Instructions to use alwaysgood/gemma4-st1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alwaysgood/gemma4-st1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="alwaysgood/gemma4-st1")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("alwaysgood/gemma4-st1") model = AutoModelForImageTextToText.from_pretrained("alwaysgood/gemma4-st1") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use alwaysgood/gemma4-st1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "alwaysgood/gemma4-st1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "alwaysgood/gemma4-st1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/alwaysgood/gemma4-st1
- SGLang
How to use alwaysgood/gemma4-st1 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 "alwaysgood/gemma4-st1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "alwaysgood/gemma4-st1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "alwaysgood/gemma4-st1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "alwaysgood/gemma4-st1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Studio new
How to use alwaysgood/gemma4-st1 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for alwaysgood/gemma4-st1 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for alwaysgood/gemma4-st1 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for alwaysgood/gemma4-st1 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="alwaysgood/gemma4-st1", max_seq_length=2048, ) - Docker Model Runner
How to use alwaysgood/gemma4-st1 with Docker Model Runner:
docker model run hf.co/alwaysgood/gemma4-st1
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 5803, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017234693437890474, | |
| "grad_norm": 252.0, | |
| "learning_rate": 1.549053356282272e-07, | |
| "loss": 4.069989395141602, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003446938687578095, | |
| "grad_norm": 242.0, | |
| "learning_rate": 3.2702237521514633e-07, | |
| "loss": 3.939067077636719, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005170408031367142, | |
| "grad_norm": 268.0, | |
| "learning_rate": 4.991394148020654e-07, | |
| "loss": 3.982646942138672, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00689387737515619, | |
| "grad_norm": 266.0, | |
| "learning_rate": 6.712564543889846e-07, | |
| "loss": 3.9836990356445314, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008617346718945236, | |
| "grad_norm": 1600.0, | |
| "learning_rate": 8.433734939759036e-07, | |
| "loss": 3.9337554931640626, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010340816062734284, | |
| "grad_norm": 247.0, | |
| "learning_rate": 1.0154905335628228e-06, | |
| "loss": 3.949005126953125, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.012064285406523332, | |
| "grad_norm": 1336.0, | |
| "learning_rate": 1.187607573149742e-06, | |
| "loss": 3.7827701568603516, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01378775475031238, | |
| "grad_norm": 1640.0, | |
| "learning_rate": 1.3597246127366612e-06, | |
| "loss": 3.6136966705322267, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.015511224094101427, | |
| "grad_norm": 466.0, | |
| "learning_rate": 1.5318416523235801e-06, | |
| "loss": 3.3442989349365235, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.017234693437890473, | |
| "grad_norm": 125.5, | |
| "learning_rate": 1.703958691910499e-06, | |
| "loss": 3.1754783630371093, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01895816278167952, | |
| "grad_norm": 161.0, | |
| "learning_rate": 1.8760757314974185e-06, | |
| "loss": 3.0345636367797852, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.020681632125468568, | |
| "grad_norm": 128.0, | |
| "learning_rate": 2.0481927710843377e-06, | |
| "loss": 2.904159736633301, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.022405101469257616, | |
| "grad_norm": 90.5, | |
| "learning_rate": 2.2203098106712566e-06, | |
| "loss": 2.7710594177246093, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.024128570813046663, | |
| "grad_norm": 144.0, | |
| "learning_rate": 2.3924268502581756e-06, | |
| "loss": 2.6466978073120115, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02585204015683571, | |
| "grad_norm": 155.0, | |
| "learning_rate": 2.5645438898450946e-06, | |
| "loss": 2.5279001235961913, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02757550950062476, | |
| "grad_norm": 37.75, | |
| "learning_rate": 2.736660929432014e-06, | |
| "loss": 2.46486759185791, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.029298978844413806, | |
| "grad_norm": 63.25, | |
| "learning_rate": 2.9087779690189333e-06, | |
| "loss": 2.371097946166992, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.031022448188202854, | |
| "grad_norm": 23.375, | |
| "learning_rate": 3.080895008605852e-06, | |
| "loss": 2.2781375885009765, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0327459175319919, | |
| "grad_norm": 36.75, | |
| "learning_rate": 3.2530120481927713e-06, | |
| "loss": 2.2452520370483398, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.034469386875780945, | |
| "grad_norm": 46.0, | |
| "learning_rate": 3.4251290877796906e-06, | |
| "loss": 2.2093746185302736, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03619285621957, | |
| "grad_norm": 36.75, | |
| "learning_rate": 3.59724612736661e-06, | |
| "loss": 2.234319877624512, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.03791632556335904, | |
| "grad_norm": 19.5, | |
| "learning_rate": 3.7693631669535286e-06, | |
| "loss": 2.2229013442993164, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.03963979490714809, | |
| "grad_norm": 39.75, | |
| "learning_rate": 3.9414802065404475e-06, | |
| "loss": 2.1696863174438477, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.041363264250937136, | |
| "grad_norm": 89.0, | |
| "learning_rate": 4.113597246127367e-06, | |
| "loss": 2.129756546020508, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04308673359472619, | |
| "grad_norm": 16.125, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 2.1558290481567384, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04481020293851523, | |
| "grad_norm": 73.0, | |
| "learning_rate": 4.457831325301205e-06, | |
| "loss": 2.1444324493408202, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.046533672282304275, | |
| "grad_norm": 31.75, | |
| "learning_rate": 4.629948364888124e-06, | |
| "loss": 2.090166473388672, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.048257141626093326, | |
| "grad_norm": 57.25, | |
| "learning_rate": 4.802065404475044e-06, | |
| "loss": 2.111903953552246, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.04998061096988237, | |
| "grad_norm": 20.0, | |
| "learning_rate": 4.974182444061962e-06, | |
| "loss": 2.0885305404663086, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.05170408031367142, | |
| "grad_norm": 80.5, | |
| "learning_rate": 5.146299483648882e-06, | |
| "loss": 2.0660512924194334, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.053427549657460466, | |
| "grad_norm": 84.0, | |
| "learning_rate": 5.318416523235801e-06, | |
| "loss": 2.0948448181152344, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.05515101900124952, | |
| "grad_norm": 30.0, | |
| "learning_rate": 5.4905335628227195e-06, | |
| "loss": 2.0578670501708984, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05687448834503856, | |
| "grad_norm": 14.0, | |
| "learning_rate": 5.66265060240964e-06, | |
| "loss": 2.0415544509887695, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.05859795768882761, | |
| "grad_norm": 37.25, | |
| "learning_rate": 5.834767641996558e-06, | |
| "loss": 2.058155822753906, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.060321427032616656, | |
| "grad_norm": 149.0, | |
| "learning_rate": 6.006884681583477e-06, | |
| "loss": 2.0764211654663085, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06204489637640571, | |
| "grad_norm": 55.5, | |
| "learning_rate": 6.179001721170397e-06, | |
| "loss": 2.0607065200805663, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06376836572019476, | |
| "grad_norm": 14.75, | |
| "learning_rate": 6.3511187607573156e-06, | |
| "loss": 1.9941295623779296, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.0654918350639838, | |
| "grad_norm": 9.6875, | |
| "learning_rate": 6.523235800344234e-06, | |
| "loss": 2.0088274002075197, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.06721530440777285, | |
| "grad_norm": 15.1875, | |
| "learning_rate": 6.695352839931154e-06, | |
| "loss": 2.0329540252685545, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.06893877375156189, | |
| "grad_norm": 22.5, | |
| "learning_rate": 6.867469879518073e-06, | |
| "loss": 1.9693401336669922, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07066224309535094, | |
| "grad_norm": 133.0, | |
| "learning_rate": 7.039586919104991e-06, | |
| "loss": 1.9934684753417968, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.07238571243914, | |
| "grad_norm": 17.125, | |
| "learning_rate": 7.211703958691912e-06, | |
| "loss": 1.9895509719848632, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.07410918178292904, | |
| "grad_norm": 14.1875, | |
| "learning_rate": 7.38382099827883e-06, | |
| "loss": 1.9678184509277343, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.07583265112671808, | |
| "grad_norm": 22.25, | |
| "learning_rate": 7.55593803786575e-06, | |
| "loss": 1.9880996704101563, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.07755612047050713, | |
| "grad_norm": 12.5625, | |
| "learning_rate": 7.728055077452669e-06, | |
| "loss": 1.98846492767334, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07927958981429618, | |
| "grad_norm": 13.875, | |
| "learning_rate": 7.900172117039587e-06, | |
| "loss": 1.9478538513183594, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08100305915808523, | |
| "grad_norm": 10.375, | |
| "learning_rate": 8.072289156626508e-06, | |
| "loss": 1.9478981018066406, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.08272652850187427, | |
| "grad_norm": 46.5, | |
| "learning_rate": 8.244406196213425e-06, | |
| "loss": 1.984210205078125, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.08444999784566332, | |
| "grad_norm": 9.1875, | |
| "learning_rate": 8.416523235800345e-06, | |
| "loss": 1.9917068481445312, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.08617346718945237, | |
| "grad_norm": 99.5, | |
| "learning_rate": 8.588640275387264e-06, | |
| "loss": 1.939429473876953, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08617346718945237, | |
| "eval_loss": 1.9641746282577515, | |
| "eval_runtime": 194.9485, | |
| "eval_samples_per_second": 24.294, | |
| "eval_steps_per_second": 3.037, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08789693653324142, | |
| "grad_norm": 28.0, | |
| "learning_rate": 8.760757314974184e-06, | |
| "loss": 1.9692066192626954, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.08962040587703046, | |
| "grad_norm": 11.5625, | |
| "learning_rate": 8.932874354561101e-06, | |
| "loss": 1.9270980834960938, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.0913438752208195, | |
| "grad_norm": 9.75, | |
| "learning_rate": 9.104991394148022e-06, | |
| "loss": 1.9370803833007812, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.09306734456460855, | |
| "grad_norm": 17.125, | |
| "learning_rate": 9.27710843373494e-06, | |
| "loss": 1.938580322265625, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.09479081390839761, | |
| "grad_norm": 21.25, | |
| "learning_rate": 9.44922547332186e-06, | |
| "loss": 1.948999786376953, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.09651428325218665, | |
| "grad_norm": 7.8125, | |
| "learning_rate": 9.621342512908779e-06, | |
| "loss": 1.9140813827514649, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.0982377525959757, | |
| "grad_norm": 6.28125, | |
| "learning_rate": 9.793459552495698e-06, | |
| "loss": 1.9098445892333984, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.09996122193976474, | |
| "grad_norm": 63.5, | |
| "learning_rate": 9.965576592082618e-06, | |
| "loss": 1.9676044464111329, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1016846912835538, | |
| "grad_norm": 7.28125, | |
| "learning_rate": 9.999942091121426e-06, | |
| "loss": 1.9416418075561523, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.10340816062734284, | |
| "grad_norm": 14.9375, | |
| "learning_rate": 9.999706838601156e-06, | |
| "loss": 1.9148761749267578, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.10513162997113189, | |
| "grad_norm": 8.4375, | |
| "learning_rate": 9.999290631642222e-06, | |
| "loss": 1.9141145706176759, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.10685509931492093, | |
| "grad_norm": 8.5625, | |
| "learning_rate": 9.99869348530841e-06, | |
| "loss": 1.9634918212890624, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.10857856865870999, | |
| "grad_norm": 9.0625, | |
| "learning_rate": 9.997915421212245e-06, | |
| "loss": 1.8770341873168945, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.11030203800249903, | |
| "grad_norm": 8.0625, | |
| "learning_rate": 9.996956467514203e-06, | |
| "loss": 1.965164566040039, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.11202550734628808, | |
| "grad_norm": 11.9375, | |
| "learning_rate": 9.99581665892171e-06, | |
| "loss": 1.903609848022461, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.11374897669007712, | |
| "grad_norm": 9.0625, | |
| "learning_rate": 9.994496036687866e-06, | |
| "loss": 1.932215118408203, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.11547244603386617, | |
| "grad_norm": 10.0, | |
| "learning_rate": 9.992994648609966e-06, | |
| "loss": 1.9616926193237305, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.11719591537765522, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 9.991312549027762e-06, | |
| "loss": 1.8867454528808594, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.11891938472144427, | |
| "grad_norm": 7.46875, | |
| "learning_rate": 9.989449798821504e-06, | |
| "loss": 1.9198978424072266, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.12064285406523331, | |
| "grad_norm": 9.0, | |
| "learning_rate": 9.987406465409725e-06, | |
| "loss": 1.9139331817626952, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12236632340902236, | |
| "grad_norm": 23.625, | |
| "learning_rate": 9.985182622746813e-06, | |
| "loss": 1.9208333969116211, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.12408979275281141, | |
| "grad_norm": 6.21875, | |
| "learning_rate": 9.982778351320329e-06, | |
| "loss": 1.9320703506469727, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.12581326209660046, | |
| "grad_norm": 8.375, | |
| "learning_rate": 9.980193738148087e-06, | |
| "loss": 1.9007251739501954, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.12753673144038952, | |
| "grad_norm": 30.625, | |
| "learning_rate": 9.977428876775022e-06, | |
| "loss": 1.8702217102050782, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.12926020078417855, | |
| "grad_norm": 8.375, | |
| "learning_rate": 9.974483867269787e-06, | |
| "loss": 1.8927556991577148, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.1309836701279676, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 9.971358816221137e-06, | |
| "loss": 1.9013349533081054, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.13270713947175664, | |
| "grad_norm": 7.46875, | |
| "learning_rate": 9.96805383673408e-06, | |
| "loss": 1.8408695220947267, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.1344306088155457, | |
| "grad_norm": 7.15625, | |
| "learning_rate": 9.96456904842577e-06, | |
| "loss": 1.869816207885742, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.13615407815933475, | |
| "grad_norm": 37.5, | |
| "learning_rate": 9.960904577421182e-06, | |
| "loss": 1.8965574264526368, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.13787754750312378, | |
| "grad_norm": 6.21875, | |
| "learning_rate": 9.957060556348554e-06, | |
| "loss": 1.9223035812377929, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13960101684691284, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 9.953037124334576e-06, | |
| "loss": 1.8931386947631836, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.14132448619070187, | |
| "grad_norm": 18.75, | |
| "learning_rate": 9.948834426999363e-06, | |
| "loss": 1.8595243453979493, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.14304795553449093, | |
| "grad_norm": 6.84375, | |
| "learning_rate": 9.944452616451182e-06, | |
| "loss": 1.859971046447754, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.14477142487828, | |
| "grad_norm": 6.59375, | |
| "learning_rate": 9.939891851280943e-06, | |
| "loss": 1.9094179153442383, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.14649489422206902, | |
| "grad_norm": 5.5, | |
| "learning_rate": 9.935152296556467e-06, | |
| "loss": 1.9463640213012696, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.14821836356585807, | |
| "grad_norm": 5.75, | |
| "learning_rate": 9.930234123816503e-06, | |
| "loss": 1.881173324584961, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.14994183290964713, | |
| "grad_norm": 6.09375, | |
| "learning_rate": 9.925137511064527e-06, | |
| "loss": 1.8919122695922852, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.15166530225343616, | |
| "grad_norm": 11.75, | |
| "learning_rate": 9.919862642762291e-06, | |
| "loss": 1.8629920959472657, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.15338877159722522, | |
| "grad_norm": 8.125, | |
| "learning_rate": 9.914409709823158e-06, | |
| "loss": 1.8775466918945312, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.15511224094101425, | |
| "grad_norm": 6.21875, | |
| "learning_rate": 9.908778909605184e-06, | |
| "loss": 1.8726503372192382, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.1568357102848033, | |
| "grad_norm": 11.8125, | |
| "learning_rate": 9.902970445903974e-06, | |
| "loss": 1.880959701538086, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.15855917962859237, | |
| "grad_norm": 8.3125, | |
| "learning_rate": 9.896984528945313e-06, | |
| "loss": 1.8687429428100586, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.1602826489723814, | |
| "grad_norm": 6.78125, | |
| "learning_rate": 9.890821375377553e-06, | |
| "loss": 1.8792970657348633, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.16200611831617046, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 9.88448120826377e-06, | |
| "loss": 1.8895078659057618, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.16372958765995949, | |
| "grad_norm": 6.84375, | |
| "learning_rate": 9.877964257073696e-06, | |
| "loss": 1.8946203231811523, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.16545305700374854, | |
| "grad_norm": 9.5, | |
| "learning_rate": 9.871270757675406e-06, | |
| "loss": 1.8623432159423827, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.1671765263475376, | |
| "grad_norm": 51.5, | |
| "learning_rate": 9.864400952326793e-06, | |
| "loss": 1.912847900390625, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.16889999569132663, | |
| "grad_norm": 8.5625, | |
| "learning_rate": 9.857355089666791e-06, | |
| "loss": 1.8621129989624023, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.1706234650351157, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 9.850133424706371e-06, | |
| "loss": 1.8847681045532227, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.17234693437890475, | |
| "grad_norm": 13.5, | |
| "learning_rate": 9.842736218819327e-06, | |
| "loss": 1.8754114151000976, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17234693437890475, | |
| "eval_loss": 1.8777226209640503, | |
| "eval_runtime": 189.0816, | |
| "eval_samples_per_second": 25.047, | |
| "eval_steps_per_second": 3.131, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17407040372269378, | |
| "grad_norm": 8.3125, | |
| "learning_rate": 9.835163739732805e-06, | |
| "loss": 1.8813297271728515, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.17579387306648284, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 9.827416261517613e-06, | |
| "loss": 1.910245704650879, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.17751734241027187, | |
| "grad_norm": 6.59375, | |
| "learning_rate": 9.819494064578305e-06, | |
| "loss": 1.8775476455688476, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.17924081175406092, | |
| "grad_norm": 4.375, | |
| "learning_rate": 9.811397435643037e-06, | |
| "loss": 1.8659778594970704, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.18096428109784998, | |
| "grad_norm": 11.25, | |
| "learning_rate": 9.803126667753175e-06, | |
| "loss": 1.886317253112793, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.182687750441639, | |
| "grad_norm": 9.0625, | |
| "learning_rate": 9.794682060252705e-06, | |
| "loss": 1.9058975219726562, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.18441121978542807, | |
| "grad_norm": 16.5, | |
| "learning_rate": 9.786063918777386e-06, | |
| "loss": 1.8786186218261718, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.1861346891292171, | |
| "grad_norm": 10.3125, | |
| "learning_rate": 9.777272555243702e-06, | |
| "loss": 1.8804399490356445, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.18785815847300616, | |
| "grad_norm": 25.875, | |
| "learning_rate": 9.768308287837555e-06, | |
| "loss": 1.83834228515625, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.18958162781679522, | |
| "grad_norm": 9.9375, | |
| "learning_rate": 9.759171441002766e-06, | |
| "loss": 1.8528076171875, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.19130509716058425, | |
| "grad_norm": 6.21875, | |
| "learning_rate": 9.74986234542932e-06, | |
| "loss": 1.8746351242065429, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.1930285665043733, | |
| "grad_norm": 6.8125, | |
| "learning_rate": 9.740381338041407e-06, | |
| "loss": 1.881591796875, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.19475203584816236, | |
| "grad_norm": 55.75, | |
| "learning_rate": 9.730728761985218e-06, | |
| "loss": 1.910407829284668, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.1964755051919514, | |
| "grad_norm": 10.25, | |
| "learning_rate": 9.720904966616533e-06, | |
| "loss": 1.8622859954833983, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.19819897453574045, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 9.710910307488075e-06, | |
| "loss": 1.8853498458862306, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.19992244387952948, | |
| "grad_norm": 28.875, | |
| "learning_rate": 9.700745146336642e-06, | |
| "loss": 1.900423812866211, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.20164591322331854, | |
| "grad_norm": 8.375, | |
| "learning_rate": 9.690409851070009e-06, | |
| "loss": 1.889995002746582, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.2033693825671076, | |
| "grad_norm": 8.875, | |
| "learning_rate": 9.679904795753616e-06, | |
| "loss": 1.8939664840698243, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.20509285191089663, | |
| "grad_norm": 7.03125, | |
| "learning_rate": 9.66923036059704e-06, | |
| "loss": 1.8157171249389648, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.2068163212546857, | |
| "grad_norm": 10.4375, | |
| "learning_rate": 9.658386931940212e-06, | |
| "loss": 1.8297653198242188, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.20853979059847472, | |
| "grad_norm": 13.25, | |
| "learning_rate": 9.647374902239452e-06, | |
| "loss": 1.8692256927490234, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.21026325994226377, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 9.636194670053263e-06, | |
| "loss": 1.8458559036254882, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.21198672928605283, | |
| "grad_norm": 10.625, | |
| "learning_rate": 9.624846640027894e-06, | |
| "loss": 1.8413688659667968, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.21371019862984186, | |
| "grad_norm": 5.375, | |
| "learning_rate": 9.61333122288271e-06, | |
| "loss": 1.8779708862304687, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.21543366797363092, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 9.601648835395314e-06, | |
| "loss": 1.8429693222045898, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.21715713731741998, | |
| "grad_norm": 29.125, | |
| "learning_rate": 9.589799900386472e-06, | |
| "loss": 1.862042236328125, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.218880606661209, | |
| "grad_norm": 10.4375, | |
| "learning_rate": 9.577784846704805e-06, | |
| "loss": 1.8681344985961914, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.22060407600499807, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 9.565604109211271e-06, | |
| "loss": 1.8646697998046875, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.2223275453487871, | |
| "grad_norm": 6.625, | |
| "learning_rate": 9.553258128763418e-06, | |
| "loss": 1.8120367050170898, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.22405101469257616, | |
| "grad_norm": 8.375, | |
| "learning_rate": 9.54074735219944e-06, | |
| "loss": 1.8799192428588867, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.22577448403636521, | |
| "grad_norm": 5.875, | |
| "learning_rate": 9.528072232321996e-06, | |
| "loss": 1.8551996231079102, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.22749795338015424, | |
| "grad_norm": 9.0, | |
| "learning_rate": 9.515233227881821e-06, | |
| "loss": 1.871938705444336, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.2292214227239433, | |
| "grad_norm": 191.0, | |
| "learning_rate": 9.502230803561132e-06, | |
| "loss": 1.8501504898071288, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.23094489206773233, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 9.4890654299568e-06, | |
| "loss": 1.8650516510009765, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.2326683614115214, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 9.475737583563318e-06, | |
| "loss": 1.860942268371582, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.23439183075531045, | |
| "grad_norm": 6.875, | |
| "learning_rate": 9.462247746755564e-06, | |
| "loss": 1.8466346740722657, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.23611530009909948, | |
| "grad_norm": 7.4375, | |
| "learning_rate": 9.448596407771333e-06, | |
| "loss": 1.8936279296875, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.23783876944288854, | |
| "grad_norm": 37.0, | |
| "learning_rate": 9.434784060693671e-06, | |
| "loss": 1.8678653717041016, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.2395622387866776, | |
| "grad_norm": 5.6875, | |
| "learning_rate": 9.420811205432991e-06, | |
| "loss": 1.8797569274902344, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.24128570813046663, | |
| "grad_norm": 7.84375, | |
| "learning_rate": 9.40667834770898e-06, | |
| "loss": 1.8689140319824218, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.24300917747425568, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 9.392385999032299e-06, | |
| "loss": 1.8364645004272462, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.2447326468180447, | |
| "grad_norm": 10.0625, | |
| "learning_rate": 9.37793467668606e-06, | |
| "loss": 1.8727912902832031, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.24645611616183377, | |
| "grad_norm": 13.5625, | |
| "learning_rate": 9.363324903707117e-06, | |
| "loss": 1.8319427490234375, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.24817958550562283, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 9.348557208867127e-06, | |
| "loss": 1.8280084609985352, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.24990305484941186, | |
| "grad_norm": 7.6875, | |
| "learning_rate": 9.333632126653412e-06, | |
| "loss": 1.8651538848876954, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.2516265241932009, | |
| "grad_norm": 29.5, | |
| "learning_rate": 9.318550197249619e-06, | |
| "loss": 1.8845842361450196, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.25334999353698995, | |
| "grad_norm": 8.3125, | |
| "learning_rate": 9.30331196651617e-06, | |
| "loss": 1.8626699447631836, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.25507346288077903, | |
| "grad_norm": 8.625, | |
| "learning_rate": 9.287917985970496e-06, | |
| "loss": 1.8710561752319337, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.25679693222456806, | |
| "grad_norm": 9.1875, | |
| "learning_rate": 9.27236881276709e-06, | |
| "loss": 1.829465675354004, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.2585204015683571, | |
| "grad_norm": 40.0, | |
| "learning_rate": 9.256665009677326e-06, | |
| "loss": 1.8205698013305665, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2585204015683571, | |
| "eval_loss": 1.8534876108169556, | |
| "eval_runtime": 189.1023, | |
| "eval_samples_per_second": 25.045, | |
| "eval_steps_per_second": 3.131, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2602438709121461, | |
| "grad_norm": 6.09375, | |
| "learning_rate": 9.240807145069106e-06, | |
| "loss": 1.8519729614257812, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.2619673402559352, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 9.224795792886276e-06, | |
| "loss": 1.827493667602539, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.26369080959972424, | |
| "grad_norm": 7.375, | |
| "learning_rate": 9.208631532627868e-06, | |
| "loss": 1.8664134979248046, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.26541427894351327, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 9.192314949327107e-06, | |
| "loss": 1.8513822555541992, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.26713774828730236, | |
| "grad_norm": 13.6875, | |
| "learning_rate": 9.175846633530257e-06, | |
| "loss": 1.828923797607422, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.2688612176310914, | |
| "grad_norm": 7.03125, | |
| "learning_rate": 9.15922718127523e-06, | |
| "loss": 1.868868637084961, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.2705846869748804, | |
| "grad_norm": 7.3125, | |
| "learning_rate": 9.142457194070024e-06, | |
| "loss": 1.8728532791137695, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.2723081563186695, | |
| "grad_norm": 11.3125, | |
| "learning_rate": 9.125537278870953e-06, | |
| "loss": 1.8872152328491212, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.27403162566245853, | |
| "grad_norm": 5.0, | |
| "learning_rate": 9.108468048060675e-06, | |
| "loss": 1.8836444854736327, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.27575509500624756, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 9.091250119426023e-06, | |
| "loss": 1.8695207595825196, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.27747856435003665, | |
| "grad_norm": 7.375, | |
| "learning_rate": 9.07388411613566e-06, | |
| "loss": 1.822032356262207, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.2792020336938257, | |
| "grad_norm": 19.375, | |
| "learning_rate": 9.056370666717513e-06, | |
| "loss": 1.8919815063476562, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.2809255030376147, | |
| "grad_norm": 10.75, | |
| "learning_rate": 9.03871040503603e-06, | |
| "loss": 1.8365257263183594, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.28264897238140374, | |
| "grad_norm": 8.9375, | |
| "learning_rate": 9.020903970269233e-06, | |
| "loss": 1.7987678527832032, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.2843724417251928, | |
| "grad_norm": 7.8125, | |
| "learning_rate": 9.002952006885592e-06, | |
| "loss": 1.8505571365356446, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.28609591106898186, | |
| "grad_norm": 7.125, | |
| "learning_rate": 8.984855164620694e-06, | |
| "loss": 1.8379674911499024, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.2878193804127709, | |
| "grad_norm": 24.125, | |
| "learning_rate": 8.966614098453728e-06, | |
| "loss": 1.8600765228271485, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.28954284975656, | |
| "grad_norm": 9.0625, | |
| "learning_rate": 8.94822946858378e-06, | |
| "loss": 1.825016975402832, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.291266319100349, | |
| "grad_norm": 9.25, | |
| "learning_rate": 8.929701940405939e-06, | |
| "loss": 1.8779399871826172, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.29298978844413803, | |
| "grad_norm": 6.65625, | |
| "learning_rate": 8.911032184487216e-06, | |
| "loss": 1.8601961135864258, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.2947132577879271, | |
| "grad_norm": 7.5, | |
| "learning_rate": 8.89222087654227e-06, | |
| "loss": 1.851213264465332, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.29643672713171615, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 8.873268697408952e-06, | |
| "loss": 1.8635419845581054, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.2981601964755052, | |
| "grad_norm": 47.25, | |
| "learning_rate": 8.85417633302367e-06, | |
| "loss": 1.8464191436767579, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.29988366581929427, | |
| "grad_norm": 5.875, | |
| "learning_rate": 8.834944474396551e-06, | |
| "loss": 1.8149053573608398, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.3016071351630833, | |
| "grad_norm": 6.84375, | |
| "learning_rate": 8.815573817586448e-06, | |
| "loss": 1.8667095184326172, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.3033306045068723, | |
| "grad_norm": 11.875, | |
| "learning_rate": 8.796065063675732e-06, | |
| "loss": 1.8508197784423828, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.30505407385066136, | |
| "grad_norm": 10.875, | |
| "learning_rate": 8.776418918744922e-06, | |
| "loss": 1.847660446166992, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.30677754319445044, | |
| "grad_norm": 13.0625, | |
| "learning_rate": 8.756636093847136e-06, | |
| "loss": 1.8635337829589844, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.30850101253823947, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 8.73671730498235e-06, | |
| "loss": 1.8322547912597655, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.3102244818820285, | |
| "grad_norm": 7.84375, | |
| "learning_rate": 8.716663273071484e-06, | |
| "loss": 1.8500213623046875, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.3119479512258176, | |
| "grad_norm": 6.4375, | |
| "learning_rate": 8.696474723930311e-06, | |
| "loss": 1.828200340270996, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.3136714205696066, | |
| "grad_norm": 6.5625, | |
| "learning_rate": 8.676152388243191e-06, | |
| "loss": 1.8678157806396485, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.31539488991339565, | |
| "grad_norm": 17.125, | |
| "learning_rate": 8.655697001536615e-06, | |
| "loss": 1.825833511352539, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.31711835925718473, | |
| "grad_norm": 5.6875, | |
| "learning_rate": 8.635109304152598e-06, | |
| "loss": 1.844728660583496, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.31884182860097376, | |
| "grad_norm": 9.875, | |
| "learning_rate": 8.614390041221872e-06, | |
| "loss": 1.8418235778808594, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.3205652979447628, | |
| "grad_norm": 11.3125, | |
| "learning_rate": 8.593539962636924e-06, | |
| "loss": 1.8504135131835937, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.3222887672885519, | |
| "grad_norm": 7.78125, | |
| "learning_rate": 8.572559823024853e-06, | |
| "loss": 1.860449981689453, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.3240122366323409, | |
| "grad_norm": 8.5625, | |
| "learning_rate": 8.551450381720056e-06, | |
| "loss": 1.8447723388671875, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.32573570597612994, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 8.530212402736751e-06, | |
| "loss": 1.8316837310791017, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.32745917531991897, | |
| "grad_norm": 9.875, | |
| "learning_rate": 8.508846654741318e-06, | |
| "loss": 1.8276691436767578, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.32918264466370806, | |
| "grad_norm": 6.0, | |
| "learning_rate": 8.487353911024488e-06, | |
| "loss": 1.8920913696289063, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.3309061140074971, | |
| "grad_norm": 21.375, | |
| "learning_rate": 8.46573494947334e-06, | |
| "loss": 1.8723810195922852, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.3326295833512861, | |
| "grad_norm": 10.4375, | |
| "learning_rate": 8.443990552543165e-06, | |
| "loss": 1.843758773803711, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.3343530526950752, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 8.42212150722913e-06, | |
| "loss": 1.8233121871948241, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.33607652203886423, | |
| "grad_norm": 7.53125, | |
| "learning_rate": 8.400128605037814e-06, | |
| "loss": 1.842045211791992, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.33779999138265326, | |
| "grad_norm": 7.9375, | |
| "learning_rate": 8.378012641958537e-06, | |
| "loss": 1.8421007156372071, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.33952346072644235, | |
| "grad_norm": 33.75, | |
| "learning_rate": 8.355774418434565e-06, | |
| "loss": 1.846714401245117, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.3412469300702314, | |
| "grad_norm": 6.875, | |
| "learning_rate": 8.333414739334147e-06, | |
| "loss": 1.858698272705078, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.3429703994140204, | |
| "grad_norm": 24.125, | |
| "learning_rate": 8.310934413921364e-06, | |
| "loss": 1.8431358337402344, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.3446938687578095, | |
| "grad_norm": 10.5, | |
| "learning_rate": 8.288334255826853e-06, | |
| "loss": 1.8638715744018555, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3446938687578095, | |
| "eval_loss": 1.8401983976364136, | |
| "eval_runtime": 188.5578, | |
| "eval_samples_per_second": 25.117, | |
| "eval_steps_per_second": 3.14, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3464173381015985, | |
| "grad_norm": 5.53125, | |
| "learning_rate": 8.26561508301836e-06, | |
| "loss": 1.8239376068115234, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.34814080744538756, | |
| "grad_norm": 7.75, | |
| "learning_rate": 8.242777717771129e-06, | |
| "loss": 1.8216110229492188, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.3498642767891766, | |
| "grad_norm": 7.21875, | |
| "learning_rate": 8.219822986638143e-06, | |
| "loss": 1.817897415161133, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.3515877461329657, | |
| "grad_norm": 6.40625, | |
| "learning_rate": 8.196751720420216e-06, | |
| "loss": 1.8432098388671876, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.3533112154767547, | |
| "grad_norm": 4.5, | |
| "learning_rate": 8.173564754135905e-06, | |
| "loss": 1.8237773895263671, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.35503468482054373, | |
| "grad_norm": 11.0, | |
| "learning_rate": 8.150262926991314e-06, | |
| "loss": 1.8344850540161133, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.3567581541643328, | |
| "grad_norm": 4.125, | |
| "learning_rate": 8.1268470823497e-06, | |
| "loss": 1.8227569580078125, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.35848162350812185, | |
| "grad_norm": 20.5, | |
| "learning_rate": 8.103318067700957e-06, | |
| "loss": 1.857133674621582, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.3602050928519109, | |
| "grad_norm": 5.375, | |
| "learning_rate": 8.079676734630941e-06, | |
| "loss": 1.8662431716918946, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.36192856219569997, | |
| "grad_norm": 8.0625, | |
| "learning_rate": 8.055923938790657e-06, | |
| "loss": 1.865074348449707, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.363652031539489, | |
| "grad_norm": 7.125, | |
| "learning_rate": 8.032060539865274e-06, | |
| "loss": 1.8386310577392577, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.365375500883278, | |
| "grad_norm": 6.8125, | |
| "learning_rate": 8.008087401543026e-06, | |
| "loss": 1.8924131393432617, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.3670989702270671, | |
| "grad_norm": 21.0, | |
| "learning_rate": 7.98400539148394e-06, | |
| "loss": 1.8141424179077148, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.36882243957085614, | |
| "grad_norm": 6.75, | |
| "learning_rate": 7.959815381288445e-06, | |
| "loss": 1.8318838119506835, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.3705459089146452, | |
| "grad_norm": 7.59375, | |
| "learning_rate": 7.935518246465815e-06, | |
| "loss": 1.8339788436889648, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.3722693782584342, | |
| "grad_norm": 12.625, | |
| "learning_rate": 7.911114866402491e-06, | |
| "loss": 1.8055469512939453, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.3739928476022233, | |
| "grad_norm": 127.5, | |
| "learning_rate": 7.886606124330249e-06, | |
| "loss": 1.8341318130493165, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.3757163169460123, | |
| "grad_norm": 10.3125, | |
| "learning_rate": 7.861992907294227e-06, | |
| "loss": 1.8485382080078125, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.37743978628980135, | |
| "grad_norm": 7.875, | |
| "learning_rate": 7.837276106120834e-06, | |
| "loss": 1.8135955810546875, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.37916325563359043, | |
| "grad_norm": 7.25, | |
| "learning_rate": 7.812456615385496e-06, | |
| "loss": 1.8876367568969727, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.38088672497737946, | |
| "grad_norm": 9.25, | |
| "learning_rate": 7.787535333380283e-06, | |
| "loss": 1.8209230422973632, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.3826101943211685, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 7.762513162081402e-06, | |
| "loss": 1.8425830841064452, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.3843336636649576, | |
| "grad_norm": 6.4375, | |
| "learning_rate": 7.737391007116542e-06, | |
| "loss": 1.869114875793457, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.3860571330087466, | |
| "grad_norm": 5.5, | |
| "learning_rate": 7.712169777732105e-06, | |
| "loss": 1.804082489013672, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.38778060235253564, | |
| "grad_norm": 4.125, | |
| "learning_rate": 7.686850386760296e-06, | |
| "loss": 1.8742061614990235, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.3895040716963247, | |
| "grad_norm": 4.75, | |
| "learning_rate": 7.661433750586077e-06, | |
| "loss": 1.8540233612060546, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.39122754104011376, | |
| "grad_norm": 6.90625, | |
| "learning_rate": 7.635920789114012e-06, | |
| "loss": 1.8454013824462892, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.3929510103839028, | |
| "grad_norm": 10.125, | |
| "learning_rate": 7.610312425734967e-06, | |
| "loss": 1.8449623107910156, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.3946744797276918, | |
| "grad_norm": 4.375, | |
| "learning_rate": 7.584609587292686e-06, | |
| "loss": 1.8612642288208008, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.3963979490714809, | |
| "grad_norm": 9.5, | |
| "learning_rate": 7.558813204050257e-06, | |
| "loss": 1.8338241577148438, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.39812141841526993, | |
| "grad_norm": 9.375, | |
| "learning_rate": 7.532924209656429e-06, | |
| "loss": 1.8515756607055665, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.39984488775905896, | |
| "grad_norm": 16.375, | |
| "learning_rate": 7.506943541111831e-06, | |
| "loss": 1.8405086517333984, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.40156835710284805, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 7.480872138735051e-06, | |
| "loss": 1.8534727096557617, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.4032918264466371, | |
| "grad_norm": 5.375, | |
| "learning_rate": 7.454710946128617e-06, | |
| "loss": 1.8462696075439453, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.4050152957904261, | |
| "grad_norm": 83.0, | |
| "learning_rate": 7.4284609101448265e-06, | |
| "loss": 1.8416885375976562, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.4067387651342152, | |
| "grad_norm": 8.25, | |
| "learning_rate": 7.402122980851491e-06, | |
| "loss": 1.8375621795654298, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.4084622344780042, | |
| "grad_norm": 8.125, | |
| "learning_rate": 7.37569811149754e-06, | |
| "loss": 1.815802764892578, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.41018570382179326, | |
| "grad_norm": 5.125, | |
| "learning_rate": 7.349187258478534e-06, | |
| "loss": 1.844595718383789, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.41190917316558234, | |
| "grad_norm": 6.21875, | |
| "learning_rate": 7.322591381302033e-06, | |
| "loss": 1.8283041000366211, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.4136326425093714, | |
| "grad_norm": 5.625, | |
| "learning_rate": 7.2959114425528835e-06, | |
| "loss": 1.8325546264648438, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.4153561118531604, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 7.269148407858367e-06, | |
| "loss": 1.8207094192504882, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.41707958119694943, | |
| "grad_norm": 13.5625, | |
| "learning_rate": 7.242303245853263e-06, | |
| "loss": 1.8134254455566405, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.4188030505407385, | |
| "grad_norm": 12.0625, | |
| "learning_rate": 7.215376928144783e-06, | |
| "loss": 1.8629745483398437, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.42052651988452755, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 7.188370429277408e-06, | |
| "loss": 1.8381343841552735, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.4222499892283166, | |
| "grad_norm": 73.0, | |
| "learning_rate": 7.161284726697616e-06, | |
| "loss": 1.8185060501098633, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.42397345857210567, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 7.134120800718507e-06, | |
| "loss": 1.8640281677246093, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.4256969279158947, | |
| "grad_norm": 5.375, | |
| "learning_rate": 7.106879634484321e-06, | |
| "loss": 1.8647268295288086, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.4274203972596837, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 7.079562213934852e-06, | |
| "loss": 1.832758331298828, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.4291438666034728, | |
| "grad_norm": 7.34375, | |
| "learning_rate": 7.052169527769772e-06, | |
| "loss": 1.8156070709228516, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.43086733594726184, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 7.024702567412839e-06, | |
| "loss": 1.8204095840454102, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.43086733594726184, | |
| "eval_loss": 1.83199143409729, | |
| "eval_runtime": 189.3842, | |
| "eval_samples_per_second": 25.007, | |
| "eval_steps_per_second": 3.126, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4325908052910509, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 6.9971623269760204e-06, | |
| "loss": 1.8643325805664062, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.43431427463483996, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 6.969549803223508e-06, | |
| "loss": 1.8427024841308595, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.436037743978629, | |
| "grad_norm": 6.03125, | |
| "learning_rate": 6.941865995535644e-06, | |
| "loss": 1.8385257720947266, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.437761213322418, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 6.914111905872752e-06, | |
| "loss": 1.8454465866088867, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.43948468266620705, | |
| "grad_norm": 6.875, | |
| "learning_rate": 6.886288538738872e-06, | |
| "loss": 1.7985853195190429, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.44120815200999614, | |
| "grad_norm": 8.8125, | |
| "learning_rate": 6.858396901145404e-06, | |
| "loss": 1.8151981353759765, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.44293162135378517, | |
| "grad_norm": 5.875, | |
| "learning_rate": 6.83043800257466e-06, | |
| "loss": 1.8277212142944337, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.4446550906975742, | |
| "grad_norm": 6.5, | |
| "learning_rate": 6.80241285494333e-06, | |
| "loss": 1.8706268310546874, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.4463785600413633, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 6.774322472565858e-06, | |
| "loss": 1.8442064285278321, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.4481020293851523, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 6.7461678721177285e-06, | |
| "loss": 1.862114715576172, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.44982549872894134, | |
| "grad_norm": 7.0, | |
| "learning_rate": 6.717950072598673e-06, | |
| "loss": 1.8287435531616212, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.45154896807273043, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 6.689670095295784e-06, | |
| "loss": 1.843255615234375, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.45327243741651946, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 6.66132896374656e-06, | |
| "loss": 1.8445619583129882, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.4549959067603085, | |
| "grad_norm": 4.75, | |
| "learning_rate": 6.6329277037018505e-06, | |
| "loss": 1.8358469009399414, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.4567193761040976, | |
| "grad_norm": 10.0625, | |
| "learning_rate": 6.604467343088742e-06, | |
| "loss": 1.8396055221557617, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.4584428454478866, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 6.575948911973343e-06, | |
| "loss": 1.8488874435424805, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.46016631479167563, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 6.547373442523511e-06, | |
| "loss": 1.8323183059692383, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.46188978413546466, | |
| "grad_norm": 6.84375, | |
| "learning_rate": 6.518741968971492e-06, | |
| "loss": 1.8678075790405273, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.46361325347925375, | |
| "grad_norm": 7.9375, | |
| "learning_rate": 6.490055527576492e-06, | |
| "loss": 1.7891368865966797, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.4653367228230428, | |
| "grad_norm": 5.75, | |
| "learning_rate": 6.461315156587162e-06, | |
| "loss": 1.8243621826171874, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.4670601921668318, | |
| "grad_norm": 4.875, | |
| "learning_rate": 6.432521896204035e-06, | |
| "loss": 1.8012350082397461, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.4687836615106209, | |
| "grad_norm": 6.375, | |
| "learning_rate": 6.4036767885418625e-06, | |
| "loss": 1.8313072204589844, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.4705071308544099, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 6.37478087759191e-06, | |
| "loss": 1.8313379287719727, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.47223060019819896, | |
| "grad_norm": 10.0, | |
| "learning_rate": 6.345835209184169e-06, | |
| "loss": 1.851654624938965, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.47395406954198804, | |
| "grad_norm": 11.4375, | |
| "learning_rate": 6.316840830949498e-06, | |
| "loss": 1.834511947631836, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.4756775388857771, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 6.287798792281713e-06, | |
| "loss": 1.831475067138672, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.4774010082295661, | |
| "grad_norm": 6.53125, | |
| "learning_rate": 6.258710144299604e-06, | |
| "loss": 1.8179866790771484, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.4791244775733552, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 6.229575939808893e-06, | |
| "loss": 1.8372505187988282, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.4808479469171442, | |
| "grad_norm": 6.84375, | |
| "learning_rate": 6.200397233264129e-06, | |
| "loss": 1.8282224655151367, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.48257141626093325, | |
| "grad_norm": 19.75, | |
| "learning_rate": 6.171175080730526e-06, | |
| "loss": 1.820566177368164, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.4842948856047223, | |
| "grad_norm": 6.71875, | |
| "learning_rate": 6.141910539845736e-06, | |
| "loss": 1.8087228775024413, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.48601835494851137, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 1.833594512939453, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.4877418242923004, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 6.083258531205681e-06, | |
| "loss": 1.8270418167114257, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.4894652936360894, | |
| "grad_norm": 10.0, | |
| "learning_rate": 6.053873186243141e-06, | |
| "loss": 1.8435356140136718, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.4911887629798785, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 6.024449698438033e-06, | |
| "loss": 1.8381929397583008, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.49291223232366754, | |
| "grad_norm": 7.53125, | |
| "learning_rate": 5.9949891327149375e-06, | |
| "loss": 1.8102424621582032, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.4946357016674566, | |
| "grad_norm": 72.5, | |
| "learning_rate": 5.965492555340401e-06, | |
| "loss": 1.8426288604736327, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.49635917101124566, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 5.935961033884336e-06, | |
| "loss": 1.8150890350341797, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.4980826403550347, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 5.9063956371813905e-06, | |
| "loss": 1.8337799072265626, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.4998061096988237, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 5.876797435292254e-06, | |
| "loss": 1.789473533630371, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.5015295790426127, | |
| "grad_norm": 9.875, | |
| "learning_rate": 5.847167499464941e-06, | |
| "loss": 1.8173267364501953, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.5032530483864018, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 5.817506902096007e-06, | |
| "loss": 1.8565616607666016, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.5049765177301909, | |
| "grad_norm": 13.75, | |
| "learning_rate": 5.787816716691746e-06, | |
| "loss": 1.8447467803955078, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.5066999870739799, | |
| "grad_norm": 6.5, | |
| "learning_rate": 5.758098017829329e-06, | |
| "loss": 1.8645750045776368, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.508423456417769, | |
| "grad_norm": 6.5, | |
| "learning_rate": 5.728351881117915e-06, | |
| "loss": 1.8155582427978516, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.5101469257615581, | |
| "grad_norm": 24.375, | |
| "learning_rate": 5.698579383159721e-06, | |
| "loss": 1.799262809753418, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.511870395105347, | |
| "grad_norm": 5.25, | |
| "learning_rate": 5.668781601511059e-06, | |
| "loss": 1.8040689468383788, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.5135938644491361, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 5.638959614643333e-06, | |
| "loss": 1.8163867950439454, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.5153173337929251, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 5.609114501904006e-06, | |
| "loss": 1.8470441818237304, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.5170408031367142, | |
| "grad_norm": 10.6875, | |
| "learning_rate": 5.579247343477533e-06, | |
| "loss": 1.8359079360961914, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.5170408031367142, | |
| "eval_loss": 1.8268558979034424, | |
| "eval_runtime": 189.165, | |
| "eval_samples_per_second": 25.036, | |
| "eval_steps_per_second": 3.13, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.5187642724805033, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 5.549359220346277e-06, | |
| "loss": 1.818197250366211, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.5204877418242922, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 5.519451214251368e-06, | |
| "loss": 1.79785213470459, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.5222112111680813, | |
| "grad_norm": 6.84375, | |
| "learning_rate": 5.489524407653566e-06, | |
| "loss": 1.824350357055664, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.5239346805118704, | |
| "grad_norm": 3.484375, | |
| "learning_rate": 5.459579883694075e-06, | |
| "loss": 1.8040481567382813, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.5256581498556594, | |
| "grad_norm": 14.4375, | |
| "learning_rate": 5.429618726155344e-06, | |
| "loss": 1.8301307678222656, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.5273816191994485, | |
| "grad_norm": 4.875, | |
| "learning_rate": 5.399642019421844e-06, | |
| "loss": 1.7872705459594727, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.5291050885432376, | |
| "grad_norm": 11.625, | |
| "learning_rate": 5.369650848440813e-06, | |
| "loss": 1.839627456665039, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.5308285578870265, | |
| "grad_norm": 8.25, | |
| "learning_rate": 5.339646298682997e-06, | |
| "loss": 1.8403564453125, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.5325520272308156, | |
| "grad_norm": 15.8125, | |
| "learning_rate": 5.30962945610336e-06, | |
| "loss": 1.8385784149169921, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.5342754965746047, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 5.279601407101782e-06, | |
| "loss": 1.8381383895874024, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5359989659183937, | |
| "grad_norm": 6.03125, | |
| "learning_rate": 5.249563238483733e-06, | |
| "loss": 1.8248268127441407, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.5377224352621828, | |
| "grad_norm": 23.0, | |
| "learning_rate": 5.219516037420946e-06, | |
| "loss": 1.8576610565185547, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.5394459046059719, | |
| "grad_norm": 9.375, | |
| "learning_rate": 5.1894608914120635e-06, | |
| "loss": 1.8108026504516601, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.5411693739497608, | |
| "grad_norm": 7.78125, | |
| "learning_rate": 5.159398888243279e-06, | |
| "loss": 1.8647409439086915, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.5428928432935499, | |
| "grad_norm": 7.3125, | |
| "learning_rate": 5.129331115948968e-06, | |
| "loss": 1.8226402282714844, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.544616312637339, | |
| "grad_norm": 6.9375, | |
| "learning_rate": 5.0992586627723075e-06, | |
| "loss": 1.820734405517578, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.546339781981128, | |
| "grad_norm": 12.625, | |
| "learning_rate": 5.069182617125892e-06, | |
| "loss": 1.8093095779418946, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.5480632513249171, | |
| "grad_norm": 15.5, | |
| "learning_rate": 5.039104067552336e-06, | |
| "loss": 1.8144065856933593, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.5497867206687062, | |
| "grad_norm": 7.375, | |
| "learning_rate": 5.0090241026848806e-06, | |
| "loss": 1.8056734085083008, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.5515101900124951, | |
| "grad_norm": 6.15625, | |
| "learning_rate": 4.978943811207988e-06, | |
| "loss": 1.8280052185058593, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5532336593562842, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 4.948864281817941e-06, | |
| "loss": 1.8493799209594726, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.5549571287000733, | |
| "grad_norm": 7.34375, | |
| "learning_rate": 4.918786603183447e-06, | |
| "loss": 1.806777000427246, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.5566805980438623, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 4.8887118639062175e-06, | |
| "loss": 1.7821395874023438, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.5584040673876514, | |
| "grad_norm": 6.59375, | |
| "learning_rate": 4.858641152481592e-06, | |
| "loss": 1.811480712890625, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.5601275367314403, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 4.82857555725912e-06, | |
| "loss": 1.7693416595458984, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.5618510060752294, | |
| "grad_norm": 7.8125, | |
| "learning_rate": 4.798516166403188e-06, | |
| "loss": 1.8069271087646483, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.5635744754190185, | |
| "grad_norm": 8.75, | |
| "learning_rate": 4.76846406785362e-06, | |
| "loss": 1.821498489379883, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.5652979447628075, | |
| "grad_norm": 5.53125, | |
| "learning_rate": 4.738420349286318e-06, | |
| "loss": 1.8615631103515624, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.5670214141065966, | |
| "grad_norm": 13.5, | |
| "learning_rate": 4.708386098073878e-06, | |
| "loss": 1.827471923828125, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.5687448834503857, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 4.6783624012462505e-06, | |
| "loss": 1.7911121368408203, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.5704683527941746, | |
| "grad_norm": 7.28125, | |
| "learning_rate": 4.648350345451394e-06, | |
| "loss": 1.8227167129516602, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.5721918221379637, | |
| "grad_norm": 9.875, | |
| "learning_rate": 4.618351016915932e-06, | |
| "loss": 1.8071161270141602, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.5739152914817528, | |
| "grad_norm": 6.8125, | |
| "learning_rate": 4.588365501405861e-06, | |
| "loss": 1.869521141052246, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.5756387608255418, | |
| "grad_norm": 10.5, | |
| "learning_rate": 4.558394884187234e-06, | |
| "loss": 1.8539451599121093, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.5773622301693309, | |
| "grad_norm": 12.6875, | |
| "learning_rate": 4.528440249986899e-06, | |
| "loss": 1.8072568893432617, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.57908569951312, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 4.498502682953219e-06, | |
| "loss": 1.8290151596069335, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.5808091688569089, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 4.468583266616856e-06, | |
| "loss": 1.789365005493164, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.582532638200698, | |
| "grad_norm": 5.75, | |
| "learning_rate": 4.43868308385154e-06, | |
| "loss": 1.8456544876098633, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.5842561075444871, | |
| "grad_norm": 34.75, | |
| "learning_rate": 4.4088032168348745e-06, | |
| "loss": 1.8169525146484375, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.5859795768882761, | |
| "grad_norm": 4.625, | |
| "learning_rate": 4.378944747009185e-06, | |
| "loss": 1.8146444320678712, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.5877030462320652, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 4.3491087550423585e-06, | |
| "loss": 1.820088768005371, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.5894265155758542, | |
| "grad_norm": 4.5, | |
| "learning_rate": 4.3192963207887466e-06, | |
| "loss": 1.831465721130371, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.5911499849196432, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 4.289508523250075e-06, | |
| "loss": 1.8280218124389649, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.5928734542634323, | |
| "grad_norm": 7.40625, | |
| "learning_rate": 4.259746440536392e-06, | |
| "loss": 1.8419511795043946, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.5945969236072214, | |
| "grad_norm": 7.625, | |
| "learning_rate": 4.230011149827049e-06, | |
| "loss": 1.8106534957885743, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.5963203929510104, | |
| "grad_norm": 17.125, | |
| "learning_rate": 4.200303727331714e-06, | |
| "loss": 1.837515640258789, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.5980438622947994, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 4.170625248251423e-06, | |
| "loss": 1.8307241439819335, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.5997673316385885, | |
| "grad_norm": 5.0, | |
| "learning_rate": 4.140976786739658e-06, | |
| "loss": 1.8505414962768554, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.6014908009823775, | |
| "grad_norm": 13.4375, | |
| "learning_rate": 4.111359415863478e-06, | |
| "loss": 1.8339092254638671, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.6032142703261666, | |
| "grad_norm": 8.8125, | |
| "learning_rate": 4.0817742075646785e-06, | |
| "loss": 1.849088478088379, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6032142703261666, | |
| "eval_loss": 1.8238149881362915, | |
| "eval_runtime": 189.2325, | |
| "eval_samples_per_second": 25.027, | |
| "eval_steps_per_second": 3.128, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6049377396699556, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 4.052222232620994e-06, | |
| "loss": 1.8315574645996093, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.6066612090137447, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 4.02270456060734e-06, | |
| "loss": 1.8226449966430665, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.6083846783575337, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 3.993222259857116e-06, | |
| "loss": 1.7947715759277343, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.6101081477013227, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 3.963776397423515e-06, | |
| "loss": 1.8149684906005858, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.6118316170451118, | |
| "grad_norm": 30.875, | |
| "learning_rate": 3.934368039040929e-06, | |
| "loss": 1.7860773086547852, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.6135550863889009, | |
| "grad_norm": 6.28125, | |
| "learning_rate": 3.904998249086362e-06, | |
| "loss": 1.826930618286133, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.6152785557326899, | |
| "grad_norm": 5.5, | |
| "learning_rate": 3.875668090540907e-06, | |
| "loss": 1.8217718124389648, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.6170020250764789, | |
| "grad_norm": 4.5, | |
| "learning_rate": 3.846378624951285e-06, | |
| "loss": 1.824087142944336, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.618725494420268, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 3.817130912391404e-06, | |
| "loss": 1.8421728134155273, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.620448963764057, | |
| "grad_norm": 5.25, | |
| "learning_rate": 3.7879260114240202e-06, | |
| "loss": 1.7913167953491211, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.6221724331078461, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 3.7587649790623925e-06, | |
| "loss": 1.8023431777954102, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.6238959024516352, | |
| "grad_norm": 4.625, | |
| "learning_rate": 3.729648870732058e-06, | |
| "loss": 1.838007354736328, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.6256193717954242, | |
| "grad_norm": 9.125, | |
| "learning_rate": 3.7005787402326064e-06, | |
| "loss": 1.8036937713623047, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.6273428411392132, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 3.6715556396995584e-06, | |
| "loss": 1.8324485778808595, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.6290663104830023, | |
| "grad_norm": 5.75, | |
| "learning_rate": 3.6425806195662777e-06, | |
| "loss": 1.8155427932739259, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.6307897798267913, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 3.613654728525948e-06, | |
| "loss": 1.8596065521240235, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.6325132491705804, | |
| "grad_norm": 5.5, | |
| "learning_rate": 3.584779013493633e-06, | |
| "loss": 1.8445602416992188, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.6342367185143695, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 3.5559545195683644e-06, | |
| "loss": 1.8150409698486327, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.6359601878581584, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 3.527182289995339e-06, | |
| "loss": 1.8006818771362305, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.6376836572019475, | |
| "grad_norm": 10.125, | |
| "learning_rate": 3.4984633661281387e-06, | |
| "loss": 1.7760576248168944, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6394071265457366, | |
| "grad_norm": 6.40625, | |
| "learning_rate": 3.46979878739106e-06, | |
| "loss": 1.8336132049560547, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.6411305958895256, | |
| "grad_norm": 10.6875, | |
| "learning_rate": 3.441189591241484e-06, | |
| "loss": 1.8170570373535155, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.6428540652333147, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 3.412636813132323e-06, | |
| "loss": 1.8622470855712892, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.6445775345771038, | |
| "grad_norm": 152.0, | |
| "learning_rate": 3.3841414864745602e-06, | |
| "loss": 1.8457544326782227, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.6463010039208927, | |
| "grad_norm": 6.6875, | |
| "learning_rate": 3.3557046425998285e-06, | |
| "loss": 1.8270475387573242, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.6480244732646818, | |
| "grad_norm": 13.0625, | |
| "learning_rate": 3.3273273107231007e-06, | |
| "loss": 1.8271034240722657, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.6497479426084708, | |
| "grad_norm": 6.9375, | |
| "learning_rate": 3.2990105179054245e-06, | |
| "loss": 1.823533821105957, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.6514714119522599, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 3.2707552890167636e-06, | |
| "loss": 1.820975112915039, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.653194881296049, | |
| "grad_norm": 162.0, | |
| "learning_rate": 3.2425626466988914e-06, | |
| "loss": 1.7972105026245118, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.6549183506398379, | |
| "grad_norm": 9.3125, | |
| "learning_rate": 3.2144336113283893e-06, | |
| "loss": 1.8197662353515625, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.656641819983627, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 3.186369200979712e-06, | |
| "loss": 1.8468887329101562, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.6583652893274161, | |
| "grad_norm": 11.9375, | |
| "learning_rate": 3.1583704313883346e-06, | |
| "loss": 1.8152883529663086, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.6600887586712051, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 3.130438315914005e-06, | |
| "loss": 1.8321706771850585, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.6618122280149942, | |
| "grad_norm": 3.890625, | |
| "learning_rate": 3.102573865504047e-06, | |
| "loss": 1.794466209411621, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.6635356973587833, | |
| "grad_norm": 6.71875, | |
| "learning_rate": 3.0747780886567922e-06, | |
| "loss": 1.792155647277832, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.6652591667025722, | |
| "grad_norm": 6.53125, | |
| "learning_rate": 3.0470519913850604e-06, | |
| "loss": 1.7653938293457032, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.6669826360463613, | |
| "grad_norm": 8.0625, | |
| "learning_rate": 3.019396577179765e-06, | |
| "loss": 1.8039230346679687, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.6687061053901504, | |
| "grad_norm": 27.0, | |
| "learning_rate": 2.9918128469735853e-06, | |
| "loss": 1.8375740051269531, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.6704295747339394, | |
| "grad_norm": 6.8125, | |
| "learning_rate": 2.964301799104735e-06, | |
| "loss": 1.812276840209961, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.6721530440777285, | |
| "grad_norm": 29.125, | |
| "learning_rate": 2.9368644292808433e-06, | |
| "loss": 1.834174919128418, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.6738765134215176, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 2.909501730542902e-06, | |
| "loss": 1.8168300628662108, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.6755999827653065, | |
| "grad_norm": 21.625, | |
| "learning_rate": 2.88221469322934e-06, | |
| "loss": 1.8631282806396485, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.6773234521090956, | |
| "grad_norm": 9.1875, | |
| "learning_rate": 2.8550043049401593e-06, | |
| "loss": 1.768804168701172, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.6790469214528847, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 2.827871550501218e-06, | |
| "loss": 1.8265512466430665, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.6807703907966737, | |
| "grad_norm": 14.3125, | |
| "learning_rate": 2.8008174119285566e-06, | |
| "loss": 1.8523290634155274, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.6824938601404628, | |
| "grad_norm": 18.0, | |
| "learning_rate": 2.7738428683928824e-06, | |
| "loss": 1.814921760559082, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.6842173294842518, | |
| "grad_norm": 6.90625, | |
| "learning_rate": 2.746948896184114e-06, | |
| "loss": 1.7983022689819337, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.6859407988280408, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 2.7201364686760493e-06, | |
| "loss": 1.8213691711425781, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.6876642681718299, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 2.6934065562911417e-06, | |
| "loss": 1.8135198593139648, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.689387737515619, | |
| "grad_norm": 7.375, | |
| "learning_rate": 2.6667601264653718e-06, | |
| "loss": 1.8103212356567382, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.689387737515619, | |
| "eval_loss": 1.8220584392547607, | |
| "eval_runtime": 189.1065, | |
| "eval_samples_per_second": 25.044, | |
| "eval_steps_per_second": 3.131, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.691111206859408, | |
| "grad_norm": 4.75, | |
| "learning_rate": 2.640198143613237e-06, | |
| "loss": 1.8163627624511718, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.692834676203197, | |
| "grad_norm": 8.8125, | |
| "learning_rate": 2.613721569092841e-06, | |
| "loss": 1.8307807922363282, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.694558145546986, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 2.587331361171107e-06, | |
| "loss": 1.8075574874877929, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.6962816148907751, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 2.561028474989088e-06, | |
| "loss": 1.8375968933105469, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.6980050842345642, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 2.5348138625274004e-06, | |
| "loss": 1.8355876922607421, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.6997285535783532, | |
| "grad_norm": 10.125, | |
| "learning_rate": 2.5086884725717764e-06, | |
| "loss": 1.8059595108032227, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.7014520229221423, | |
| "grad_norm": 12.3125, | |
| "learning_rate": 2.482653250678702e-06, | |
| "loss": 1.832951545715332, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.7031754922659313, | |
| "grad_norm": 7.5625, | |
| "learning_rate": 2.4567091391412274e-06, | |
| "loss": 1.7960575103759766, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.7048989616097203, | |
| "grad_norm": 6.84375, | |
| "learning_rate": 2.4308570769548277e-06, | |
| "loss": 1.7987342834472657, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.7066224309535094, | |
| "grad_norm": 6.25, | |
| "learning_rate": 2.405097999783451e-06, | |
| "loss": 1.8265256881713867, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.7083459002972985, | |
| "grad_norm": 100.0, | |
| "learning_rate": 2.3794328399256235e-06, | |
| "loss": 1.8468996047973634, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.7100693696410875, | |
| "grad_norm": 11.1875, | |
| "learning_rate": 2.353862526280732e-06, | |
| "loss": 1.8254108428955078, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.7117928389848766, | |
| "grad_norm": 7.5, | |
| "learning_rate": 2.3283879843153873e-06, | |
| "loss": 1.8398422241210937, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.7135163083286656, | |
| "grad_norm": 4.5, | |
| "learning_rate": 2.3030101360299377e-06, | |
| "loss": 1.8488418579101562, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.7152397776724546, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 2.2777298999250946e-06, | |
| "loss": 1.834120750427246, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.7169632470162437, | |
| "grad_norm": 9.875, | |
| "learning_rate": 2.2525481909686916e-06, | |
| "loss": 1.8231204986572265, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.7186867163600328, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 2.227465920562567e-06, | |
| "loss": 1.8394210815429688, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.7204101857038218, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 2.2024839965095814e-06, | |
| "loss": 1.829633903503418, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.7221336550476108, | |
| "grad_norm": 9.8125, | |
| "learning_rate": 2.177603322980756e-06, | |
| "loss": 1.8519102096557618, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.7238571243913999, | |
| "grad_norm": 7.28125, | |
| "learning_rate": 2.152824800482552e-06, | |
| "loss": 1.8017757415771485, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.7255805937351889, | |
| "grad_norm": 8.3125, | |
| "learning_rate": 2.1281493258242754e-06, | |
| "loss": 1.8026397705078125, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.727304063078978, | |
| "grad_norm": 9.125, | |
| "learning_rate": 2.1035777920856282e-06, | |
| "loss": 1.806100845336914, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.7290275324227671, | |
| "grad_norm": 18.5, | |
| "learning_rate": 2.079111088584365e-06, | |
| "loss": 1.8078620910644532, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.730751001766556, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 2.0547501008441336e-06, | |
| "loss": 1.8371273040771485, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.7324744711103451, | |
| "grad_norm": 9.8125, | |
| "learning_rate": 2.0304957105623936e-06, | |
| "loss": 1.8442197799682618, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.7341979404541342, | |
| "grad_norm": 6.21875, | |
| "learning_rate": 2.006348795578538e-06, | |
| "loss": 1.8367244720458984, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.7359214097979232, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.9823102298420916e-06, | |
| "loss": 1.8028837203979493, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.7376448791417123, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.958380883381105e-06, | |
| "loss": 1.7981758117675781, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.7393683484855013, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 1.934561622270645e-06, | |
| "loss": 1.839104461669922, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.7410918178292903, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.9108533086014656e-06, | |
| "loss": 1.8137498855590821, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.7428152871730794, | |
| "grad_norm": 12.625, | |
| "learning_rate": 1.8872568004487963e-06, | |
| "loss": 1.8252948760986327, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.7445387565168684, | |
| "grad_norm": 20.25, | |
| "learning_rate": 1.8637729518412861e-06, | |
| "loss": 1.8452091217041016, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.7462622258606575, | |
| "grad_norm": 8.3125, | |
| "learning_rate": 1.8404026127300996e-06, | |
| "loss": 1.8453563690185546, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.7479856952044466, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.8171466289581492e-06, | |
| "loss": 1.8368492126464844, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.7497091645482356, | |
| "grad_norm": 7.125, | |
| "learning_rate": 1.7940058422294825e-06, | |
| "loss": 1.8596685409545899, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.7514326338920246, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.7709810900788226e-06, | |
| "loss": 1.780243492126465, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.7531561032358137, | |
| "grad_norm": 5.71875, | |
| "learning_rate": 1.748073205841247e-06, | |
| "loss": 1.8522743225097655, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.7548795725796027, | |
| "grad_norm": 8.3125, | |
| "learning_rate": 1.7252830186220405e-06, | |
| "loss": 1.8165380477905273, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.7566030419233918, | |
| "grad_norm": 6.125, | |
| "learning_rate": 1.702611353266665e-06, | |
| "loss": 1.8107898712158204, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.7583265112671809, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.6800590303309343e-06, | |
| "loss": 1.8114805221557617, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.7600499806109698, | |
| "grad_norm": 7.15625, | |
| "learning_rate": 1.6576268660512873e-06, | |
| "loss": 1.8261451721191406, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.7617734499547589, | |
| "grad_norm": 9.75, | |
| "learning_rate": 1.635315672315272e-06, | |
| "loss": 1.7968561172485351, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.763496919298548, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.613126256632136e-06, | |
| "loss": 1.8128055572509765, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.765220388642337, | |
| "grad_norm": 8.5, | |
| "learning_rate": 1.5910594221036236e-06, | |
| "loss": 1.8332168579101562, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.7669438579861261, | |
| "grad_norm": 6.375, | |
| "learning_rate": 1.569115967394892e-06, | |
| "loss": 1.8408638000488282, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.7686673273299152, | |
| "grad_norm": 15.8125, | |
| "learning_rate": 1.5472966867056122e-06, | |
| "loss": 1.8163379669189452, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.7703907966737041, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 1.5256023697412242e-06, | |
| "loss": 1.8224592208862305, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.7721142660174932, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.5040338016843552e-06, | |
| "loss": 1.8208709716796876, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.7738377353612823, | |
| "grad_norm": 6.6875, | |
| "learning_rate": 1.482591763166401e-06, | |
| "loss": 1.8458805084228516, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.7755612047050713, | |
| "grad_norm": 8.125, | |
| "learning_rate": 1.461277030239271e-06, | |
| "loss": 1.8372306823730469, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.7755612047050713, | |
| "eval_loss": 1.8214198350906372, | |
| "eval_runtime": 189.2666, | |
| "eval_samples_per_second": 25.023, | |
| "eval_steps_per_second": 3.128, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.7772846740488604, | |
| "grad_norm": 72.0, | |
| "learning_rate": 1.4400903743473032e-06, | |
| "loss": 1.80096435546875, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.7790081433926495, | |
| "grad_norm": 6.0, | |
| "learning_rate": 1.4190325622993434e-06, | |
| "loss": 1.8002546310424805, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.7807316127364384, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.398104356240988e-06, | |
| "loss": 1.7890960693359375, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.7824550820802275, | |
| "grad_norm": 31.125, | |
| "learning_rate": 1.3773065136270036e-06, | |
| "loss": 1.8436212539672852, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.7841785514240165, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.3566397871939147e-06, | |
| "loss": 1.8495201110839843, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.7859020207678056, | |
| "grad_norm": 6.4375, | |
| "learning_rate": 1.336104924932753e-06, | |
| "loss": 1.7932083129882812, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.7876254901115947, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.3157026700619885e-06, | |
| "loss": 1.8371917724609375, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.7893489594553836, | |
| "grad_norm": 10.0, | |
| "learning_rate": 1.2954337610006335e-06, | |
| "loss": 1.8438575744628907, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.7910724287991727, | |
| "grad_norm": 7.25, | |
| "learning_rate": 1.275298931341511e-06, | |
| "loss": 1.7834117889404297, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.7927958981429618, | |
| "grad_norm": 6.0, | |
| "learning_rate": 1.2552989098247092e-06, | |
| "loss": 1.8135692596435546, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.7945193674867508, | |
| "grad_norm": 21.875, | |
| "learning_rate": 1.2354344203112035e-06, | |
| "loss": 1.8180233001708985, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.7962428368305399, | |
| "grad_norm": 5.84375, | |
| "learning_rate": 1.2157061817566568e-06, | |
| "loss": 1.8474626541137695, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.797966306174329, | |
| "grad_norm": 36.5, | |
| "learning_rate": 1.1961149081854006e-06, | |
| "loss": 1.8520895004272462, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.7996897755181179, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.1766613086645928e-06, | |
| "loss": 1.8065855026245117, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.801413244861907, | |
| "grad_norm": 34.5, | |
| "learning_rate": 1.1573460872785503e-06, | |
| "loss": 1.8209779739379883, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.8031367142056961, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 1.1381699431032695e-06, | |
| "loss": 1.830772590637207, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.8048601835494851, | |
| "grad_norm": 7.375, | |
| "learning_rate": 1.1191335701811285e-06, | |
| "loss": 1.8219244003295898, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.8065836528932742, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.100237657495754e-06, | |
| "loss": 1.8321475982666016, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.8083071222370632, | |
| "grad_norm": 9.1875, | |
| "learning_rate": 1.0814828889471047e-06, | |
| "loss": 1.7924293518066405, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.8100305915808522, | |
| "grad_norm": 7.53125, | |
| "learning_rate": 1.062869943326697e-06, | |
| "loss": 1.8244857788085938, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.8117540609246413, | |
| "grad_norm": 6.53125, | |
| "learning_rate": 1.0443994942930592e-06, | |
| "loss": 1.825185775756836, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.8134775302684304, | |
| "grad_norm": 7.25, | |
| "learning_rate": 1.0260722103473314e-06, | |
| "loss": 1.834679412841797, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.8152009996122194, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.0078887548090827e-06, | |
| "loss": 1.8148757934570312, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.8169244689560085, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 9.898497857922978e-07, | |
| "loss": 1.8438005447387695, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.8186479382997975, | |
| "grad_norm": 4.5, | |
| "learning_rate": 9.719559561815584e-07, | |
| "loss": 1.8407489776611328, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.8203714076435865, | |
| "grad_norm": 5.625, | |
| "learning_rate": 9.542079136084154e-07, | |
| "loss": 1.7916162490844727, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.8220948769873756, | |
| "grad_norm": 14.5, | |
| "learning_rate": 9.36606300427948e-07, | |
| "loss": 1.8000501632690429, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.8238183463311647, | |
| "grad_norm": 12.0, | |
| "learning_rate": 9.191517536955152e-07, | |
| "loss": 1.8663785934448243, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.8255418156749537, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 9.018449051436973e-07, | |
| "loss": 1.8362834930419922, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.8272652850187427, | |
| "grad_norm": 28.625, | |
| "learning_rate": 8.846863811594325e-07, | |
| "loss": 1.8352352142333985, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.8289887543625317, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 8.676768027613525e-07, | |
| "loss": 1.824945068359375, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.8307122237063208, | |
| "grad_norm": 23.25, | |
| "learning_rate": 8.508167855772886e-07, | |
| "loss": 1.830651092529297, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.8324356930501099, | |
| "grad_norm": 19.125, | |
| "learning_rate": 8.341069398220147e-07, | |
| "loss": 1.7930862426757812, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.8341591623938989, | |
| "grad_norm": 6.625, | |
| "learning_rate": 8.17547870275136e-07, | |
| "loss": 1.8139684677124024, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.835882631737688, | |
| "grad_norm": 6.25, | |
| "learning_rate": 8.011401762592242e-07, | |
| "loss": 1.8471323013305665, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.837606101081477, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 7.848844516181059e-07, | |
| "loss": 1.8401981353759767, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.839329570425266, | |
| "grad_norm": 6.09375, | |
| "learning_rate": 7.687812846953846e-07, | |
| "loss": 1.8234878540039063, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.8410530397690551, | |
| "grad_norm": 6.375, | |
| "learning_rate": 7.528312583131387e-07, | |
| "loss": 1.8374950408935546, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.8427765091128442, | |
| "grad_norm": 6.65625, | |
| "learning_rate": 7.370349497508294e-07, | |
| "loss": 1.8332042694091797, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.8444999784566332, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 7.213929307244072e-07, | |
| "loss": 1.8149314880371095, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.8462234478004222, | |
| "grad_norm": 6.90625, | |
| "learning_rate": 7.059057673656195e-07, | |
| "loss": 1.8300373077392578, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.8479469171442113, | |
| "grad_norm": 4.375, | |
| "learning_rate": 6.905740202015232e-07, | |
| "loss": 1.8287410736083984, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.8496703864880003, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 6.753982441341928e-07, | |
| "loss": 1.8332706451416017, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.8513938558317894, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 6.603789884206402e-07, | |
| "loss": 1.8314176559448243, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.8531173251755785, | |
| "grad_norm": 6.375, | |
| "learning_rate": 6.455167966529357e-07, | |
| "loss": 1.8223894119262696, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.8548407945193675, | |
| "grad_norm": 5.25, | |
| "learning_rate": 6.308122067385302e-07, | |
| "loss": 1.8024940490722656, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.8565642638631565, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 6.162657508807934e-07, | |
| "loss": 1.8048280715942382, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.8582877332069456, | |
| "grad_norm": 29.875, | |
| "learning_rate": 6.01877955559742e-07, | |
| "loss": 1.8184221267700196, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.8600112025507346, | |
| "grad_norm": 5.0, | |
| "learning_rate": 5.876493415129958e-07, | |
| "loss": 1.8146427154541016, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.8617346718945237, | |
| "grad_norm": 5.625, | |
| "learning_rate": 5.735804237169196e-07, | |
| "loss": 1.8287715911865234, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.8617346718945237, | |
| "eval_loss": 1.82126784324646, | |
| "eval_runtime": 189.0457, | |
| "eval_samples_per_second": 25.052, | |
| "eval_steps_per_second": 3.132, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.8634581412383128, | |
| "grad_norm": 36.75, | |
| "learning_rate": 5.596717113679973e-07, | |
| "loss": 1.804646110534668, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.8651816105821017, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 5.459237078643864e-07, | |
| "loss": 1.8178810119628905, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.8669050799258908, | |
| "grad_norm": 10.25, | |
| "learning_rate": 5.323369107877175e-07, | |
| "loss": 1.8536310195922852, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.8686285492696799, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 5.189118118850661e-07, | |
| "loss": 1.815272903442383, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.8703520186134689, | |
| "grad_norm": 9.8125, | |
| "learning_rate": 5.056488970511714e-07, | |
| "loss": 1.8256004333496094, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.872075487957258, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 4.925486463108397e-07, | |
| "loss": 1.839909553527832, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.873798957301047, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 4.796115338015739e-07, | |
| "loss": 1.8029901504516601, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.875522426644836, | |
| "grad_norm": 7.21875, | |
| "learning_rate": 4.668380277564144e-07, | |
| "loss": 1.8375946044921876, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.8772458959886251, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 4.542285904869903e-07, | |
| "loss": 1.8381671905517578, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.8789693653324141, | |
| "grad_norm": 5.84375, | |
| "learning_rate": 4.417836783667889e-07, | |
| "loss": 1.8078067779541016, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.8806928346762032, | |
| "grad_norm": 6.46875, | |
| "learning_rate": 4.2950374181463636e-07, | |
| "loss": 1.850840187072754, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.8824163040199923, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 4.173892252783962e-07, | |
| "loss": 1.8183349609375, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.8841397733637812, | |
| "grad_norm": 7.375, | |
| "learning_rate": 4.0544056721888713e-07, | |
| "loss": 1.7968463897705078, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.8858632427075703, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 3.936582000940031e-07, | |
| "loss": 1.8175657272338868, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.8875867120513594, | |
| "grad_norm": 7.25, | |
| "learning_rate": 3.8204255034307744e-07, | |
| "loss": 1.8261638641357423, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.8893101813951484, | |
| "grad_norm": 7.5, | |
| "learning_rate": 3.705940383714318e-07, | |
| "loss": 1.8337011337280273, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.8910336507389375, | |
| "grad_norm": 20.0, | |
| "learning_rate": 3.593130785351745e-07, | |
| "loss": 1.8448541641235352, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.8927571200827266, | |
| "grad_norm": 13.8125, | |
| "learning_rate": 3.4820007912619523e-07, | |
| "loss": 1.8629817962646484, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.8944805894265155, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 3.372554423573904e-07, | |
| "loss": 1.8010009765625, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.8962040587703046, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 3.2647956434810556e-07, | |
| "loss": 1.835978126525879, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.8979275281140937, | |
| "grad_norm": 8.875, | |
| "learning_rate": 3.1587283510980003e-07, | |
| "loss": 1.8105642318725585, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 0.8996509974578827, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 3.0543563853192903e-07, | |
| "loss": 1.848411750793457, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.9013744668016718, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 2.951683523680504e-07, | |
| "loss": 1.820380401611328, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 0.9030979361454609, | |
| "grad_norm": 9.8125, | |
| "learning_rate": 2.850713482221529e-07, | |
| "loss": 1.8283926010131837, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.9048214054892498, | |
| "grad_norm": 7.46875, | |
| "learning_rate": 2.751449915352067e-07, | |
| "loss": 1.825888442993164, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.9065448748330389, | |
| "grad_norm": 7.09375, | |
| "learning_rate": 2.65389641571937e-07, | |
| "loss": 1.815310287475586, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.908268344176828, | |
| "grad_norm": 8.625, | |
| "learning_rate": 2.5580565140781943e-07, | |
| "loss": 1.8344499588012695, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 0.909991813520617, | |
| "grad_norm": 6.21875, | |
| "learning_rate": 2.463933679163072e-07, | |
| "loss": 1.8131536483764648, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.9117152828644061, | |
| "grad_norm": 8.875, | |
| "learning_rate": 2.3715313175626585e-07, | |
| "loss": 1.8332439422607423, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 0.9134387522081951, | |
| "grad_norm": 7.25, | |
| "learning_rate": 2.280852773596548e-07, | |
| "loss": 1.826437759399414, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.9151622215519841, | |
| "grad_norm": 9.0, | |
| "learning_rate": 2.1919013291941683e-07, | |
| "loss": 1.816366958618164, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 0.9168856908957732, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 2.1046802037760273e-07, | |
| "loss": 1.8252386093139648, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.9186091602395622, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 2.0191925541371617e-07, | |
| "loss": 1.8262447357177733, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 0.9203326295833513, | |
| "grad_norm": 6.875, | |
| "learning_rate": 1.935441474332922e-07, | |
| "loss": 1.8153100967407227, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.9220560989271404, | |
| "grad_norm": 8.4375, | |
| "learning_rate": 1.8534299955669522e-07, | |
| "loss": 1.8286188125610352, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.9237795682709293, | |
| "grad_norm": 7.78125, | |
| "learning_rate": 1.7731610860815152e-07, | |
| "loss": 1.809466552734375, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.9255030376147184, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.6946376510500406e-07, | |
| "loss": 1.8004470825195313, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 0.9272265069585075, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.617862532471981e-07, | |
| "loss": 1.837824821472168, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.9289499763022965, | |
| "grad_norm": 10.125, | |
| "learning_rate": 1.5428385090699438e-07, | |
| "loss": 1.7913677215576171, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 0.9306734456460856, | |
| "grad_norm": 6.25, | |
| "learning_rate": 1.469568296189172e-07, | |
| "loss": 1.838983917236328, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.9323969149898746, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.3980545456991678e-07, | |
| "loss": 1.8198732376098632, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 0.9341203843336636, | |
| "grad_norm": 65.0, | |
| "learning_rate": 1.328299845897829e-07, | |
| "loss": 1.8647430419921875, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.9358438536774527, | |
| "grad_norm": 7.40625, | |
| "learning_rate": 1.2603067214176756e-07, | |
| "loss": 1.8113037109375, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 0.9375673230212418, | |
| "grad_norm": 6.5, | |
| "learning_rate": 1.1940776331345383e-07, | |
| "loss": 1.8113178253173827, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.9392907923650308, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 1.1296149780784471e-07, | |
| "loss": 1.8082130432128907, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.9410142617088199, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.0669210893469173e-07, | |
| "loss": 1.8550947189331055, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.9427377310526089, | |
| "grad_norm": 6.6875, | |
| "learning_rate": 1.0059982360204834e-07, | |
| "loss": 1.8423307418823243, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 0.9444612003963979, | |
| "grad_norm": 4.5, | |
| "learning_rate": 9.468486230805652e-08, | |
| "loss": 1.829061508178711, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.946184669740187, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 8.894743913296866e-08, | |
| "loss": 1.8378089904785155, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 0.9479081390839761, | |
| "grad_norm": 10.6875, | |
| "learning_rate": 8.338776173139773e-08, | |
| "loss": 1.8404531478881836, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.9479081390839761, | |
| "eval_loss": 1.8212356567382812, | |
| "eval_runtime": 188.6548, | |
| "eval_samples_per_second": 25.104, | |
| "eval_steps_per_second": 3.138, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.9496316084277651, | |
| "grad_norm": 5.375, | |
| "learning_rate": 7.800603132480322e-08, | |
| "loss": 1.8184125900268555, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 0.9513550777715541, | |
| "grad_norm": 6.15625, | |
| "learning_rate": 7.280244269420588e-08, | |
| "loss": 1.868013572692871, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.9530785471153432, | |
| "grad_norm": 5.5, | |
| "learning_rate": 6.777718417314005e-08, | |
| "loss": 1.8153545379638671, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 0.9548020164591322, | |
| "grad_norm": 16.125, | |
| "learning_rate": 6.293043764083684e-08, | |
| "loss": 1.8529928207397461, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.9565254858029213, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 5.826237851564109e-08, | |
| "loss": 1.8267868041992188, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.9582489551467104, | |
| "grad_norm": 6.59375, | |
| "learning_rate": 5.377317574866314e-08, | |
| "loss": 1.8245101928710938, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.9599724244904994, | |
| "grad_norm": 15.9375, | |
| "learning_rate": 4.946299181766201e-08, | |
| "loss": 1.8356136322021483, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 0.9616958938342884, | |
| "grad_norm": 7.75, | |
| "learning_rate": 4.5331982721167345e-08, | |
| "loss": 1.8132728576660155, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.9634193631780774, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 4.138029797283116e-08, | |
| "loss": 1.7819122314453124, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 0.9651428325218665, | |
| "grad_norm": 18.625, | |
| "learning_rate": 3.760808059601939e-08, | |
| "loss": 1.8247360229492187, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.9668663018656556, | |
| "grad_norm": 5.71875, | |
| "learning_rate": 3.4015467118631574e-08, | |
| "loss": 1.8269477844238282, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 0.9685897712094446, | |
| "grad_norm": 6.21875, | |
| "learning_rate": 3.06025875681637e-08, | |
| "loss": 1.8041257858276367, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.9703132405532336, | |
| "grad_norm": 225.0, | |
| "learning_rate": 2.736956546699754e-08, | |
| "loss": 1.8447729110717774, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 0.9720367098970227, | |
| "grad_norm": 4.375, | |
| "learning_rate": 2.4316517827934204e-08, | |
| "loss": 1.831043815612793, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.9737601792408117, | |
| "grad_norm": 5.375, | |
| "learning_rate": 2.1443555149957552e-08, | |
| "loss": 1.8120197296142577, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.9754836485846008, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 1.8750781414232923e-08, | |
| "loss": 1.7766189575195312, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.9772071179283899, | |
| "grad_norm": 14.25, | |
| "learning_rate": 1.6238294080347382e-08, | |
| "loss": 1.8399539947509767, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 0.9789305872721789, | |
| "grad_norm": 7.78125, | |
| "learning_rate": 1.3906184082779218e-08, | |
| "loss": 1.7913579940795898, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.9806540566159679, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.1754535827608327e-08, | |
| "loss": 1.8301204681396483, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 0.982377525959757, | |
| "grad_norm": 10.1875, | |
| "learning_rate": 9.783427189462013e-09, | |
| "loss": 1.8386709213256835, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.984100995303546, | |
| "grad_norm": 8.8125, | |
| "learning_rate": 7.992929508692793e-09, | |
| "loss": 1.8085201263427735, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 0.9858244646473351, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 6.383107588802673e-09, | |
| "loss": 1.7927364349365233, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.9875479339911242, | |
| "grad_norm": 19.0, | |
| "learning_rate": 4.95401969409115e-09, | |
| "loss": 1.8080327987670899, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 0.9892714033349131, | |
| "grad_norm": 15.0, | |
| "learning_rate": 3.70571754755078e-09, | |
| "loss": 1.832293701171875, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.9909948726787022, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 2.6382463289931215e-09, | |
| "loss": 1.833485221862793, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.9927183420224913, | |
| "grad_norm": 5.625, | |
| "learning_rate": 1.7516446734150427e-09, | |
| "loss": 1.8248113632202148, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.9944418113662803, | |
| "grad_norm": 6.25, | |
| "learning_rate": 1.0459446695981756e-09, | |
| "loss": 1.8026580810546875, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 0.9961652807100694, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 5.211718589498427e-10, | |
| "loss": 1.8091909408569335, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.9978887500538585, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 1.7734523457824116e-10, | |
| "loss": 1.8309267044067383, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 0.9996122193976474, | |
| "grad_norm": 9.375, | |
| "learning_rate": 1.4477240602439601e-11, | |
| "loss": 1.8328081130981446, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8212566375732422, | |
| "eval_runtime": 189.0392, | |
| "eval_samples_per_second": 25.053, | |
| "eval_steps_per_second": 3.132, | |
| "step": 5803 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 5803, | |
| "total_flos": 2.9588344254445286e+18, | |
| "train_loss": 1.8961432821972912, | |
| "train_runtime": 37256.7001, | |
| "train_samples_per_second": 6.229, | |
| "train_steps_per_second": 0.156 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5803, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.9588344254445286e+18, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |