Instructions to use Kukedlc/Slopus-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kukedlc/Slopus-9B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Kukedlc/Slopus-9B", dtype="auto") - llama-cpp-python
How to use Kukedlc/Slopus-9B with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Kukedlc/Slopus-9B", filename="Slopus-9B-Q2_K.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Kukedlc/Slopus-9B with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Kukedlc/Slopus-9B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Kukedlc/Slopus-9B:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Kukedlc/Slopus-9B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Kukedlc/Slopus-9B:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Kukedlc/Slopus-9B:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Kukedlc/Slopus-9B:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Kukedlc/Slopus-9B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Kukedlc/Slopus-9B:Q4_K_M
Use Docker
docker model run hf.co/Kukedlc/Slopus-9B:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Kukedlc/Slopus-9B with Ollama:
ollama run hf.co/Kukedlc/Slopus-9B:Q4_K_M
- Unsloth Studio
How to use Kukedlc/Slopus-9B 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 Kukedlc/Slopus-9B 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 Kukedlc/Slopus-9B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Kukedlc/Slopus-9B to start chatting
- Pi
How to use Kukedlc/Slopus-9B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Kukedlc/Slopus-9B:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Kukedlc/Slopus-9B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Kukedlc/Slopus-9B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Kukedlc/Slopus-9B:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Kukedlc/Slopus-9B:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use Kukedlc/Slopus-9B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Kukedlc/Slopus-9B:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "Kukedlc/Slopus-9B:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use Kukedlc/Slopus-9B with Docker Model Runner:
docker model run hf.co/Kukedlc/Slopus-9B:Q4_K_M
- Lemonade
How to use Kukedlc/Slopus-9B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Kukedlc/Slopus-9B:Q4_K_M
Run and chat with the model
lemonade run user.Slopus-9B-Q4_K_M
List all available models
lemonade list
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 758, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002638522427440633, | |
| "grad_norm": 0.3394036889076233, | |
| "learning_rate": 0.0, | |
| "loss": 1.0827826261520386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005277044854881266, | |
| "grad_norm": 0.2860078513622284, | |
| "learning_rate": 5e-06, | |
| "loss": 1.102963924407959, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0079155672823219, | |
| "grad_norm": 0.3322666585445404, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9182360172271729, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010554089709762533, | |
| "grad_norm": 0.29622846841812134, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.9905988574028015, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013192612137203167, | |
| "grad_norm": 0.26111382246017456, | |
| "learning_rate": 2e-05, | |
| "loss": 1.096787691116333, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0158311345646438, | |
| "grad_norm": 0.2614597976207733, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.105420708656311, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018469656992084433, | |
| "grad_norm": 0.2569218873977661, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9514756202697754, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021108179419525065, | |
| "grad_norm": 0.24397169053554535, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.9208998680114746, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023746701846965697, | |
| "grad_norm": 0.30534666776657104, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0918810367584229, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026385224274406333, | |
| "grad_norm": 0.2684849202632904, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.0292065143585205, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029023746701846966, | |
| "grad_norm": 0.26211386919021606, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0240130424499512, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0316622691292876, | |
| "grad_norm": 0.2565249502658844, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.9769070148468018, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03430079155672823, | |
| "grad_norm": 0.26444166898727417, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0853519439697266, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.036939313984168866, | |
| "grad_norm": 0.2618539035320282, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.0640870332717896, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0395778364116095, | |
| "grad_norm": 0.2667272388935089, | |
| "learning_rate": 7e-05, | |
| "loss": 0.998728334903717, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04221635883905013, | |
| "grad_norm": 0.2519418001174927, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9445884227752686, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.044854881266490766, | |
| "grad_norm": 0.23243127763271332, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9943759441375732, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.047493403693931395, | |
| "grad_norm": 0.24636130034923553, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.087374210357666, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05013192612137203, | |
| "grad_norm": 0.2173345983028412, | |
| "learning_rate": 9e-05, | |
| "loss": 1.0086473226547241, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.052770448548812667, | |
| "grad_norm": 0.20626968145370483, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.8200538158416748, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.055408970976253295, | |
| "grad_norm": 0.23201459646224976, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9757561683654785, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05804749340369393, | |
| "grad_norm": 0.20844975113868713, | |
| "learning_rate": 9.999954697061305e-05, | |
| "loss": 0.9280185103416443, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06068601583113457, | |
| "grad_norm": 0.20567265152931213, | |
| "learning_rate": 9.999818789066165e-05, | |
| "loss": 1.0713424682617188, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0633245382585752, | |
| "grad_norm": 0.22238284349441528, | |
| "learning_rate": 9.999592278477388e-05, | |
| "loss": 0.9708124995231628, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06596306068601583, | |
| "grad_norm": 0.2274278849363327, | |
| "learning_rate": 9.999275169399614e-05, | |
| "loss": 1.0282939672470093, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06860158311345646, | |
| "grad_norm": 0.2159455567598343, | |
| "learning_rate": 9.998867467579234e-05, | |
| "loss": 1.1293445825576782, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0712401055408971, | |
| "grad_norm": 0.1889648586511612, | |
| "learning_rate": 9.998369180404283e-05, | |
| "loss": 0.8767735958099365, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07387862796833773, | |
| "grad_norm": 0.2028406262397766, | |
| "learning_rate": 9.997780316904311e-05, | |
| "loss": 1.0634520053863525, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07651715039577836, | |
| "grad_norm": 0.180164635181427, | |
| "learning_rate": 9.997100887750215e-05, | |
| "loss": 0.8971686363220215, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.079155672823219, | |
| "grad_norm": 0.18992403149604797, | |
| "learning_rate": 9.99633090525405e-05, | |
| "loss": 0.9242538809776306, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08179419525065963, | |
| "grad_norm": 0.1975812315940857, | |
| "learning_rate": 9.995470383368808e-05, | |
| "loss": 1.0072821378707886, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08443271767810026, | |
| "grad_norm": 0.21048954129219055, | |
| "learning_rate": 9.994519337688152e-05, | |
| "loss": 1.0022131204605103, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0870712401055409, | |
| "grad_norm": 0.20481035113334656, | |
| "learning_rate": 9.99347778544615e-05, | |
| "loss": 1.032679796218872, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08970976253298153, | |
| "grad_norm": 0.1966608613729477, | |
| "learning_rate": 9.992345745516953e-05, | |
| "loss": 1.0260268449783325, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09234828496042216, | |
| "grad_norm": 0.19506685435771942, | |
| "learning_rate": 9.991123238414455e-05, | |
| "loss": 1.0653270483016968, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09498680738786279, | |
| "grad_norm": 0.19783715903759003, | |
| "learning_rate": 9.989810286291923e-05, | |
| "loss": 1.0186381340026855, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09762532981530343, | |
| "grad_norm": 0.19126851856708527, | |
| "learning_rate": 9.98840691294159e-05, | |
| "loss": 0.9795345067977905, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10026385224274406, | |
| "grad_norm": 0.19075506925582886, | |
| "learning_rate": 9.986913143794232e-05, | |
| "loss": 0.9185978770256042, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10290237467018469, | |
| "grad_norm": 0.20359137654304504, | |
| "learning_rate": 9.985329005918702e-05, | |
| "loss": 1.068305253982544, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10554089709762533, | |
| "grad_norm": 0.17329703271389008, | |
| "learning_rate": 9.983654528021442e-05, | |
| "loss": 0.8745554685592651, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10817941952506596, | |
| "grad_norm": 0.184177964925766, | |
| "learning_rate": 9.981889740445958e-05, | |
| "loss": 1.0511523485183716, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11081794195250659, | |
| "grad_norm": 0.17558042705059052, | |
| "learning_rate": 9.980034675172274e-05, | |
| "loss": 1.0206934213638306, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11345646437994723, | |
| "grad_norm": 0.1741347759962082, | |
| "learning_rate": 9.978089365816357e-05, | |
| "loss": 0.993105947971344, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11609498680738786, | |
| "grad_norm": 0.18105603754520416, | |
| "learning_rate": 9.976053847629496e-05, | |
| "loss": 0.9645117521286011, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11873350923482849, | |
| "grad_norm": 0.18442459404468536, | |
| "learning_rate": 9.973928157497674e-05, | |
| "loss": 1.0399397611618042, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12137203166226913, | |
| "grad_norm": 0.1740163266658783, | |
| "learning_rate": 9.971712333940895e-05, | |
| "loss": 1.0997076034545898, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12401055408970976, | |
| "grad_norm": 0.16615112125873566, | |
| "learning_rate": 9.969406417112489e-05, | |
| "loss": 0.9800876379013062, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1266490765171504, | |
| "grad_norm": 0.17227014899253845, | |
| "learning_rate": 9.967010448798375e-05, | |
| "loss": 0.9780592918395996, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12928759894459102, | |
| "grad_norm": 0.20567218959331512, | |
| "learning_rate": 9.964524472416319e-05, | |
| "loss": 1.0072335004806519, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13192612137203166, | |
| "grad_norm": 0.18364901840686798, | |
| "learning_rate": 9.961948533015133e-05, | |
| "loss": 1.0017499923706055, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1345646437994723, | |
| "grad_norm": 0.1748533993959427, | |
| "learning_rate": 9.95928267727387e-05, | |
| "loss": 0.9483516216278076, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.13720316622691292, | |
| "grad_norm": 0.17033548653125763, | |
| "learning_rate": 9.956526953500964e-05, | |
| "loss": 0.9018915891647339, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13984168865435356, | |
| "grad_norm": 0.1777356117963791, | |
| "learning_rate": 9.953681411633376e-05, | |
| "loss": 0.9655129909515381, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1424802110817942, | |
| "grad_norm": 0.1858673244714737, | |
| "learning_rate": 9.950746103235663e-05, | |
| "loss": 1.0894356966018677, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.14511873350923482, | |
| "grad_norm": 0.16702871024608612, | |
| "learning_rate": 9.947721081499068e-05, | |
| "loss": 0.9454880952835083, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14775725593667546, | |
| "grad_norm": 0.16913406550884247, | |
| "learning_rate": 9.944606401240539e-05, | |
| "loss": 0.9937676191329956, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1503957783641161, | |
| "grad_norm": 0.17091500759124756, | |
| "learning_rate": 9.941402118901744e-05, | |
| "loss": 0.9700629711151123, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.15303430079155672, | |
| "grad_norm": 0.18050940334796906, | |
| "learning_rate": 9.938108292548044e-05, | |
| "loss": 1.009847640991211, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.15567282321899736, | |
| "grad_norm": 0.1656666100025177, | |
| "learning_rate": 9.934724981867446e-05, | |
| "loss": 0.9251805543899536, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.158311345646438, | |
| "grad_norm": 0.17462797462940216, | |
| "learning_rate": 9.931252248169518e-05, | |
| "loss": 0.9192997813224792, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16094986807387862, | |
| "grad_norm": 0.1910332590341568, | |
| "learning_rate": 9.927690154384273e-05, | |
| "loss": 0.9398717880249023, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.16358839050131926, | |
| "grad_norm": 0.17913269996643066, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.9283158779144287, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1662269129287599, | |
| "grad_norm": 0.17269554734230042, | |
| "learning_rate": 9.920298146367286e-05, | |
| "loss": 0.9414621591567993, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.16886543535620052, | |
| "grad_norm": 0.15802136063575745, | |
| "learning_rate": 9.916468366087417e-05, | |
| "loss": 1.0821268558502197, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.17150395778364116, | |
| "grad_norm": 0.16915935277938843, | |
| "learning_rate": 9.912549493621554e-05, | |
| "loss": 0.909949541091919, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1741424802110818, | |
| "grad_norm": 0.181443452835083, | |
| "learning_rate": 9.908541599984276e-05, | |
| "loss": 1.0008492469787598, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.17678100263852242, | |
| "grad_norm": 0.1813468486070633, | |
| "learning_rate": 9.904444757803321e-05, | |
| "loss": 0.9849015474319458, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17941952506596306, | |
| "grad_norm": 0.18925133347511292, | |
| "learning_rate": 9.900259041318289e-05, | |
| "loss": 1.089128017425537, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1820580474934037, | |
| "grad_norm": 0.17448389530181885, | |
| "learning_rate": 9.895984526379281e-05, | |
| "loss": 1.0046229362487793, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.18469656992084432, | |
| "grad_norm": 0.16590456664562225, | |
| "learning_rate": 9.891621290445534e-05, | |
| "loss": 0.9553288221359253, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18733509234828497, | |
| "grad_norm": 0.18540161848068237, | |
| "learning_rate": 9.887169412584011e-05, | |
| "loss": 1.0598280429840088, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.18997361477572558, | |
| "grad_norm": 0.1836412101984024, | |
| "learning_rate": 9.882628973467972e-05, | |
| "loss": 1.0192971229553223, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.19261213720316622, | |
| "grad_norm": 0.1572759449481964, | |
| "learning_rate": 9.878000055375512e-05, | |
| "loss": 1.0670673847198486, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.19525065963060687, | |
| "grad_norm": 0.16847407817840576, | |
| "learning_rate": 9.873282742188066e-05, | |
| "loss": 1.0559749603271484, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.19788918205804748, | |
| "grad_norm": 0.18431080877780914, | |
| "learning_rate": 9.868477119388896e-05, | |
| "loss": 1.0605112314224243, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.20052770448548812, | |
| "grad_norm": 0.17507214844226837, | |
| "learning_rate": 9.863583274061534e-05, | |
| "loss": 0.9671310186386108, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.20316622691292877, | |
| "grad_norm": 0.169069305062294, | |
| "learning_rate": 9.858601294888213e-05, | |
| "loss": 0.9900617003440857, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.20580474934036938, | |
| "grad_norm": 0.1741606891155243, | |
| "learning_rate": 9.853531272148249e-05, | |
| "loss": 1.0460593700408936, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.20844327176781002, | |
| "grad_norm": 0.18498769402503967, | |
| "learning_rate": 9.848373297716414e-05, | |
| "loss": 1.0282113552093506, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.21108179419525067, | |
| "grad_norm": 0.15732872486114502, | |
| "learning_rate": 9.84312746506127e-05, | |
| "loss": 0.9001719951629639, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21372031662269128, | |
| "grad_norm": 0.18386222422122955, | |
| "learning_rate": 9.837793869243468e-05, | |
| "loss": 0.9183194637298584, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.21635883905013192, | |
| "grad_norm": 0.17975150048732758, | |
| "learning_rate": 9.832372606914037e-05, | |
| "loss": 1.0881237983703613, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.21899736147757257, | |
| "grad_norm": 0.17720025777816772, | |
| "learning_rate": 9.82686377631262e-05, | |
| "loss": 0.9983437061309814, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.22163588390501318, | |
| "grad_norm": 0.18643102049827576, | |
| "learning_rate": 9.821267477265705e-05, | |
| "loss": 1.1010072231292725, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.22427440633245382, | |
| "grad_norm": 0.19078285992145538, | |
| "learning_rate": 9.815583811184808e-05, | |
| "loss": 1.091160774230957, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22691292875989447, | |
| "grad_norm": 0.1700907051563263, | |
| "learning_rate": 9.80981288106464e-05, | |
| "loss": 0.9641087055206299, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.22955145118733508, | |
| "grad_norm": 0.1585739403963089, | |
| "learning_rate": 9.803954791481239e-05, | |
| "loss": 0.9505077600479126, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.23218997361477572, | |
| "grad_norm": 0.16782094538211823, | |
| "learning_rate": 9.798009648590072e-05, | |
| "loss": 1.0017526149749756, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.23482849604221637, | |
| "grad_norm": 0.17637847363948822, | |
| "learning_rate": 9.791977560124119e-05, | |
| "loss": 0.9929439425468445, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.23746701846965698, | |
| "grad_norm": 0.17673365771770477, | |
| "learning_rate": 9.785858635391914e-05, | |
| "loss": 1.0124274492263794, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.24010554089709762, | |
| "grad_norm": 0.16427874565124512, | |
| "learning_rate": 9.779652985275562e-05, | |
| "loss": 0.8820173144340515, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.24274406332453827, | |
| "grad_norm": 0.1866939812898636, | |
| "learning_rate": 9.773360722228742e-05, | |
| "loss": 0.9582796096801758, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.24538258575197888, | |
| "grad_norm": 0.16584990918636322, | |
| "learning_rate": 9.766981960274653e-05, | |
| "loss": 0.9931353330612183, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.24802110817941952, | |
| "grad_norm": 0.1827409565448761, | |
| "learning_rate": 9.760516815003964e-05, | |
| "loss": 1.0762715339660645, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.25065963060686014, | |
| "grad_norm": 0.1706336885690689, | |
| "learning_rate": 9.753965403572703e-05, | |
| "loss": 0.9621766805648804, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2532981530343008, | |
| "grad_norm": 0.17512862384319305, | |
| "learning_rate": 9.747327844700147e-05, | |
| "loss": 1.0493756532669067, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2559366754617414, | |
| "grad_norm": 0.1861727088689804, | |
| "learning_rate": 9.740604258666668e-05, | |
| "loss": 0.9710463285446167, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.25857519788918204, | |
| "grad_norm": 0.17469093203544617, | |
| "learning_rate": 9.733794767311544e-05, | |
| "loss": 1.0105197429656982, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2612137203166227, | |
| "grad_norm": 0.1550728976726532, | |
| "learning_rate": 9.726899494030768e-05, | |
| "loss": 0.8987333178520203, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2638522427440633, | |
| "grad_norm": 0.17990083992481232, | |
| "learning_rate": 9.719918563774792e-05, | |
| "loss": 0.8861106038093567, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26649076517150394, | |
| "grad_norm": 0.15576201677322388, | |
| "learning_rate": 9.71285210304628e-05, | |
| "loss": 1.059525728225708, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.2691292875989446, | |
| "grad_norm": 0.16039283573627472, | |
| "learning_rate": 9.705700239897809e-05, | |
| "loss": 0.9966175556182861, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2717678100263852, | |
| "grad_norm": 0.1752789467573166, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.9518905878067017, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.27440633245382584, | |
| "grad_norm": 0.18624742329120636, | |
| "learning_rate": 9.691140826286893e-05, | |
| "loss": 0.9436296224594116, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.2770448548812665, | |
| "grad_norm": 0.160239577293396, | |
| "learning_rate": 9.683733539658139e-05, | |
| "loss": 1.0474563837051392, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2796833773087071, | |
| "grad_norm": 0.1599990278482437, | |
| "learning_rate": 9.676241378272021e-05, | |
| "loss": 1.0836262702941895, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.28232189973614774, | |
| "grad_norm": 0.1549750417470932, | |
| "learning_rate": 9.66866447789531e-05, | |
| "loss": 0.9756717085838318, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.2849604221635884, | |
| "grad_norm": 0.1627299189567566, | |
| "learning_rate": 9.661002975830349e-05, | |
| "loss": 0.9459734559059143, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.287598944591029, | |
| "grad_norm": 0.15503612160682678, | |
| "learning_rate": 9.653257010912559e-05, | |
| "loss": 0.9717468023300171, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.29023746701846964, | |
| "grad_norm": 0.16452868282794952, | |
| "learning_rate": 9.645426723507929e-05, | |
| "loss": 0.9126809239387512, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2928759894459103, | |
| "grad_norm": 0.17188014090061188, | |
| "learning_rate": 9.637512255510475e-05, | |
| "loss": 0.9921525120735168, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.2955145118733509, | |
| "grad_norm": 0.1495610475540161, | |
| "learning_rate": 9.629513750339655e-05, | |
| "loss": 0.866377592086792, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.29815303430079154, | |
| "grad_norm": 0.17267285287380219, | |
| "learning_rate": 9.621431352937789e-05, | |
| "loss": 0.9987406730651855, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.3007915567282322, | |
| "grad_norm": 0.15371519327163696, | |
| "learning_rate": 9.613265209767417e-05, | |
| "loss": 0.8675357103347778, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.3034300791556728, | |
| "grad_norm": 0.169174462556839, | |
| "learning_rate": 9.605015468808651e-05, | |
| "loss": 0.9573705792427063, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.30606860158311344, | |
| "grad_norm": 0.17276419699192047, | |
| "learning_rate": 9.596682279556498e-05, | |
| "loss": 1.0629740953445435, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.3087071240105541, | |
| "grad_norm": 0.16400578618049622, | |
| "learning_rate": 9.58826579301814e-05, | |
| "loss": 0.9535355567932129, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.3113456464379947, | |
| "grad_norm": 0.18149444460868835, | |
| "learning_rate": 9.579766161710209e-05, | |
| "loss": 1.0182714462280273, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.31398416886543534, | |
| "grad_norm": 0.17230141162872314, | |
| "learning_rate": 9.571183539656011e-05, | |
| "loss": 1.0627704858779907, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.316622691292876, | |
| "grad_norm": 0.16222770512104034, | |
| "learning_rate": 9.56251808238275e-05, | |
| "loss": 1.0022966861724854, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31926121372031663, | |
| "grad_norm": 0.1661306470632553, | |
| "learning_rate": 9.553769946918697e-05, | |
| "loss": 0.9902384877204895, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.32189973614775724, | |
| "grad_norm": 0.1522214263677597, | |
| "learning_rate": 9.544939291790351e-05, | |
| "loss": 1.0071738958358765, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3245382585751979, | |
| "grad_norm": 0.1561179757118225, | |
| "learning_rate": 9.536026277019561e-05, | |
| "loss": 1.0049107074737549, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.32717678100263853, | |
| "grad_norm": 0.16295814514160156, | |
| "learning_rate": 9.527031064120632e-05, | |
| "loss": 0.9579784870147705, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.32981530343007914, | |
| "grad_norm": 0.1570494920015335, | |
| "learning_rate": 9.517953816097396e-05, | |
| "loss": 0.9788990020751953, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3324538258575198, | |
| "grad_norm": 0.1672319918870926, | |
| "learning_rate": 9.508794697440257e-05, | |
| "loss": 1.018532395362854, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.33509234828496043, | |
| "grad_norm": 0.1804421991109848, | |
| "learning_rate": 9.499553874123212e-05, | |
| "loss": 0.9944267272949219, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.33773087071240104, | |
| "grad_norm": 0.17225806415081024, | |
| "learning_rate": 9.490231513600843e-05, | |
| "loss": 1.0111069679260254, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.3403693931398417, | |
| "grad_norm": 0.15516908466815948, | |
| "learning_rate": 9.480827784805278e-05, | |
| "loss": 0.9605324268341064, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.34300791556728233, | |
| "grad_norm": 0.16040503978729248, | |
| "learning_rate": 9.47134285814314e-05, | |
| "loss": 0.933555006980896, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34564643799472294, | |
| "grad_norm": 0.18396888673305511, | |
| "learning_rate": 9.461776905492446e-05, | |
| "loss": 1.0374318361282349, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.3482849604221636, | |
| "grad_norm": 0.17078086733818054, | |
| "learning_rate": 9.452130100199503e-05, | |
| "loss": 0.9799578785896301, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.35092348284960423, | |
| "grad_norm": 0.1631857305765152, | |
| "learning_rate": 9.442402617075765e-05, | |
| "loss": 0.9599941968917847, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.35356200527704484, | |
| "grad_norm": 0.15046699345111847, | |
| "learning_rate": 9.43259463239466e-05, | |
| "loss": 0.9483698010444641, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.3562005277044855, | |
| "grad_norm": 0.14928267896175385, | |
| "learning_rate": 9.422706323888397e-05, | |
| "loss": 0.8940687775611877, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.35883905013192613, | |
| "grad_norm": 0.17583905160427094, | |
| "learning_rate": 9.412737870744752e-05, | |
| "loss": 0.8684873580932617, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.36147757255936674, | |
| "grad_norm": 0.16805775463581085, | |
| "learning_rate": 9.402689453603815e-05, | |
| "loss": 1.027605652809143, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.3641160949868074, | |
| "grad_norm": 0.16120663285255432, | |
| "learning_rate": 9.392561254554713e-05, | |
| "loss": 0.9406588673591614, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.36675461741424803, | |
| "grad_norm": 0.16707223653793335, | |
| "learning_rate": 9.382353457132317e-05, | |
| "loss": 1.0448381900787354, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.36939313984168864, | |
| "grad_norm": 0.17459368705749512, | |
| "learning_rate": 9.372066246313921e-05, | |
| "loss": 0.9596197605133057, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3720316622691293, | |
| "grad_norm": 0.16556183993816376, | |
| "learning_rate": 9.361699808515876e-05, | |
| "loss": 1.0335559844970703, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.37467018469656993, | |
| "grad_norm": 0.16449083387851715, | |
| "learning_rate": 9.351254331590215e-05, | |
| "loss": 0.9463608860969543, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.37730870712401055, | |
| "grad_norm": 0.16412568092346191, | |
| "learning_rate": 9.340730004821266e-05, | |
| "loss": 0.9579424858093262, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.37994722955145116, | |
| "grad_norm": 0.176985964179039, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0462236404418945, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.38258575197889183, | |
| "grad_norm": 0.1623564213514328, | |
| "learning_rate": 9.31944556603157e-05, | |
| "loss": 0.9870291948318481, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.38522427440633245, | |
| "grad_norm": 0.18084806203842163, | |
| "learning_rate": 9.308685839709879e-05, | |
| "loss": 1.0054789781570435, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.38786279683377306, | |
| "grad_norm": 0.18217523396015167, | |
| "learning_rate": 9.297848034936006e-05, | |
| "loss": 1.019425868988037, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.39050131926121373, | |
| "grad_norm": 0.15862634778022766, | |
| "learning_rate": 9.286932348103716e-05, | |
| "loss": 0.8727700710296631, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.39313984168865435, | |
| "grad_norm": 0.17286421358585358, | |
| "learning_rate": 9.275938977018081e-05, | |
| "loss": 1.0189862251281738, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.39577836411609496, | |
| "grad_norm": 0.16580720245838165, | |
| "learning_rate": 9.264868120891912e-05, | |
| "loss": 1.0655592679977417, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.39841688654353563, | |
| "grad_norm": 0.16368559002876282, | |
| "learning_rate": 9.253719980342135e-05, | |
| "loss": 0.937400221824646, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.40105540897097625, | |
| "grad_norm": 0.1721360981464386, | |
| "learning_rate": 9.24249475738616e-05, | |
| "loss": 0.9234015941619873, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.40369393139841686, | |
| "grad_norm": 0.18208572268486023, | |
| "learning_rate": 9.231192655438221e-05, | |
| "loss": 1.0558464527130127, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.40633245382585753, | |
| "grad_norm": 0.1552550047636032, | |
| "learning_rate": 9.219813879305692e-05, | |
| "loss": 0.9326491355895996, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.40897097625329815, | |
| "grad_norm": 0.1624125838279724, | |
| "learning_rate": 9.208358635185373e-05, | |
| "loss": 1.020031452178955, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.41160949868073876, | |
| "grad_norm": 0.1575743854045868, | |
| "learning_rate": 9.19682713065975e-05, | |
| "loss": 1.0257234573364258, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.41424802110817943, | |
| "grad_norm": 0.14020493626594543, | |
| "learning_rate": 9.185219574693242e-05, | |
| "loss": 0.9181210994720459, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.41688654353562005, | |
| "grad_norm": 0.18366360664367676, | |
| "learning_rate": 9.173536177628409e-05, | |
| "loss": 1.1496880054473877, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.41952506596306066, | |
| "grad_norm": 0.15704800188541412, | |
| "learning_rate": 9.161777151182136e-05, | |
| "loss": 0.9523612260818481, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.42216358839050133, | |
| "grad_norm": 0.20316386222839355, | |
| "learning_rate": 9.149942708441808e-05, | |
| "loss": 1.1875518560409546, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.42480211081794195, | |
| "grad_norm": 0.16364015638828278, | |
| "learning_rate": 9.138033063861436e-05, | |
| "loss": 0.9598340392112732, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.42744063324538256, | |
| "grad_norm": 0.17661993205547333, | |
| "learning_rate": 9.126048433257779e-05, | |
| "loss": 1.0217077732086182, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.43007915567282323, | |
| "grad_norm": 0.1741223782300949, | |
| "learning_rate": 9.113989033806434e-05, | |
| "loss": 1.0106780529022217, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.43271767810026385, | |
| "grad_norm": 0.1821887344121933, | |
| "learning_rate": 9.101855084037894e-05, | |
| "loss": 0.992047905921936, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.43535620052770446, | |
| "grad_norm": 0.1628859043121338, | |
| "learning_rate": 9.089646803833589e-05, | |
| "loss": 1.083019733428955, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.43799472295514513, | |
| "grad_norm": 0.1696838140487671, | |
| "learning_rate": 9.077364414421909e-05, | |
| "loss": 1.0616456270217896, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.44063324538258575, | |
| "grad_norm": 0.17563055455684662, | |
| "learning_rate": 9.065008138374189e-05, | |
| "loss": 0.981091320514679, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.44327176781002636, | |
| "grad_norm": 0.16527481377124786, | |
| "learning_rate": 9.052578199600675e-05, | |
| "loss": 0.9541459083557129, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.44591029023746703, | |
| "grad_norm": 0.1794591099023819, | |
| "learning_rate": 9.040074823346465e-05, | |
| "loss": 0.9892167448997498, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.44854881266490765, | |
| "grad_norm": 0.1672830432653427, | |
| "learning_rate": 9.027498236187439e-05, | |
| "loss": 1.0351946353912354, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.45118733509234826, | |
| "grad_norm": 0.17655089497566223, | |
| "learning_rate": 9.014848666026138e-05, | |
| "loss": 0.9711981415748596, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.45382585751978893, | |
| "grad_norm": 0.1557280719280243, | |
| "learning_rate": 9.002126342087642e-05, | |
| "loss": 0.9778252840042114, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.45646437994722955, | |
| "grad_norm": 0.17430546879768372, | |
| "learning_rate": 8.989331494915417e-05, | |
| "loss": 1.0428410768508911, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.45910290237467016, | |
| "grad_norm": 0.1841093748807907, | |
| "learning_rate": 8.976464356367134e-05, | |
| "loss": 0.9610801935195923, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.46174142480211083, | |
| "grad_norm": 0.18140369653701782, | |
| "learning_rate": 8.963525159610465e-05, | |
| "loss": 1.0488272905349731, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.46437994722955145, | |
| "grad_norm": 0.16312600672245026, | |
| "learning_rate": 8.950514139118868e-05, | |
| "loss": 0.995346188545227, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.46701846965699206, | |
| "grad_norm": 0.18155968189239502, | |
| "learning_rate": 8.937431530667328e-05, | |
| "loss": 1.089247226715088, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.46965699208443273, | |
| "grad_norm": 0.16854368150234222, | |
| "learning_rate": 8.92427757132809e-05, | |
| "loss": 1.0536508560180664, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.47229551451187335, | |
| "grad_norm": 0.16431039571762085, | |
| "learning_rate": 8.911052499466357e-05, | |
| "loss": 0.9526739716529846, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.47493403693931396, | |
| "grad_norm": 0.16609320044517517, | |
| "learning_rate": 8.897756554735977e-05, | |
| "loss": 1.0196548700332642, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.47757255936675463, | |
| "grad_norm": 0.16544099152088165, | |
| "learning_rate": 8.884389978075098e-05, | |
| "loss": 0.9600881338119507, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.48021108179419525, | |
| "grad_norm": 0.18530991673469543, | |
| "learning_rate": 8.870953011701804e-05, | |
| "loss": 1.0501227378845215, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.48284960422163586, | |
| "grad_norm": 0.147592693567276, | |
| "learning_rate": 8.857445899109715e-05, | |
| "loss": 1.0376373529434204, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.48548812664907653, | |
| "grad_norm": 0.19425112009048462, | |
| "learning_rate": 8.843868885063593e-05, | |
| "loss": 1.0233935117721558, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.48812664907651715, | |
| "grad_norm": 0.15668635070323944, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.0277446508407593, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.49076517150395776, | |
| "grad_norm": 0.1669091135263443, | |
| "learning_rate": 8.8165061379973e-05, | |
| "loss": 1.032301425933838, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.49340369393139843, | |
| "grad_norm": 0.1691151261329651, | |
| "learning_rate": 8.80272090082227e-05, | |
| "loss": 0.9066123366355896, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.49604221635883905, | |
| "grad_norm": 0.17567206919193268, | |
| "learning_rate": 8.788866753874503e-05, | |
| "loss": 1.017852544784546, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.49868073878627966, | |
| "grad_norm": 0.17546191811561584, | |
| "learning_rate": 8.774943948207426e-05, | |
| "loss": 1.0644317865371704, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.5013192612137203, | |
| "grad_norm": 0.16563469171524048, | |
| "learning_rate": 8.760952736118644e-05, | |
| "loss": 1.0079925060272217, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.503957783641161, | |
| "grad_norm": 0.15652592480182648, | |
| "learning_rate": 8.746893371145366e-05, | |
| "loss": 0.9726508855819702, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.5065963060686016, | |
| "grad_norm": 0.16774515807628632, | |
| "learning_rate": 8.732766108059813e-05, | |
| "loss": 1.0333598852157593, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.5092348284960422, | |
| "grad_norm": 0.19023677706718445, | |
| "learning_rate": 8.718571202864598e-05, | |
| "loss": 1.0274595022201538, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.5118733509234829, | |
| "grad_norm": 0.16863608360290527, | |
| "learning_rate": 8.70430891278809e-05, | |
| "loss": 0.990319013595581, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.5145118733509235, | |
| "grad_norm": 0.1866767555475235, | |
| "learning_rate": 8.689979496279746e-05, | |
| "loss": 1.0066261291503906, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5171503957783641, | |
| "grad_norm": 0.1698773354291916, | |
| "learning_rate": 8.675583213005443e-05, | |
| "loss": 1.0301073789596558, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.5197889182058048, | |
| "grad_norm": 0.18543866276741028, | |
| "learning_rate": 8.661120323842751e-05, | |
| "loss": 1.0110327005386353, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.5224274406332454, | |
| "grad_norm": 0.17273621261119843, | |
| "learning_rate": 8.646591090876224e-05, | |
| "loss": 0.942511796951294, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.525065963060686, | |
| "grad_norm": 0.17858357727527618, | |
| "learning_rate": 8.631995777392645e-05, | |
| "loss": 0.9492037892341614, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.5277044854881267, | |
| "grad_norm": 0.21972784399986267, | |
| "learning_rate": 8.61733464787625e-05, | |
| "loss": 1.125957727432251, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5303430079155673, | |
| "grad_norm": 0.17801721394062042, | |
| "learning_rate": 8.602607968003935e-05, | |
| "loss": 1.0186785459518433, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.5329815303430079, | |
| "grad_norm": 0.1811058521270752, | |
| "learning_rate": 8.587816004640456e-05, | |
| "loss": 1.0295569896697998, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.5356200527704486, | |
| "grad_norm": 0.1558198630809784, | |
| "learning_rate": 8.572959025833573e-05, | |
| "loss": 0.882567286491394, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.5382585751978892, | |
| "grad_norm": 0.1586204618215561, | |
| "learning_rate": 8.558037300809208e-05, | |
| "loss": 0.8986984491348267, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.5408970976253298, | |
| "grad_norm": 0.17992497980594635, | |
| "learning_rate": 8.543051099966558e-05, | |
| "loss": 0.9992472529411316, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5435356200527705, | |
| "grad_norm": 0.16778439283370972, | |
| "learning_rate": 8.528000694873198e-05, | |
| "loss": 0.9697674512863159, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.5461741424802111, | |
| "grad_norm": 0.15742550790309906, | |
| "learning_rate": 8.512886358260162e-05, | |
| "loss": 0.9573698043823242, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.5488126649076517, | |
| "grad_norm": 0.16890263557434082, | |
| "learning_rate": 8.49770836401699e-05, | |
| "loss": 0.8758108615875244, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.5514511873350924, | |
| "grad_norm": 0.16583888232707977, | |
| "learning_rate": 8.482466987186785e-05, | |
| "loss": 0.9687983989715576, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.554089709762533, | |
| "grad_norm": 0.17507483065128326, | |
| "learning_rate": 8.467162503961208e-05, | |
| "loss": 1.0307694673538208, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5567282321899736, | |
| "grad_norm": 0.1639733910560608, | |
| "learning_rate": 8.451795191675488e-05, | |
| "loss": 0.9487868547439575, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.5593667546174143, | |
| "grad_norm": 0.18524755537509918, | |
| "learning_rate": 8.436365328803385e-05, | |
| "loss": 1.0524779558181763, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.5620052770448549, | |
| "grad_norm": 0.1726824939250946, | |
| "learning_rate": 8.420873194952152e-05, | |
| "loss": 1.0479933023452759, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.5646437994722955, | |
| "grad_norm": 0.15832193195819855, | |
| "learning_rate": 8.405319070857467e-05, | |
| "loss": 0.9252246022224426, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.5672823218997362, | |
| "grad_norm": 0.18013589084148407, | |
| "learning_rate": 8.389703238378339e-05, | |
| "loss": 1.035888671875, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5699208443271768, | |
| "grad_norm": 0.1560203582048416, | |
| "learning_rate": 8.374025980492011e-05, | |
| "loss": 0.9540398120880127, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.5725593667546174, | |
| "grad_norm": 0.16869907081127167, | |
| "learning_rate": 8.358287581288822e-05, | |
| "loss": 1.0841728448867798, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.575197889182058, | |
| "grad_norm": 0.1753094494342804, | |
| "learning_rate": 8.342488325967068e-05, | |
| "loss": 1.0053566694259644, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.5778364116094987, | |
| "grad_norm": 0.16862048208713531, | |
| "learning_rate": 8.326628500827826e-05, | |
| "loss": 0.9311268329620361, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.5804749340369393, | |
| "grad_norm": 0.1801312416791916, | |
| "learning_rate": 8.310708393269772e-05, | |
| "loss": 0.9063538908958435, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.58311345646438, | |
| "grad_norm": 0.18925103545188904, | |
| "learning_rate": 8.294728291783966e-05, | |
| "loss": 1.0815038681030273, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.5857519788918206, | |
| "grad_norm": 0.18007421493530273, | |
| "learning_rate": 8.278688485948633e-05, | |
| "loss": 1.0415452718734741, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.5883905013192612, | |
| "grad_norm": 0.1658685952425003, | |
| "learning_rate": 8.262589266423908e-05, | |
| "loss": 0.9547388553619385, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.5910290237467019, | |
| "grad_norm": 0.16324631869792938, | |
| "learning_rate": 8.246430924946575e-05, | |
| "loss": 0.900030791759491, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.5936675461741425, | |
| "grad_norm": 0.17047886550426483, | |
| "learning_rate": 8.230213754324773e-05, | |
| "loss": 0.914841890335083, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5963060686015831, | |
| "grad_norm": 0.18901900947093964, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.8218327760696411, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.5989445910290238, | |
| "grad_norm": 0.18023498356342316, | |
| "learning_rate": 8.197604102205271e-05, | |
| "loss": 1.0853064060211182, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.6015831134564644, | |
| "grad_norm": 0.16877271234989166, | |
| "learning_rate": 8.181212211632799e-05, | |
| "loss": 0.9420395493507385, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.604221635883905, | |
| "grad_norm": 0.1619059145450592, | |
| "learning_rate": 8.16476267375561e-05, | |
| "loss": 0.9768050909042358, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.6068601583113457, | |
| "grad_norm": 0.18686461448669434, | |
| "learning_rate": 8.14825578665866e-05, | |
| "loss": 1.000288486480713, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6094986807387863, | |
| "grad_norm": 0.1876915544271469, | |
| "learning_rate": 8.131691849466153e-05, | |
| "loss": 1.0954421758651733, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.6121372031662269, | |
| "grad_norm": 0.17862121760845184, | |
| "learning_rate": 8.115071162336098e-05, | |
| "loss": 0.9122456908226013, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.6147757255936676, | |
| "grad_norm": 0.17977792024612427, | |
| "learning_rate": 8.098394026454885e-05, | |
| "loss": 0.9491496086120605, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.6174142480211082, | |
| "grad_norm": 0.1632521152496338, | |
| "learning_rate": 8.081660744031819e-05, | |
| "loss": 0.9856275916099548, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.6200527704485488, | |
| "grad_norm": 0.17910513281822205, | |
| "learning_rate": 8.064871618293646e-05, | |
| "loss": 1.0011181831359863, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.6226912928759895, | |
| "grad_norm": 0.1681145429611206, | |
| "learning_rate": 8.048026953479062e-05, | |
| "loss": 0.973308801651001, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.6253298153034301, | |
| "grad_norm": 0.18468503654003143, | |
| "learning_rate": 8.03112705483319e-05, | |
| "loss": 1.0287890434265137, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.6279683377308707, | |
| "grad_norm": 0.16042198240756989, | |
| "learning_rate": 8.014172228602064e-05, | |
| "loss": 0.9670297503471375, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.6306068601583114, | |
| "grad_norm": 0.16996483504772186, | |
| "learning_rate": 7.997162782027061e-05, | |
| "loss": 0.9653870463371277, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.633245382585752, | |
| "grad_norm": 0.1739293932914734, | |
| "learning_rate": 7.98009902333935e-05, | |
| "loss": 0.9817367792129517, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6358839050131926, | |
| "grad_norm": 0.17517700791358948, | |
| "learning_rate": 7.962981261754294e-05, | |
| "loss": 0.9925550222396851, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.6385224274406333, | |
| "grad_norm": 0.1885872781276703, | |
| "learning_rate": 7.945809807465857e-05, | |
| "loss": 0.9885467886924744, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.6411609498680739, | |
| "grad_norm": 0.1705755591392517, | |
| "learning_rate": 7.928584971640974e-05, | |
| "loss": 1.0115675926208496, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.6437994722955145, | |
| "grad_norm": 0.15275037288665771, | |
| "learning_rate": 7.911307066413919e-05, | |
| "loss": 0.9338511228561401, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.6464379947229552, | |
| "grad_norm": 0.17367307841777802, | |
| "learning_rate": 7.893976404880643e-05, | |
| "loss": 0.9358500242233276, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.6490765171503958, | |
| "grad_norm": 0.18579082190990448, | |
| "learning_rate": 7.876593301093104e-05, | |
| "loss": 0.993777871131897, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.6517150395778364, | |
| "grad_norm": 0.17416690289974213, | |
| "learning_rate": 7.859158070053577e-05, | |
| "loss": 0.9911141991615295, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.6543535620052771, | |
| "grad_norm": 0.17322957515716553, | |
| "learning_rate": 7.841671027708944e-05, | |
| "loss": 0.9777154922485352, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.6569920844327177, | |
| "grad_norm": 0.14296574890613556, | |
| "learning_rate": 7.824132490944967e-05, | |
| "loss": 0.8306946158409119, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.6596306068601583, | |
| "grad_norm": 0.18208211660385132, | |
| "learning_rate": 7.80654277758055e-05, | |
| "loss": 0.9833745956420898, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.662269129287599, | |
| "grad_norm": 0.15957476198673248, | |
| "learning_rate": 7.788902206361973e-05, | |
| "loss": 0.9916603565216064, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.6649076517150396, | |
| "grad_norm": 0.17746901512145996, | |
| "learning_rate": 7.771211096957125e-05, | |
| "loss": 0.9748624563217163, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.6675461741424802, | |
| "grad_norm": 0.19569706916809082, | |
| "learning_rate": 7.7534697699497e-05, | |
| "loss": 0.9759517908096313, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.6701846965699209, | |
| "grad_norm": 0.1637251377105713, | |
| "learning_rate": 7.735678546833402e-05, | |
| "loss": 0.9450954794883728, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.6728232189973615, | |
| "grad_norm": 0.18049630522727966, | |
| "learning_rate": 7.717837750006106e-05, | |
| "loss": 1.0253992080688477, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6754617414248021, | |
| "grad_norm": 0.165897935628891, | |
| "learning_rate": 7.699947702764021e-05, | |
| "loss": 1.0213006734848022, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.6781002638522428, | |
| "grad_norm": 0.20414817333221436, | |
| "learning_rate": 7.682008729295833e-05, | |
| "loss": 1.0483496189117432, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.6807387862796834, | |
| "grad_norm": 0.16246487200260162, | |
| "learning_rate": 7.664021154676829e-05, | |
| "loss": 0.9613660573959351, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.683377308707124, | |
| "grad_norm": 0.18064430356025696, | |
| "learning_rate": 7.645985304863003e-05, | |
| "loss": 0.9091204404830933, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.6860158311345647, | |
| "grad_norm": 0.17883849143981934, | |
| "learning_rate": 7.627901506685157e-05, | |
| "loss": 0.9444289207458496, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6886543535620053, | |
| "grad_norm": 0.17278419435024261, | |
| "learning_rate": 7.609770087842969e-05, | |
| "loss": 0.8510349988937378, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.6912928759894459, | |
| "grad_norm": 0.15988567471504211, | |
| "learning_rate": 7.591591376899062e-05, | |
| "loss": 0.9418317079544067, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.6939313984168866, | |
| "grad_norm": 0.1863398402929306, | |
| "learning_rate": 7.573365703273046e-05, | |
| "loss": 0.9580644369125366, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.6965699208443272, | |
| "grad_norm": 0.16767530143260956, | |
| "learning_rate": 7.555093397235552e-05, | |
| "loss": 0.8833745121955872, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.6992084432717678, | |
| "grad_norm": 0.17919766902923584, | |
| "learning_rate": 7.536774789902246e-05, | |
| "loss": 0.9687992334365845, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.7018469656992085, | |
| "grad_norm": 0.20329569280147552, | |
| "learning_rate": 7.518410213227822e-05, | |
| "loss": 0.8355344533920288, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.7044854881266491, | |
| "grad_norm": 0.17873340845108032, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9391046166419983, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.7071240105540897, | |
| "grad_norm": 0.17777030169963837, | |
| "learning_rate": 7.481544483833485e-05, | |
| "loss": 1.0823737382888794, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.7097625329815304, | |
| "grad_norm": 0.18217693269252777, | |
| "learning_rate": 7.463043999163919e-05, | |
| "loss": 1.016803503036499, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.712401055408971, | |
| "grad_norm": 0.1759069412946701, | |
| "learning_rate": 7.444498881241835e-05, | |
| "loss": 1.019862413406372, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7150395778364116, | |
| "grad_norm": 0.17746379971504211, | |
| "learning_rate": 7.425909466126568e-05, | |
| "loss": 0.996162474155426, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.7176781002638523, | |
| "grad_norm": 0.1615501195192337, | |
| "learning_rate": 7.407276090680172e-05, | |
| "loss": 1.0143609046936035, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.7203166226912929, | |
| "grad_norm": 0.17791925370693207, | |
| "learning_rate": 7.388599092561315e-05, | |
| "loss": 0.9809026718139648, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.7229551451187335, | |
| "grad_norm": 0.17972691357135773, | |
| "learning_rate": 7.369878810219154e-05, | |
| "loss": 1.0634626150131226, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.7255936675461742, | |
| "grad_norm": 0.18457219004631042, | |
| "learning_rate": 7.351115582887211e-05, | |
| "loss": 0.9123151302337646, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.7282321899736148, | |
| "grad_norm": 0.1787765920162201, | |
| "learning_rate": 7.332309750577222e-05, | |
| "loss": 1.0113319158554077, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.7308707124010554, | |
| "grad_norm": 0.15324430167675018, | |
| "learning_rate": 7.313461654072973e-05, | |
| "loss": 0.8716138601303101, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.7335092348284961, | |
| "grad_norm": 0.17701661586761475, | |
| "learning_rate": 7.29457163492413e-05, | |
| "loss": 0.9495022296905518, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.7361477572559367, | |
| "grad_norm": 0.1860339343547821, | |
| "learning_rate": 7.275640035440045e-05, | |
| "loss": 1.1002585887908936, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.7387862796833773, | |
| "grad_norm": 0.1833198368549347, | |
| "learning_rate": 7.256667198683552e-05, | |
| "loss": 1.0140724182128906, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.741424802110818, | |
| "grad_norm": 0.16927815973758698, | |
| "learning_rate": 7.237653468464756e-05, | |
| "loss": 0.8884044885635376, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.7440633245382586, | |
| "grad_norm": 0.1619526445865631, | |
| "learning_rate": 7.218599189334799e-05, | |
| "loss": 0.8716824054718018, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.7467018469656992, | |
| "grad_norm": 0.1803620606660843, | |
| "learning_rate": 7.199504706579617e-05, | |
| "loss": 0.9060261845588684, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.7493403693931399, | |
| "grad_norm": 0.1543535739183426, | |
| "learning_rate": 7.180370366213684e-05, | |
| "loss": 0.9115622043609619, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.7519788918205804, | |
| "grad_norm": 0.18664343655109406, | |
| "learning_rate": 7.161196514973734e-05, | |
| "loss": 0.9853682518005371, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7546174142480211, | |
| "grad_norm": 0.165468230843544, | |
| "learning_rate": 7.141983500312498e-05, | |
| "loss": 0.9828847646713257, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.7572559366754618, | |
| "grad_norm": 0.16414625942707062, | |
| "learning_rate": 7.12273167039238e-05, | |
| "loss": 0.9459795951843262, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.7598944591029023, | |
| "grad_norm": 0.16700607538223267, | |
| "learning_rate": 7.10344137407917e-05, | |
| "loss": 0.9463711977005005, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.762532981530343, | |
| "grad_norm": 0.18241791427135468, | |
| "learning_rate": 7.084112960935716e-05, | |
| "loss": 1.0513451099395752, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.7651715039577837, | |
| "grad_norm": 0.1688919961452484, | |
| "learning_rate": 7.064746781215577e-05, | |
| "loss": 0.9387044310569763, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7678100263852242, | |
| "grad_norm": 0.19025741517543793, | |
| "learning_rate": 7.045343185856701e-05, | |
| "loss": 1.0054974555969238, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.7704485488126649, | |
| "grad_norm": 0.15950188040733337, | |
| "learning_rate": 7.02590252647504e-05, | |
| "loss": 0.958078920841217, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.7730870712401056, | |
| "grad_norm": 0.16371142864227295, | |
| "learning_rate": 7.006425155358195e-05, | |
| "loss": 0.8427443504333496, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.7757255936675461, | |
| "grad_norm": 0.16640605032444, | |
| "learning_rate": 6.986911425459028e-05, | |
| "loss": 0.9656301736831665, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.7783641160949868, | |
| "grad_norm": 0.15756769478321075, | |
| "learning_rate": 6.967361690389258e-05, | |
| "loss": 0.8850897550582886, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7810026385224275, | |
| "grad_norm": 0.1860872358083725, | |
| "learning_rate": 6.947776304413071e-05, | |
| "loss": 1.0678696632385254, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.783641160949868, | |
| "grad_norm": 0.1724071353673935, | |
| "learning_rate": 6.92815562244068e-05, | |
| "loss": 0.9517515897750854, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.7862796833773087, | |
| "grad_norm": 0.163114994764328, | |
| "learning_rate": 6.908500000021904e-05, | |
| "loss": 1.0018560886383057, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.7889182058047494, | |
| "grad_norm": 0.1724291294813156, | |
| "learning_rate": 6.88880979333973e-05, | |
| "loss": 0.8515908718109131, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.7915567282321899, | |
| "grad_norm": 0.18454426527023315, | |
| "learning_rate": 6.869085359203844e-05, | |
| "loss": 1.0833189487457275, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7941952506596306, | |
| "grad_norm": 0.19565890729427338, | |
| "learning_rate": 6.849327055044183e-05, | |
| "loss": 0.9864209294319153, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.7968337730870713, | |
| "grad_norm": 0.1698215752840042, | |
| "learning_rate": 6.82953523890444e-05, | |
| "loss": 1.0138895511627197, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.7994722955145118, | |
| "grad_norm": 0.18076743185520172, | |
| "learning_rate": 6.809710269435589e-05, | |
| "loss": 0.9143779277801514, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.8021108179419525, | |
| "grad_norm": 0.18112292885780334, | |
| "learning_rate": 6.789852505889383e-05, | |
| "loss": 0.9987108707427979, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.8047493403693932, | |
| "grad_norm": 0.19905203580856323, | |
| "learning_rate": 6.769962308111839e-05, | |
| "loss": 1.0594322681427002, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.8073878627968337, | |
| "grad_norm": 0.15984803438186646, | |
| "learning_rate": 6.750040036536718e-05, | |
| "loss": 0.8765107989311218, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.8100263852242744, | |
| "grad_norm": 0.18265588581562042, | |
| "learning_rate": 6.730086052179004e-05, | |
| "loss": 1.0807573795318604, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.8126649076517151, | |
| "grad_norm": 0.17338073253631592, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.0164018869400024, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.8153034300791556, | |
| "grad_norm": 0.16966766119003296, | |
| "learning_rate": 6.690084392042513e-05, | |
| "loss": 0.8892185688018799, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.8179419525065963, | |
| "grad_norm": 0.1647440642118454, | |
| "learning_rate": 6.670037441140843e-05, | |
| "loss": 0.9149801731109619, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.820580474934037, | |
| "grad_norm": 0.1590905487537384, | |
| "learning_rate": 6.649960227197647e-05, | |
| "loss": 0.9656392335891724, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.8232189973614775, | |
| "grad_norm": 0.1711450070142746, | |
| "learning_rate": 6.629853114035642e-05, | |
| "loss": 0.8801575899124146, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.8258575197889182, | |
| "grad_norm": 0.16500213742256165, | |
| "learning_rate": 6.609716466019356e-05, | |
| "loss": 0.962440013885498, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.8284960422163589, | |
| "grad_norm": 0.16399310529232025, | |
| "learning_rate": 6.589550648048517e-05, | |
| "loss": 0.9615823030471802, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.8311345646437994, | |
| "grad_norm": 0.1439095288515091, | |
| "learning_rate": 6.569356025551454e-05, | |
| "loss": 0.8974040150642395, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.8337730870712401, | |
| "grad_norm": 0.1773672252893448, | |
| "learning_rate": 6.549132964478465e-05, | |
| "loss": 0.8947254419326782, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.8364116094986808, | |
| "grad_norm": 0.1713113933801651, | |
| "learning_rate": 6.528881831295188e-05, | |
| "loss": 0.9751154184341431, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.8390501319261213, | |
| "grad_norm": 0.16960115730762482, | |
| "learning_rate": 6.508602992975963e-05, | |
| "loss": 0.887660026550293, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.841688654353562, | |
| "grad_norm": 0.16344815492630005, | |
| "learning_rate": 6.488296816997173e-05, | |
| "loss": 1.0093176364898682, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.8443271767810027, | |
| "grad_norm": 0.1804485321044922, | |
| "learning_rate": 6.467963671330602e-05, | |
| "loss": 0.9559671878814697, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8469656992084432, | |
| "grad_norm": 0.1776222586631775, | |
| "learning_rate": 6.447603924436744e-05, | |
| "loss": 0.9938176870346069, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.8496042216358839, | |
| "grad_norm": 0.18694733083248138, | |
| "learning_rate": 6.427217945258151e-05, | |
| "loss": 1.0674500465393066, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.8522427440633246, | |
| "grad_norm": 0.19572079181671143, | |
| "learning_rate": 6.406806103212725e-05, | |
| "loss": 1.019213318824768, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.8548812664907651, | |
| "grad_norm": 0.18069222569465637, | |
| "learning_rate": 6.38636876818704e-05, | |
| "loss": 1.1204936504364014, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.8575197889182058, | |
| "grad_norm": 0.18144075572490692, | |
| "learning_rate": 6.36590631052963e-05, | |
| "loss": 0.9554729461669922, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8601583113456465, | |
| "grad_norm": 0.17216528952121735, | |
| "learning_rate": 6.34541910104428e-05, | |
| "loss": 0.9567139148712158, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.862796833773087, | |
| "grad_norm": 0.16113649308681488, | |
| "learning_rate": 6.32490751098331e-05, | |
| "loss": 0.8932434320449829, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.8654353562005277, | |
| "grad_norm": 0.17543751001358032, | |
| "learning_rate": 6.304371912040839e-05, | |
| "loss": 1.0658743381500244, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.8680738786279684, | |
| "grad_norm": 0.1963348686695099, | |
| "learning_rate": 6.283812676346063e-05, | |
| "loss": 0.9329290390014648, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.8707124010554089, | |
| "grad_norm": 0.14915871620178223, | |
| "learning_rate": 6.263230176456498e-05, | |
| "loss": 0.8152093291282654, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8733509234828496, | |
| "grad_norm": 0.16528934240341187, | |
| "learning_rate": 6.242624785351236e-05, | |
| "loss": 0.9133073091506958, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.8759894459102903, | |
| "grad_norm": 0.16276095807552338, | |
| "learning_rate": 6.221996876424185e-05, | |
| "loss": 0.9373147487640381, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.8786279683377308, | |
| "grad_norm": 0.1769801527261734, | |
| "learning_rate": 6.201346823477303e-05, | |
| "loss": 0.9239742159843445, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.8812664907651715, | |
| "grad_norm": 0.166982963681221, | |
| "learning_rate": 6.180675000713825e-05, | |
| "loss": 0.9344125986099243, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.8839050131926122, | |
| "grad_norm": 0.17170056700706482, | |
| "learning_rate": 6.159981782731474e-05, | |
| "loss": 0.9131274223327637, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.8865435356200527, | |
| "grad_norm": 0.1550513505935669, | |
| "learning_rate": 6.139267544515689e-05, | |
| "loss": 0.9826679229736328, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.8891820580474934, | |
| "grad_norm": 0.16641782224178314, | |
| "learning_rate": 6.118532661432812e-05, | |
| "loss": 0.9474678039550781, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.8918205804749341, | |
| "grad_norm": 0.1698181927204132, | |
| "learning_rate": 6.097777509223299e-05, | |
| "loss": 0.9482673406600952, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.8944591029023746, | |
| "grad_norm": 0.17008566856384277, | |
| "learning_rate": 6.0770024639949074e-05, | |
| "loss": 0.9680395126342773, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.8970976253298153, | |
| "grad_norm": 0.15967540442943573, | |
| "learning_rate": 6.056207902215874e-05, | |
| "loss": 1.001111388206482, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.899736147757256, | |
| "grad_norm": 0.1756800413131714, | |
| "learning_rate": 6.0353942007081046e-05, | |
| "loss": 0.9691710472106934, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.9023746701846965, | |
| "grad_norm": 0.1710166037082672, | |
| "learning_rate": 6.014561736640334e-05, | |
| "loss": 0.945921778678894, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.9050131926121372, | |
| "grad_norm": 0.17799116671085358, | |
| "learning_rate": 5.993710887521302e-05, | |
| "loss": 1.0534354448318481, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.9076517150395779, | |
| "grad_norm": 0.1695486456155777, | |
| "learning_rate": 5.9728420311929014e-05, | |
| "loss": 0.9974007606506348, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.9102902374670184, | |
| "grad_norm": 0.176923930644989, | |
| "learning_rate": 5.951955545823342e-05, | |
| "loss": 0.8604757785797119, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.9129287598944591, | |
| "grad_norm": 0.17479252815246582, | |
| "learning_rate": 5.93105180990029e-05, | |
| "loss": 0.9862606525421143, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.9155672823218998, | |
| "grad_norm": 0.18432128429412842, | |
| "learning_rate": 5.9101312022240106e-05, | |
| "loss": 1.0248565673828125, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.9182058047493403, | |
| "grad_norm": 0.18314237892627716, | |
| "learning_rate": 5.889194101900509e-05, | |
| "loss": 0.9174256324768066, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.920844327176781, | |
| "grad_norm": 0.16578571498394012, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.056714415550232, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.9234828496042217, | |
| "grad_norm": 0.15476450324058533, | |
| "learning_rate": 5.847271941223301e-05, | |
| "loss": 0.9293104410171509, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9261213720316622, | |
| "grad_norm": 0.1833016276359558, | |
| "learning_rate": 5.826287640548425e-05, | |
| "loss": 0.9992409348487854, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.9287598944591029, | |
| "grad_norm": 0.17842108011245728, | |
| "learning_rate": 5.8052883665702195e-05, | |
| "loss": 1.0228012800216675, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.9313984168865436, | |
| "grad_norm": 0.18546055257320404, | |
| "learning_rate": 5.784274499820214e-05, | |
| "loss": 0.9743684530258179, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.9340369393139841, | |
| "grad_norm": 0.16940274834632874, | |
| "learning_rate": 5.7632464210943726e-05, | |
| "loss": 0.9181085824966431, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.9366754617414248, | |
| "grad_norm": 0.1520531177520752, | |
| "learning_rate": 5.742204511446203e-05, | |
| "loss": 0.9358412623405457, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.9393139841688655, | |
| "grad_norm": 0.1511743813753128, | |
| "learning_rate": 5.72114915217984e-05, | |
| "loss": 0.932067334651947, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.941952506596306, | |
| "grad_norm": 0.1603623628616333, | |
| "learning_rate": 5.700080724843147e-05, | |
| "loss": 0.8600016832351685, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.9445910290237467, | |
| "grad_norm": 0.16928866505622864, | |
| "learning_rate": 5.678999611220786e-05, | |
| "loss": 0.9700044393539429, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.9472295514511874, | |
| "grad_norm": 0.1810542345046997, | |
| "learning_rate": 5.657906193327325e-05, | |
| "loss": 0.9956720471382141, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.9498680738786279, | |
| "grad_norm": 0.16913573443889618, | |
| "learning_rate": 5.636800853400285e-05, | |
| "loss": 0.9498183727264404, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9525065963060686, | |
| "grad_norm": 0.17175836861133575, | |
| "learning_rate": 5.6156839738932343e-05, | |
| "loss": 0.9880730509757996, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.9551451187335093, | |
| "grad_norm": 0.1765371859073639, | |
| "learning_rate": 5.594555937468856e-05, | |
| "loss": 0.9926971197128296, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.9577836411609498, | |
| "grad_norm": 0.17631809413433075, | |
| "learning_rate": 5.573417126992003e-05, | |
| "loss": 1.1096311807632446, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.9604221635883905, | |
| "grad_norm": 0.18647527694702148, | |
| "learning_rate": 5.5522679255227695e-05, | |
| "loss": 0.9738677740097046, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.9630606860158312, | |
| "grad_norm": 0.17723622918128967, | |
| "learning_rate": 5.531108716309547e-05, | |
| "loss": 1.0370627641677856, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.9656992084432717, | |
| "grad_norm": 0.18259158730506897, | |
| "learning_rate": 5.509939882782077e-05, | |
| "loss": 1.0807445049285889, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.9683377308707124, | |
| "grad_norm": 0.15763477981090546, | |
| "learning_rate": 5.4887618085445094e-05, | |
| "loss": 0.958760142326355, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.9709762532981531, | |
| "grad_norm": 0.15909765660762787, | |
| "learning_rate": 5.467574877368441e-05, | |
| "loss": 0.873651921749115, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.9736147757255936, | |
| "grad_norm": 0.16833601891994476, | |
| "learning_rate": 5.446379473185972e-05, | |
| "loss": 0.9816885590553284, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.9762532981530343, | |
| "grad_norm": 0.15526193380355835, | |
| "learning_rate": 5.42517598008274e-05, | |
| "loss": 0.9115396738052368, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.978891820580475, | |
| "grad_norm": 0.16502319276332855, | |
| "learning_rate": 5.4039647822909624e-05, | |
| "loss": 0.8796002864837646, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.9815303430079155, | |
| "grad_norm": 0.16136875748634338, | |
| "learning_rate": 5.38274626418248e-05, | |
| "loss": 0.9705801010131836, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.9841688654353562, | |
| "grad_norm": 0.15776164829730988, | |
| "learning_rate": 5.361520810261779e-05, | |
| "loss": 0.9282939434051514, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.9868073878627969, | |
| "grad_norm": 0.1755094826221466, | |
| "learning_rate": 5.340288805159036e-05, | |
| "loss": 0.8166096806526184, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.9894459102902374, | |
| "grad_norm": 0.15046261250972748, | |
| "learning_rate": 5.319050633623142e-05, | |
| "loss": 0.8774311542510986, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9920844327176781, | |
| "grad_norm": 0.17574267089366913, | |
| "learning_rate": 5.297806680514731e-05, | |
| "loss": 0.9345486164093018, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.9947229551451188, | |
| "grad_norm": 0.17158278822898865, | |
| "learning_rate": 5.2765573307992036e-05, | |
| "loss": 0.9240652322769165, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.9973614775725593, | |
| "grad_norm": 0.17372801899909973, | |
| "learning_rate": 5.2553029695397525e-05, | |
| "loss": 0.9987330436706543, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.18322864174842834, | |
| "learning_rate": 5.234043981890394e-05, | |
| "loss": 0.9055143594741821, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 1.0026385224274406, | |
| "grad_norm": 0.163027822971344, | |
| "learning_rate": 5.212780753088968e-05, | |
| "loss": 0.8689513206481934, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.0052770448548813, | |
| "grad_norm": 0.16747920215129852, | |
| "learning_rate": 5.191513668450178e-05, | |
| "loss": 0.8572540283203125, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.007915567282322, | |
| "grad_norm": 0.15519443154335022, | |
| "learning_rate": 5.170243113358594e-05, | |
| "loss": 0.7752639651298523, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.0105540897097625, | |
| "grad_norm": 0.17219293117523193, | |
| "learning_rate": 5.14896947326168e-05, | |
| "loss": 0.8173640966415405, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.0131926121372032, | |
| "grad_norm": 0.18401013314723969, | |
| "learning_rate": 5.127693133662801e-05, | |
| "loss": 0.9488857388496399, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.0158311345646438, | |
| "grad_norm": 0.16421173512935638, | |
| "learning_rate": 5.1064144801142374e-05, | |
| "loss": 0.8519411087036133, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.0184696569920844, | |
| "grad_norm": 0.16793890297412872, | |
| "learning_rate": 5.0851338982102084e-05, | |
| "loss": 0.8834291696548462, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 1.0211081794195251, | |
| "grad_norm": 0.15045003592967987, | |
| "learning_rate": 5.0638517735798696e-05, | |
| "loss": 0.7745985984802246, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.0237467018469657, | |
| "grad_norm": 0.18770800530910492, | |
| "learning_rate": 5.042568491880339e-05, | |
| "loss": 0.8939248919487, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 1.0263852242744063, | |
| "grad_norm": 0.1821233332157135, | |
| "learning_rate": 5.021284438789694e-05, | |
| "loss": 0.8552336096763611, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 1.029023746701847, | |
| "grad_norm": 0.16420002281665802, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8692670464515686, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0316622691292876, | |
| "grad_norm": 0.18629834055900574, | |
| "learning_rate": 4.9787155612103074e-05, | |
| "loss": 0.8282995820045471, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.0343007915567282, | |
| "grad_norm": 0.1892436146736145, | |
| "learning_rate": 4.957431508119663e-05, | |
| "loss": 0.8892487287521362, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.036939313984169, | |
| "grad_norm": 0.22068382799625397, | |
| "learning_rate": 4.936148226420132e-05, | |
| "loss": 0.8855545520782471, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.0395778364116095, | |
| "grad_norm": 0.1730453372001648, | |
| "learning_rate": 4.914866101789792e-05, | |
| "loss": 0.9536787271499634, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.04221635883905, | |
| "grad_norm": 0.17769935727119446, | |
| "learning_rate": 4.893585519885764e-05, | |
| "loss": 0.841202974319458, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.0448548812664908, | |
| "grad_norm": 0.16897647082805634, | |
| "learning_rate": 4.8723068663372006e-05, | |
| "loss": 0.8201183080673218, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.0474934036939314, | |
| "grad_norm": 0.16851696372032166, | |
| "learning_rate": 4.851030526738321e-05, | |
| "loss": 0.7748086452484131, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 1.050131926121372, | |
| "grad_norm": 0.1909930258989334, | |
| "learning_rate": 4.829756886641407e-05, | |
| "loss": 0.9193738698959351, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.0527704485488127, | |
| "grad_norm": 0.18687032163143158, | |
| "learning_rate": 4.8084863315498234e-05, | |
| "loss": 0.838584303855896, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.0554089709762533, | |
| "grad_norm": 0.1934981346130371, | |
| "learning_rate": 4.787219246911034e-05, | |
| "loss": 0.9033339619636536, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0580474934036939, | |
| "grad_norm": 0.18443354964256287, | |
| "learning_rate": 4.765956018109607e-05, | |
| "loss": 0.8763784766197205, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 1.0606860158311346, | |
| "grad_norm": 0.18538866937160492, | |
| "learning_rate": 4.744697030460248e-05, | |
| "loss": 0.8398501873016357, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.0633245382585752, | |
| "grad_norm": 0.16640767455101013, | |
| "learning_rate": 4.723442669200798e-05, | |
| "loss": 0.8269528150558472, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.0659630606860158, | |
| "grad_norm": 0.22288216650485992, | |
| "learning_rate": 4.702193319485271e-05, | |
| "loss": 0.8861086368560791, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.0686015831134565, | |
| "grad_norm": 0.18035729229450226, | |
| "learning_rate": 4.680949366376858e-05, | |
| "loss": 0.824222981929779, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.071240105540897, | |
| "grad_norm": 0.17725308239459991, | |
| "learning_rate": 4.659711194840964e-05, | |
| "loss": 0.9309662580490112, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.0738786279683377, | |
| "grad_norm": 0.19792447984218597, | |
| "learning_rate": 4.638479189738224e-05, | |
| "loss": 0.9101674556732178, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.0765171503957784, | |
| "grad_norm": 0.19369834661483765, | |
| "learning_rate": 4.6172537358175214e-05, | |
| "loss": 0.8125869631767273, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.079155672823219, | |
| "grad_norm": 0.2080707997083664, | |
| "learning_rate": 4.5960352177090395e-05, | |
| "loss": 0.9006462097167969, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.0817941952506596, | |
| "grad_norm": 0.1985592097043991, | |
| "learning_rate": 4.5748240199172614e-05, | |
| "loss": 0.8294681310653687, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.0844327176781003, | |
| "grad_norm": 0.18108457326889038, | |
| "learning_rate": 4.5536205268140294e-05, | |
| "loss": 0.8876621127128601, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.087071240105541, | |
| "grad_norm": 0.21750716865062714, | |
| "learning_rate": 4.532425122631559e-05, | |
| "loss": 0.868391752243042, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 1.0897097625329815, | |
| "grad_norm": 0.19873136281967163, | |
| "learning_rate": 4.511238191455491e-05, | |
| "loss": 0.8306460380554199, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 1.0923482849604222, | |
| "grad_norm": 0.18541795015335083, | |
| "learning_rate": 4.4900601172179244e-05, | |
| "loss": 0.9179568290710449, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.0949868073878628, | |
| "grad_norm": 0.18384666740894318, | |
| "learning_rate": 4.468891283690454e-05, | |
| "loss": 0.8310732841491699, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.0976253298153034, | |
| "grad_norm": 0.1964699774980545, | |
| "learning_rate": 4.447732074477233e-05, | |
| "loss": 0.9393026828765869, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.1002638522427441, | |
| "grad_norm": 0.19017209112644196, | |
| "learning_rate": 4.4265828730079987e-05, | |
| "loss": 0.8362956047058105, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.1029023746701847, | |
| "grad_norm": 0.19348829984664917, | |
| "learning_rate": 4.405444062531145e-05, | |
| "loss": 0.7968118190765381, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.1055408970976253, | |
| "grad_norm": 0.17324209213256836, | |
| "learning_rate": 4.3843160261067655e-05, | |
| "loss": 0.7850878834724426, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 1.108179419525066, | |
| "grad_norm": 0.17320138216018677, | |
| "learning_rate": 4.363199146599717e-05, | |
| "loss": 0.9237335324287415, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.1108179419525066, | |
| "grad_norm": 0.19056344032287598, | |
| "learning_rate": 4.342093806672678e-05, | |
| "loss": 0.8847521543502808, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 1.1134564643799472, | |
| "grad_norm": 0.17850638926029205, | |
| "learning_rate": 4.321000388779214e-05, | |
| "loss": 0.8789336681365967, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.116094986807388, | |
| "grad_norm": 0.17765560746192932, | |
| "learning_rate": 4.2999192751568564e-05, | |
| "loss": 0.8255523443222046, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.1187335092348285, | |
| "grad_norm": 0.17237840592861176, | |
| "learning_rate": 4.2788508478201606e-05, | |
| "loss": 0.8108619451522827, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 1.121372031662269, | |
| "grad_norm": 0.18996207416057587, | |
| "learning_rate": 4.2577954885537986e-05, | |
| "loss": 0.8163636922836304, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.1240105540897098, | |
| "grad_norm": 0.19661268591880798, | |
| "learning_rate": 4.236753578905627e-05, | |
| "loss": 0.8180580139160156, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.1266490765171504, | |
| "grad_norm": 0.1983136236667633, | |
| "learning_rate": 4.215725500179787e-05, | |
| "loss": 0.8661148548126221, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 1.129287598944591, | |
| "grad_norm": 0.20327302813529968, | |
| "learning_rate": 4.194711633429782e-05, | |
| "loss": 0.8483480215072632, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 1.1319261213720317, | |
| "grad_norm": 0.18003475666046143, | |
| "learning_rate": 4.1737123594515756e-05, | |
| "loss": 0.7864603996276855, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.1345646437994723, | |
| "grad_norm": 0.19587212800979614, | |
| "learning_rate": 4.152728058776701e-05, | |
| "loss": 0.8808155059814453, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.1372031662269129, | |
| "grad_norm": 0.19418397545814514, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.832161545753479, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 1.1398416886543536, | |
| "grad_norm": 0.2255297303199768, | |
| "learning_rate": 4.110805898099493e-05, | |
| "loss": 0.8426797986030579, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.1424802110817942, | |
| "grad_norm": 0.19156090915203094, | |
| "learning_rate": 4.089868797775989e-05, | |
| "loss": 0.8604530096054077, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.1451187335092348, | |
| "grad_norm": 0.20741666853427887, | |
| "learning_rate": 4.06894819009971e-05, | |
| "loss": 0.9090075492858887, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.1477572559366755, | |
| "grad_norm": 0.19898787140846252, | |
| "learning_rate": 4.0480444541766576e-05, | |
| "loss": 0.8166146874427795, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.150395778364116, | |
| "grad_norm": 0.1938183307647705, | |
| "learning_rate": 4.0271579688071e-05, | |
| "loss": 0.7139468193054199, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 1.1530343007915567, | |
| "grad_norm": 0.19528253376483917, | |
| "learning_rate": 4.0062891124787e-05, | |
| "loss": 0.8504555821418762, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 1.1556728232189974, | |
| "grad_norm": 0.1629706174135208, | |
| "learning_rate": 3.9854382633596664e-05, | |
| "loss": 0.7654178142547607, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.158311345646438, | |
| "grad_norm": 0.18239827454090118, | |
| "learning_rate": 3.964605799291897e-05, | |
| "loss": 0.8295183777809143, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 1.1609498680738786, | |
| "grad_norm": 0.20417547225952148, | |
| "learning_rate": 3.943792097784127e-05, | |
| "loss": 0.8282760977745056, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.1635883905013193, | |
| "grad_norm": 0.16850367188453674, | |
| "learning_rate": 3.922997536005094e-05, | |
| "loss": 0.7826701998710632, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.16622691292876, | |
| "grad_norm": 0.23355093598365784, | |
| "learning_rate": 3.9022224907767005e-05, | |
| "loss": 0.8789860010147095, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.1688654353562005, | |
| "grad_norm": 0.21100738644599915, | |
| "learning_rate": 3.8814673385671894e-05, | |
| "loss": 0.8798761367797852, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.1715039577836412, | |
| "grad_norm": 0.19496478140354156, | |
| "learning_rate": 3.8607324554843136e-05, | |
| "loss": 0.8681943416595459, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.1741424802110818, | |
| "grad_norm": 0.2121591866016388, | |
| "learning_rate": 3.840018217268527e-05, | |
| "loss": 0.8384369015693665, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.1767810026385224, | |
| "grad_norm": 0.1898183971643448, | |
| "learning_rate": 3.819324999286177e-05, | |
| "loss": 0.7906219959259033, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 1.1794195250659631, | |
| "grad_norm": 0.20216920971870422, | |
| "learning_rate": 3.7986531765226964e-05, | |
| "loss": 0.7790259122848511, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.1820580474934037, | |
| "grad_norm": 0.20957563817501068, | |
| "learning_rate": 3.778003123575815e-05, | |
| "loss": 0.7760137915611267, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.1846965699208443, | |
| "grad_norm": 0.20613044500350952, | |
| "learning_rate": 3.757375214648764e-05, | |
| "loss": 0.8447249531745911, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 1.187335092348285, | |
| "grad_norm": 0.2005365639925003, | |
| "learning_rate": 3.7367698235435036e-05, | |
| "loss": 0.8000772595405579, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.1899736147757256, | |
| "grad_norm": 0.18416504561901093, | |
| "learning_rate": 3.716187323653939e-05, | |
| "loss": 0.8127347230911255, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 1.1926121372031662, | |
| "grad_norm": 0.18120023608207703, | |
| "learning_rate": 3.695628087959162e-05, | |
| "loss": 0.8312699794769287, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 1.195250659630607, | |
| "grad_norm": 0.19914136826992035, | |
| "learning_rate": 3.675092489016693e-05, | |
| "loss": 0.8587290048599243, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.1978891820580475, | |
| "grad_norm": 0.18168587982654572, | |
| "learning_rate": 3.6545808989557205e-05, | |
| "loss": 0.8895556926727295, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.200527704485488, | |
| "grad_norm": 0.19216057658195496, | |
| "learning_rate": 3.634093689470371e-05, | |
| "loss": 0.8902896642684937, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.2031662269129288, | |
| "grad_norm": 0.19391824305057526, | |
| "learning_rate": 3.61363123181296e-05, | |
| "loss": 0.7836971282958984, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.2058047493403694, | |
| "grad_norm": 0.22049692273139954, | |
| "learning_rate": 3.5931938967872766e-05, | |
| "loss": 0.9629299640655518, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 1.20844327176781, | |
| "grad_norm": 0.20522050559520721, | |
| "learning_rate": 3.5727820547418524e-05, | |
| "loss": 0.8854247331619263, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 1.2110817941952507, | |
| "grad_norm": 0.19162432849407196, | |
| "learning_rate": 3.5523960755632574e-05, | |
| "loss": 0.8424211740493774, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.2137203166226913, | |
| "grad_norm": 0.19570188224315643, | |
| "learning_rate": 3.5320363286694015e-05, | |
| "loss": 0.7317659854888916, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.2163588390501319, | |
| "grad_norm": 0.2107311189174652, | |
| "learning_rate": 3.5117031830028274e-05, | |
| "loss": 0.8849686980247498, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.2189973614775726, | |
| "grad_norm": 0.20445716381072998, | |
| "learning_rate": 3.4913970070240386e-05, | |
| "loss": 0.8883921504020691, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.2216358839050132, | |
| "grad_norm": 0.2084072083234787, | |
| "learning_rate": 3.471118168704811e-05, | |
| "loss": 0.8633065819740295, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 1.2242744063324538, | |
| "grad_norm": 0.2052319049835205, | |
| "learning_rate": 3.450867035521536e-05, | |
| "loss": 0.8934541344642639, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.2269129287598945, | |
| "grad_norm": 0.19645145535469055, | |
| "learning_rate": 3.4306439744485454e-05, | |
| "loss": 0.9101189970970154, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.229551451187335, | |
| "grad_norm": 0.2135409414768219, | |
| "learning_rate": 3.4104493519514844e-05, | |
| "loss": 0.833043098449707, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 1.2321899736147757, | |
| "grad_norm": 0.18406689167022705, | |
| "learning_rate": 3.390283533980646e-05, | |
| "loss": 0.8629342317581177, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 1.2348284960422165, | |
| "grad_norm": 0.2001754194498062, | |
| "learning_rate": 3.370146885964358e-05, | |
| "loss": 0.873695969581604, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.237467018469657, | |
| "grad_norm": 0.2148927003145218, | |
| "learning_rate": 3.350039772802354e-05, | |
| "loss": 0.8796666264533997, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 1.2401055408970976, | |
| "grad_norm": 0.21805380284786224, | |
| "learning_rate": 3.3299625588591564e-05, | |
| "loss": 0.9472431540489197, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.2427440633245384, | |
| "grad_norm": 0.1728621870279312, | |
| "learning_rate": 3.309915607957487e-05, | |
| "loss": 0.7903483510017395, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.245382585751979, | |
| "grad_norm": 0.1994401216506958, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.8357045650482178, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.2480211081794195, | |
| "grad_norm": 0.1856645941734314, | |
| "learning_rate": 3.269913947820998e-05, | |
| "loss": 0.8685092926025391, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 1.2506596306068603, | |
| "grad_norm": 0.18104133009910583, | |
| "learning_rate": 3.249959963463283e-05, | |
| "loss": 0.8382564783096313, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.2532981530343008, | |
| "grad_norm": 0.1977917104959488, | |
| "learning_rate": 3.2300376918881624e-05, | |
| "loss": 0.7892318964004517, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.2559366754617414, | |
| "grad_norm": 0.19494417309761047, | |
| "learning_rate": 3.210147494110618e-05, | |
| "loss": 0.8779850602149963, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.258575197889182, | |
| "grad_norm": 0.18986152112483978, | |
| "learning_rate": 3.1902897305644095e-05, | |
| "loss": 0.8703120350837708, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.2612137203166227, | |
| "grad_norm": 0.21342100203037262, | |
| "learning_rate": 3.170464761095562e-05, | |
| "loss": 0.8629742860794067, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 1.2638522427440633, | |
| "grad_norm": 0.19701190292835236, | |
| "learning_rate": 3.1506729449558184e-05, | |
| "loss": 0.8151880502700806, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.266490765171504, | |
| "grad_norm": 0.19951196014881134, | |
| "learning_rate": 3.130914640796157e-05, | |
| "loss": 0.7900158762931824, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.2691292875989446, | |
| "grad_norm": 0.1988476812839508, | |
| "learning_rate": 3.1111902066602724e-05, | |
| "loss": 0.8788620233535767, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.2717678100263852, | |
| "grad_norm": 0.2119346261024475, | |
| "learning_rate": 3.091499999978097e-05, | |
| "loss": 0.9024869799613953, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 1.2744063324538257, | |
| "grad_norm": 0.1857406198978424, | |
| "learning_rate": 3.071844377559323e-05, | |
| "loss": 0.8004682064056396, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.2770448548812665, | |
| "grad_norm": 0.2080564647912979, | |
| "learning_rate": 3.052223695586929e-05, | |
| "loss": 0.7997844815254211, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.279683377308707, | |
| "grad_norm": 0.20487792789936066, | |
| "learning_rate": 3.0326383096107426e-05, | |
| "loss": 0.8369828462600708, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.2823218997361479, | |
| "grad_norm": 0.21704550087451935, | |
| "learning_rate": 3.013088574540974e-05, | |
| "loss": 0.8362990617752075, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.2849604221635884, | |
| "grad_norm": 0.1796228289604187, | |
| "learning_rate": 2.9935748446418066e-05, | |
| "loss": 0.7657400369644165, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 1.287598944591029, | |
| "grad_norm": 0.19341661036014557, | |
| "learning_rate": 2.9740974735249627e-05, | |
| "loss": 0.8564615845680237, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.2902374670184695, | |
| "grad_norm": 0.19471068680286407, | |
| "learning_rate": 2.9546568141433006e-05, | |
| "loss": 0.8282036781311035, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.2928759894459103, | |
| "grad_norm": 0.19298681616783142, | |
| "learning_rate": 2.9352532187844252e-05, | |
| "loss": 0.7633144855499268, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.2955145118733509, | |
| "grad_norm": 0.2185523808002472, | |
| "learning_rate": 2.915887039064287e-05, | |
| "loss": 0.8637824058532715, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 1.2981530343007917, | |
| "grad_norm": 0.18757079541683197, | |
| "learning_rate": 2.8965586259208295e-05, | |
| "loss": 0.9021022915840149, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.3007915567282322, | |
| "grad_norm": 0.22943295538425446, | |
| "learning_rate": 2.8772683296076196e-05, | |
| "loss": 0.7836156487464905, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.3034300791556728, | |
| "grad_norm": 0.22361497581005096, | |
| "learning_rate": 2.858016499687503e-05, | |
| "loss": 0.8892571926116943, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.3060686015831133, | |
| "grad_norm": 0.17517295479774475, | |
| "learning_rate": 2.8388034850262646e-05, | |
| "loss": 0.7846842408180237, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.3087071240105541, | |
| "grad_norm": 0.21480333805084229, | |
| "learning_rate": 2.8196296337863193e-05, | |
| "loss": 0.8207566142082214, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.3113456464379947, | |
| "grad_norm": 0.20812678337097168, | |
| "learning_rate": 2.8004952934203838e-05, | |
| "loss": 0.8578101396560669, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.3139841688654355, | |
| "grad_norm": 0.20664533972740173, | |
| "learning_rate": 2.7814008106652012e-05, | |
| "loss": 0.8509771823883057, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 1.316622691292876, | |
| "grad_norm": 0.21508260071277618, | |
| "learning_rate": 2.762346531535246e-05, | |
| "loss": 0.8185523748397827, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 1.3192612137203166, | |
| "grad_norm": 0.1851697713136673, | |
| "learning_rate": 2.7433328013164495e-05, | |
| "loss": 0.7895690202713013, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3218997361477571, | |
| "grad_norm": 0.21966880559921265, | |
| "learning_rate": 2.7243599645599576e-05, | |
| "loss": 0.8147685527801514, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 1.324538258575198, | |
| "grad_norm": 0.2082214504480362, | |
| "learning_rate": 2.7054283650758682e-05, | |
| "loss": 0.9062052369117737, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 1.3271767810026385, | |
| "grad_norm": 0.18478548526763916, | |
| "learning_rate": 2.6865383459270265e-05, | |
| "loss": 0.8946532011032104, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 1.3298153034300793, | |
| "grad_norm": 0.2242600917816162, | |
| "learning_rate": 2.6676902494227795e-05, | |
| "loss": 0.8830220699310303, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.3324538258575198, | |
| "grad_norm": 0.22042159736156464, | |
| "learning_rate": 2.6488844171127903e-05, | |
| "loss": 0.8637486696243286, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.3350923482849604, | |
| "grad_norm": 0.19908133149147034, | |
| "learning_rate": 2.6301211897808464e-05, | |
| "loss": 0.9240211248397827, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.337730870712401, | |
| "grad_norm": 0.21462836861610413, | |
| "learning_rate": 2.6114009074386846e-05, | |
| "loss": 0.8997042179107666, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.3403693931398417, | |
| "grad_norm": 0.2102992832660675, | |
| "learning_rate": 2.5927239093198274e-05, | |
| "loss": 0.8191858530044556, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.3430079155672823, | |
| "grad_norm": 0.21195337176322937, | |
| "learning_rate": 2.574090533873431e-05, | |
| "loss": 0.8745005130767822, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 1.345646437994723, | |
| "grad_norm": 0.17979484796524048, | |
| "learning_rate": 2.555501118758167e-05, | |
| "loss": 0.8337305784225464, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.3482849604221636, | |
| "grad_norm": 0.19970622658729553, | |
| "learning_rate": 2.5369560008360828e-05, | |
| "loss": 0.8389545679092407, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.3509234828496042, | |
| "grad_norm": 0.2224525660276413, | |
| "learning_rate": 2.518455516166517e-05, | |
| "loss": 0.9300051927566528, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.3535620052770447, | |
| "grad_norm": 0.2070772796869278, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8477452993392944, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.3562005277044855, | |
| "grad_norm": 0.20911110937595367, | |
| "learning_rate": 2.4815897867721784e-05, | |
| "loss": 0.8734545707702637, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.358839050131926, | |
| "grad_norm": 0.21647144854068756, | |
| "learning_rate": 2.4632252100977566e-05, | |
| "loss": 0.8972655534744263, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.3614775725593669, | |
| "grad_norm": 0.21526023745536804, | |
| "learning_rate": 2.4449066027644475e-05, | |
| "loss": 0.8118870258331299, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.3641160949868074, | |
| "grad_norm": 0.20327945053577423, | |
| "learning_rate": 2.4266342967269552e-05, | |
| "loss": 0.855424165725708, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.366754617414248, | |
| "grad_norm": 0.19717800617218018, | |
| "learning_rate": 2.4084086231009395e-05, | |
| "loss": 0.7565803527832031, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.3693931398416885, | |
| "grad_norm": 0.20523078739643097, | |
| "learning_rate": 2.3902299121570333e-05, | |
| "loss": 0.9261975288391113, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.3720316622691293, | |
| "grad_norm": 0.219309002161026, | |
| "learning_rate": 2.3720984933148444e-05, | |
| "loss": 0.7988795042037964, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.3746701846965699, | |
| "grad_norm": 0.24325881898403168, | |
| "learning_rate": 2.354014695136997e-05, | |
| "loss": 0.8413968086242676, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.3773087071240107, | |
| "grad_norm": 0.19859999418258667, | |
| "learning_rate": 2.3359788453231724e-05, | |
| "loss": 0.8811598420143127, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.3799472295514512, | |
| "grad_norm": 0.2395762950181961, | |
| "learning_rate": 2.317991270704167e-05, | |
| "loss": 0.8950267434120178, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.3825857519788918, | |
| "grad_norm": 0.17747214436531067, | |
| "learning_rate": 2.30005229723598e-05, | |
| "loss": 0.7522149085998535, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.3852242744063323, | |
| "grad_norm": 0.2008499652147293, | |
| "learning_rate": 2.282162249993895e-05, | |
| "loss": 0.727147102355957, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.3878627968337731, | |
| "grad_norm": 0.20609167218208313, | |
| "learning_rate": 2.2643214531665978e-05, | |
| "loss": 0.8256455659866333, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.3905013192612137, | |
| "grad_norm": 0.20032787322998047, | |
| "learning_rate": 2.246530230050301e-05, | |
| "loss": 0.8437114357948303, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.3931398416886545, | |
| "grad_norm": 0.21618762612342834, | |
| "learning_rate": 2.228788903042877e-05, | |
| "loss": 0.8061575293540955, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.395778364116095, | |
| "grad_norm": 0.2020416408777237, | |
| "learning_rate": 2.211097793638029e-05, | |
| "loss": 0.7951303124427795, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.3984168865435356, | |
| "grad_norm": 0.21808432042598724, | |
| "learning_rate": 2.19345722241945e-05, | |
| "loss": 0.893155038356781, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.4010554089709761, | |
| "grad_norm": 0.20245902240276337, | |
| "learning_rate": 2.175867509055033e-05, | |
| "loss": 0.8358583450317383, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.403693931398417, | |
| "grad_norm": 0.20912860333919525, | |
| "learning_rate": 2.158328972291056e-05, | |
| "loss": 0.8978977799415588, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.4063324538258575, | |
| "grad_norm": 0.22441457211971283, | |
| "learning_rate": 2.1408419299464245e-05, | |
| "loss": 0.861559271812439, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.4089709762532983, | |
| "grad_norm": 0.19903819262981415, | |
| "learning_rate": 2.1234066989068972e-05, | |
| "loss": 0.8497825860977173, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.4116094986807388, | |
| "grad_norm": 0.2019970715045929, | |
| "learning_rate": 2.106023595119358e-05, | |
| "loss": 0.8910925388336182, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.4142480211081794, | |
| "grad_norm": 0.19506564736366272, | |
| "learning_rate": 2.0886929335860826e-05, | |
| "loss": 0.8591622710227966, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.41688654353562, | |
| "grad_norm": 0.19065196812152863, | |
| "learning_rate": 2.071415028359026e-05, | |
| "loss": 0.8114444017410278, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.4195250659630607, | |
| "grad_norm": 0.20525790750980377, | |
| "learning_rate": 2.0541901925341445e-05, | |
| "loss": 0.8627693057060242, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.4221635883905013, | |
| "grad_norm": 0.1845739483833313, | |
| "learning_rate": 2.0370187382457068e-05, | |
| "loss": 0.784498929977417, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.424802110817942, | |
| "grad_norm": 0.19489313662052155, | |
| "learning_rate": 2.0199009766606507e-05, | |
| "loss": 0.8950122594833374, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.4274406332453826, | |
| "grad_norm": 0.19720782339572906, | |
| "learning_rate": 2.0028372179729403e-05, | |
| "loss": 0.8929563760757446, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.4300791556728232, | |
| "grad_norm": 0.2457919865846634, | |
| "learning_rate": 1.985827771397938e-05, | |
| "loss": 0.8557782173156738, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.4327176781002637, | |
| "grad_norm": 0.212116539478302, | |
| "learning_rate": 1.9688729451668114e-05, | |
| "loss": 0.8671682476997375, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.4353562005277045, | |
| "grad_norm": 0.20607347786426544, | |
| "learning_rate": 1.9519730465209384e-05, | |
| "loss": 0.8468962907791138, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.437994722955145, | |
| "grad_norm": 0.19764231145381927, | |
| "learning_rate": 1.935128381706355e-05, | |
| "loss": 0.8730595707893372, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.4406332453825859, | |
| "grad_norm": 0.20810900628566742, | |
| "learning_rate": 1.9183392559681812e-05, | |
| "loss": 0.905620813369751, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.4432717678100264, | |
| "grad_norm": 0.20794421434402466, | |
| "learning_rate": 1.901605973545116e-05, | |
| "loss": 0.8467898964881897, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.445910290237467, | |
| "grad_norm": 0.1914779394865036, | |
| "learning_rate": 1.8849288376639017e-05, | |
| "loss": 0.8068687915802002, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.4485488126649075, | |
| "grad_norm": 0.21812552213668823, | |
| "learning_rate": 1.868308150533847e-05, | |
| "loss": 0.8541518449783325, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.4511873350923483, | |
| "grad_norm": 0.2212463617324829, | |
| "learning_rate": 1.8517442133413403e-05, | |
| "loss": 0.8813215494155884, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.4538258575197889, | |
| "grad_norm": 0.22319260239601135, | |
| "learning_rate": 1.8352373262443916e-05, | |
| "loss": 0.9005920886993408, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.4564643799472297, | |
| "grad_norm": 0.22040770947933197, | |
| "learning_rate": 1.818787788367202e-05, | |
| "loss": 0.8013516664505005, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.4591029023746702, | |
| "grad_norm": 0.21650803089141846, | |
| "learning_rate": 1.8023958977947304e-05, | |
| "loss": 0.8534271717071533, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.4617414248021108, | |
| "grad_norm": 0.2045343667268753, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.7753493785858154, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.4643799472295513, | |
| "grad_norm": 0.20727676153182983, | |
| "learning_rate": 1.7697862456752273e-05, | |
| "loss": 0.8886493444442749, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.4670184696569921, | |
| "grad_norm": 0.19541321694850922, | |
| "learning_rate": 1.7535690750534266e-05, | |
| "loss": 0.7950649261474609, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.4696569920844327, | |
| "grad_norm": 0.21428488194942474, | |
| "learning_rate": 1.7374107335760936e-05, | |
| "loss": 0.8809351921081543, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.4722955145118735, | |
| "grad_norm": 0.1980544626712799, | |
| "learning_rate": 1.7213115140513686e-05, | |
| "loss": 0.7901041507720947, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.474934036939314, | |
| "grad_norm": 0.19511975347995758, | |
| "learning_rate": 1.7052717082160346e-05, | |
| "loss": 0.8931927680969238, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.4775725593667546, | |
| "grad_norm": 0.20257903635501862, | |
| "learning_rate": 1.689291606730228e-05, | |
| "loss": 0.7760272026062012, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.4802110817941951, | |
| "grad_norm": 0.2089790254831314, | |
| "learning_rate": 1.673371499172174e-05, | |
| "loss": 0.8708549737930298, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.482849604221636, | |
| "grad_norm": 0.2033015638589859, | |
| "learning_rate": 1.6575116740329317e-05, | |
| "loss": 0.8020316362380981, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.4854881266490765, | |
| "grad_norm": 0.19399622082710266, | |
| "learning_rate": 1.6417124187111775e-05, | |
| "loss": 0.8268682956695557, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.4881266490765173, | |
| "grad_norm": 0.2089431881904602, | |
| "learning_rate": 1.6259740195079903e-05, | |
| "loss": 0.8855108618736267, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.4907651715039578, | |
| "grad_norm": 0.2224927544593811, | |
| "learning_rate": 1.610296761621662e-05, | |
| "loss": 0.825925350189209, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.4934036939313984, | |
| "grad_norm": 0.22050341963768005, | |
| "learning_rate": 1.594680929142535e-05, | |
| "loss": 0.896023690700531, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.496042216358839, | |
| "grad_norm": 0.193280890583992, | |
| "learning_rate": 1.5791268050478486e-05, | |
| "loss": 0.7469483017921448, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.4986807387862797, | |
| "grad_norm": 0.20433108508586884, | |
| "learning_rate": 1.5636346711966155e-05, | |
| "loss": 0.8419564962387085, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.5013192612137203, | |
| "grad_norm": 0.2134133279323578, | |
| "learning_rate": 1.5482048083245114e-05, | |
| "loss": 0.8411462903022766, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.503957783641161, | |
| "grad_norm": 0.2517402470111847, | |
| "learning_rate": 1.532837496038792e-05, | |
| "loss": 0.8998865485191345, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.5065963060686016, | |
| "grad_norm": 0.19719058275222778, | |
| "learning_rate": 1.517533012813217e-05, | |
| "loss": 0.790407121181488, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.5092348284960422, | |
| "grad_norm": 0.19815827906131744, | |
| "learning_rate": 1.5022916359830113e-05, | |
| "loss": 0.827681303024292, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.5118733509234827, | |
| "grad_norm": 0.20996305346488953, | |
| "learning_rate": 1.4871136417398406e-05, | |
| "loss": 0.8366416692733765, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.5145118733509235, | |
| "grad_norm": 0.20357419550418854, | |
| "learning_rate": 1.4719993051268022e-05, | |
| "loss": 0.7767808437347412, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.517150395778364, | |
| "grad_norm": 0.19412170350551605, | |
| "learning_rate": 1.4569489000334436e-05, | |
| "loss": 0.8966915011405945, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.5197889182058049, | |
| "grad_norm": 0.21949054300785065, | |
| "learning_rate": 1.4419626991907925e-05, | |
| "loss": 0.9867626428604126, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.5224274406332454, | |
| "grad_norm": 0.21542461216449738, | |
| "learning_rate": 1.427040974166427e-05, | |
| "loss": 0.7484675645828247, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.525065963060686, | |
| "grad_norm": 0.20638151466846466, | |
| "learning_rate": 1.412183995359544e-05, | |
| "loss": 0.8688530921936035, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.5277044854881265, | |
| "grad_norm": 0.21876366436481476, | |
| "learning_rate": 1.3973920319960655e-05, | |
| "loss": 0.9383907318115234, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.5303430079155673, | |
| "grad_norm": 0.21015901863574982, | |
| "learning_rate": 1.3826653521237525e-05, | |
| "loss": 0.7594534754753113, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.5329815303430079, | |
| "grad_norm": 0.19950366020202637, | |
| "learning_rate": 1.3680042226073552e-05, | |
| "loss": 0.8834112882614136, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.5356200527704487, | |
| "grad_norm": 0.21755766868591309, | |
| "learning_rate": 1.3534089091237755e-05, | |
| "loss": 0.8213707208633423, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.5382585751978892, | |
| "grad_norm": 0.19696074724197388, | |
| "learning_rate": 1.3388796761572492e-05, | |
| "loss": 0.9167644381523132, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.5408970976253298, | |
| "grad_norm": 0.21788553893566132, | |
| "learning_rate": 1.3244167869945589e-05, | |
| "loss": 0.931348443031311, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.5435356200527703, | |
| "grad_norm": 0.2014394998550415, | |
| "learning_rate": 1.310020503720254e-05, | |
| "loss": 0.8700617551803589, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.5461741424802111, | |
| "grad_norm": 0.21630780398845673, | |
| "learning_rate": 1.295691087211912e-05, | |
| "loss": 0.8227249979972839, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.5488126649076517, | |
| "grad_norm": 0.18821114301681519, | |
| "learning_rate": 1.2814287971354022e-05, | |
| "loss": 0.8128796815872192, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.5514511873350925, | |
| "grad_norm": 0.2557939887046814, | |
| "learning_rate": 1.2672338919401866e-05, | |
| "loss": 0.8653614521026611, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.554089709762533, | |
| "grad_norm": 0.1947825402021408, | |
| "learning_rate": 1.253106628854635e-05, | |
| "loss": 0.9020968675613403, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.5567282321899736, | |
| "grad_norm": 0.21898962557315826, | |
| "learning_rate": 1.2390472638813571e-05, | |
| "loss": 0.7656817436218262, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.5593667546174141, | |
| "grad_norm": 0.21510836482048035, | |
| "learning_rate": 1.2250560517925746e-05, | |
| "loss": 0.8295509815216064, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.562005277044855, | |
| "grad_norm": 0.2284301370382309, | |
| "learning_rate": 1.211133246125497e-05, | |
| "loss": 0.8284837603569031, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.5646437994722955, | |
| "grad_norm": 0.20992207527160645, | |
| "learning_rate": 1.1972790991777311e-05, | |
| "loss": 0.8653608560562134, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.5672823218997363, | |
| "grad_norm": 0.22688503563404083, | |
| "learning_rate": 1.183493862002702e-05, | |
| "loss": 0.8686569929122925, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.5699208443271768, | |
| "grad_norm": 0.19538283348083496, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.7942227125167847, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.5725593667546174, | |
| "grad_norm": 0.21061819791793823, | |
| "learning_rate": 1.1561311149364073e-05, | |
| "loss": 0.84868323802948, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.575197889182058, | |
| "grad_norm": 0.21847675740718842, | |
| "learning_rate": 1.1425541008902851e-05, | |
| "loss": 0.8898189067840576, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.5778364116094987, | |
| "grad_norm": 0.20205287635326385, | |
| "learning_rate": 1.1290469882981986e-05, | |
| "loss": 0.6871122121810913, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.5804749340369393, | |
| "grad_norm": 0.209647536277771, | |
| "learning_rate": 1.1156100219249022e-05, | |
| "loss": 0.7839260101318359, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.58311345646438, | |
| "grad_norm": 0.19462355971336365, | |
| "learning_rate": 1.102243445264025e-05, | |
| "loss": 0.7594859600067139, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.5857519788918206, | |
| "grad_norm": 0.20564399659633636, | |
| "learning_rate": 1.0889475005336446e-05, | |
| "loss": 0.9194256067276001, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.5883905013192612, | |
| "grad_norm": 0.2016313374042511, | |
| "learning_rate": 1.075722428671911e-05, | |
| "loss": 0.8529200553894043, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.5910290237467017, | |
| "grad_norm": 0.22161997854709625, | |
| "learning_rate": 1.0625684693326727e-05, | |
| "loss": 0.8794209957122803, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.5936675461741425, | |
| "grad_norm": 0.19965285062789917, | |
| "learning_rate": 1.0494858608811326e-05, | |
| "loss": 0.7318451404571533, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.596306068601583, | |
| "grad_norm": 0.21324901282787323, | |
| "learning_rate": 1.036474840389537e-05, | |
| "loss": 0.7938931584358215, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.5989445910290239, | |
| "grad_norm": 0.2236800491809845, | |
| "learning_rate": 1.0235356436328675e-05, | |
| "loss": 0.9312845468521118, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.6015831134564644, | |
| "grad_norm": 0.20095610618591309, | |
| "learning_rate": 1.0106685050845838e-05, | |
| "loss": 0.9334725737571716, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.604221635883905, | |
| "grad_norm": 0.24465373158454895, | |
| "learning_rate": 9.978736579123577e-06, | |
| "loss": 0.9391512274742126, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.6068601583113455, | |
| "grad_norm": 0.21828067302703857, | |
| "learning_rate": 9.851513339738628e-06, | |
| "loss": 0.9064762592315674, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.6094986807387863, | |
| "grad_norm": 0.21165606379508972, | |
| "learning_rate": 9.72501763812561e-06, | |
| "loss": 0.8413673639297485, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.6121372031662269, | |
| "grad_norm": 0.19530081748962402, | |
| "learning_rate": 9.599251766535345e-06, | |
| "loss": 0.8129094839096069, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.6147757255936677, | |
| "grad_norm": 0.19908255338668823, | |
| "learning_rate": 9.474218003993273e-06, | |
| "loss": 0.7808138132095337, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.6174142480211082, | |
| "grad_norm": 0.1975618451833725, | |
| "learning_rate": 9.349918616258114e-06, | |
| "loss": 0.7855852842330933, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.6200527704485488, | |
| "grad_norm": 0.20149685442447662, | |
| "learning_rate": 9.226355855780921e-06, | |
| "loss": 0.774482011795044, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.6226912928759893, | |
| "grad_norm": 0.21338312327861786, | |
| "learning_rate": 9.103531961664118e-06, | |
| "loss": 0.8815280199050903, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.6253298153034301, | |
| "grad_norm": 0.2008296102285385, | |
| "learning_rate": 8.981449159621074e-06, | |
| "loss": 0.8243716359138489, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.6279683377308707, | |
| "grad_norm": 0.21292272210121155, | |
| "learning_rate": 8.860109661935674e-06, | |
| "loss": 0.8072988390922546, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.6306068601583115, | |
| "grad_norm": 0.23465301096439362, | |
| "learning_rate": 8.73951566742221e-06, | |
| "loss": 0.8511773347854614, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.633245382585752, | |
| "grad_norm": 0.46375322341918945, | |
| "learning_rate": 8.619669361385663e-06, | |
| "loss": 0.853812575340271, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.6358839050131926, | |
| "grad_norm": 0.18248288333415985, | |
| "learning_rate": 8.500572915581922e-06, | |
| "loss": 0.7355204224586487, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.6385224274406331, | |
| "grad_norm": 0.18261535465717316, | |
| "learning_rate": 8.38222848817864e-06, | |
| "loss": 0.8264297246932983, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.641160949868074, | |
| "grad_norm": 0.20754438638687134, | |
| "learning_rate": 8.264638223715916e-06, | |
| "loss": 0.8225191235542297, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.6437994722955145, | |
| "grad_norm": 0.20159278810024261, | |
| "learning_rate": 8.14780425306758e-06, | |
| "loss": 0.87016361951828, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.6464379947229553, | |
| "grad_norm": 0.22935034334659576, | |
| "learning_rate": 8.031728693402502e-06, | |
| "loss": 0.8048298358917236, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.6490765171503958, | |
| "grad_norm": 0.18488283455371857, | |
| "learning_rate": 7.91641364814628e-06, | |
| "loss": 0.8106614351272583, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.6517150395778364, | |
| "grad_norm": 0.21160657703876495, | |
| "learning_rate": 7.801861206943089e-06, | |
| "loss": 0.8310866951942444, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 1.654353562005277, | |
| "grad_norm": 0.1970130354166031, | |
| "learning_rate": 7.688073445617799e-06, | |
| "loss": 0.7170044779777527, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 1.6569920844327177, | |
| "grad_norm": 0.20660647749900818, | |
| "learning_rate": 7.5750524261384235e-06, | |
| "loss": 0.7831541299819946, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.6596306068601583, | |
| "grad_norm": 0.20981073379516602, | |
| "learning_rate": 7.462800196578662e-06, | |
| "loss": 0.8566669225692749, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.662269129287599, | |
| "grad_norm": 0.23708082735538483, | |
| "learning_rate": 7.35131879108088e-06, | |
| "loss": 0.8529813289642334, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.6649076517150396, | |
| "grad_norm": 0.9549576640129089, | |
| "learning_rate": 7.240610229819195e-06, | |
| "loss": 0.8493508100509644, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 1.6675461741424802, | |
| "grad_norm": 0.2114357352256775, | |
| "learning_rate": 7.130676518962859e-06, | |
| "loss": 0.8748669624328613, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.6701846965699207, | |
| "grad_norm": 0.19402459263801575, | |
| "learning_rate": 7.0215196506399515e-06, | |
| "loss": 0.8187092542648315, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 1.6728232189973615, | |
| "grad_norm": 0.20854152739048004, | |
| "learning_rate": 6.913141602901213e-06, | |
| "loss": 0.9096065163612366, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 1.675461741424802, | |
| "grad_norm": 0.21093755960464478, | |
| "learning_rate": 6.8055443396842945e-06, | |
| "loss": 0.8709210157394409, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.6781002638522429, | |
| "grad_norm": 0.21466106176376343, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8059540390968323, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.6807387862796834, | |
| "grad_norm": 0.19374695420265198, | |
| "learning_rate": 6.592699951787362e-06, | |
| "loss": 0.8607715368270874, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 1.683377308707124, | |
| "grad_norm": 0.2216903418302536, | |
| "learning_rate": 6.487456684097848e-06, | |
| "loss": 0.8703226447105408, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 1.6860158311345645, | |
| "grad_norm": 0.24131982028484344, | |
| "learning_rate": 6.3830019148412525e-06, | |
| "loss": 0.8075211048126221, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 1.6886543535620053, | |
| "grad_norm": 0.19988761842250824, | |
| "learning_rate": 6.279337536860785e-06, | |
| "loss": 0.8634479641914368, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.6912928759894459, | |
| "grad_norm": 0.21736286580562592, | |
| "learning_rate": 6.17646542867682e-06, | |
| "loss": 0.8513948321342468, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 1.6939313984168867, | |
| "grad_norm": 0.21482457220554352, | |
| "learning_rate": 6.07438745445289e-06, | |
| "loss": 0.8792531490325928, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 1.6965699208443272, | |
| "grad_norm": 0.20397554337978363, | |
| "learning_rate": 5.973105463961865e-06, | |
| "loss": 0.8307263851165771, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 1.6992084432717678, | |
| "grad_norm": 0.20772746205329895, | |
| "learning_rate": 5.872621292552477e-06, | |
| "loss": 0.8588171005249023, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.7018469656992083, | |
| "grad_norm": 0.21618413925170898, | |
| "learning_rate": 5.772936761116027e-06, | |
| "loss": 0.8800046443939209, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.7044854881266491, | |
| "grad_norm": 0.20802974700927734, | |
| "learning_rate": 5.6740536760534144e-06, | |
| "loss": 0.9347285032272339, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 1.7071240105540897, | |
| "grad_norm": 0.22136233747005463, | |
| "learning_rate": 5.575973829242364e-06, | |
| "loss": 0.8545072078704834, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 1.7097625329815305, | |
| "grad_norm": 0.2067175656557083, | |
| "learning_rate": 5.478698998004967e-06, | |
| "loss": 0.8864841461181641, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.712401055408971, | |
| "grad_norm": 0.23648934066295624, | |
| "learning_rate": 5.382230945075556e-06, | |
| "loss": 0.86419677734375, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 1.7150395778364116, | |
| "grad_norm": 0.20306909084320068, | |
| "learning_rate": 5.286571418568615e-06, | |
| "loss": 0.8809700012207031, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.7176781002638521, | |
| "grad_norm": 0.2015990912914276, | |
| "learning_rate": 5.191722151947226e-06, | |
| "loss": 0.7576265931129456, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 1.720316622691293, | |
| "grad_norm": 0.20526087284088135, | |
| "learning_rate": 5.097684863991575e-06, | |
| "loss": 0.8124517798423767, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 1.7229551451187335, | |
| "grad_norm": 0.21329709887504578, | |
| "learning_rate": 5.004461258767873e-06, | |
| "loss": 0.8556035757064819, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 1.7255936675461743, | |
| "grad_norm": 0.21723578870296478, | |
| "learning_rate": 4.912053025597429e-06, | |
| "loss": 0.8384562134742737, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 1.7282321899736148, | |
| "grad_norm": 0.19574065506458282, | |
| "learning_rate": 4.820461839026047e-06, | |
| "loss": 0.8278510570526123, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.7308707124010554, | |
| "grad_norm": 0.1882028728723526, | |
| "learning_rate": 4.729689358793693e-06, | |
| "loss": 0.8415632843971252, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 1.733509234828496, | |
| "grad_norm": 0.22890862822532654, | |
| "learning_rate": 4.639737229804403e-06, | |
| "loss": 0.8932334184646606, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 1.7361477572559367, | |
| "grad_norm": 0.2388426512479782, | |
| "learning_rate": 4.5506070820964976e-06, | |
| "loss": 0.7936335802078247, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 1.7387862796833773, | |
| "grad_norm": 0.2018558830022812, | |
| "learning_rate": 4.462300530813024e-06, | |
| "loss": 0.7627620100975037, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 1.741424802110818, | |
| "grad_norm": 0.2154654711484909, | |
| "learning_rate": 4.374819176172501e-06, | |
| "loss": 0.8787714838981628, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.7440633245382586, | |
| "grad_norm": 0.2038903832435608, | |
| "learning_rate": 4.2881646034398925e-06, | |
| "loss": 0.8130042552947998, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 1.7467018469656992, | |
| "grad_norm": 0.21601106226444244, | |
| "learning_rate": 4.20233838289793e-06, | |
| "loss": 0.835135281085968, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 1.7493403693931397, | |
| "grad_norm": 0.2100323736667633, | |
| "learning_rate": 4.117342069818603e-06, | |
| "loss": 0.8817960023880005, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 1.7519788918205803, | |
| "grad_norm": 0.20168212056159973, | |
| "learning_rate": 4.033177204435024e-06, | |
| "loss": 0.8514724969863892, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 1.754617414248021, | |
| "grad_norm": 0.2164795845746994, | |
| "learning_rate": 3.949845311913492e-06, | |
| "loss": 0.8425164818763733, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.7572559366754619, | |
| "grad_norm": 0.19507786631584167, | |
| "learning_rate": 3.8673479023258465e-06, | |
| "loss": 0.8335729241371155, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 1.7598944591029024, | |
| "grad_norm": 0.23975177109241486, | |
| "learning_rate": 3.7856864706221185e-06, | |
| "loss": 0.8719772696495056, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 1.762532981530343, | |
| "grad_norm": 0.21782037615776062, | |
| "learning_rate": 3.7048624966034506e-06, | |
| "loss": 0.8989812135696411, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 1.7651715039577835, | |
| "grad_norm": 0.1859140247106552, | |
| "learning_rate": 3.6248774448952695e-06, | |
| "loss": 0.8056320548057556, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 1.767810026385224, | |
| "grad_norm": 0.19920724630355835, | |
| "learning_rate": 3.5457327649207172e-06, | |
| "loss": 0.7947468757629395, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.770448548812665, | |
| "grad_norm": 0.19092382490634918, | |
| "learning_rate": 3.467429890874424e-06, | |
| "loss": 0.7448170781135559, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 1.7730870712401057, | |
| "grad_norm": 0.22142529487609863, | |
| "learning_rate": 3.389970241696516e-06, | |
| "loss": 0.9054186344146729, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 1.7757255936675462, | |
| "grad_norm": 0.22562207281589508, | |
| "learning_rate": 3.3133552210468875e-06, | |
| "loss": 0.9187839031219482, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 1.7783641160949868, | |
| "grad_norm": 0.21036329865455627, | |
| "learning_rate": 3.2375862172797864e-06, | |
| "loss": 0.7974717020988464, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 1.7810026385224274, | |
| "grad_norm": 0.21586009860038757, | |
| "learning_rate": 3.162664603418608e-06, | |
| "loss": 0.9025945663452148, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.783641160949868, | |
| "grad_norm": 0.20773616433143616, | |
| "learning_rate": 3.0885917371310745e-06, | |
| "loss": 0.8064232468605042, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 1.7862796833773087, | |
| "grad_norm": 0.2322840839624405, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.7908546924591064, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 1.7889182058047495, | |
| "grad_norm": 0.2061799168586731, | |
| "learning_rate": 2.942997601021924e-06, | |
| "loss": 0.8989397287368774, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 1.79155672823219, | |
| "grad_norm": 0.2287965565919876, | |
| "learning_rate": 2.871478969537206e-06, | |
| "loss": 0.9402959942817688, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 1.7941952506596306, | |
| "grad_norm": 0.22069700062274933, | |
| "learning_rate": 2.800814362252091e-06, | |
| "loss": 0.7985097169876099, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.7968337730870712, | |
| "grad_norm": 0.20467771589756012, | |
| "learning_rate": 2.731005059692332e-06, | |
| "loss": 0.7937331199645996, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 1.7994722955145117, | |
| "grad_norm": 0.21517489850521088, | |
| "learning_rate": 2.662052326884551e-06, | |
| "loss": 0.8889937996864319, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 1.8021108179419525, | |
| "grad_norm": 0.20879219472408295, | |
| "learning_rate": 2.5939574133333312e-06, | |
| "loss": 0.875966489315033, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 1.8047493403693933, | |
| "grad_norm": 0.20481455326080322, | |
| "learning_rate": 2.5267215529985342e-06, | |
| "loss": 0.7772852778434753, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 1.8073878627968338, | |
| "grad_norm": 0.23448669910430908, | |
| "learning_rate": 2.4603459642729863e-06, | |
| "loss": 0.9144713878631592, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.8100263852242744, | |
| "grad_norm": 0.22476829588413239, | |
| "learning_rate": 2.394831849960377e-06, | |
| "loss": 0.802951455116272, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 1.812664907651715, | |
| "grad_norm": 0.20005077123641968, | |
| "learning_rate": 2.330180397253473e-06, | |
| "loss": 0.7209995985031128, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 1.8153034300791555, | |
| "grad_norm": 0.21807320415973663, | |
| "learning_rate": 2.266392777712595e-06, | |
| "loss": 0.8040324449539185, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 1.8179419525065963, | |
| "grad_norm": 0.21830332279205322, | |
| "learning_rate": 2.203470147244385e-06, | |
| "loss": 0.875383734703064, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 1.820580474934037, | |
| "grad_norm": 0.23793306946754456, | |
| "learning_rate": 2.1414136460808807e-06, | |
| "loss": 0.7538058161735535, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.8232189973614776, | |
| "grad_norm": 0.22125472128391266, | |
| "learning_rate": 2.0802243987588066e-06, | |
| "loss": 0.8075780868530273, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 1.8258575197889182, | |
| "grad_norm": 0.21494165062904358, | |
| "learning_rate": 2.019903514099275e-06, | |
| "loss": 0.8103631138801575, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 1.8284960422163588, | |
| "grad_norm": 0.23122619092464447, | |
| "learning_rate": 1.9604520851876198e-06, | |
| "loss": 0.8613567352294922, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 1.8311345646437993, | |
| "grad_norm": 0.20822040736675262, | |
| "learning_rate": 1.901871189353599e-06, | |
| "loss": 0.9021971225738525, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 1.83377308707124, | |
| "grad_norm": 0.20075157284736633, | |
| "learning_rate": 1.8441618881519184e-06, | |
| "loss": 0.8062754273414612, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.8364116094986809, | |
| "grad_norm": 0.20415347814559937, | |
| "learning_rate": 1.7873252273429509e-06, | |
| "loss": 0.811295747756958, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 1.8390501319261214, | |
| "grad_norm": 0.21688245236873627, | |
| "learning_rate": 1.7313622368738014e-06, | |
| "loss": 0.8866380453109741, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 1.841688654353562, | |
| "grad_norm": 0.19460809230804443, | |
| "learning_rate": 1.6762739308596343e-06, | |
| "loss": 0.8552433252334595, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 1.8443271767810026, | |
| "grad_norm": 0.1838616132736206, | |
| "learning_rate": 1.6220613075653202e-06, | |
| "loss": 0.6805065274238586, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 1.8469656992084431, | |
| "grad_norm": 0.1913633495569229, | |
| "learning_rate": 1.5687253493873067e-06, | |
| "loss": 0.7490788698196411, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.849604221635884, | |
| "grad_norm": 0.2015620470046997, | |
| "learning_rate": 1.51626702283586e-06, | |
| "loss": 0.8849630355834961, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 1.8522427440633247, | |
| "grad_norm": 0.2095753252506256, | |
| "learning_rate": 1.464687278517518e-06, | |
| "loss": 0.8486800193786621, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 1.8548812664907652, | |
| "grad_norm": 0.21090112626552582, | |
| "learning_rate": 1.4139870511178766e-06, | |
| "loss": 0.8101059794425964, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 1.8575197889182058, | |
| "grad_norm": 0.22010932862758636, | |
| "learning_rate": 1.3641672593846632e-06, | |
| "loss": 0.8158517479896545, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.8601583113456464, | |
| "grad_norm": 0.20055443048477173, | |
| "learning_rate": 1.3152288061110518e-06, | |
| "loss": 0.7629213333129883, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.862796833773087, | |
| "grad_norm": 0.19355174899101257, | |
| "learning_rate": 1.2671725781193467e-06, | |
| "loss": 0.7851141691207886, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 1.8654353562005277, | |
| "grad_norm": 0.2218313366174698, | |
| "learning_rate": 1.2199994462448904e-06, | |
| "loss": 0.8358639478683472, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 1.8680738786279685, | |
| "grad_norm": 0.20099952816963196, | |
| "learning_rate": 1.1737102653202826e-06, | |
| "loss": 0.8785051107406616, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 1.870712401055409, | |
| "grad_norm": 0.20789465308189392, | |
| "learning_rate": 1.128305874159896e-06, | |
| "loss": 0.7248390316963196, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 1.8733509234828496, | |
| "grad_norm": 0.20585159957408905, | |
| "learning_rate": 1.0837870955446638e-06, | |
| "loss": 0.8331854343414307, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.8759894459102902, | |
| "grad_norm": 0.21308377385139465, | |
| "learning_rate": 1.040154736207194e-06, | |
| "loss": 0.860977292060852, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 1.8786279683377307, | |
| "grad_norm": 0.21850626170635223, | |
| "learning_rate": 9.974095868171162e-07, | |
| "loss": 0.8206614255905151, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 1.8812664907651715, | |
| "grad_norm": 0.19836367666721344, | |
| "learning_rate": 9.555524219667989e-07, | |
| "loss": 0.8025310635566711, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 1.8839050131926123, | |
| "grad_norm": 0.21136832237243652, | |
| "learning_rate": 9.145840001572537e-07, | |
| "loss": 0.8504902124404907, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 1.8865435356200528, | |
| "grad_norm": 0.23634563386440277, | |
| "learning_rate": 8.745050637844532e-07, | |
| "loss": 0.8698995113372803, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.8891820580474934, | |
| "grad_norm": 0.2007746547460556, | |
| "learning_rate": 8.353163391258301e-07, | |
| "loss": 0.8317679166793823, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 1.891820580474934, | |
| "grad_norm": 0.20997071266174316, | |
| "learning_rate": 7.970185363271431e-07, | |
| "loss": 0.7819387912750244, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 1.8944591029023745, | |
| "grad_norm": 0.21593962609767914, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.8462232947349548, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 1.8970976253298153, | |
| "grad_norm": 0.20098824799060822, | |
| "learning_rate": 7.230984561572729e-07, | |
| "loss": 0.835645318031311, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 1.899736147757256, | |
| "grad_norm": 0.20634238421916962, | |
| "learning_rate": 6.874775183048299e-07, | |
| "loss": 0.8471999764442444, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.9023746701846966, | |
| "grad_norm": 0.18705205619335175, | |
| "learning_rate": 6.527501813255344e-07, | |
| "loss": 0.8066807389259338, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 1.9050131926121372, | |
| "grad_norm": 0.22316007316112518, | |
| "learning_rate": 6.189170745195649e-07, | |
| "loss": 0.8412566184997559, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 1.9076517150395778, | |
| "grad_norm": 0.20048147439956665, | |
| "learning_rate": 5.859788109825793e-07, | |
| "loss": 0.7970318794250488, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 1.9102902374670183, | |
| "grad_norm": 0.22987322509288788, | |
| "learning_rate": 5.53935987594617e-07, | |
| "loss": 0.7696294188499451, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 1.912928759894459, | |
| "grad_norm": 0.23662720620632172, | |
| "learning_rate": 5.227891850093314e-07, | |
| "loss": 0.8058530688285828, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.9155672823218999, | |
| "grad_norm": 0.2005518525838852, | |
| "learning_rate": 4.925389676433745e-07, | |
| "loss": 0.7893189191818237, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 1.9182058047493404, | |
| "grad_norm": 0.22957301139831543, | |
| "learning_rate": 4.6318588366625616e-07, | |
| "loss": 0.9222890138626099, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 1.920844327176781, | |
| "grad_norm": 0.20035627484321594, | |
| "learning_rate": 4.347304649903572e-07, | |
| "loss": 0.8075400590896606, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 1.9234828496042216, | |
| "grad_norm": 0.22035662829875946, | |
| "learning_rate": 4.071732272613149e-07, | |
| "loss": 0.800722599029541, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 1.9261213720316621, | |
| "grad_norm": 0.21661067008972168, | |
| "learning_rate": 3.805146698486695e-07, | |
| "loss": 0.8441472053527832, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.928759894459103, | |
| "grad_norm": 0.2007487416267395, | |
| "learning_rate": 3.5475527583681e-07, | |
| "loss": 0.720578134059906, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 1.9313984168865437, | |
| "grad_norm": 0.2147989273071289, | |
| "learning_rate": 3.2989551201624835e-07, | |
| "loss": 0.8720710277557373, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 1.9340369393139842, | |
| "grad_norm": 0.2244662344455719, | |
| "learning_rate": 3.059358288751202e-07, | |
| "loss": 0.8538236021995544, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 1.9366754617414248, | |
| "grad_norm": 0.1987634301185608, | |
| "learning_rate": 2.828766605910471e-07, | |
| "loss": 0.8031460642814636, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 1.9393139841688654, | |
| "grad_norm": 0.23431123793125153, | |
| "learning_rate": 2.6071842502326527e-07, | |
| "loss": 0.9187484979629517, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.941952506596306, | |
| "grad_norm": 0.20140373706817627, | |
| "learning_rate": 2.3946152370505346e-07, | |
| "loss": 0.8281949758529663, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 1.9445910290237467, | |
| "grad_norm": 0.20692074298858643, | |
| "learning_rate": 2.1910634183644474e-07, | |
| "loss": 0.7750309705734253, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 1.9472295514511875, | |
| "grad_norm": 0.2009861320257187, | |
| "learning_rate": 1.996532482772595e-07, | |
| "loss": 0.8492032885551453, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 1.949868073878628, | |
| "grad_norm": 0.21607014536857605, | |
| "learning_rate": 1.811025955404333e-07, | |
| "loss": 0.8605877161026001, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 1.9525065963060686, | |
| "grad_norm": 0.21618352830410004, | |
| "learning_rate": 1.6345471978558845e-07, | |
| "loss": 0.8067154884338379, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.9551451187335092, | |
| "grad_norm": 0.1969093680381775, | |
| "learning_rate": 1.4670994081297795e-07, | |
| "loss": 0.8418698310852051, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 1.9577836411609497, | |
| "grad_norm": 0.21148380637168884, | |
| "learning_rate": 1.3086856205768438e-07, | |
| "loss": 0.9082729816436768, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 1.9604221635883905, | |
| "grad_norm": 0.21570627391338348, | |
| "learning_rate": 1.1593087058410779e-07, | |
| "loss": 0.828383207321167, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 1.9630606860158313, | |
| "grad_norm": 0.22988225519657135, | |
| "learning_rate": 1.0189713708078085e-07, | |
| "loss": 0.8422545194625854, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 1.9656992084432718, | |
| "grad_norm": 0.21034526824951172, | |
| "learning_rate": 8.876761585545068e-08, | |
| "loss": 0.8603432774543762, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.9683377308707124, | |
| "grad_norm": 0.23274272680282593, | |
| "learning_rate": 7.65425448304713e-08, | |
| "loss": 0.9002218246459961, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 1.970976253298153, | |
| "grad_norm": 0.19577914476394653, | |
| "learning_rate": 6.522214553850159e-08, | |
| "loss": 0.8663936853408813, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 1.9736147757255935, | |
| "grad_norm": 0.2175392359495163, | |
| "learning_rate": 5.4806623118486275e-08, | |
| "loss": 0.8117172122001648, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 1.9762532981530343, | |
| "grad_norm": 0.2106153666973114, | |
| "learning_rate": 4.529616631193112e-08, | |
| "loss": 0.9605646133422852, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 1.978891820580475, | |
| "grad_norm": 0.20242197811603546, | |
| "learning_rate": 3.669094745950008e-08, | |
| "loss": 0.7868301272392273, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.9815303430079156, | |
| "grad_norm": 0.22185878455638885, | |
| "learning_rate": 2.899112249786229e-08, | |
| "loss": 0.9537394046783447, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 1.9841688654353562, | |
| "grad_norm": 0.2320915013551712, | |
| "learning_rate": 2.219683095690539e-08, | |
| "loss": 0.9150735139846802, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 1.9868073878627968, | |
| "grad_norm": 0.24962309002876282, | |
| "learning_rate": 1.6308195957182027e-08, | |
| "loss": 0.769099235534668, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 1.9894459102902373, | |
| "grad_norm": 0.20675364136695862, | |
| "learning_rate": 1.1325324207667188e-08, | |
| "loss": 0.8421361446380615, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 1.992084432717678, | |
| "grad_norm": 0.1924310028553009, | |
| "learning_rate": 7.248306003865279e-09, | |
| "loss": 0.8723808526992798, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.9947229551451189, | |
| "grad_norm": 0.2054050862789154, | |
| "learning_rate": 4.07721522613369e-09, | |
| "loss": 0.8893437385559082, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 1.9973614775725594, | |
| "grad_norm": 0.21500982344150543, | |
| "learning_rate": 1.8121093383671738e-09, | |
| "loss": 0.9416911602020264, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.2577999234199524, | |
| "learning_rate": 4.5302938694868903e-10, | |
| "loss": 0.8910604119300842, | |
| "step": 758 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 758, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.294513101283913e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |