Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use modrill/think_8b_full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use modrill/think_8b_full with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="modrill/think_8b_full") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("modrill/think_8b_full") model = AutoModelForCausalLM.from_pretrained("modrill/think_8b_full") 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 modrill/think_8b_full with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "modrill/think_8b_full" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modrill/think_8b_full", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/modrill/think_8b_full
- SGLang
How to use modrill/think_8b_full 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 "modrill/think_8b_full" \ --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": "modrill/think_8b_full", "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 "modrill/think_8b_full" \ --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": "modrill/think_8b_full", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use modrill/think_8b_full with Docker Model Runner:
docker model run hf.co/modrill/think_8b_full
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 2050, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00976145445671405, | |
| "grad_norm": 2.7171718937708893, | |
| "learning_rate": 2.903225806451613e-06, | |
| "loss": 0.836665153503418, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0195229089134281, | |
| "grad_norm": 2.07278967505522, | |
| "learning_rate": 6.129032258064517e-06, | |
| "loss": 0.7774394035339356, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02928436337014215, | |
| "grad_norm": 0.8052418041946412, | |
| "learning_rate": 9.35483870967742e-06, | |
| "loss": 0.7118394851684571, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0390458178268562, | |
| "grad_norm": 0.48425847572228153, | |
| "learning_rate": 1.2580645161290324e-05, | |
| "loss": 0.6741247177124023, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04880727228357025, | |
| "grad_norm": 0.46915653943519686, | |
| "learning_rate": 1.5806451612903226e-05, | |
| "loss": 0.6543425559997559, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0585687267402843, | |
| "grad_norm": 0.4655546322355271, | |
| "learning_rate": 1.903225806451613e-05, | |
| "loss": 0.6383125305175781, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06833018119699835, | |
| "grad_norm": 0.5385119940038303, | |
| "learning_rate": 1.9999388172996495e-05, | |
| "loss": 0.631153678894043, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0780916356537124, | |
| "grad_norm": 0.48632725158098256, | |
| "learning_rate": 1.9996391649532744e-05, | |
| "loss": 0.620881175994873, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08785309011042645, | |
| "grad_norm": 0.5147422480903651, | |
| "learning_rate": 1.999089880058469e-05, | |
| "loss": 0.6154061794281006, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0976145445671405, | |
| "grad_norm": 0.4859310369557681, | |
| "learning_rate": 1.9982910997841175e-05, | |
| "loss": 0.608434009552002, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10737599902385456, | |
| "grad_norm": 0.49855799612783797, | |
| "learning_rate": 1.9972430236037522e-05, | |
| "loss": 0.6053113460540771, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1171374534805686, | |
| "grad_norm": 0.4389090045007552, | |
| "learning_rate": 1.9959459132457415e-05, | |
| "loss": 0.6017628192901612, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12689890793728265, | |
| "grad_norm": 0.656672526601482, | |
| "learning_rate": 1.9944000926279304e-05, | |
| "loss": 0.5999305725097657, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1366603623939967, | |
| "grad_norm": 0.4397790605918159, | |
| "learning_rate": 1.992605947776752e-05, | |
| "loss": 0.5955329895019531, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14642181685071076, | |
| "grad_norm": 0.4826398780157024, | |
| "learning_rate": 1.9905639267308244e-05, | |
| "loss": 0.5946754932403564, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1561832713074248, | |
| "grad_norm": 0.445880792065111, | |
| "learning_rate": 1.9882745394290705e-05, | |
| "loss": 0.5919600009918213, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16594472576413885, | |
| "grad_norm": 0.4224995436975534, | |
| "learning_rate": 1.9857383575833693e-05, | |
| "loss": 0.591130542755127, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1757061802208529, | |
| "grad_norm": 0.489317471321096, | |
| "learning_rate": 1.9829560145357906e-05, | |
| "loss": 0.5881345748901368, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18546763467756697, | |
| "grad_norm": 0.391013199589406, | |
| "learning_rate": 1.979928205100434e-05, | |
| "loss": 0.5874452114105224, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.195229089134281, | |
| "grad_norm": 0.5132703421819202, | |
| "learning_rate": 1.9766556853899153e-05, | |
| "loss": 0.5850434303283691, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20499054359099506, | |
| "grad_norm": 0.4317384739639613, | |
| "learning_rate": 1.9731392726265538e-05, | |
| "loss": 0.5791005611419677, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.21475199804770911, | |
| "grad_norm": 0.5450508704505641, | |
| "learning_rate": 1.9693798449382873e-05, | |
| "loss": 0.5837528228759765, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.22451345250442317, | |
| "grad_norm": 0.3995851796223643, | |
| "learning_rate": 1.9653783411393875e-05, | |
| "loss": 0.5809955596923828, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2342749069611372, | |
| "grad_norm": 0.515662880685764, | |
| "learning_rate": 1.9611357604960156e-05, | |
| "loss": 0.5800333499908448, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.24403636141785126, | |
| "grad_norm": 0.5467899695375602, | |
| "learning_rate": 1.956653162476683e-05, | |
| "loss": 0.5769859313964844, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2537978158745653, | |
| "grad_norm": 0.5737871165214032, | |
| "learning_rate": 1.9519316664876782e-05, | |
| "loss": 0.5788938999176025, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.26355927033127935, | |
| "grad_norm": 0.4010513125091312, | |
| "learning_rate": 1.9469724515935242e-05, | |
| "loss": 0.5743288993835449, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.2733207247879934, | |
| "grad_norm": 0.4230903232640434, | |
| "learning_rate": 1.9417767562225422e-05, | |
| "loss": 0.574954605102539, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.28308217924470747, | |
| "grad_norm": 0.3663575439721741, | |
| "learning_rate": 1.9363458778575857e-05, | |
| "loss": 0.5711943149566651, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2928436337014215, | |
| "grad_norm": 0.3917259340992501, | |
| "learning_rate": 1.9306811727120305e-05, | |
| "loss": 0.5710340976715088, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3026050881581356, | |
| "grad_norm": 0.3906911977658059, | |
| "learning_rate": 1.9247840553910974e-05, | |
| "loss": 0.5703779220581054, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3123665426148496, | |
| "grad_norm": 0.3869882324226975, | |
| "learning_rate": 1.918655998538593e-05, | |
| "loss": 0.5712218761444092, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.32212799707156364, | |
| "grad_norm": 0.42061349121115077, | |
| "learning_rate": 1.9122985324691576e-05, | |
| "loss": 0.5702820777893066, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.3318894515282777, | |
| "grad_norm": 0.3490137440957352, | |
| "learning_rate": 1.9057132447861104e-05, | |
| "loss": 0.5708161354064941, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.34165090598499176, | |
| "grad_norm": 0.3818865656026688, | |
| "learning_rate": 1.8989017799849896e-05, | |
| "loss": 0.5661185264587403, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3514123604417058, | |
| "grad_norm": 0.4120345721034505, | |
| "learning_rate": 1.891865839042884e-05, | |
| "loss": 0.567262077331543, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3611738148984199, | |
| "grad_norm": 0.43217811509239235, | |
| "learning_rate": 1.8846071789936614e-05, | |
| "loss": 0.5655131340026855, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.37093526935513393, | |
| "grad_norm": 0.4701369380275007, | |
| "learning_rate": 1.8771276124891957e-05, | |
| "loss": 0.5688438892364502, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.380696723811848, | |
| "grad_norm": 0.46742334095939286, | |
| "learning_rate": 1.8694290073467095e-05, | |
| "loss": 0.5635671138763427, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.390458178268562, | |
| "grad_norm": 0.3883819468179728, | |
| "learning_rate": 1.861513286082334e-05, | |
| "loss": 0.565738296508789, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.40021963272527605, | |
| "grad_norm": 0.3827208108942853, | |
| "learning_rate": 1.853382425431017e-05, | |
| "loss": 0.559232521057129, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.4099810871819901, | |
| "grad_norm": 0.4254061229161546, | |
| "learning_rate": 1.8450384558528848e-05, | |
| "loss": 0.5624125003814697, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.41974254163870417, | |
| "grad_norm": 0.35465965142588046, | |
| "learning_rate": 1.8364834610261916e-05, | |
| "loss": 0.5655581474304199, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.42950399609541823, | |
| "grad_norm": 0.4281031584614048, | |
| "learning_rate": 1.8277195773269766e-05, | |
| "loss": 0.5620370388031006, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4392654505521323, | |
| "grad_norm": 0.4804782555657488, | |
| "learning_rate": 1.818748993295564e-05, | |
| "loss": 0.5620602607727051, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.44902690500884634, | |
| "grad_norm": 0.38870985648173306, | |
| "learning_rate": 1.8095739490900344e-05, | |
| "loss": 0.5619917392730713, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.45878835946556035, | |
| "grad_norm": 0.3609209290714297, | |
| "learning_rate": 1.8001967359268057e-05, | |
| "loss": 0.5599178314208985, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.4685498139222744, | |
| "grad_norm": 0.4060075614643235, | |
| "learning_rate": 1.7906196955084655e-05, | |
| "loss": 0.5566294193267822, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.47831126837898846, | |
| "grad_norm": 0.354932964564927, | |
| "learning_rate": 1.780845219438994e-05, | |
| "loss": 0.5581831932067871, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.4880727228357025, | |
| "grad_norm": 0.45534621360021393, | |
| "learning_rate": 1.7708757486265272e-05, | |
| "loss": 0.5574597358703614, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4978341772924166, | |
| "grad_norm": 0.40068634910147427, | |
| "learning_rate": 1.7607137726738074e-05, | |
| "loss": 0.5564365863800049, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5075956317491306, | |
| "grad_norm": 0.34894544504616437, | |
| "learning_rate": 1.7503618292564698e-05, | |
| "loss": 0.5602200984954834, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5173570862058446, | |
| "grad_norm": 0.37009751996998264, | |
| "learning_rate": 1.7398225034893316e-05, | |
| "loss": 0.5574421882629395, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5271185406625587, | |
| "grad_norm": 0.4134599279143897, | |
| "learning_rate": 1.7290984272808276e-05, | |
| "loss": 0.5567829132080078, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5368799951192728, | |
| "grad_norm": 0.332174943430511, | |
| "learning_rate": 1.718192278675763e-05, | |
| "loss": 0.5541606426239014, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5466414495759868, | |
| "grad_norm": 0.33602414898403216, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 0.5544651985168457, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.5564029040327009, | |
| "grad_norm": 0.33647281770469845, | |
| "learning_rate": 1.695844703113069e-05, | |
| "loss": 0.5550961971282959, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5661643584894149, | |
| "grad_norm": 0.3715339963292226, | |
| "learning_rate": 1.6844088568513885e-05, | |
| "loss": 0.5519819259643555, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.575925812946129, | |
| "grad_norm": 0.40192776010408143, | |
| "learning_rate": 1.6728020981914207e-05, | |
| "loss": 0.5516290664672852, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.585687267402843, | |
| "grad_norm": 0.43597621131226744, | |
| "learning_rate": 1.661027325603779e-05, | |
| "loss": 0.5543393611907959, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5954487218595571, | |
| "grad_norm": 0.3551114083289793, | |
| "learning_rate": 1.6490874795159613e-05, | |
| "loss": 0.5514196395874024, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6052101763162712, | |
| "grad_norm": 0.33284570590742457, | |
| "learning_rate": 1.6369855415780577e-05, | |
| "loss": 0.5529036045074462, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6149716307729852, | |
| "grad_norm": 0.34597390793742416, | |
| "learning_rate": 1.624724533918166e-05, | |
| "loss": 0.5506466388702392, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6247330852296992, | |
| "grad_norm": 0.41047533039337214, | |
| "learning_rate": 1.612307518387699e-05, | |
| "loss": 0.5541812896728515, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6344945396864132, | |
| "grad_norm": 0.42638581477939697, | |
| "learning_rate": 1.5997375957967672e-05, | |
| "loss": 0.5505136966705322, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6442559941431273, | |
| "grad_norm": 0.3472164806411414, | |
| "learning_rate": 1.5870179051398405e-05, | |
| "loss": 0.5473326683044434, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.6540174485998413, | |
| "grad_norm": 0.4198356949808895, | |
| "learning_rate": 1.5741516228118677e-05, | |
| "loss": 0.5478506088256836, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.6637789030565554, | |
| "grad_norm": 0.4438126537908133, | |
| "learning_rate": 1.561141961815058e-05, | |
| "loss": 0.5543909072875977, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6735403575132695, | |
| "grad_norm": 0.33771998620183863, | |
| "learning_rate": 1.5479921709565244e-05, | |
| "loss": 0.5508096218109131, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.6833018119699835, | |
| "grad_norm": 0.340535151725663, | |
| "learning_rate": 1.5347055340369806e-05, | |
| "loss": 0.5471370220184326, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6930632664266976, | |
| "grad_norm": 0.4340557843782887, | |
| "learning_rate": 1.521285369030702e-05, | |
| "loss": 0.5477546691894531, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7028247208834116, | |
| "grad_norm": 0.36480023918471327, | |
| "learning_rate": 1.5077350272569531e-05, | |
| "loss": 0.5477032661437988, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.7125861753401257, | |
| "grad_norm": 0.3173237839308878, | |
| "learning_rate": 1.4940578925430866e-05, | |
| "loss": 0.547743844985962, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.7223476297968398, | |
| "grad_norm": 0.3798598286861374, | |
| "learning_rate": 1.480257380379525e-05, | |
| "loss": 0.544849967956543, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.7321090842535538, | |
| "grad_norm": 0.32520027859246653, | |
| "learning_rate": 1.4663369370668348e-05, | |
| "loss": 0.5443988800048828, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7418705387102679, | |
| "grad_norm": 0.42154822049578927, | |
| "learning_rate": 1.4523000388551089e-05, | |
| "loss": 0.5458567619323731, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.7516319931669819, | |
| "grad_norm": 0.35290152971174465, | |
| "learning_rate": 1.4381501910758662e-05, | |
| "loss": 0.5455081939697266, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.761393447623696, | |
| "grad_norm": 0.36092224743501783, | |
| "learning_rate": 1.4238909272666919e-05, | |
| "loss": 0.5444242477416992, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.7711549020804099, | |
| "grad_norm": 0.33599605389036247, | |
| "learning_rate": 1.409525808288833e-05, | |
| "loss": 0.5462691307067871, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.780916356537124, | |
| "grad_norm": 0.28914267872490046, | |
| "learning_rate": 1.3950584214379703e-05, | |
| "loss": 0.5470402717590332, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.790677810993838, | |
| "grad_norm": 0.31535694158721245, | |
| "learning_rate": 1.38049237954839e-05, | |
| "loss": 0.5445716381072998, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.8004392654505521, | |
| "grad_norm": 0.3928771588299645, | |
| "learning_rate": 1.365831320090776e-05, | |
| "loss": 0.5462616920471192, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.8102007199072662, | |
| "grad_norm": 0.3047321449256657, | |
| "learning_rate": 1.3510789042638525e-05, | |
| "loss": 0.5432579040527343, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.8199621743639802, | |
| "grad_norm": 0.3068462237254663, | |
| "learning_rate": 1.3362388160800992e-05, | |
| "loss": 0.5435873985290527, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.8297236288206943, | |
| "grad_norm": 0.34358206165151545, | |
| "learning_rate": 1.321314761445768e-05, | |
| "loss": 0.5405595302581787, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8394850832774083, | |
| "grad_norm": 0.42312860515314266, | |
| "learning_rate": 1.3063104672354384e-05, | |
| "loss": 0.5467127799987793, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.8492465377341224, | |
| "grad_norm": 0.3673885167838325, | |
| "learning_rate": 1.2912296803613275e-05, | |
| "loss": 0.5438889026641845, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.8590079921908365, | |
| "grad_norm": 0.36921788638943953, | |
| "learning_rate": 1.2760761668376063e-05, | |
| "loss": 0.5435795783996582, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.8687694466475505, | |
| "grad_norm": 0.32043541605358555, | |
| "learning_rate": 1.2608537108399354e-05, | |
| "loss": 0.5429807662963867, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.8785309011042646, | |
| "grad_norm": 0.5009575102224276, | |
| "learning_rate": 1.245566113760475e-05, | |
| "loss": 0.5389288902282715, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8882923555609786, | |
| "grad_norm": 0.2979746358811125, | |
| "learning_rate": 1.2302171932585885e-05, | |
| "loss": 0.5378171920776367, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.8980538100176927, | |
| "grad_norm": 0.28399182752163593, | |
| "learning_rate": 1.2148107823074873e-05, | |
| "loss": 0.5402212142944336, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.9078152644744066, | |
| "grad_norm": 0.3370739446485531, | |
| "learning_rate": 1.1993507282370514e-05, | |
| "loss": 0.5409811019897461, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.9175767189311207, | |
| "grad_norm": 0.3550432507180414, | |
| "learning_rate": 1.183840891773062e-05, | |
| "loss": 0.539578914642334, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.9273381733878348, | |
| "grad_norm": 0.34671610827130145, | |
| "learning_rate": 1.168285146073092e-05, | |
| "loss": 0.5414035797119141, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.9370996278445488, | |
| "grad_norm": 0.37188884026877206, | |
| "learning_rate": 1.1526873757592918e-05, | |
| "loss": 0.5388407230377197, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.9468610823012629, | |
| "grad_norm": 0.3200151532383385, | |
| "learning_rate": 1.1370514759483082e-05, | |
| "loss": 0.5389005184173584, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.9566225367579769, | |
| "grad_norm": 0.32261766442972056, | |
| "learning_rate": 1.1213813512785897e-05, | |
| "loss": 0.5396491050720215, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.966383991214691, | |
| "grad_norm": 0.34539226916656524, | |
| "learning_rate": 1.1056809149353054e-05, | |
| "loss": 0.5376710891723633, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.976145445671405, | |
| "grad_norm": 0.2641656693803474, | |
| "learning_rate": 1.0899540876731366e-05, | |
| "loss": 0.5359292984008789, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9859069001281191, | |
| "grad_norm": 0.3181162211492277, | |
| "learning_rate": 1.074204796837176e-05, | |
| "loss": 0.539863920211792, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.9956683545848332, | |
| "grad_norm": 0.3150477781887309, | |
| "learning_rate": 1.0584369753821781e-05, | |
| "loss": 0.53628511428833, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.004880727228357, | |
| "grad_norm": 0.29779537591859595, | |
| "learning_rate": 1.0426545608904141e-05, | |
| "loss": 0.5282849788665771, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.014642181685071, | |
| "grad_norm": 0.2966743319834602, | |
| "learning_rate": 1.0268614945883664e-05, | |
| "loss": 0.5184188842773437, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.0244036361417852, | |
| "grad_norm": 0.3260541525878062, | |
| "learning_rate": 1.011061720362516e-05, | |
| "loss": 0.5220568656921387, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.0341650905984991, | |
| "grad_norm": 0.31299117990102804, | |
| "learning_rate": 9.952591837744642e-06, | |
| "loss": 0.5197721004486084, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.0439265450552133, | |
| "grad_norm": 0.34448199483903647, | |
| "learning_rate": 9.794578310756374e-06, | |
| "loss": 0.5208293914794921, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.0536879995119273, | |
| "grad_norm": 0.2638359119791302, | |
| "learning_rate": 9.63661608221817e-06, | |
| "loss": 0.5157252788543701, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.0634494539686412, | |
| "grad_norm": 0.2903025405775747, | |
| "learning_rate": 9.478744598877469e-06, | |
| "loss": 0.5209471702575683, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.0732109084253554, | |
| "grad_norm": 0.2932303464794665, | |
| "learning_rate": 9.321003284820576e-06, | |
| "loss": 0.5197690963745117, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0829723628820693, | |
| "grad_norm": 0.2662280101895485, | |
| "learning_rate": 9.163431531627569e-06, | |
| "loss": 0.5224910736083984, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.0927338173387835, | |
| "grad_norm": 0.28431364201602966, | |
| "learning_rate": 9.006068688535342e-06, | |
| "loss": 0.5179880619049072, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.1024952717954974, | |
| "grad_norm": 0.2973709269157597, | |
| "learning_rate": 8.848954052611206e-06, | |
| "loss": 0.5165664672851562, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.1122567262522116, | |
| "grad_norm": 0.314239603184092, | |
| "learning_rate": 8.692126858939515e-06, | |
| "loss": 0.5158205986022949, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.1220181807089256, | |
| "grad_norm": 0.2922205576849918, | |
| "learning_rate": 8.535626270823782e-06, | |
| "loss": 0.5197366714477539, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.1317796351656397, | |
| "grad_norm": 0.27987339622032165, | |
| "learning_rate": 8.379491370006711e-06, | |
| "loss": 0.5200955390930175, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.1415410896223537, | |
| "grad_norm": 0.3320797014169903, | |
| "learning_rate": 8.223761146910603e-06, | |
| "loss": 0.5186254024505615, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.1513025440790678, | |
| "grad_norm": 0.26868857833224674, | |
| "learning_rate": 8.068474490900558e-06, | |
| "loss": 0.5169284820556641, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.1610639985357818, | |
| "grad_norm": 0.27906695212992894, | |
| "learning_rate": 7.913670180572936e-06, | |
| "loss": 0.5188753128051757, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.170825452992496, | |
| "grad_norm": 0.2499968634248986, | |
| "learning_rate": 7.759386874071444e-06, | |
| "loss": 0.5169572353363037, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.18058690744921, | |
| "grad_norm": 0.25669523715148324, | |
| "learning_rate": 7.60566309943333e-06, | |
| "loss": 0.5177628040313721, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.190348361905924, | |
| "grad_norm": 0.3127411523406545, | |
| "learning_rate": 7.4525372449680555e-06, | |
| "loss": 0.5184590339660644, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.200109816362638, | |
| "grad_norm": 0.29021698280349795, | |
| "learning_rate": 7.300047549670871e-06, | |
| "loss": 0.5188806533813477, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.209871270819352, | |
| "grad_norm": 0.28856677054504354, | |
| "learning_rate": 7.148232093673672e-06, | |
| "loss": 0.515787410736084, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.2196327252760661, | |
| "grad_norm": 0.3023289378181344, | |
| "learning_rate": 6.9971287887355254e-06, | |
| "loss": 0.5163328647613525, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.22939417973278, | |
| "grad_norm": 0.26247524274089795, | |
| "learning_rate": 6.846775368775231e-06, | |
| "loss": 0.5181135177612305, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.2391556341894943, | |
| "grad_norm": 0.2990280458656863, | |
| "learning_rate": 6.697209380448333e-06, | |
| "loss": 0.5180223464965821, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.2489170886462082, | |
| "grad_norm": 0.27826406563749756, | |
| "learning_rate": 6.548468173770845e-06, | |
| "loss": 0.5206103801727295, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.2586785431029224, | |
| "grad_norm": 0.2509774400736038, | |
| "learning_rate": 6.400588892792127e-06, | |
| "loss": 0.5194956302642822, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.2684399975596363, | |
| "grad_norm": 0.3003807314209112, | |
| "learning_rate": 6.253608466319157e-06, | |
| "loss": 0.5183727264404296, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.2782014520163505, | |
| "grad_norm": 0.28566950902389265, | |
| "learning_rate": 6.107563598694577e-06, | |
| "loss": 0.5115070343017578, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.2879629064730644, | |
| "grad_norm": 0.2775455085835586, | |
| "learning_rate": 5.962490760630787e-06, | |
| "loss": 0.5156794548034668, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.2977243609297786, | |
| "grad_norm": 0.24707871015785107, | |
| "learning_rate": 5.818426180102382e-06, | |
| "loss": 0.5146899223327637, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.3074858153864926, | |
| "grad_norm": 0.2431650508539672, | |
| "learning_rate": 5.675405833299215e-06, | |
| "loss": 0.516709280014038, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.3172472698432065, | |
| "grad_norm": 0.2484262146803382, | |
| "learning_rate": 5.533465435642305e-06, | |
| "loss": 0.5153475761413574, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.3270087242999207, | |
| "grad_norm": 0.2580363818385725, | |
| "learning_rate": 5.392640432864913e-06, | |
| "loss": 0.5175045013427735, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.3367701787566348, | |
| "grad_norm": 0.2703904724879195, | |
| "learning_rate": 5.252965992160914e-06, | |
| "loss": 0.5145888328552246, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.3465316332133488, | |
| "grad_norm": 0.2731121542706405, | |
| "learning_rate": 5.114476993402772e-06, | |
| "loss": 0.5174077033996582, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.3562930876700627, | |
| "grad_norm": 0.2789434054296118, | |
| "learning_rate": 4.977208020431246e-06, | |
| "loss": 0.5140918731689453, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.366054542126777, | |
| "grad_norm": 0.25224799646541446, | |
| "learning_rate": 4.841193352419003e-06, | |
| "loss": 0.5124314785003662, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.375815996583491, | |
| "grad_norm": 0.23367404244092368, | |
| "learning_rate": 4.706466955310343e-06, | |
| "loss": 0.5177772521972657, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.385577451040205, | |
| "grad_norm": 0.25239349321695426, | |
| "learning_rate": 4.573062473339135e-06, | |
| "loss": 0.5172656059265137, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.395338905496919, | |
| "grad_norm": 0.25085980708060507, | |
| "learning_rate": 4.441013220627087e-06, | |
| "loss": 0.5163529396057129, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.4051003599536331, | |
| "grad_norm": 0.25699494935708533, | |
| "learning_rate": 4.310352172864468e-06, | |
| "loss": 0.5130033016204834, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.414861814410347, | |
| "grad_norm": 0.30451562530875587, | |
| "learning_rate": 4.181111959075295e-06, | |
| "loss": 0.5169584274291992, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.4246232688670613, | |
| "grad_norm": 0.22347789229405868, | |
| "learning_rate": 4.053324853469164e-06, | |
| "loss": 0.5177071571350098, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.4343847233237752, | |
| "grad_norm": 0.22872455022553068, | |
| "learning_rate": 3.927022767381634e-06, | |
| "loss": 0.5152188301086426, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.4441461777804894, | |
| "grad_norm": 0.25388484440810843, | |
| "learning_rate": 3.8022372413052424e-06, | |
| "loss": 0.5127427101135253, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.4539076322372033, | |
| "grad_norm": 0.25866952949094735, | |
| "learning_rate": 3.678999437013129e-06, | |
| "loss": 0.5151724338531494, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.4636690866939173, | |
| "grad_norm": 0.24712009382832717, | |
| "learning_rate": 3.5573401297772404e-06, | |
| "loss": 0.5154451370239258, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.4734305411506314, | |
| "grad_norm": 0.2500686833810677, | |
| "learning_rate": 3.437289700683042e-06, | |
| "loss": 0.5136337280273438, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.4831919956073456, | |
| "grad_norm": 0.24386033509991423, | |
| "learning_rate": 3.318878129042675e-06, | |
| "loss": 0.5164509296417237, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.4929534500640596, | |
| "grad_norm": 0.21789060953672507, | |
| "learning_rate": 3.2021349849084425e-06, | |
| "loss": 0.5164978504180908, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.5027149045207735, | |
| "grad_norm": 0.23279008504583068, | |
| "learning_rate": 3.0870894216884994e-06, | |
| "loss": 0.5138144493103027, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.5124763589774877, | |
| "grad_norm": 0.23798382143370084, | |
| "learning_rate": 2.97377016886658e-06, | |
| "loss": 0.5130619049072266, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.5222378134342018, | |
| "grad_norm": 0.22614472917954062, | |
| "learning_rate": 2.8622055248276037e-06, | |
| "loss": 0.5171074867248535, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.5319992678909158, | |
| "grad_norm": 0.22130974012180282, | |
| "learning_rate": 2.7524233497909183e-06, | |
| "loss": 0.5185530185699463, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.5417607223476297, | |
| "grad_norm": 0.24403616744222512, | |
| "learning_rate": 2.644451058852979e-06, | |
| "loss": 0.5162991046905517, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.551522176804344, | |
| "grad_norm": 0.22243870099915153, | |
| "learning_rate": 2.5383156151411736e-06, | |
| "loss": 0.5156514644622803, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.5612836312610578, | |
| "grad_norm": 0.2140937785595596, | |
| "learning_rate": 2.4340435230805235e-06, | |
| "loss": 0.5116523742675781, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.5710450857177718, | |
| "grad_norm": 0.22846166989495398, | |
| "learning_rate": 2.331660821774915e-06, | |
| "loss": 0.5128523826599121, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.580806540174486, | |
| "grad_norm": 0.23853426482035037, | |
| "learning_rate": 2.231193078504561e-06, | |
| "loss": 0.5140191078186035, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.5905679946312001, | |
| "grad_norm": 0.2546194675779906, | |
| "learning_rate": 2.1326653823412703e-06, | |
| "loss": 0.5155912876129151, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.600329449087914, | |
| "grad_norm": 0.21571313679227117, | |
| "learning_rate": 2.036102337883129e-06, | |
| "loss": 0.513617467880249, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.610090903544628, | |
| "grad_norm": 0.21005916699635413, | |
| "learning_rate": 1.9415280591101738e-06, | |
| "loss": 0.5121469974517823, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.6198523580013422, | |
| "grad_norm": 0.21340720820134304, | |
| "learning_rate": 1.8489661633625955e-06, | |
| "loss": 0.5160678863525391, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.6296138124580564, | |
| "grad_norm": 0.21247785817165615, | |
| "learning_rate": 1.7584397654429475e-06, | |
| "loss": 0.5125009059906006, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.6393752669147703, | |
| "grad_norm": 0.22116699930479886, | |
| "learning_rate": 1.6699714718438643e-06, | |
| "loss": 0.5144219398498535, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.6491367213714843, | |
| "grad_norm": 0.21584368154418007, | |
| "learning_rate": 1.5835833751026853e-06, | |
| "loss": 0.5139463424682618, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.6588981758281984, | |
| "grad_norm": 0.19776671497752707, | |
| "learning_rate": 1.4992970482844759e-06, | |
| "loss": 0.5122383117675782, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.6686596302849126, | |
| "grad_norm": 0.20581304506094591, | |
| "learning_rate": 1.4171335395947272e-06, | |
| "loss": 0.5123903274536132, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.6784210847416265, | |
| "grad_norm": 0.18158853274045864, | |
| "learning_rate": 1.3371133671231473e-06, | |
| "loss": 0.512973690032959, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.6881825391983405, | |
| "grad_norm": 0.20825010878190528, | |
| "learning_rate": 1.2592565137198298e-06, | |
| "loss": 0.5119497299194335, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.6979439936550547, | |
| "grad_norm": 0.1929130458685117, | |
| "learning_rate": 1.1835824220050796e-06, | |
| "loss": 0.5152641296386719, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.7077054481117686, | |
| "grad_norm": 0.2048451686581624, | |
| "learning_rate": 1.1101099895141542e-06, | |
| "loss": 0.5131969451904297, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.7174669025684826, | |
| "grad_norm": 0.20763283463158677, | |
| "learning_rate": 1.0388575639781217e-06, | |
| "loss": 0.5137289047241211, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.7272283570251967, | |
| "grad_norm": 0.2248311820725527, | |
| "learning_rate": 9.698429387420126e-07, | |
| "loss": 0.513949966430664, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.736989811481911, | |
| "grad_norm": 0.21038849674395077, | |
| "learning_rate": 9.030833483214208e-07, | |
| "loss": 0.5135007858276367, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.7467512659386248, | |
| "grad_norm": 0.20000937826548337, | |
| "learning_rate": 8.385954640986538e-07, | |
| "loss": 0.5094645023345947, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.7565127203953388, | |
| "grad_norm": 0.20796482171526587, | |
| "learning_rate": 7.763953901595111e-07, | |
| "loss": 0.5141811847686768, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.766274174852053, | |
| "grad_norm": 0.20836986545080005, | |
| "learning_rate": 7.164986592717327e-07, | |
| "loss": 0.5138214111328125, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.7760356293087671, | |
| "grad_norm": 0.19539889121407583, | |
| "learning_rate": 6.589202290061015e-07, | |
| "loss": 0.5120339393615723, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.785797083765481, | |
| "grad_norm": 0.1945833663604816, | |
| "learning_rate": 6.036744780012227e-07, | |
| "loss": 0.5104346752166748, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.795558538222195, | |
| "grad_norm": 0.21461561202531795, | |
| "learning_rate": 5.507752023728286e-07, | |
| "loss": 0.5140288829803467, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.8053199926789092, | |
| "grad_norm": 0.2233570865176135, | |
| "learning_rate": 5.002356122685914e-07, | |
| "loss": 0.5119523048400879, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.8150814471356234, | |
| "grad_norm": 0.2140208043729751, | |
| "learning_rate": 4.5206832856923845e-07, | |
| "loss": 0.5112673759460449, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.8248429015923373, | |
| "grad_norm": 0.1939353070117794, | |
| "learning_rate": 4.0628537973684046e-07, | |
| "loss": 0.5132551193237305, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.8346043560490513, | |
| "grad_norm": 0.27662385856633, | |
| "learning_rate": 3.628981988110336e-07, | |
| "loss": 0.5113656997680665, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.8443658105057654, | |
| "grad_norm": 0.1873684185676719, | |
| "learning_rate": 3.219176205539243e-07, | |
| "loss": 0.5143997192382812, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.8541272649624794, | |
| "grad_norm": 0.20006694507765596, | |
| "learning_rate": 2.8335387874440124e-07, | |
| "loss": 0.5133038520812988, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.8638887194191933, | |
| "grad_norm": 0.19111674150717217, | |
| "learning_rate": 2.4721660362253875e-07, | |
| "loss": 0.5143795013427734, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.8736501738759075, | |
| "grad_norm": 0.19076088219226814, | |
| "learning_rate": 2.1351481948470142e-07, | |
| "loss": 0.5107194900512695, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.8834116283326217, | |
| "grad_norm": 0.18506982350558332, | |
| "learning_rate": 1.8225694242997583e-07, | |
| "loss": 0.5127174377441406, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.8931730827893356, | |
| "grad_norm": 0.1927401327626226, | |
| "learning_rate": 1.5345077825847266e-07, | |
| "loss": 0.5101862907409668, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.9029345372460496, | |
| "grad_norm": 0.20294868114498626, | |
| "learning_rate": 1.2710352052205166e-07, | |
| "loss": 0.5122389316558837, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.9126959917027637, | |
| "grad_norm": 0.20549210839176393, | |
| "learning_rate": 1.032217487279219e-07, | |
| "loss": 0.5123374938964844, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.922457446159478, | |
| "grad_norm": 0.19146983404482038, | |
| "learning_rate": 8.181142669559383e-08, | |
| "loss": 0.5149818420410156, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.9322189006161918, | |
| "grad_norm": 0.17721381649523446, | |
| "learning_rate": 6.287790106757396e-08, | |
| "loss": 0.5127687454223633, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.9419803550729058, | |
| "grad_norm": 0.2043110697294413, | |
| "learning_rate": 4.642589997419178e-08, | |
| "loss": 0.5103424549102783, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.95174180952962, | |
| "grad_norm": 0.1853816182353607, | |
| "learning_rate": 3.2459531852873094e-08, | |
| "loss": 0.5141597747802734, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.9615032639863341, | |
| "grad_norm": 0.19375887604251124, | |
| "learning_rate": 2.0982284422177424e-08, | |
| "loss": 0.512387752532959, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.971264718443048, | |
| "grad_norm": 0.18628635952710476, | |
| "learning_rate": 1.1997023810829122e-08, | |
| "loss": 0.5112565994262696, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.981026172899762, | |
| "grad_norm": 0.18661183658691527, | |
| "learning_rate": 5.505993841982138e-09, | |
| "loss": 0.5109218120574951, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.9907876273564762, | |
| "grad_norm": 0.19195728014363997, | |
| "learning_rate": 1.5108154728882273e-09, | |
| "loss": 0.5125418186187745, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.27523895648188323, | |
| "learning_rate": 1.2486390105204138e-11, | |
| "loss": 0.5148112297058105, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 2050, | |
| "total_flos": 4770492701474816.0, | |
| "train_loss": 0.5427387805101348, | |
| "train_runtime": 247087.7187, | |
| "train_samples_per_second": 0.531, | |
| "train_steps_per_second": 0.008 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2050, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4770492701474816.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null, | |
| "train_runtime": 259200.0 | |
| } |