm": 11.052030563354492, | |
| "learning_rate": 3.0326383096107424e-06, | |
| "loss": 0.0417, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.3743641912512716, | |
| "grad_norm": 7.482065200805664, | |
| "learning_rate": 2.9029972123809425e-06, | |
| "loss": 0.0385, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.415055951169888, | |
| "grad_norm": 3.1411232948303223, | |
| "learning_rate": 2.775044900152873e-06, | |
| "loss": 0.0462, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.4557477110885046, | |
| "grad_norm": 6.443966865539551, | |
| "learning_rate": 2.6488844171127903e-06, | |
| "loss": 0.0286, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.496439471007121, | |
| "grad_norm": 1.3803751468658447, | |
| "learning_rate": 2.52461736442824e-06, | |
| "loss": 0.0427, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.5371312309257377, | |
| "grad_norm": 2.6109228134155273, | |
| "learning_rate": 2.4023438184253115e-06, | |
| "loss": 0.0318, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.577822990844354, | |
| "grad_norm": 13.580485343933105, | |
| "learning_rate": 2.282162249993895e-06, | |
| "loss": 0.0298, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.6185147507629702, | |
| "grad_norm": 4.953476428985596, | |
| "learning_rate": 2.1641694452858486e-06, | |
| "loss": 0.0449, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.659206510681587, | |
| "grad_norm": 5.721762180328369, | |
| "learning_rate": 2.0484604277699437e-06, | |
| "loss": 0.024, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.6998982706002037, | |
| "grad_norm": 9.605400085449219, | |
| "learning_rate": 1.935128381706355e-06, | |
| "loss": 0.0313, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.74059003051882, | |
| "grad_norm": 10.484853744506836, | |
| "learning_rate": 1.8242645771023205e-06, | |
| "loss": 0.0418, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.7812817904374363, | |
| "grad_norm": 3.3977503776550293, | |
| "learning_rate": 1.7159582962094224e-06, | |
| "loss": 0.0303, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.821973550356053, | |
| "grad_norm": 5.522541046142578, | |
| "learning_rate": 1.610296761621662e-06, | |
| "loss": 0.0226, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.8626653102746693, | |
| "grad_norm": 3.5375092029571533, | |
| "learning_rate": 1.5073650660322509e-06, | |
| "loss": 0.0426, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.9033570701932856, | |
| "grad_norm": 3.804013252258301, | |
| "learning_rate": 1.4072461037056806e-06, | |
| "loss": 0.0355, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.9440488301119023, | |
| "grad_norm": 5.605400562286377, | |
| "learning_rate": 1.310020503720254e-06, | |
| "loss": 0.0458, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.984740590030519, | |
| "grad_norm": 7.182610034942627, | |
| "learning_rate": 1.2157665650348516e-06, | |
| "loss": 0.0435, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 4.02441505595117, | |
| "grad_norm": 3.481231451034546, | |
| "learning_rate": 1.1245601934322148e-06, | |
| "loss": 0.026, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.065106815869786, | |
| "grad_norm": 3.90126371383667, | |
| "learning_rate": 1.0364748403895368e-06, | |
| "loss": 0.0141, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.105798575788403, | |
| "grad_norm": 4.6030988693237305, | |
| "learning_rate": 9.51581443925576e-07, | |
| "loss": 0.0072, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 4.1464903357070195, | |
| "grad_norm": 3.77740740776062, | |
| "learning_rate": 8.699483714719547e-07, | |
| "loss": 0.0062, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.187182095625635, | |
| "grad_norm": 7.921717166900635, | |
| "learning_rate": 7.916413648146282e-07, | |
| "loss": 0.0082, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 4.227873855544252, | |
| "grad_norm": 1.4501222372055054, | |
| "learning_rate": 7.167234871498646e-07, | |
| "loss": 0.0073, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 4.268565615462869, | |
| "grad_norm": 0.24920102953910828, | |
| "learning_rate": 6.452550722973927e-07, | |
| "loss": 0.0074, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.309257375381486, | |
| "grad_norm": 0.32345661520957947, | |
| "learning_rate": 5.772936761116027e-07, | |
| "loss": 0.004, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 4.349949135300101, | |
| "grad_norm": 0.8181068301200867, | |
| "learning_rate": 5.128940301299334e-07, | |
| "loss": 0.0046, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 4.390640895218718, | |
| "grad_norm": 7.7283034324646, | |
| "learning_rate": 4.5210799749576815e-07, | |
| "loss": 0.0073, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 4.431332655137335, | |
| "grad_norm": 3.3843209743499756, | |
| "learning_rate": 3.9498453119134917e-07, | |
| "loss": 0.0099, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 4.472024415055952, | |
| "grad_norm": 2.583136558532715, | |
| "learning_rate": 3.4156963461434156e-07, | |
| "loss": 0.0082, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.5127161749745675, | |
| "grad_norm": 9.884654998779297, | |
| "learning_rate": 2.9190632452978706e-07, | |
| "loss": 0.0138, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 4.553407934893184, | |
| "grad_norm": 1.5282453298568726, | |
| "learning_rate": 2.4603459642729867e-07, | |
| "loss": 0.0025, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 4.594099694811801, | |
| "grad_norm": 0.5775611400604248, | |
| "learning_rate": 2.0399139231137731e-07, | |
| "loss": 0.0112, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 4.634791454730417, | |
| "grad_norm": 0.4762841761112213, | |
| "learning_rate": 1.6581057095081288e-07, | |
| "loss": 0.0078, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 4.6754832146490335, | |
| "grad_norm": 5.955403804779053, | |
| "learning_rate": 1.3152288061110518e-07, | |
| "loss": 0.0241, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.71617497456765, | |
| "grad_norm": 10.070328712463379, | |
| "learning_rate": 1.0115593429187942e-07, | |
| "loss": 0.0126, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 4.756866734486266, | |
| "grad_norm": 1.1140167713165283, | |
| "learning_rate": 7.473418748923545e-08, | |
| "loss": 0.0087, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 4.797558494404883, | |
| "grad_norm": 1.3013957738876343, | |
| "learning_rate": 5.227891850093314e-08, | |
| "loss": 0.0086, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 4.8382502543234995, | |
| "grad_norm": 0.7713027000427246, | |
| "learning_rate": 3.3808211290284886e-08, | |
| "loss": 0.0045, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 4.878942014242116, | |
| "grad_norm": 8.83694076538086, | |
| "learning_rate": 1.933694092254801e-08, | |
| "loss": 0.0153, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.919633774160732, | |
| "grad_norm": 2.105724811553955, | |
| "learning_rate": 8.87676158554507e-09, | |
| "loss": 0.0027, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 4.960325534079349, | |
| "grad_norm": 2.0107879638671875, | |
| "learning_rate": 2.436097204167043e-09, | |
| "loss": 0.0053, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.160478949546814, | |
| "learning_rate": 2.0134656311676658e-11, | |
| "loss": 0.0035, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1230, | |
| "total_flos": 4663176100577280.0, | |
| "train_loss": 0.2664417123225162, | |
| "train_runtime": 550.7151, | |
| "train_samples_per_second": 8.925, | |
| "train_steps_per_second": 2.233 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1230, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 4663176100577280.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |