Instructions to use Purino/scam-ads-detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Purino/scam-ads-detection with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-E4B-it-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "Purino/scam-ads-detection") - Transformers
How to use Purino/scam-ads-detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Purino/scam-ads-detection") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Purino/scam-ads-detection", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Purino/scam-ads-detection with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Purino/scam-ads-detection" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Purino/scam-ads-detection", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Purino/scam-ads-detection
- SGLang
How to use Purino/scam-ads-detection 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 "Purino/scam-ads-detection" \ --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": "Purino/scam-ads-detection", "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 "Purino/scam-ads-detection" \ --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": "Purino/scam-ads-detection", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use Purino/scam-ads-detection with Docker Model Runner:
docker model run hf.co/Purino/scam-ads-detection
| { | |
| "best_global_step": 738, | |
| "best_metric": 1.9550799131393433, | |
| "best_model_checkpoint": "/content/drive/MyDrive/NCKH/outputs/gemma-4-E4B-it-unsloth-bnb-4bit-lora/checkpoint-738", | |
| "epoch": 5.0, | |
| "eval_steps": 25, | |
| "global_step": 1845, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02710027100271003, | |
| "grad_norm": 22.728397369384766, | |
| "learning_rate": 2.432432432432433e-06, | |
| "loss": 11.919314575195312, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05420054200542006, | |
| "grad_norm": 22.40118408203125, | |
| "learning_rate": 5.135135135135136e-06, | |
| "loss": 11.23604507446289, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08130081300813008, | |
| "grad_norm": 23.464128494262695, | |
| "learning_rate": 7.837837837837838e-06, | |
| "loss": 9.405374145507812, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10840108401084012, | |
| "grad_norm": 10.659221649169922, | |
| "learning_rate": 1.0540540540540541e-05, | |
| "loss": 6.506309509277344, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13550135501355012, | |
| "grad_norm": 7.267085075378418, | |
| "learning_rate": 1.3243243243243244e-05, | |
| "loss": 3.981406402587891, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16260162601626016, | |
| "grad_norm": 7.117081165313721, | |
| "learning_rate": 1.5945945945945947e-05, | |
| "loss": 2.373625373840332, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1897018970189702, | |
| "grad_norm": 1.1280121803283691, | |
| "learning_rate": 1.864864864864865e-05, | |
| "loss": 1.5003188133239747, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21680216802168023, | |
| "grad_norm": 2.7155864238739014, | |
| "learning_rate": 2.1351351351351353e-05, | |
| "loss": 1.072439193725586, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 3.442587375640869, | |
| "learning_rate": 2.4054054054054056e-05, | |
| "loss": 1.1835954666137696, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.27100271002710025, | |
| "grad_norm": 0.24733102321624756, | |
| "learning_rate": 2.6756756756756756e-05, | |
| "loss": 0.5424500942230225, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2981029810298103, | |
| "grad_norm": 2.9170358180999756, | |
| "learning_rate": 2.945945945945946e-05, | |
| "loss": 1.1580610275268555, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": 2.135418176651001, | |
| "learning_rate": 3.2162162162162165e-05, | |
| "loss": 0.7624737739562988, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3523035230352303, | |
| "grad_norm": 2.1784112453460693, | |
| "learning_rate": 3.486486486486487e-05, | |
| "loss": 0.769621467590332, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3794037940379404, | |
| "grad_norm": 3.46102237701416, | |
| "learning_rate": 3.756756756756757e-05, | |
| "loss": 0.9935452461242675, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4065040650406504, | |
| "grad_norm": 2.1675102710723877, | |
| "learning_rate": 4.0270270270270274e-05, | |
| "loss": 0.6819512844085693, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.43360433604336046, | |
| "grad_norm": 2.2418923377990723, | |
| "learning_rate": 4.297297297297298e-05, | |
| "loss": 0.6065433502197266, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.46070460704607047, | |
| "grad_norm": 1.215096116065979, | |
| "learning_rate": 4.567567567567568e-05, | |
| "loss": 0.9963153839111328, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 1.9262304306030273, | |
| "learning_rate": 4.837837837837838e-05, | |
| "loss": 0.7181135177612304, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5149051490514905, | |
| "grad_norm": 2.643014669418335, | |
| "learning_rate": 4.987951807228916e-05, | |
| "loss": 0.44757895469665526, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5420054200542005, | |
| "grad_norm": 1.5491818189620972, | |
| "learning_rate": 4.957831325301205e-05, | |
| "loss": 0.6427767276763916, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5691056910569106, | |
| "grad_norm": 2.8546581268310547, | |
| "learning_rate": 4.927710843373494e-05, | |
| "loss": 0.7251592159271241, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5962059620596206, | |
| "grad_norm": 0.9586758613586426, | |
| "learning_rate": 4.8975903614457834e-05, | |
| "loss": 0.503507137298584, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6233062330623306, | |
| "grad_norm": 2.097965717315674, | |
| "learning_rate": 4.8674698795180725e-05, | |
| "loss": 0.6909904956817627, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": 2.5051257610321045, | |
| "learning_rate": 4.837349397590362e-05, | |
| "loss": 0.486527681350708, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6775067750677507, | |
| "grad_norm": 0.34357234835624695, | |
| "learning_rate": 4.807228915662651e-05, | |
| "loss": 0.4830454349517822, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7046070460704607, | |
| "grad_norm": 2.0146594047546387, | |
| "learning_rate": 4.7771084337349394e-05, | |
| "loss": 0.5729067325592041, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.0874701589345932, | |
| "learning_rate": 4.746987951807229e-05, | |
| "loss": 0.4739652156829834, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7588075880758808, | |
| "grad_norm": 2.5818629264831543, | |
| "learning_rate": 4.7168674698795185e-05, | |
| "loss": 0.6038558006286621, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7859078590785907, | |
| "grad_norm": 1.2498514652252197, | |
| "learning_rate": 4.686746987951807e-05, | |
| "loss": 0.5109341144561768, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8130081300813008, | |
| "grad_norm": 1.7125121355056763, | |
| "learning_rate": 4.656626506024097e-05, | |
| "loss": 0.485601806640625, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8401084010840109, | |
| "grad_norm": 1.4098396301269531, | |
| "learning_rate": 4.626506024096386e-05, | |
| "loss": 0.38882980346679685, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8672086720867209, | |
| "grad_norm": 1.7848849296569824, | |
| "learning_rate": 4.5963855421686746e-05, | |
| "loss": 0.7246835708618165, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8943089430894309, | |
| "grad_norm": 1.9683917760849, | |
| "learning_rate": 4.566265060240964e-05, | |
| "loss": 0.49833040237426757, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9214092140921409, | |
| "grad_norm": 1.1137908697128296, | |
| "learning_rate": 4.5361445783132537e-05, | |
| "loss": 0.5018684387207031, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.948509485094851, | |
| "grad_norm": 1.7771272659301758, | |
| "learning_rate": 4.506024096385542e-05, | |
| "loss": 0.5021445751190186, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 1.9330641031265259, | |
| "learning_rate": 4.4759036144578314e-05, | |
| "loss": 0.5039750099182129, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.9937856197357178, | |
| "eval_runtime": 34.3095, | |
| "eval_samples_per_second": 10.755, | |
| "eval_steps_per_second": 1.37, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.002710027100271, | |
| "grad_norm": 0.005452820099890232, | |
| "learning_rate": 4.4457831325301206e-05, | |
| "loss": 0.40453200340270995, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.029810298102981, | |
| "grad_norm": 0.7742593288421631, | |
| "learning_rate": 4.41566265060241e-05, | |
| "loss": 0.4177242755889893, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.056910569105691, | |
| "grad_norm": 0.011842379346489906, | |
| "learning_rate": 4.385542168674699e-05, | |
| "loss": 0.4176949501037598, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.084010840108401, | |
| "grad_norm": 1.8473925590515137, | |
| "learning_rate": 4.355421686746988e-05, | |
| "loss": 0.45896615982055666, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 1.9900813102722168, | |
| "learning_rate": 4.325301204819277e-05, | |
| "loss": 0.5105923175811767, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.1382113821138211, | |
| "grad_norm": 1.7401782274246216, | |
| "learning_rate": 4.2951807228915665e-05, | |
| "loss": 0.2536778450012207, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.165311653116531, | |
| "grad_norm": 1.3964563608169556, | |
| "learning_rate": 4.265060240963856e-05, | |
| "loss": 0.48720102310180663, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.1924119241192412, | |
| "grad_norm": 0.01112714409828186, | |
| "learning_rate": 4.234939759036145e-05, | |
| "loss": 0.43120126724243163, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "grad_norm": 0.6834083795547485, | |
| "learning_rate": 4.204819277108434e-05, | |
| "loss": 0.3716581344604492, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.2466124661246614, | |
| "grad_norm": 1.7361128330230713, | |
| "learning_rate": 4.174698795180723e-05, | |
| "loss": 0.4478722095489502, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.2737127371273713, | |
| "grad_norm": 1.3282142877578735, | |
| "learning_rate": 4.1445783132530125e-05, | |
| "loss": 0.40467066764831544, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.3008130081300813, | |
| "grad_norm": 1.0177502632141113, | |
| "learning_rate": 4.114457831325301e-05, | |
| "loss": 0.4328292369842529, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.3279132791327912, | |
| "grad_norm": 2.367649793624878, | |
| "learning_rate": 4.084337349397591e-05, | |
| "loss": 0.47493462562561034, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.3550135501355014, | |
| "grad_norm": 2.39469838142395, | |
| "learning_rate": 4.05421686746988e-05, | |
| "loss": 0.42293686866760255, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3821138211382114, | |
| "grad_norm": 1.8532780408859253, | |
| "learning_rate": 4.0240963855421686e-05, | |
| "loss": 0.4274147987365723, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.4092140921409215, | |
| "grad_norm": 2.1795737743377686, | |
| "learning_rate": 3.993975903614458e-05, | |
| "loss": 0.4310306549072266, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.4363143631436315, | |
| "grad_norm": 1.617717981338501, | |
| "learning_rate": 3.9638554216867476e-05, | |
| "loss": 0.4066213607788086, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 1.9892994165420532, | |
| "learning_rate": 3.933734939759036e-05, | |
| "loss": 0.33212642669677733, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.4905149051490514, | |
| "grad_norm": 1.493666648864746, | |
| "learning_rate": 3.903614457831325e-05, | |
| "loss": 0.21177103519439697, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.5176151761517616, | |
| "grad_norm": 4.7155375480651855, | |
| "learning_rate": 3.8734939759036145e-05, | |
| "loss": 0.3580620527267456, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.5447154471544715, | |
| "grad_norm": 1.7162026166915894, | |
| "learning_rate": 3.843373493975904e-05, | |
| "loss": 0.38322744369506834, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.5718157181571817, | |
| "grad_norm": 0.0026090233586728573, | |
| "learning_rate": 3.813253012048193e-05, | |
| "loss": 0.3508410930633545, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.5989159891598916, | |
| "grad_norm": 1.2260611057281494, | |
| "learning_rate": 3.783132530120482e-05, | |
| "loss": 0.398317551612854, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.6260162601626016, | |
| "grad_norm": 1.6680866479873657, | |
| "learning_rate": 3.753012048192771e-05, | |
| "loss": 0.29882686138153075, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6531165311653115, | |
| "grad_norm": 1.2418262958526611, | |
| "learning_rate": 3.7228915662650605e-05, | |
| "loss": 0.36798510551452634, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.6802168021680217, | |
| "grad_norm": 1.9428493976593018, | |
| "learning_rate": 3.69277108433735e-05, | |
| "loss": 0.538023042678833, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.7073170731707317, | |
| "grad_norm": 1.5121231079101562, | |
| "learning_rate": 3.662650602409639e-05, | |
| "loss": 0.3228819131851196, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.7344173441734418, | |
| "grad_norm": 0.003926251549273729, | |
| "learning_rate": 3.632530120481928e-05, | |
| "loss": 0.3228945732116699, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.7615176151761518, | |
| "grad_norm": 2.2107574939727783, | |
| "learning_rate": 3.602409638554217e-05, | |
| "loss": 0.25911893844604494, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.7886178861788617, | |
| "grad_norm": 1.656571388244629, | |
| "learning_rate": 3.572289156626506e-05, | |
| "loss": 0.3195812463760376, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.8157181571815717, | |
| "grad_norm": 1.494348168373108, | |
| "learning_rate": 3.5421686746987956e-05, | |
| "loss": 0.4198177337646484, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.8428184281842819, | |
| "grad_norm": 1.5578944683074951, | |
| "learning_rate": 3.512048192771085e-05, | |
| "loss": 0.30634071826934817, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.8699186991869918, | |
| "grad_norm": 1.459014654159546, | |
| "learning_rate": 3.4819277108433733e-05, | |
| "loss": 0.2012237787246704, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.897018970189702, | |
| "grad_norm": 1.9899115562438965, | |
| "learning_rate": 3.4518072289156625e-05, | |
| "loss": 0.3630890130996704, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.924119241192412, | |
| "grad_norm": 1.7434362173080444, | |
| "learning_rate": 3.4216867469879524e-05, | |
| "loss": 0.38361058235168455, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 2.506061315536499, | |
| "learning_rate": 3.391566265060241e-05, | |
| "loss": 0.36006913185119627, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.9783197831978319, | |
| "grad_norm": 1.2967313528060913, | |
| "learning_rate": 3.36144578313253e-05, | |
| "loss": 0.43243207931518557, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.9550799131393433, | |
| "eval_runtime": 16.9034, | |
| "eval_samples_per_second": 21.83, | |
| "eval_steps_per_second": 2.781, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 2.005420054200542, | |
| "grad_norm": 1.7908809185028076, | |
| "learning_rate": 3.331325301204819e-05, | |
| "loss": 0.3564627647399902, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.032520325203252, | |
| "grad_norm": 2.3227219581604004, | |
| "learning_rate": 3.3012048192771085e-05, | |
| "loss": 0.2629601240158081, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.059620596205962, | |
| "grad_norm": 1.3656333684921265, | |
| "learning_rate": 3.271084337349398e-05, | |
| "loss": 0.23673155307769775, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.086720867208672, | |
| "grad_norm": 0.779041051864624, | |
| "learning_rate": 3.240963855421687e-05, | |
| "loss": 0.2373396635055542, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.113821138211382, | |
| "grad_norm": 2.1576573848724365, | |
| "learning_rate": 3.210843373493976e-05, | |
| "loss": 0.30527400970458984, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.140921409214092, | |
| "grad_norm": 0.8158577084541321, | |
| "learning_rate": 3.180722891566265e-05, | |
| "loss": 0.2940396785736084, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.168021680216802, | |
| "grad_norm": 1.594860553741455, | |
| "learning_rate": 3.1506024096385545e-05, | |
| "loss": 0.20990023612976075, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.1951219512195124, | |
| "grad_norm": 0.4698055386543274, | |
| "learning_rate": 3.1204819277108436e-05, | |
| "loss": 0.26699907779693605, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 2.378993034362793, | |
| "learning_rate": 3.090361445783133e-05, | |
| "loss": 0.27274370193481445, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.2493224932249323, | |
| "grad_norm": 1.2885280847549438, | |
| "learning_rate": 3.060240963855422e-05, | |
| "loss": 0.3429036855697632, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.2764227642276422, | |
| "grad_norm": 1.4905011653900146, | |
| "learning_rate": 3.0301204819277112e-05, | |
| "loss": 0.2828040361404419, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.303523035230352, | |
| "grad_norm": 1.5921467542648315, | |
| "learning_rate": 3e-05, | |
| "loss": 0.35811243057250974, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.330623306233062, | |
| "grad_norm": 1.7875797748565674, | |
| "learning_rate": 2.9698795180722893e-05, | |
| "loss": 0.32458696365356443, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.3577235772357725, | |
| "grad_norm": 1.420148491859436, | |
| "learning_rate": 2.9397590361445788e-05, | |
| "loss": 0.2281116485595703, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.3848238482384825, | |
| "grad_norm": 1.8053313493728638, | |
| "learning_rate": 2.9096385542168677e-05, | |
| "loss": 0.2463682174682617, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.4119241192411924, | |
| "grad_norm": 1.9201525449752808, | |
| "learning_rate": 2.879518072289157e-05, | |
| "loss": 0.22586345672607422, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.4390243902439024, | |
| "grad_norm": 0.002116014016792178, | |
| "learning_rate": 2.849397590361446e-05, | |
| "loss": 0.21752567291259767, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.4661246612466123, | |
| "grad_norm": 0.8621284365653992, | |
| "learning_rate": 2.819277108433735e-05, | |
| "loss": 0.22801313400268555, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.4932249322493227, | |
| "grad_norm": 1.477442979812622, | |
| "learning_rate": 2.7891566265060244e-05, | |
| "loss": 0.15715408325195312, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.5203252032520327, | |
| "grad_norm": 1.900180459022522, | |
| "learning_rate": 2.7590361445783136e-05, | |
| "loss": 0.3475168466567993, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.5474254742547426, | |
| "grad_norm": 0.9240522980690002, | |
| "learning_rate": 2.7289156626506025e-05, | |
| "loss": 0.3510331630706787, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.5745257452574526, | |
| "grad_norm": 0.0004255448584444821, | |
| "learning_rate": 2.6987951807228917e-05, | |
| "loss": 0.23643341064453124, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.6016260162601625, | |
| "grad_norm": 2.2889161109924316, | |
| "learning_rate": 2.6686746987951812e-05, | |
| "loss": 0.3139182567596436, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.6287262872628725, | |
| "grad_norm": 2.3648195266723633, | |
| "learning_rate": 2.6385542168674697e-05, | |
| "loss": 0.26003103256225585, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.6558265582655824, | |
| "grad_norm": 2.294528007507324, | |
| "learning_rate": 2.6084337349397592e-05, | |
| "loss": 0.3664748191833496, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.682926829268293, | |
| "grad_norm": 2.02767014503479, | |
| "learning_rate": 2.5783132530120484e-05, | |
| "loss": 0.28735396862030027, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.710027100271003, | |
| "grad_norm": 1.2427754402160645, | |
| "learning_rate": 2.5481927710843373e-05, | |
| "loss": 0.32174689769744874, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.7371273712737128, | |
| "grad_norm": 1.545106053352356, | |
| "learning_rate": 2.5180722891566265e-05, | |
| "loss": 0.18646930456161498, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.7642276422764227, | |
| "grad_norm": 1.4381146430969238, | |
| "learning_rate": 2.4879518072289157e-05, | |
| "loss": 0.18642499446868896, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.7913279132791327, | |
| "grad_norm": 2.0318527221679688, | |
| "learning_rate": 2.4578313253012052e-05, | |
| "loss": 0.29974429607391356, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.818428184281843, | |
| "grad_norm": 1.4769566059112549, | |
| "learning_rate": 2.427710843373494e-05, | |
| "loss": 0.211688232421875, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.845528455284553, | |
| "grad_norm": 0.5660593509674072, | |
| "learning_rate": 2.3975903614457832e-05, | |
| "loss": 0.2741595506668091, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.872628726287263, | |
| "grad_norm": 2.2198262214660645, | |
| "learning_rate": 2.3674698795180724e-05, | |
| "loss": 0.28442981243133547, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.899728997289973, | |
| "grad_norm": 1.2250746488571167, | |
| "learning_rate": 2.3373493975903616e-05, | |
| "loss": 0.3678981065750122, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "grad_norm": 1.323784589767456, | |
| "learning_rate": 2.3072289156626505e-05, | |
| "loss": 0.19401313066482545, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.953929539295393, | |
| "grad_norm": 1.2216640710830688, | |
| "learning_rate": 2.27710843373494e-05, | |
| "loss": 0.24386465549468994, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.9810298102981028, | |
| "grad_norm": 0.0011535240337252617, | |
| "learning_rate": 2.246987951807229e-05, | |
| "loss": 0.18954521417617798, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.054677963256836, | |
| "eval_runtime": 16.8639, | |
| "eval_samples_per_second": 21.881, | |
| "eval_steps_per_second": 2.787, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 3.008130081300813, | |
| "grad_norm": 0.9947961568832397, | |
| "learning_rate": 2.216867469879518e-05, | |
| "loss": 0.2884655475616455, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.035230352303523, | |
| "grad_norm": 0.0003063350450247526, | |
| "learning_rate": 2.1867469879518072e-05, | |
| "loss": 0.11665208339691162, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.062330623306233, | |
| "grad_norm": 3.730006694793701, | |
| "learning_rate": 2.1566265060240964e-05, | |
| "loss": 0.1934136390686035, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.089430894308943, | |
| "grad_norm": 2.041410207748413, | |
| "learning_rate": 2.1265060240963856e-05, | |
| "loss": 0.24326050281524658, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.116531165311653, | |
| "grad_norm": 0.8090879321098328, | |
| "learning_rate": 2.0963855421686748e-05, | |
| "loss": 0.14255741834640503, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.1436314363143634, | |
| "grad_norm": 1.8423101902008057, | |
| "learning_rate": 2.066265060240964e-05, | |
| "loss": 0.22453477382659912, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.1707317073170733, | |
| "grad_norm": 1.2213603258132935, | |
| "learning_rate": 2.0361445783132532e-05, | |
| "loss": 0.1474652409553528, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.1978319783197833, | |
| "grad_norm": 1.6069453954696655, | |
| "learning_rate": 2.0060240963855424e-05, | |
| "loss": 0.18184350728988646, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.2249322493224932, | |
| "grad_norm": 2.2042312622070312, | |
| "learning_rate": 1.9759036144578312e-05, | |
| "loss": 0.20034589767456054, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.252032520325203, | |
| "grad_norm": 1.6379846334457397, | |
| "learning_rate": 1.9457831325301208e-05, | |
| "loss": 0.1619314432144165, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.279132791327913, | |
| "grad_norm": 2.0756173133850098, | |
| "learning_rate": 1.9156626506024096e-05, | |
| "loss": 0.15652774572372435, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.306233062330623, | |
| "grad_norm": 1.7097762823104858, | |
| "learning_rate": 1.8855421686746988e-05, | |
| "loss": 0.13532664775848388, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 1.3465607166290283, | |
| "learning_rate": 1.855421686746988e-05, | |
| "loss": 0.15555697679519653, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.3604336043360434, | |
| "grad_norm": 1.7080705165863037, | |
| "learning_rate": 1.8253012048192772e-05, | |
| "loss": 0.1912943482398987, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.3875338753387534, | |
| "grad_norm": 0.000967069179750979, | |
| "learning_rate": 1.7951807228915664e-05, | |
| "loss": 0.18387593030929567, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.4146341463414633, | |
| "grad_norm": 1.7816832065582275, | |
| "learning_rate": 1.7650602409638556e-05, | |
| "loss": 0.18378511667251587, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.4417344173441733, | |
| "grad_norm": 2.6202845573425293, | |
| "learning_rate": 1.7349397590361448e-05, | |
| "loss": 0.23261580467224122, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.4688346883468837, | |
| "grad_norm": 2.1822383403778076, | |
| "learning_rate": 1.7048192771084336e-05, | |
| "loss": 0.14113547801971435, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.4959349593495936, | |
| "grad_norm": 1.4640594720840454, | |
| "learning_rate": 1.674698795180723e-05, | |
| "loss": 0.20534427165985109, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.5230352303523036, | |
| "grad_norm": 1.213744878768921, | |
| "learning_rate": 1.644578313253012e-05, | |
| "loss": 0.18255839347839356, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.5501355013550135, | |
| "grad_norm": 1.1535859107971191, | |
| "learning_rate": 1.6144578313253012e-05, | |
| "loss": 0.2130563497543335, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.5772357723577235, | |
| "grad_norm": 2.318845272064209, | |
| "learning_rate": 1.5843373493975904e-05, | |
| "loss": 0.16065138578414917, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.6043360433604335, | |
| "grad_norm": 2.619586706161499, | |
| "learning_rate": 1.5542168674698796e-05, | |
| "loss": 0.17162058353424073, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.6314363143631434, | |
| "grad_norm": 2.33847713470459, | |
| "learning_rate": 1.524096385542169e-05, | |
| "loss": 0.20561666488647462, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.658536585365854, | |
| "grad_norm": 1.9664802551269531, | |
| "learning_rate": 1.493975903614458e-05, | |
| "loss": 0.19157127141952515, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.6856368563685638, | |
| "grad_norm": 2.329408645629883, | |
| "learning_rate": 1.463855421686747e-05, | |
| "loss": 0.21277453899383544, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.7127371273712737, | |
| "grad_norm": 1.6541913747787476, | |
| "learning_rate": 1.4337349397590364e-05, | |
| "loss": 0.1630422830581665, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.7398373983739837, | |
| "grad_norm": 0.0003956485306844115, | |
| "learning_rate": 1.4036144578313254e-05, | |
| "loss": 0.185025954246521, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.7669376693766936, | |
| "grad_norm": 2.3650405406951904, | |
| "learning_rate": 1.3734939759036144e-05, | |
| "loss": 0.22130346298217773, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 3.794037940379404, | |
| "grad_norm": 1.982306957244873, | |
| "learning_rate": 1.3433734939759038e-05, | |
| "loss": 0.1326514720916748, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.821138211382114, | |
| "grad_norm": 2.5378623008728027, | |
| "learning_rate": 1.3132530120481928e-05, | |
| "loss": 0.18815650939941406, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 3.848238482384824, | |
| "grad_norm": 1.572888731956482, | |
| "learning_rate": 1.283132530120482e-05, | |
| "loss": 0.24666080474853516, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 3.875338753387534, | |
| "grad_norm": 2.4423999786376953, | |
| "learning_rate": 1.2530120481927712e-05, | |
| "loss": 0.13651864528656005, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 3.902439024390244, | |
| "grad_norm": 2.614476203918457, | |
| "learning_rate": 1.2228915662650604e-05, | |
| "loss": 0.16551176309585572, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 3.9295392953929538, | |
| "grad_norm": 2.7172443866729736, | |
| "learning_rate": 1.1927710843373496e-05, | |
| "loss": 0.22759897708892823, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.9566395663956637, | |
| "grad_norm": 2.725436210632324, | |
| "learning_rate": 1.1626506024096386e-05, | |
| "loss": 0.17690047025680541, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 3.983739837398374, | |
| "grad_norm": 1.7033926248550415, | |
| "learning_rate": 1.1325301204819278e-05, | |
| "loss": 0.19610682725906373, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.159024953842163, | |
| "eval_runtime": 16.8991, | |
| "eval_samples_per_second": 21.836, | |
| "eval_steps_per_second": 2.781, | |
| "step": 1476 | |
| }, | |
| { | |
| "epoch": 4.010840108401084, | |
| "grad_norm": 1.5601325035095215, | |
| "learning_rate": 1.102409638554217e-05, | |
| "loss": 0.1691329598426819, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 4.0379403794037945, | |
| "grad_norm": 1.649061679840088, | |
| "learning_rate": 1.0722891566265062e-05, | |
| "loss": 0.13990991115570067, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 4.065040650406504, | |
| "grad_norm": 3.2786800861358643, | |
| "learning_rate": 1.0421686746987952e-05, | |
| "loss": 0.15654369592666625, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.092140921409214, | |
| "grad_norm": 1.1028623580932617, | |
| "learning_rate": 1.0120481927710844e-05, | |
| "loss": 0.08107818961143494, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 4.119241192411924, | |
| "grad_norm": 2.663709878921509, | |
| "learning_rate": 9.819277108433736e-06, | |
| "loss": 0.11348884105682373, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.146341463414634, | |
| "grad_norm": 2.1573872566223145, | |
| "learning_rate": 9.518072289156626e-06, | |
| "loss": 0.15013401508331298, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.173441734417344, | |
| "grad_norm": 2.9208433628082275, | |
| "learning_rate": 9.216867469879518e-06, | |
| "loss": 0.13929959535598754, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.200542005420054, | |
| "grad_norm": 3.1555604934692383, | |
| "learning_rate": 8.91566265060241e-06, | |
| "loss": 0.16203492879867554, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.227642276422764, | |
| "grad_norm": 2.0795438289642334, | |
| "learning_rate": 8.614457831325302e-06, | |
| "loss": 0.07984868288040162, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.254742547425474, | |
| "grad_norm": 2.296844005584717, | |
| "learning_rate": 8.313253012048194e-06, | |
| "loss": 0.12368906736373901, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 4.281842818428184, | |
| "grad_norm": 2.429440498352051, | |
| "learning_rate": 8.012048192771085e-06, | |
| "loss": 0.11656389236450196, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.308943089430894, | |
| "grad_norm": 2.974891424179077, | |
| "learning_rate": 7.710843373493977e-06, | |
| "loss": 0.0838359236717224, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 4.336043360433604, | |
| "grad_norm": 3.0825984477996826, | |
| "learning_rate": 7.409638554216868e-06, | |
| "loss": 0.1049979567527771, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.363143631436314, | |
| "grad_norm": 0.01348312571644783, | |
| "learning_rate": 7.1084337349397595e-06, | |
| "loss": 0.10732258558273315, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 4.390243902439025, | |
| "grad_norm": 1.7159212827682495, | |
| "learning_rate": 6.8072289156626514e-06, | |
| "loss": 0.1017596960067749, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 4.417344173441735, | |
| "grad_norm": 2.7607741355895996, | |
| "learning_rate": 6.506024096385542e-06, | |
| "loss": 0.1391127347946167, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 2.652299165725708, | |
| "learning_rate": 6.2048192771084344e-06, | |
| "loss": 0.07451351284980774, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 4.471544715447155, | |
| "grad_norm": 1.3986726999282837, | |
| "learning_rate": 5.9036144578313255e-06, | |
| "loss": 0.1240576982498169, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 4.4986449864498645, | |
| "grad_norm": 2.370952844619751, | |
| "learning_rate": 5.602409638554217e-06, | |
| "loss": 0.1331729531288147, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 4.5257452574525745, | |
| "grad_norm": 0.0007586497813463211, | |
| "learning_rate": 5.3012048192771085e-06, | |
| "loss": 0.06634545922279358, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 4.5528455284552845, | |
| "grad_norm": 2.4504480361938477, | |
| "learning_rate": 5e-06, | |
| "loss": 0.11947824954986572, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 4.579945799457994, | |
| "grad_norm": 1.3551121950149536, | |
| "learning_rate": 4.6987951807228915e-06, | |
| "loss": 0.10382745265960694, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 4.607046070460704, | |
| "grad_norm": 2.601646661758423, | |
| "learning_rate": 4.397590361445783e-06, | |
| "loss": 0.14869719743728638, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.634146341463414, | |
| "grad_norm": 4.1014533042907715, | |
| "learning_rate": 4.096385542168675e-06, | |
| "loss": 0.13243969678878784, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 4.661246612466124, | |
| "grad_norm": 1.2210009098052979, | |
| "learning_rate": 3.7951807228915664e-06, | |
| "loss": 0.074852854013443, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 4.688346883468835, | |
| "grad_norm": 0.0020269318483769894, | |
| "learning_rate": 3.4939759036144583e-06, | |
| "loss": 0.11936783790588379, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 4.715447154471545, | |
| "grad_norm": 1.9909566640853882, | |
| "learning_rate": 3.1927710843373494e-06, | |
| "loss": 0.0912780523300171, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 4.742547425474255, | |
| "grad_norm": 1.2086187601089478, | |
| "learning_rate": 2.8915662650602413e-06, | |
| "loss": 0.10006617307662964, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 4.769647696476965, | |
| "grad_norm": 2.497040033340454, | |
| "learning_rate": 2.590361445783133e-06, | |
| "loss": 0.15474247932434082, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 4.796747967479675, | |
| "grad_norm": 4.443364143371582, | |
| "learning_rate": 2.2891566265060243e-06, | |
| "loss": 0.09296027421951295, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 4.823848238482385, | |
| "grad_norm": 0.013439181260764599, | |
| "learning_rate": 1.987951807228916e-06, | |
| "loss": 0.11202136278152466, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 4.850948509485095, | |
| "grad_norm": 2.0051348209381104, | |
| "learning_rate": 1.6867469879518073e-06, | |
| "loss": 0.1054147720336914, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 4.878048780487805, | |
| "grad_norm": 2.147296190261841, | |
| "learning_rate": 1.3855421686746988e-06, | |
| "loss": 0.12650834321975707, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.905149051490515, | |
| "grad_norm": 1.688089370727539, | |
| "learning_rate": 1.0843373493975905e-06, | |
| "loss": 0.09542213678359986, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 4.932249322493225, | |
| "grad_norm": 1.27448308467865, | |
| "learning_rate": 7.83132530120482e-07, | |
| "loss": 0.08753200769424438, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 4.959349593495935, | |
| "grad_norm": 2.552873373031616, | |
| "learning_rate": 4.819277108433736e-07, | |
| "loss": 0.12638814449310304, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 4.9864498644986455, | |
| "grad_norm": 2.642066240310669, | |
| "learning_rate": 1.8072289156626508e-07, | |
| "loss": 0.1587662935256958, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.2943406105041504, | |
| "eval_runtime": 16.9282, | |
| "eval_samples_per_second": 21.798, | |
| "eval_steps_per_second": 2.776, | |
| "step": 1845 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1845, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7157314578953306e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |