Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use jackysnake/llama-debug-stop-wmdp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jackysnake/llama-debug-stop-wmdp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jackysnake/llama-debug-stop-wmdp") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jackysnake/llama-debug-stop-wmdp") model = AutoModelForCausalLM.from_pretrained("jackysnake/llama-debug-stop-wmdp", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jackysnake/llama-debug-stop-wmdp with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jackysnake/llama-debug-stop-wmdp" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jackysnake/llama-debug-stop-wmdp", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/jackysnake/llama-debug-stop-wmdp
- SGLang
How to use jackysnake/llama-debug-stop-wmdp 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 "jackysnake/llama-debug-stop-wmdp" \ --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": "jackysnake/llama-debug-stop-wmdp", "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 "jackysnake/llama-debug-stop-wmdp" \ --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": "jackysnake/llama-debug-stop-wmdp", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use jackysnake/llama-debug-stop-wmdp with Docker Model Runner:
docker model run hf.co/jackysnake/llama-debug-stop-wmdp
Download trainer_state.json from jackysnake/llama-debug-stop-wmdp: direct link, hf CLI and curl.
- Browser
- Download file 19.3 kB
-
https://huggingface.co/jackysnake/llama-debug-stop-wmdp/resolve/main/trainer_state.json
- Command line
-
hf download hf://jackysnake/llama-debug-stop-wmdp/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/jackysnake/llama-debug-stop-wmdp/resolve/main/trainer_state.json
19.3 kB
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1068, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.028089887640449437, | |
| "grad_norm": 22.7819163924511, | |
| "learning_rate": 8.411214953271029e-07, | |
| "loss": 2.9231, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.056179775280898875, | |
| "grad_norm": 30.169298145178146, | |
| "learning_rate": 1.7757009345794394e-06, | |
| "loss": 2.4062, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08426966292134831, | |
| "grad_norm": 6.202690798445886, | |
| "learning_rate": 2.7102803738317757e-06, | |
| "loss": 1.9513, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11235955056179775, | |
| "grad_norm": 5.263465562808427, | |
| "learning_rate": 3.6448598130841123e-06, | |
| "loss": 1.8496, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1404494382022472, | |
| "grad_norm": 5.4274100871384725, | |
| "learning_rate": 4.579439252336449e-06, | |
| "loss": 1.7673, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16853932584269662, | |
| "grad_norm": 5.083967528341353, | |
| "learning_rate": 5.514018691588785e-06, | |
| "loss": 1.7726, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19662921348314608, | |
| "grad_norm": 4.413569304884172, | |
| "learning_rate": 6.448598130841122e-06, | |
| "loss": 1.7101, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2247191011235955, | |
| "grad_norm": 5.11665572703267, | |
| "learning_rate": 7.383177570093458e-06, | |
| "loss": 1.6601, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.25280898876404495, | |
| "grad_norm": 5.127775524118529, | |
| "learning_rate": 8.317757009345795e-06, | |
| "loss": 1.6524, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2808988764044944, | |
| "grad_norm": 5.103050689720349, | |
| "learning_rate": 9.252336448598132e-06, | |
| "loss": 1.6333, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3089887640449438, | |
| "grad_norm": 5.047765658117637, | |
| "learning_rate": 9.999893131079397e-06, | |
| "loss": 1.5379, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.33707865168539325, | |
| "grad_norm": 4.666373415727088, | |
| "learning_rate": 9.996153198516951e-06, | |
| "loss": 1.6205, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3651685393258427, | |
| "grad_norm": 5.030887005471109, | |
| "learning_rate": 9.987074387433024e-06, | |
| "loss": 1.4815, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.39325842696629215, | |
| "grad_norm": 5.751538740001306, | |
| "learning_rate": 9.972666399425538e-06, | |
| "loss": 1.5154, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.42134831460674155, | |
| "grad_norm": 4.6927345288937286, | |
| "learning_rate": 9.952944630839371e-06, | |
| "loss": 1.5739, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "grad_norm": 4.916388835208482, | |
| "learning_rate": 9.92793015631386e-06, | |
| "loss": 1.5092, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.47752808988764045, | |
| "grad_norm": 4.9934704736472675, | |
| "learning_rate": 9.897649706262474e-06, | |
| "loss": 1.4422, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5056179775280899, | |
| "grad_norm": 5.483074092056045, | |
| "learning_rate": 9.862135638308763e-06, | |
| "loss": 1.4518, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5337078651685393, | |
| "grad_norm": 5.379268658454326, | |
| "learning_rate": 9.821425902709072e-06, | |
| "loss": 1.344, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5617977528089888, | |
| "grad_norm": 5.364666367895533, | |
| "learning_rate": 9.775564001798973e-06, | |
| "loss": 1.3404, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5898876404494382, | |
| "grad_norm": 5.243909104292613, | |
| "learning_rate": 9.724598943506762e-06, | |
| "loss": 1.3106, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6179775280898876, | |
| "grad_norm": 4.912799311162487, | |
| "learning_rate": 9.6685851889837e-06, | |
| "loss": 1.2557, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6460674157303371, | |
| "grad_norm": 5.607392649989989, | |
| "learning_rate": 9.607582594406941e-06, | |
| "loss": 1.2706, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6741573033707865, | |
| "grad_norm": 5.0693403656816365, | |
| "learning_rate": 9.541656347017345e-06, | |
| "loss": 1.2485, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.702247191011236, | |
| "grad_norm": 5.736859966996421, | |
| "learning_rate": 9.470876895460545e-06, | |
| "loss": 1.2168, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7303370786516854, | |
| "grad_norm": 4.782228278164676, | |
| "learning_rate": 9.395319874505661e-06, | |
| "loss": 1.2281, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7584269662921348, | |
| "grad_norm": 5.550206300204117, | |
| "learning_rate": 9.315066024222163e-06, | |
| "loss": 1.162, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7865168539325843, | |
| "grad_norm": 5.219689547227467, | |
| "learning_rate": 9.230201103701201e-06, | |
| "loss": 1.1131, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8146067415730337, | |
| "grad_norm": 5.102313121412946, | |
| "learning_rate": 9.140815799413624e-06, | |
| "loss": 1.11, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8426966292134831, | |
| "grad_norm": 5.5553404145592875, | |
| "learning_rate": 9.047005628302617e-06, | |
| "loss": 1.0506, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8707865168539326, | |
| "grad_norm": 6.8885505748823395, | |
| "learning_rate": 8.948870835714491e-06, | |
| "loss": 1.0996, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 5.75097828808934, | |
| "learning_rate": 8.846516288276743e-06, | |
| "loss": 0.9563, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9269662921348315, | |
| "grad_norm": 5.522884680949851, | |
| "learning_rate": 8.740051361837786e-06, | |
| "loss": 0.9441, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9550561797752809, | |
| "grad_norm": 5.0573808083469345, | |
| "learning_rate": 8.629589824588158e-06, | |
| "loss": 0.9792, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9831460674157303, | |
| "grad_norm": 6.071287853595073, | |
| "learning_rate": 8.515249715488085e-06, | |
| "loss": 0.8838, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0112359550561798, | |
| "grad_norm": 5.290451423113777, | |
| "learning_rate": 8.397153218131297e-06, | |
| "loss": 0.639, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0393258426966292, | |
| "grad_norm": 4.891918887355522, | |
| "learning_rate": 8.2754265301799e-06, | |
| "loss": 0.386, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.0674157303370786, | |
| "grad_norm": 5.773434510473206, | |
| "learning_rate": 8.150199728509844e-06, | |
| "loss": 0.3622, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.095505617977528, | |
| "grad_norm": 5.639061209982648, | |
| "learning_rate": 8.02160663021103e-06, | |
| "loss": 0.3669, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.1235955056179776, | |
| "grad_norm": 4.857615838112837, | |
| "learning_rate": 7.889784649590673e-06, | |
| "loss": 0.355, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.151685393258427, | |
| "grad_norm": 5.00938149460149, | |
| "learning_rate": 7.754874651332671e-06, | |
| "loss": 0.3453, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.1797752808988764, | |
| "grad_norm": 5.104430557325571, | |
| "learning_rate": 7.617020799969895e-06, | |
| "loss": 0.3302, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.2078651685393258, | |
| "grad_norm": 5.552866511883807, | |
| "learning_rate": 7.476370405830293e-06, | |
| "loss": 0.3926, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.2359550561797752, | |
| "grad_norm": 5.2615493857886255, | |
| "learning_rate": 7.333073767621385e-06, | |
| "loss": 0.328, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.2640449438202248, | |
| "grad_norm": 4.652382868595637, | |
| "learning_rate": 7.18728401182139e-06, | |
| "loss": 0.3245, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.2921348314606742, | |
| "grad_norm": 4.858950309293884, | |
| "learning_rate": 7.039156929048603e-06, | |
| "loss": 0.3238, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.3202247191011236, | |
| "grad_norm": 4.872411285739121, | |
| "learning_rate": 6.888850807583875e-06, | |
| "loss": 0.3014, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.348314606741573, | |
| "grad_norm": 5.912861518919336, | |
| "learning_rate": 6.736526264224101e-06, | |
| "loss": 0.3173, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.3764044943820224, | |
| "grad_norm": 5.815405179050917, | |
| "learning_rate": 6.582346072647455e-06, | |
| "loss": 0.3163, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.404494382022472, | |
| "grad_norm": 4.366225871228438, | |
| "learning_rate": 6.426474989473785e-06, | |
| "loss": 0.3016, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.4325842696629214, | |
| "grad_norm": 5.84016971749359, | |
| "learning_rate": 6.2690795782060535e-06, | |
| "loss": 0.2568, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.4606741573033708, | |
| "grad_norm": 6.166567012198751, | |
| "learning_rate": 6.1103280312409355e-06, | |
| "loss": 0.2613, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.4887640449438202, | |
| "grad_norm": 4.2939430683495985, | |
| "learning_rate": 5.950389990138774e-06, | |
| "loss": 0.2731, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.5168539325842696, | |
| "grad_norm": 5.133914114632436, | |
| "learning_rate": 5.789436364344998e-06, | |
| "loss": 0.25, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.5449438202247192, | |
| "grad_norm": 4.156401846037989, | |
| "learning_rate": 5.627639148556638e-06, | |
| "loss": 0.2397, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.5730337078651684, | |
| "grad_norm": 5.021723670464346, | |
| "learning_rate": 5.465171238929173e-06, | |
| "loss": 0.2319, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.601123595505618, | |
| "grad_norm": 3.8323276940770086, | |
| "learning_rate": 5.30220624832007e-06, | |
| "loss": 0.1869, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.6292134831460674, | |
| "grad_norm": 5.0978859322012715, | |
| "learning_rate": 5.13891832076646e-06, | |
| "loss": 0.2227, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.6573033707865168, | |
| "grad_norm": 4.08012916281094, | |
| "learning_rate": 4.9754819453951986e-06, | |
| "loss": 0.2014, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.6853932584269664, | |
| "grad_norm": 4.896132407766081, | |
| "learning_rate": 4.8120717699641535e-06, | |
| "loss": 0.1826, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7134831460674156, | |
| "grad_norm": 4.088139396488562, | |
| "learning_rate": 4.648862414233998e-06, | |
| "loss": 0.1831, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.7415730337078652, | |
| "grad_norm": 3.7782908427414243, | |
| "learning_rate": 4.486028283369901e-06, | |
| "loss": 0.1841, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.7696629213483146, | |
| "grad_norm": 4.5303753028746465, | |
| "learning_rate": 4.323743381572557e-06, | |
| "loss": 0.1481, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.797752808988764, | |
| "grad_norm": 5.2440255614580815, | |
| "learning_rate": 4.162181126137658e-06, | |
| "loss": 0.1812, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.8258426966292136, | |
| "grad_norm": 4.522179501739034, | |
| "learning_rate": 4.001514162142559e-06, | |
| "loss": 0.1398, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.8539325842696628, | |
| "grad_norm": 4.399657568666563, | |
| "learning_rate": 3.84191417795811e-06, | |
| "loss": 0.1267, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.8820224719101124, | |
| "grad_norm": 4.6584255922603806, | |
| "learning_rate": 3.6835517217828442e-06, | |
| "loss": 0.1292, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.9101123595505618, | |
| "grad_norm": 3.364324997617781, | |
| "learning_rate": 3.5265960193955338e-06, | |
| "loss": 0.1007, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.9382022471910112, | |
| "grad_norm": 4.327833688875914, | |
| "learning_rate": 3.3712147933208885e-06, | |
| "loss": 0.1065, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.9662921348314608, | |
| "grad_norm": 3.5921786463086693, | |
| "learning_rate": 3.2175740836016323e-06, | |
| "loss": 0.0886, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.99438202247191, | |
| "grad_norm": 3.2409244138270408, | |
| "learning_rate": 3.065838070368469e-06, | |
| "loss": 0.0959, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.0224719101123596, | |
| "grad_norm": 1.8814994184676492, | |
| "learning_rate": 2.9161688983975466e-06, | |
| "loss": 0.0377, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.050561797752809, | |
| "grad_norm": 1.5053488307678218, | |
| "learning_rate": 2.7687265038429074e-06, | |
| "loss": 0.0216, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.0786516853932584, | |
| "grad_norm": 2.502066820671665, | |
| "learning_rate": 2.6236684433290494e-06, | |
| "loss": 0.0255, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.106741573033708, | |
| "grad_norm": 2.3514055536589558, | |
| "learning_rate": 2.4811497255862634e-06, | |
| "loss": 0.026, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.134831460674157, | |
| "grad_norm": 1.8804832087765475, | |
| "learning_rate": 2.341322645808642e-06, | |
| "loss": 0.0264, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.162921348314607, | |
| "grad_norm": 1.9959479335272763, | |
| "learning_rate": 2.204336622911753e-06, | |
| "loss": 0.0254, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.191011235955056, | |
| "grad_norm": 2.1439850805162566, | |
| "learning_rate": 2.070338039863917e-06, | |
| "loss": 0.0289, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.2191011235955056, | |
| "grad_norm": 1.8333707683328262, | |
| "learning_rate": 1.9394700872616856e-06, | |
| "loss": 0.0271, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.247191011235955, | |
| "grad_norm": 1.7599990210450056, | |
| "learning_rate": 1.8118726103166706e-06, | |
| "loss": 0.028, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.2752808988764044, | |
| "grad_norm": 2.827218718432996, | |
| "learning_rate": 1.6876819594172578e-06, | |
| "loss": 0.0253, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.303370786516854, | |
| "grad_norm": 2.0316861235237957, | |
| "learning_rate": 1.5670308444248777e-06, | |
| "loss": 0.0258, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.331460674157303, | |
| "grad_norm": 1.5453668410450907, | |
| "learning_rate": 1.4500481928605304e-06, | |
| "loss": 0.0215, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.359550561797753, | |
| "grad_norm": 2.695179021406971, | |
| "learning_rate": 1.3368590121331166e-06, | |
| "loss": 0.0225, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.3876404494382024, | |
| "grad_norm": 1.954342184379783, | |
| "learning_rate": 1.2275842559567947e-06, | |
| "loss": 0.0229, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.4157303370786516, | |
| "grad_norm": 1.4275966394165036, | |
| "learning_rate": 1.1223406951000936e-06, | |
| "loss": 0.022, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.443820224719101, | |
| "grad_norm": 1.3558757122974379, | |
| "learning_rate": 1.021240792604929e-06, | |
| "loss": 0.0196, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.4719101123595504, | |
| "grad_norm": 1.1767311794004252, | |
| "learning_rate": 9.243925836088386e-07, | |
| "loss": 0.0195, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 1.1869896295471005, | |
| "learning_rate": 8.318995598988649e-07, | |
| "loss": 0.019, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.5280898876404496, | |
| "grad_norm": 1.7268491118892093, | |
| "learning_rate": 7.438605593204562e-07, | |
| "loss": 0.0218, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.556179775280899, | |
| "grad_norm": 1.137871984603961, | |
| "learning_rate": 6.603696601595577e-07, | |
| "loss": 0.016, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.5842696629213484, | |
| "grad_norm": 2.86247217703931, | |
| "learning_rate": 5.8151608061076e-07, | |
| "loss": 0.0184, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.6123595505617976, | |
| "grad_norm": 1.7320846371149687, | |
| "learning_rate": 5.073840834389293e-07, | |
| "loss": 0.0189, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.640449438202247, | |
| "grad_norm": 2.9271667139526665, | |
| "learning_rate": 4.380528859361954e-07, | |
| "loss": 0.0225, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.668539325842697, | |
| "grad_norm": 1.5072751176957493, | |
| "learning_rate": 3.735965752705256e-07, | |
| "loss": 0.0173, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.696629213483146, | |
| "grad_norm": 1.3108462533652585, | |
| "learning_rate": 3.1408402931634163e-07, | |
| "loss": 0.017, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.7247191011235956, | |
| "grad_norm": 1.0954009866198928, | |
| "learning_rate": 2.595788430517637e-07, | |
| "loss": 0.0128, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.752808988764045, | |
| "grad_norm": 0.6759041389055112, | |
| "learning_rate": 2.1013926060116042e-07, | |
| "loss": 0.0149, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.7808988764044944, | |
| "grad_norm": 1.058628316365804, | |
| "learning_rate": 1.6581811299560212e-07, | |
| "loss": 0.0139, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.808988764044944, | |
| "grad_norm": 1.0674017020844853, | |
| "learning_rate": 1.2666276171773073e-07, | |
| "loss": 0.0158, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.837078651685393, | |
| "grad_norm": 1.3365845674516978, | |
| "learning_rate": 9.271504809138854e-08, | |
| "loss": 0.0164, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.865168539325843, | |
| "grad_norm": 1.2402769734441241, | |
| "learning_rate": 6.401124857006502e-08, | |
| "loss": 0.0147, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.893258426966292, | |
| "grad_norm": 0.557082827456061, | |
| "learning_rate": 4.058203597195831e-08, | |
| "loss": 0.0117, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.9213483146067416, | |
| "grad_norm": 1.3256107006475653, | |
| "learning_rate": 2.2452446703067897e-08, | |
| "loss": 0.0125, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.949438202247191, | |
| "grad_norm": 0.5004503844337672, | |
| "learning_rate": 9.641854003346607e-09, | |
| "loss": 0.0118, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.9775280898876404, | |
| "grad_norm": 1.0030208037614885, | |
| "learning_rate": 2.1639472444956454e-09, | |
| "loss": 0.0122, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1068, | |
| "total_flos": 38985510420480.0, | |
| "train_loss": 0.5699994009029999, | |
| "train_runtime": 4399.6336, | |
| "train_samples_per_second": 15.526, | |
| "train_steps_per_second": 0.243 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1068, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 38985510420480.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |