Text Generation
Transformers
TensorBoard
Safetensors
PEFT
Trained with AutoTrain
text-generation-inference
conversational
Instructions to use BINARIAL/GALIA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BINARIAL/GALIA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BINARIAL/GALIA") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BINARIAL/GALIA", device_map="auto") - PEFT
How to use BINARIAL/GALIA with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BINARIAL/GALIA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BINARIAL/GALIA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BINARIAL/GALIA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/BINARIAL/GALIA
- SGLang
How to use BINARIAL/GALIA 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 "BINARIAL/GALIA" \ --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": "BINARIAL/GALIA", "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 "BINARIAL/GALIA" \ --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": "BINARIAL/GALIA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use BINARIAL/GALIA with Docker Model Runner:
docker model run hf.co/BINARIAL/GALIA
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.999724391364263, | |
| "eval_steps": 500, | |
| "global_step": 8163, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 5.019594669342041, | |
| "learning_rate": 8.812729498164015e-07, | |
| "loss": 2.5969, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.2792530059814453, | |
| "learning_rate": 1.799265605875153e-06, | |
| "loss": 2.5712, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.6284871101379395, | |
| "learning_rate": 2.7172582619339046e-06, | |
| "loss": 2.4269, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 2.638899803161621, | |
| "learning_rate": 3.6352509179926564e-06, | |
| "loss": 2.3086, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 3.020103693008423, | |
| "learning_rate": 4.553243574051408e-06, | |
| "loss": 2.152, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 2.3148763179779053, | |
| "learning_rate": 5.47123623011016e-06, | |
| "loss": 2.0393, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 2.275376558303833, | |
| "learning_rate": 6.389228886168911e-06, | |
| "loss": 1.954, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 2.5663716793060303, | |
| "learning_rate": 7.307221542227662e-06, | |
| "loss": 1.9075, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 2.4330193996429443, | |
| "learning_rate": 8.225214198286414e-06, | |
| "loss": 1.8074, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 2.7704484462738037, | |
| "learning_rate": 9.143206854345165e-06, | |
| "loss": 1.7968, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 3.2770776748657227, | |
| "learning_rate": 1.0061199510403917e-05, | |
| "loss": 1.7784, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 2.754490613937378, | |
| "learning_rate": 1.097919216646267e-05, | |
| "loss": 1.6953, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 3.240971326828003, | |
| "learning_rate": 1.189718482252142e-05, | |
| "loss": 1.6694, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 3.4175171852111816, | |
| "learning_rate": 1.2815177478580172e-05, | |
| "loss": 1.6863, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 2.8977129459381104, | |
| "learning_rate": 1.3733170134638923e-05, | |
| "loss": 1.6488, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 3.4206955432891846, | |
| "learning_rate": 1.4651162790697674e-05, | |
| "loss": 1.659, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 3.3763089179992676, | |
| "learning_rate": 1.556915544675643e-05, | |
| "loss": 1.6077, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 3.212315320968628, | |
| "learning_rate": 1.6487148102815178e-05, | |
| "loss": 1.6231, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 3.6150689125061035, | |
| "learning_rate": 1.7405140758873927e-05, | |
| "loss": 1.6708, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 3.622896671295166, | |
| "learning_rate": 1.8323133414932683e-05, | |
| "loss": 1.5761, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 3.499622106552124, | |
| "learning_rate": 1.9241126070991433e-05, | |
| "loss": 1.6017, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 3.657644748687744, | |
| "learning_rate": 2.0159118727050182e-05, | |
| "loss": 1.5908, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 3.4769978523254395, | |
| "learning_rate": 2.1077111383108938e-05, | |
| "loss": 1.6129, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 3.1776161193847656, | |
| "learning_rate": 2.1995104039167688e-05, | |
| "loss": 1.5764, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 3.463768482208252, | |
| "learning_rate": 2.2913096695226437e-05, | |
| "loss": 1.579, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 3.202385902404785, | |
| "learning_rate": 2.383108935128519e-05, | |
| "loss": 1.5452, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 3.233647108078003, | |
| "learning_rate": 2.4749082007343942e-05, | |
| "loss": 1.6323, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 3.332144021987915, | |
| "learning_rate": 2.5667074663402692e-05, | |
| "loss": 1.6045, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 3.251033306121826, | |
| "learning_rate": 2.6585067319461444e-05, | |
| "loss": 1.5763, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 3.138462781906128, | |
| "learning_rate": 2.7503059975520197e-05, | |
| "loss": 1.5706, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 3.0554285049438477, | |
| "learning_rate": 2.8421052631578946e-05, | |
| "loss": 1.5216, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 3.0504651069641113, | |
| "learning_rate": 2.93390452876377e-05, | |
| "loss": 1.57, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 2.95691180229187, | |
| "learning_rate": 2.997141301388511e-05, | |
| "loss": 1.5168, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 2.863208293914795, | |
| "learning_rate": 2.986931663490335e-05, | |
| "loss": 1.5552, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 2.5448153018951416, | |
| "learning_rate": 2.9767220255921593e-05, | |
| "loss": 1.5648, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 2.7234387397766113, | |
| "learning_rate": 2.9665123876939832e-05, | |
| "loss": 1.5216, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 2.56977915763855, | |
| "learning_rate": 2.956302749795807e-05, | |
| "loss": 1.4888, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 2.7813570499420166, | |
| "learning_rate": 2.9460931118976314e-05, | |
| "loss": 1.55, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 2.516843318939209, | |
| "learning_rate": 2.9358834739994553e-05, | |
| "loss": 1.5215, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 2.7116241455078125, | |
| "learning_rate": 2.9256738361012796e-05, | |
| "loss": 1.5186, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 2.504891872406006, | |
| "learning_rate": 2.9154641982031038e-05, | |
| "loss": 1.4975, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 2.4921352863311768, | |
| "learning_rate": 2.9052545603049277e-05, | |
| "loss": 1.5364, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.4780983924865723, | |
| "learning_rate": 2.895044922406752e-05, | |
| "loss": 1.5075, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.5795676708221436, | |
| "learning_rate": 2.884835284508576e-05, | |
| "loss": 1.5197, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 2.4717788696289062, | |
| "learning_rate": 2.8746256466104002e-05, | |
| "loss": 1.5436, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 2.516700029373169, | |
| "learning_rate": 2.8644160087122245e-05, | |
| "loss": 1.5227, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 2.3301610946655273, | |
| "learning_rate": 2.8542063708140484e-05, | |
| "loss": 1.5403, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 2.5666234493255615, | |
| "learning_rate": 2.8439967329158726e-05, | |
| "loss": 1.484, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 2.273963689804077, | |
| "learning_rate": 2.8337870950176966e-05, | |
| "loss": 1.4857, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 2.419245958328247, | |
| "learning_rate": 2.8239858426354477e-05, | |
| "loss": 1.4803, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 2.312894821166992, | |
| "learning_rate": 2.813776204737272e-05, | |
| "loss": 1.497, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 2.3168880939483643, | |
| "learning_rate": 2.8035665668390962e-05, | |
| "loss": 1.5124, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 2.245943546295166, | |
| "learning_rate": 2.79335692894092e-05, | |
| "loss": 1.4894, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 2.4954259395599365, | |
| "learning_rate": 2.7831472910427444e-05, | |
| "loss": 1.5054, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.5361862182617188, | |
| "learning_rate": 2.7729376531445686e-05, | |
| "loss": 1.515, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.41825795173645, | |
| "learning_rate": 2.7627280152463926e-05, | |
| "loss": 1.4432, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 2.2795910835266113, | |
| "learning_rate": 2.7525183773482168e-05, | |
| "loss": 1.4956, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 2.272019624710083, | |
| "learning_rate": 2.7423087394500407e-05, | |
| "loss": 1.5067, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 2.297214984893799, | |
| "learning_rate": 2.732099101551865e-05, | |
| "loss": 1.459, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 2.2966599464416504, | |
| "learning_rate": 2.7218894636536893e-05, | |
| "loss": 1.463, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.258310556411743, | |
| "learning_rate": 2.7116798257555132e-05, | |
| "loss": 1.4855, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 2.2546372413635254, | |
| "learning_rate": 2.7014701878573375e-05, | |
| "loss": 1.4389, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 2.2848825454711914, | |
| "learning_rate": 2.6912605499591614e-05, | |
| "loss": 1.4709, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 2.4607439041137695, | |
| "learning_rate": 2.6810509120609856e-05, | |
| "loss": 1.4738, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.17085599899292, | |
| "learning_rate": 2.67084127416281e-05, | |
| "loss": 1.4427, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 2.3322973251342773, | |
| "learning_rate": 2.6606316362646338e-05, | |
| "loss": 1.4576, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 2.157118558883667, | |
| "learning_rate": 2.650421998366458e-05, | |
| "loss": 1.4368, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 2.3906755447387695, | |
| "learning_rate": 2.640212360468282e-05, | |
| "loss": 1.4464, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 2.19273042678833, | |
| "learning_rate": 2.6300027225701063e-05, | |
| "loss": 1.4032, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 2.0533928871154785, | |
| "learning_rate": 2.6197930846719305e-05, | |
| "loss": 1.4803, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 2.090940237045288, | |
| "learning_rate": 2.6095834467737544e-05, | |
| "loss": 1.4613, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 2.2770726680755615, | |
| "learning_rate": 2.5993738088755787e-05, | |
| "loss": 1.4975, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 2.3754994869232178, | |
| "learning_rate": 2.589164170977403e-05, | |
| "loss": 1.4286, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 2.255023717880249, | |
| "learning_rate": 2.578954533079227e-05, | |
| "loss": 1.4112, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 2.0663328170776367, | |
| "learning_rate": 2.568744895181051e-05, | |
| "loss": 1.4288, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 2.1688010692596436, | |
| "learning_rate": 2.558535257282875e-05, | |
| "loss": 1.4175, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 2.078010320663452, | |
| "learning_rate": 2.5483256193846993e-05, | |
| "loss": 1.44, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 2.0523500442504883, | |
| "learning_rate": 2.5381159814865236e-05, | |
| "loss": 1.402, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.2531204223632812, | |
| "learning_rate": 2.5279063435883475e-05, | |
| "loss": 1.442, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.2075908184051514, | |
| "learning_rate": 2.5176967056901718e-05, | |
| "loss": 1.4466, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 2.06585431098938, | |
| "learning_rate": 2.5074870677919957e-05, | |
| "loss": 1.445, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 2.291527271270752, | |
| "learning_rate": 2.4972774298938196e-05, | |
| "loss": 1.4239, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.077122688293457, | |
| "learning_rate": 2.487067791995644e-05, | |
| "loss": 1.4512, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 2.0683939456939697, | |
| "learning_rate": 2.4768581540974678e-05, | |
| "loss": 1.4313, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 2.2548866271972656, | |
| "learning_rate": 2.466648516199292e-05, | |
| "loss": 1.4499, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 2.0333142280578613, | |
| "learning_rate": 2.4564388783011163e-05, | |
| "loss": 1.489, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 2.0241236686706543, | |
| "learning_rate": 2.4462292404029403e-05, | |
| "loss": 1.4531, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 2.0434224605560303, | |
| "learning_rate": 2.4360196025047645e-05, | |
| "loss": 1.4067, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 2.0772247314453125, | |
| "learning_rate": 2.4258099646065884e-05, | |
| "loss": 1.4512, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 2.219872236251831, | |
| "learning_rate": 2.4156003267084127e-05, | |
| "loss": 1.4136, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 2.0617380142211914, | |
| "learning_rate": 2.405390688810237e-05, | |
| "loss": 1.4189, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 2.143292188644409, | |
| "learning_rate": 2.395181050912061e-05, | |
| "loss": 1.4343, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 2.2767598628997803, | |
| "learning_rate": 2.384971413013885e-05, | |
| "loss": 1.4309, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 1.9452316761016846, | |
| "learning_rate": 2.374761775115709e-05, | |
| "loss": 1.4525, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 1.9767943620681763, | |
| "learning_rate": 2.3645521372175333e-05, | |
| "loss": 1.4146, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 2.1205859184265137, | |
| "learning_rate": 2.3543424993193576e-05, | |
| "loss": 1.3848, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 2.1726503372192383, | |
| "learning_rate": 2.3441328614211815e-05, | |
| "loss": 1.4229, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 2.1361019611358643, | |
| "learning_rate": 2.3339232235230058e-05, | |
| "loss": 1.3928, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 1.9983566999435425, | |
| "learning_rate": 2.32371358562483e-05, | |
| "loss": 1.4177, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 2.072235107421875, | |
| "learning_rate": 2.313503947726654e-05, | |
| "loss": 1.4299, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 1.9266953468322754, | |
| "learning_rate": 2.3032943098284782e-05, | |
| "loss": 1.4124, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 1.9758812189102173, | |
| "learning_rate": 2.293084671930302e-05, | |
| "loss": 1.4642, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 1.9793875217437744, | |
| "learning_rate": 2.2828750340321264e-05, | |
| "loss": 1.4216, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.8431023359298706, | |
| "learning_rate": 2.2726653961339507e-05, | |
| "loss": 1.4259, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 2.120908260345459, | |
| "learning_rate": 2.2624557582357746e-05, | |
| "loss": 1.3896, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 1.8971043825149536, | |
| "learning_rate": 2.252246120337599e-05, | |
| "loss": 1.4137, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 1.79995858669281, | |
| "learning_rate": 2.2420364824394228e-05, | |
| "loss": 1.4027, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 1.9894652366638184, | |
| "learning_rate": 2.231826844541247e-05, | |
| "loss": 1.4241, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.8721575736999512, | |
| "learning_rate": 2.2216172066430713e-05, | |
| "loss": 1.4167, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 2.1240813732147217, | |
| "learning_rate": 2.2114075687448952e-05, | |
| "loss": 1.324, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 1.9302886724472046, | |
| "learning_rate": 2.2011979308467195e-05, | |
| "loss": 1.3041, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 2.2087652683258057, | |
| "learning_rate": 2.1909882929485437e-05, | |
| "loss": 1.3632, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 2.057499885559082, | |
| "learning_rate": 2.1807786550503677e-05, | |
| "loss": 1.3536, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 2.1920557022094727, | |
| "learning_rate": 2.170569017152192e-05, | |
| "loss": 1.3375, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 1.917410135269165, | |
| "learning_rate": 2.160359379254016e-05, | |
| "loss": 1.3396, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 1.910172462463379, | |
| "learning_rate": 2.15014974135584e-05, | |
| "loss": 1.2931, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 1.9294995069503784, | |
| "learning_rate": 2.1399401034576644e-05, | |
| "loss": 1.3, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 2.2092173099517822, | |
| "learning_rate": 2.1297304655594883e-05, | |
| "loss": 1.3196, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 2.212209939956665, | |
| "learning_rate": 2.1195208276613126e-05, | |
| "loss": 1.3623, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 2.3022515773773193, | |
| "learning_rate": 2.109311189763136e-05, | |
| "loss": 1.3402, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 2.2032854557037354, | |
| "learning_rate": 2.0991015518649604e-05, | |
| "loss": 1.3677, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 1.9251583814620972, | |
| "learning_rate": 2.0888919139667847e-05, | |
| "loss": 1.2894, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 2.1988320350646973, | |
| "learning_rate": 2.0786822760686086e-05, | |
| "loss": 1.3709, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 2.201289415359497, | |
| "learning_rate": 2.068472638170433e-05, | |
| "loss": 1.3145, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 1.992992877960205, | |
| "learning_rate": 2.058263000272257e-05, | |
| "loss": 1.3233, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 2.088419198989868, | |
| "learning_rate": 2.048053362374081e-05, | |
| "loss": 1.3669, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 1.9846084117889404, | |
| "learning_rate": 2.0378437244759053e-05, | |
| "loss": 1.3646, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 2.0262553691864014, | |
| "learning_rate": 2.0276340865777292e-05, | |
| "loss": 1.3577, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 2.1256277561187744, | |
| "learning_rate": 2.0174244486795535e-05, | |
| "loss": 1.3292, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 2.043562889099121, | |
| "learning_rate": 2.0072148107813777e-05, | |
| "loss": 1.3132, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.0755374431610107, | |
| "learning_rate": 1.9970051728832017e-05, | |
| "loss": 1.2979, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 2.0620744228363037, | |
| "learning_rate": 1.986795534985026e-05, | |
| "loss": 1.3518, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 2.1864535808563232, | |
| "learning_rate": 1.97658589708685e-05, | |
| "loss": 1.3529, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 2.22280216217041, | |
| "learning_rate": 1.966376259188674e-05, | |
| "loss": 1.3006, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 1.9707540273666382, | |
| "learning_rate": 1.9561666212904984e-05, | |
| "loss": 1.3253, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 2.134737730026245, | |
| "learning_rate": 1.9459569833923223e-05, | |
| "loss": 1.3208, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 2.4195773601531982, | |
| "learning_rate": 1.9357473454941465e-05, | |
| "loss": 1.3174, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.222219944000244, | |
| "learning_rate": 1.9255377075959708e-05, | |
| "loss": 1.3443, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 2.2541654109954834, | |
| "learning_rate": 1.9153280696977947e-05, | |
| "loss": 1.3312, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 2.124866008758545, | |
| "learning_rate": 1.905118431799619e-05, | |
| "loss": 1.3368, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 2.191096305847168, | |
| "learning_rate": 1.894908793901443e-05, | |
| "loss": 1.3447, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 2.2031023502349854, | |
| "learning_rate": 1.8846991560032672e-05, | |
| "loss": 1.3101, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 2.1442978382110596, | |
| "learning_rate": 1.8744895181050914e-05, | |
| "loss": 1.3408, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 2.281747579574585, | |
| "learning_rate": 1.8642798802069154e-05, | |
| "loss": 1.3028, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 2.128450870513916, | |
| "learning_rate": 1.8540702423087396e-05, | |
| "loss": 1.3117, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 1.925809383392334, | |
| "learning_rate": 1.8438606044105635e-05, | |
| "loss": 1.3104, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 2.0832419395446777, | |
| "learning_rate": 1.8336509665123878e-05, | |
| "loss": 1.3134, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 2.3211681842803955, | |
| "learning_rate": 1.823441328614212e-05, | |
| "loss": 1.323, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 2.2126524448394775, | |
| "learning_rate": 1.813231690716036e-05, | |
| "loss": 1.307, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 2.2093470096588135, | |
| "learning_rate": 1.8030220528178603e-05, | |
| "loss": 1.3194, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 2.089864730834961, | |
| "learning_rate": 1.7928124149196842e-05, | |
| "loss": 1.3191, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 2.3088159561157227, | |
| "learning_rate": 1.7826027770215084e-05, | |
| "loss": 1.3545, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 2.17684006690979, | |
| "learning_rate": 1.7723931391233327e-05, | |
| "loss": 1.3452, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 2.3744864463806152, | |
| "learning_rate": 1.7621835012251566e-05, | |
| "loss": 1.3193, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 2.2248189449310303, | |
| "learning_rate": 1.751973863326981e-05, | |
| "loss": 1.3183, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 2.2989003658294678, | |
| "learning_rate": 1.741764225428805e-05, | |
| "loss": 1.3086, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 2.115312099456787, | |
| "learning_rate": 1.731554587530629e-05, | |
| "loss": 1.3372, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 2.2466862201690674, | |
| "learning_rate": 1.721344949632453e-05, | |
| "loss": 1.3126, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 2.152052164077759, | |
| "learning_rate": 1.711135311734277e-05, | |
| "loss": 1.3127, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 2.276834487915039, | |
| "learning_rate": 1.7009256738361012e-05, | |
| "loss": 1.2936, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 2.3417012691497803, | |
| "learning_rate": 1.6907160359379254e-05, | |
| "loss": 1.2999, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 2.0875630378723145, | |
| "learning_rate": 1.6805063980397494e-05, | |
| "loss": 1.3186, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 2.3512613773345947, | |
| "learning_rate": 1.6702967601415736e-05, | |
| "loss": 1.3242, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 2.24100399017334, | |
| "learning_rate": 1.6600871222433975e-05, | |
| "loss": 1.3525, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.2629716396331787, | |
| "learning_rate": 1.6498774843452218e-05, | |
| "loss": 1.3386, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 2.21623158454895, | |
| "learning_rate": 1.639667846447046e-05, | |
| "loss": 1.3263, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 2.26880145072937, | |
| "learning_rate": 1.62945820854887e-05, | |
| "loss": 1.3296, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 2.2265172004699707, | |
| "learning_rate": 1.6192485706506942e-05, | |
| "loss": 1.3424, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 2.2084670066833496, | |
| "learning_rate": 1.6090389327525185e-05, | |
| "loss": 1.333, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 2.146636486053467, | |
| "learning_rate": 1.5988292948543424e-05, | |
| "loss": 1.324, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 2.2078332901000977, | |
| "learning_rate": 1.5886196569561667e-05, | |
| "loss": 1.3032, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 2.1620240211486816, | |
| "learning_rate": 1.5784100190579906e-05, | |
| "loss": 1.3679, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 2.176711082458496, | |
| "learning_rate": 1.568200381159815e-05, | |
| "loss": 1.3096, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.3900365829467773, | |
| "learning_rate": 1.557990743261639e-05, | |
| "loss": 1.3396, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 2.100839853286743, | |
| "learning_rate": 1.547781105363463e-05, | |
| "loss": 1.3264, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 2.218968629837036, | |
| "learning_rate": 1.5375714674652873e-05, | |
| "loss": 1.3195, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 2.4888713359832764, | |
| "learning_rate": 1.5273618295671112e-05, | |
| "loss": 1.295, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 2.2046141624450684, | |
| "learning_rate": 1.5171521916689355e-05, | |
| "loss": 1.3003, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 2.1647400856018066, | |
| "learning_rate": 1.5069425537707598e-05, | |
| "loss": 1.2842, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 2.187425136566162, | |
| "learning_rate": 1.4967329158725839e-05, | |
| "loss": 1.3049, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 2.2171578407287598, | |
| "learning_rate": 1.486523277974408e-05, | |
| "loss": 1.2987, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 2.1128668785095215, | |
| "learning_rate": 1.476313640076232e-05, | |
| "loss": 1.2926, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 2.1411571502685547, | |
| "learning_rate": 1.4661040021780561e-05, | |
| "loss": 1.3205, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 2.165693521499634, | |
| "learning_rate": 1.4558943642798804e-05, | |
| "loss": 1.3014, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 2.217212200164795, | |
| "learning_rate": 1.4456847263817045e-05, | |
| "loss": 1.3198, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 2.3008174896240234, | |
| "learning_rate": 1.4354750884835284e-05, | |
| "loss": 1.2913, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 2.0766916275024414, | |
| "learning_rate": 1.4252654505853525e-05, | |
| "loss": 1.2867, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 2.187500476837158, | |
| "learning_rate": 1.4150558126871766e-05, | |
| "loss": 1.3605, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 2.143425226211548, | |
| "learning_rate": 1.4048461747890009e-05, | |
| "loss": 1.3432, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 2.3163678646087646, | |
| "learning_rate": 1.394636536890825e-05, | |
| "loss": 1.3338, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 2.1427390575408936, | |
| "learning_rate": 1.384426898992649e-05, | |
| "loss": 1.3201, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 2.3347136974334717, | |
| "learning_rate": 1.3742172610944731e-05, | |
| "loss": 1.3103, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 2.1402597427368164, | |
| "learning_rate": 1.3640076231962974e-05, | |
| "loss": 1.3339, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 2.13971209526062, | |
| "learning_rate": 1.3537979852981215e-05, | |
| "loss": 1.3285, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 2.146343231201172, | |
| "learning_rate": 1.3435883473999456e-05, | |
| "loss": 1.3313, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 2.221480369567871, | |
| "learning_rate": 1.3333787095017697e-05, | |
| "loss": 1.3038, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 2.243988275527954, | |
| "learning_rate": 1.323169071603594e-05, | |
| "loss": 1.3234, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 2.0634615421295166, | |
| "learning_rate": 1.312959433705418e-05, | |
| "loss": 1.2806, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 2.2551660537719727, | |
| "learning_rate": 1.3027497958072421e-05, | |
| "loss": 1.3113, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 2.1955995559692383, | |
| "learning_rate": 1.2925401579090662e-05, | |
| "loss": 1.3229, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 2.1404623985290527, | |
| "learning_rate": 1.2823305200108903e-05, | |
| "loss": 1.2855, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 2.2120893001556396, | |
| "learning_rate": 1.2721208821127146e-05, | |
| "loss": 1.3126, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 2.3724899291992188, | |
| "learning_rate": 1.2619112442145386e-05, | |
| "loss": 1.307, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 2.3382725715637207, | |
| "learning_rate": 1.2517016063163627e-05, | |
| "loss": 1.3255, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 2.240473508834839, | |
| "learning_rate": 1.2414919684181867e-05, | |
| "loss": 1.339, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 2.2863121032714844, | |
| "learning_rate": 1.231282330520011e-05, | |
| "loss": 1.3023, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 2.3358094692230225, | |
| "learning_rate": 1.221072692621835e-05, | |
| "loss": 1.293, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 2.1806859970092773, | |
| "learning_rate": 1.2108630547236591e-05, | |
| "loss": 1.2709, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 2.169222593307495, | |
| "learning_rate": 1.2006534168254832e-05, | |
| "loss": 1.2991, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 2.1876134872436523, | |
| "learning_rate": 1.1904437789273075e-05, | |
| "loss": 1.2875, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 2.261347532272339, | |
| "learning_rate": 1.1802341410291316e-05, | |
| "loss": 1.3095, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 2.2739272117614746, | |
| "learning_rate": 1.1700245031309556e-05, | |
| "loss": 1.3498, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 2.3991880416870117, | |
| "learning_rate": 1.1598148652327797e-05, | |
| "loss": 1.3053, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 2.3285093307495117, | |
| "learning_rate": 1.1496052273346038e-05, | |
| "loss": 1.3284, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 2.225856065750122, | |
| "learning_rate": 1.1393955894364281e-05, | |
| "loss": 1.2987, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 2.265589952468872, | |
| "learning_rate": 1.1291859515382522e-05, | |
| "loss": 1.3131, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 2.41005802154541, | |
| "learning_rate": 1.1189763136400763e-05, | |
| "loss": 1.3106, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.9434266090393066, | |
| "learning_rate": 1.1087666757419004e-05, | |
| "loss": 1.2548, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 2.1135506629943848, | |
| "learning_rate": 1.0985570378437246e-05, | |
| "loss": 1.2141, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 2.289918899536133, | |
| "learning_rate": 1.0883473999455487e-05, | |
| "loss": 1.2105, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 2.446237802505493, | |
| "learning_rate": 1.0781377620473728e-05, | |
| "loss": 1.2309, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 2.164933681488037, | |
| "learning_rate": 1.0679281241491969e-05, | |
| "loss": 1.2119, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 2.468120813369751, | |
| "learning_rate": 1.057718486251021e-05, | |
| "loss": 1.222, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 2.208359479904175, | |
| "learning_rate": 1.0475088483528451e-05, | |
| "loss": 1.2341, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 2.425952196121216, | |
| "learning_rate": 1.0372992104546692e-05, | |
| "loss": 1.2579, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 2.4723472595214844, | |
| "learning_rate": 1.0270895725564933e-05, | |
| "loss": 1.2541, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 2.573694944381714, | |
| "learning_rate": 1.0168799346583174e-05, | |
| "loss": 1.2233, | |
| "step": 5675 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 2.234358072280884, | |
| "learning_rate": 1.0066702967601416e-05, | |
| "loss": 1.2408, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 2.3570847511291504, | |
| "learning_rate": 9.964606588619657e-06, | |
| "loss": 1.2057, | |
| "step": 5725 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 2.402945041656494, | |
| "learning_rate": 9.862510209637898e-06, | |
| "loss": 1.2441, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 2.3379828929901123, | |
| "learning_rate": 9.760413830656139e-06, | |
| "loss": 1.2095, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 2.4580986499786377, | |
| "learning_rate": 9.658317451674382e-06, | |
| "loss": 1.2138, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 2.361599922180176, | |
| "learning_rate": 9.556221072692623e-06, | |
| "loss": 1.2519, | |
| "step": 5825 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 2.320232629776001, | |
| "learning_rate": 9.454124693710863e-06, | |
| "loss": 1.2443, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 2.411405086517334, | |
| "learning_rate": 9.352028314729104e-06, | |
| "loss": 1.2062, | |
| "step": 5875 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 2.377734661102295, | |
| "learning_rate": 9.254015790906616e-06, | |
| "loss": 1.2335, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "grad_norm": 2.619082450866699, | |
| "learning_rate": 9.151919411924856e-06, | |
| "loss": 1.2421, | |
| "step": 5925 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 2.4038760662078857, | |
| "learning_rate": 9.049823032943099e-06, | |
| "loss": 1.2226, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 2.423957109451294, | |
| "learning_rate": 8.94772665396134e-06, | |
| "loss": 1.208, | |
| "step": 5975 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 2.4431958198547363, | |
| "learning_rate": 8.845630274979581e-06, | |
| "loss": 1.2105, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "grad_norm": 2.4713828563690186, | |
| "learning_rate": 8.743533895997822e-06, | |
| "loss": 1.2297, | |
| "step": 6025 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 2.3229868412017822, | |
| "learning_rate": 8.641437517016064e-06, | |
| "loss": 1.2162, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": 2.483553886413574, | |
| "learning_rate": 8.539341138034305e-06, | |
| "loss": 1.25, | |
| "step": 6075 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 2.567758083343506, | |
| "learning_rate": 8.437244759052546e-06, | |
| "loss": 1.2351, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 2.5052988529205322, | |
| "learning_rate": 8.335148380070787e-06, | |
| "loss": 1.2068, | |
| "step": 6125 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "grad_norm": 2.3063817024230957, | |
| "learning_rate": 8.233052001089028e-06, | |
| "loss": 1.2116, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": 2.531585931777954, | |
| "learning_rate": 8.13095562210727e-06, | |
| "loss": 1.1786, | |
| "step": 6175 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 2.1010377407073975, | |
| "learning_rate": 8.028859243125512e-06, | |
| "loss": 1.2529, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "grad_norm": 2.465160369873047, | |
| "learning_rate": 7.926762864143753e-06, | |
| "loss": 1.221, | |
| "step": 6225 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 2.3965258598327637, | |
| "learning_rate": 7.824666485161992e-06, | |
| "loss": 1.2492, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "grad_norm": 2.4250175952911377, | |
| "learning_rate": 7.722570106180234e-06, | |
| "loss": 1.2392, | |
| "step": 6275 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 2.4409801959991455, | |
| "learning_rate": 7.620473727198476e-06, | |
| "loss": 1.2195, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 2.476854085922241, | |
| "learning_rate": 7.518377348216717e-06, | |
| "loss": 1.2412, | |
| "step": 6325 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 2.489551305770874, | |
| "learning_rate": 7.416280969234958e-06, | |
| "loss": 1.262, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "grad_norm": 2.5215299129486084, | |
| "learning_rate": 7.314184590253199e-06, | |
| "loss": 1.2228, | |
| "step": 6375 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "grad_norm": 2.517064332962036, | |
| "learning_rate": 7.21208821127144e-06, | |
| "loss": 1.2175, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 2.503761053085327, | |
| "learning_rate": 7.109991832289682e-06, | |
| "loss": 1.2174, | |
| "step": 6425 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "grad_norm": 2.4488444328308105, | |
| "learning_rate": 7.0078954533079225e-06, | |
| "loss": 1.2293, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": 2.539790391921997, | |
| "learning_rate": 6.905799074326164e-06, | |
| "loss": 1.2505, | |
| "step": 6475 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "grad_norm": 2.5282349586486816, | |
| "learning_rate": 6.803702695344405e-06, | |
| "loss": 1.2311, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 2.55580472946167, | |
| "learning_rate": 6.701606316362647e-06, | |
| "loss": 1.2493, | |
| "step": 6525 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "grad_norm": 2.6252071857452393, | |
| "learning_rate": 6.599509937380888e-06, | |
| "loss": 1.2434, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 2.510460138320923, | |
| "learning_rate": 6.49741355839913e-06, | |
| "loss": 1.2583, | |
| "step": 6575 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 2.6028640270233154, | |
| "learning_rate": 6.39531717941737e-06, | |
| "loss": 1.2593, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 2.2769548892974854, | |
| "learning_rate": 6.2932208004356115e-06, | |
| "loss": 1.2259, | |
| "step": 6625 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 2.4939069747924805, | |
| "learning_rate": 6.191124421453852e-06, | |
| "loss": 1.1955, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "grad_norm": 2.3038108348846436, | |
| "learning_rate": 6.089028042472093e-06, | |
| "loss": 1.2067, | |
| "step": 6675 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "grad_norm": 2.5069258213043213, | |
| "learning_rate": 5.986931663490335e-06, | |
| "loss": 1.2033, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 2.5253121852874756, | |
| "learning_rate": 5.884835284508576e-06, | |
| "loss": 1.245, | |
| "step": 6725 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 2.492309808731079, | |
| "learning_rate": 5.782738905526818e-06, | |
| "loss": 1.2218, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "grad_norm": 2.399568796157837, | |
| "learning_rate": 5.680642526545059e-06, | |
| "loss": 1.2092, | |
| "step": 6775 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 2.5190510749816895, | |
| "learning_rate": 5.5785461475633005e-06, | |
| "loss": 1.2157, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "grad_norm": 2.393317937850952, | |
| "learning_rate": 5.4764497685815405e-06, | |
| "loss": 1.2373, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 2.5895726680755615, | |
| "learning_rate": 5.374353389599782e-06, | |
| "loss": 1.2178, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "grad_norm": 2.3802356719970703, | |
| "learning_rate": 5.272257010618023e-06, | |
| "loss": 1.1854, | |
| "step": 6875 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 2.3995566368103027, | |
| "learning_rate": 5.170160631636265e-06, | |
| "loss": 1.2082, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 2.3092782497406006, | |
| "learning_rate": 5.068064252654506e-06, | |
| "loss": 1.2167, | |
| "step": 6925 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "grad_norm": 2.5264272689819336, | |
| "learning_rate": 4.965967873672747e-06, | |
| "loss": 1.2114, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 2.6355152130126953, | |
| "learning_rate": 4.863871494690989e-06, | |
| "loss": 1.205, | |
| "step": 6975 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 2.6680080890655518, | |
| "learning_rate": 4.7617751157092295e-06, | |
| "loss": 1.2288, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "grad_norm": 2.520815134048462, | |
| "learning_rate": 4.659678736727471e-06, | |
| "loss": 1.2385, | |
| "step": 7025 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "grad_norm": 2.6535727977752686, | |
| "learning_rate": 4.557582357745712e-06, | |
| "loss": 1.2037, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 2.6128251552581787, | |
| "learning_rate": 4.455485978763953e-06, | |
| "loss": 1.2381, | |
| "step": 7075 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "grad_norm": 2.3994832038879395, | |
| "learning_rate": 4.353389599782194e-06, | |
| "loss": 1.1994, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 2.610602617263794, | |
| "learning_rate": 4.251293220800436e-06, | |
| "loss": 1.2032, | |
| "step": 7125 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "grad_norm": 2.55776309967041, | |
| "learning_rate": 4.149196841818677e-06, | |
| "loss": 1.2614, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 2.387730121612549, | |
| "learning_rate": 4.0471004628369185e-06, | |
| "loss": 1.2142, | |
| "step": 7175 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "grad_norm": 2.4818918704986572, | |
| "learning_rate": 3.945004083855159e-06, | |
| "loss": 1.1894, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 2.4564781188964844, | |
| "learning_rate": 3.842907704873401e-06, | |
| "loss": 1.2254, | |
| "step": 7225 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 2.775742769241333, | |
| "learning_rate": 3.7408113258916417e-06, | |
| "loss": 1.2283, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 2.6153032779693604, | |
| "learning_rate": 3.638714946909883e-06, | |
| "loss": 1.2595, | |
| "step": 7275 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 2.6812705993652344, | |
| "learning_rate": 3.5366185679281243e-06, | |
| "loss": 1.2156, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "grad_norm": 2.290558338165283, | |
| "learning_rate": 3.4345221889463657e-06, | |
| "loss": 1.2215, | |
| "step": 7325 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 2.6138980388641357, | |
| "learning_rate": 3.332425809964607e-06, | |
| "loss": 1.2172, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": 2.496048927307129, | |
| "learning_rate": 3.230329430982848e-06, | |
| "loss": 1.2826, | |
| "step": 7375 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "grad_norm": 2.5548458099365234, | |
| "learning_rate": 3.128233052001089e-06, | |
| "loss": 1.2524, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "grad_norm": 2.4902689456939697, | |
| "learning_rate": 3.02613667301933e-06, | |
| "loss": 1.2359, | |
| "step": 7425 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 2.5479485988616943, | |
| "learning_rate": 2.9240402940375716e-06, | |
| "loss": 1.2085, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 2.4236271381378174, | |
| "learning_rate": 2.8219439150558125e-06, | |
| "loss": 1.2098, | |
| "step": 7475 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 2.533890724182129, | |
| "learning_rate": 2.719847536074054e-06, | |
| "loss": 1.1894, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "grad_norm": 2.7152767181396484, | |
| "learning_rate": 2.617751157092295e-06, | |
| "loss": 1.2183, | |
| "step": 7525 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "grad_norm": 2.515911102294922, | |
| "learning_rate": 2.5156547781105365e-06, | |
| "loss": 1.2222, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "grad_norm": 2.4286630153656006, | |
| "learning_rate": 2.413558399128778e-06, | |
| "loss": 1.2213, | |
| "step": 7575 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 2.542311429977417, | |
| "learning_rate": 2.3114620201470188e-06, | |
| "loss": 1.2121, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 2.5168519020080566, | |
| "learning_rate": 2.20936564116526e-06, | |
| "loss": 1.2178, | |
| "step": 7625 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "grad_norm": 2.389608383178711, | |
| "learning_rate": 2.1072692621835014e-06, | |
| "loss": 1.2118, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "grad_norm": 2.4580190181732178, | |
| "learning_rate": 2.005172883201743e-06, | |
| "loss": 1.2192, | |
| "step": 7675 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "grad_norm": 2.519462823867798, | |
| "learning_rate": 1.9030765042199835e-06, | |
| "loss": 1.1993, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 2.493283748626709, | |
| "learning_rate": 1.800980125238225e-06, | |
| "loss": 1.2079, | |
| "step": 7725 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": 2.400961399078369, | |
| "learning_rate": 1.6988837462564662e-06, | |
| "loss": 1.2182, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "grad_norm": 2.7420430183410645, | |
| "learning_rate": 1.5967873672747073e-06, | |
| "loss": 1.2169, | |
| "step": 7775 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "grad_norm": 2.488145351409912, | |
| "learning_rate": 1.4946909882929484e-06, | |
| "loss": 1.2227, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 2.531705856323242, | |
| "learning_rate": 1.3925946093111898e-06, | |
| "loss": 1.2156, | |
| "step": 7825 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 2.5031278133392334, | |
| "learning_rate": 1.2904982303294311e-06, | |
| "loss": 1.2055, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "grad_norm": 2.546499729156494, | |
| "learning_rate": 1.1884018513476723e-06, | |
| "loss": 1.2362, | |
| "step": 7875 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 2.5064220428466797, | |
| "learning_rate": 1.0863054723659136e-06, | |
| "loss": 1.1923, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "grad_norm": 2.7137672901153564, | |
| "learning_rate": 9.842090933841545e-07, | |
| "loss": 1.2136, | |
| "step": 7925 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "grad_norm": 2.4040451049804688, | |
| "learning_rate": 8.821127144023959e-07, | |
| "loss": 1.1781, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 2.744879961013794, | |
| "learning_rate": 7.800163354206371e-07, | |
| "loss": 1.2054, | |
| "step": 7975 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "grad_norm": 2.4355337619781494, | |
| "learning_rate": 6.779199564388783e-07, | |
| "loss": 1.221, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "grad_norm": 2.56799054145813, | |
| "learning_rate": 5.758235774571195e-07, | |
| "loss": 1.1876, | |
| "step": 8025 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 2.6261682510375977, | |
| "learning_rate": 4.7372719847536076e-07, | |
| "loss": 1.1994, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "grad_norm": 2.609344482421875, | |
| "learning_rate": 3.7163081949360194e-07, | |
| "loss": 1.2013, | |
| "step": 8075 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "grad_norm": 2.4968795776367188, | |
| "learning_rate": 2.695344405118432e-07, | |
| "loss": 1.206, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "grad_norm": 2.639547109603882, | |
| "learning_rate": 1.674380615300844e-07, | |
| "loss": 1.2188, | |
| "step": 8125 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "grad_norm": 2.6444761753082275, | |
| "learning_rate": 6.534168254832563e-08, | |
| "loss": 1.2206, | |
| "step": 8150 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 8163, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.4349115244339528e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |