Instructions to use Kukedlc/Slopus-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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

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

Slopus-9B / adapter_phase1 /trainer_state.json

Kukedlc

Add adapter_phase1/trainer_state.json (ckpt-506 final phase 1)

a811ed8 verified about 1 month ago

Raw

History Blame Contribute Delete

94.6 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 2.0,
	"eval_steps": 500,
	"global_step": 506,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.003954522985664854,
	"grad_norm": 0.2544356882572174,
	"learning_rate": 0.0,
	"loss": 1.180017113685608,
	"step": 1
	},
	{
	"epoch": 0.007909045971329708,
	"grad_norm": 0.2469092607498169,
	"learning_rate": 4e-05,
	"loss": 1.1813130378723145,
	"step": 2
	},
	{
	"epoch": 0.011863568956994563,
	"grad_norm": 0.20873534679412842,
	"learning_rate": 8e-05,
	"loss": 1.1847681999206543,
	"step": 3
	},
	{
	"epoch": 0.015818091942659415,
	"grad_norm": 0.22851118445396423,
	"learning_rate": 0.00012,
	"loss": 1.1241787672042847,
	"step": 4
	},
	{
	"epoch": 0.019772614928324272,
	"grad_norm": 0.22521217167377472,
	"learning_rate": 0.00016,
	"loss": 1.1387571096420288,
	"step": 5
	},
	{
	"epoch": 0.023727137913989126,
	"grad_norm": 0.21741724014282227,
	"learning_rate": 0.0002,
	"loss": 1.103634238243103,
	"step": 6
	},
	{
	"epoch": 0.02768166089965398,
	"grad_norm": 0.1713864952325821,
	"learning_rate": 0.0001996007984031936,
	"loss": 1.1193780899047852,
	"step": 7
	},
	{
	"epoch": 0.03163618388531883,
	"grad_norm": 0.1551392674446106,
	"learning_rate": 0.00019920159680638725,
	"loss": 1.209862470626831,
	"step": 8
	},
	{
	"epoch": 0.03559070687098369,
	"grad_norm": 0.17870232462882996,
	"learning_rate": 0.00019880239520958084,
	"loss": 1.1225727796554565,
	"step": 9
	},
	{
	"epoch": 0.039545229856648545,
	"grad_norm": 0.20667865872383118,
	"learning_rate": 0.00019840319361277446,
	"loss": 1.0327069759368896,
	"step": 10
	},
	{
	"epoch": 0.043499752842313395,
	"grad_norm": 0.19965171813964844,
	"learning_rate": 0.00019800399201596808,
	"loss": 0.9479315280914307,
	"step": 11
	},
	{
	"epoch": 0.04745427582797825,
	"grad_norm": 0.21041055023670197,
	"learning_rate": 0.0001976047904191617,
	"loss": 1.1442006826400757,
	"step": 12
	},
	{
	"epoch": 0.0514087988136431,
	"grad_norm": 0.16018487513065338,
	"learning_rate": 0.0001972055888223553,
	"loss": 1.0416808128356934,
	"step": 13
	},
	{
	"epoch": 0.05536332179930796,
	"grad_norm": 0.141277477145195,
	"learning_rate": 0.0001968063872255489,
	"loss": 1.1698994636535645,
	"step": 14
	},
	{
	"epoch": 0.05931784478497281,
	"grad_norm": 0.12079285830259323,
	"learning_rate": 0.00019640718562874253,
	"loss": 0.9101760983467102,
	"step": 15
	},
	{
	"epoch": 0.06327236777063766,
	"grad_norm": 0.13878197968006134,
	"learning_rate": 0.00019600798403193614,
	"loss": 1.1655550003051758,
	"step": 16
	},
	{
	"epoch": 0.06722689075630252,
	"grad_norm": 0.16896755993366241,
	"learning_rate": 0.00019560878243512974,
	"loss": 1.0796542167663574,
	"step": 17
	},
	{
	"epoch": 0.07118141374196738,
	"grad_norm": 0.12621314823627472,
	"learning_rate": 0.00019520958083832338,
	"loss": 1.1336424350738525,
	"step": 18
	},
	{
	"epoch": 0.07513593672763223,
	"grad_norm": 0.1260470598936081,
	"learning_rate": 0.00019481037924151697,
	"loss": 1.02823805809021,
	"step": 19
	},
	{
	"epoch": 0.07909045971329709,
	"grad_norm": 0.1230599507689476,
	"learning_rate": 0.0001944111776447106,
	"loss": 0.9280879497528076,
	"step": 20
	},
	{
	"epoch": 0.08304498269896193,
	"grad_norm": 0.11235114187002182,
	"learning_rate": 0.00019401197604790419,
	"loss": 1.0234721899032593,
	"step": 21
	},
	{
	"epoch": 0.08699950568462679,
	"grad_norm": 0.1244259923696518,
	"learning_rate": 0.00019361277445109783,
	"loss": 0.9619145393371582,
	"step": 22
	},
	{
	"epoch": 0.09095402867029165,
	"grad_norm": 0.10888625681400299,
	"learning_rate": 0.00019321357285429142,
	"loss": 1.0350663661956787,
	"step": 23
	},
	{
	"epoch": 0.0949085516559565,
	"grad_norm": 0.12405306845903397,
	"learning_rate": 0.00019281437125748504,
	"loss": 1.1137639284133911,
	"step": 24
	},
	{
	"epoch": 0.09886307464162135,
	"grad_norm": 0.1365104615688324,
	"learning_rate": 0.00019241516966067866,
	"loss": 1.082958459854126,
	"step": 25
	},
	{
	"epoch": 0.1028175976272862,
	"grad_norm": 0.12047652900218964,
	"learning_rate": 0.00019201596806387228,
	"loss": 1.031674861907959,
	"step": 26
	},
	{
	"epoch": 0.10677212061295106,
	"grad_norm": 0.10935146361589432,
	"learning_rate": 0.00019161676646706587,
	"loss": 0.9122903347015381,
	"step": 27
	},
	{
	"epoch": 0.11072664359861592,
	"grad_norm": 0.1395711451768875,
	"learning_rate": 0.0001912175648702595,
	"loss": 0.9628266096115112,
	"step": 28
	},
	{
	"epoch": 0.11468116658428078,
	"grad_norm": 0.13380995392799377,
	"learning_rate": 0.0001908183632734531,
	"loss": 0.962996244430542,
	"step": 29
	},
	{
	"epoch": 0.11863568956994562,
	"grad_norm": 0.12701313197612762,
	"learning_rate": 0.0001904191616766467,
	"loss": 0.9316821694374084,
	"step": 30
	},
	{
	"epoch": 0.12259021255561048,
	"grad_norm": 0.12657427787780762,
	"learning_rate": 0.00019001996007984032,
	"loss": 1.0292439460754395,
	"step": 31
	},
	{
	"epoch": 0.12654473554127532,
	"grad_norm": 0.13929884135723114,
	"learning_rate": 0.00018962075848303394,
	"loss": 1.0495136976242065,
	"step": 32
	},
	{
	"epoch": 0.1304992585269402,
	"grad_norm": 0.1292039155960083,
	"learning_rate": 0.00018922155688622756,
	"loss": 1.0562491416931152,
	"step": 33
	},
	{
	"epoch": 0.13445378151260504,
	"grad_norm": 0.1383693516254425,
	"learning_rate": 0.00018882235528942115,
	"loss": 1.012336015701294,
	"step": 34
	},
	{
	"epoch": 0.1384083044982699,
	"grad_norm": 0.11728740483522415,
	"learning_rate": 0.0001884231536926148,
	"loss": 0.903199315071106,
	"step": 35
	},
	{
	"epoch": 0.14236282748393475,
	"grad_norm": 0.12921994924545288,
	"learning_rate": 0.0001880239520958084,
	"loss": 1.0892961025238037,
	"step": 36
	},
	{
	"epoch": 0.1463173504695996,
	"grad_norm": 0.1262505203485489,
	"learning_rate": 0.000187624750499002,
	"loss": 1.1606205701828003,
	"step": 37
	},
	{
	"epoch": 0.15027187345526447,
	"grad_norm": 0.12508349120616913,
	"learning_rate": 0.00018722554890219563,
	"loss": 1.0895495414733887,
	"step": 38
	},
	{
	"epoch": 0.1542263964409293,
	"grad_norm": 0.12130790203809738,
	"learning_rate": 0.00018682634730538924,
	"loss": 1.0368725061416626,
	"step": 39
	},
	{
	"epoch": 0.15818091942659418,
	"grad_norm": 0.12927809357643127,
	"learning_rate": 0.00018642714570858284,
	"loss": 1.0340652465820312,
	"step": 40
	},
	{
	"epoch": 0.16213544241225902,
	"grad_norm": 0.12635737657546997,
	"learning_rate": 0.00018602794411177646,
	"loss": 1.1098253726959229,
	"step": 41
	},
	{
	"epoch": 0.16608996539792387,
	"grad_norm": 0.1303265392780304,
	"learning_rate": 0.00018562874251497007,
	"loss": 1.0297881364822388,
	"step": 42
	},
	{
	"epoch": 0.17004448838358874,
	"grad_norm": 0.12825307250022888,
	"learning_rate": 0.0001852295409181637,
	"loss": 0.9129877090454102,
	"step": 43
	},
	{
	"epoch": 0.17399901136925358,
	"grad_norm": 0.12521876394748688,
	"learning_rate": 0.00018483033932135728,
	"loss": 0.97171550989151,
	"step": 44
	},
	{
	"epoch": 0.17795353435491842,
	"grad_norm": 0.13904021680355072,
	"learning_rate": 0.00018443113772455093,
	"loss": 1.097721815109253,
	"step": 45
	},
	{
	"epoch": 0.1819080573405833,
	"grad_norm": 0.14009957015514374,
	"learning_rate": 0.00018403193612774452,
	"loss": 0.9984307885169983,
	"step": 46
	},
	{
	"epoch": 0.18586258032624814,
	"grad_norm": 0.12277879565954208,
	"learning_rate": 0.00018363273453093811,
	"loss": 0.9881635904312134,
	"step": 47
	},
	{
	"epoch": 0.189817103311913,
	"grad_norm": 0.13878905773162842,
	"learning_rate": 0.00018323353293413173,
	"loss": 0.9900161027908325,
	"step": 48
	},
	{
	"epoch": 0.19377162629757785,
	"grad_norm": 0.1394307166337967,
	"learning_rate": 0.00018283433133732535,
	"loss": 0.8905137777328491,
	"step": 49
	},
	{
	"epoch": 0.1977261492832427,
	"grad_norm": 0.1348118931055069,
	"learning_rate": 0.00018243512974051897,
	"loss": 1.001299500465393,
	"step": 50
	},
	{
	"epoch": 0.20168067226890757,
	"grad_norm": 0.14841432869434357,
	"learning_rate": 0.00018203592814371256,
	"loss": 1.114479899406433,
	"step": 51
	},
	{
	"epoch": 0.2056351952545724,
	"grad_norm": 0.12918154895305634,
	"learning_rate": 0.0001816367265469062,
	"loss": 1.075540542602539,
	"step": 52
	},
	{
	"epoch": 0.20958971824023728,
	"grad_norm": 0.137839674949646,
	"learning_rate": 0.0001812375249500998,
	"loss": 0.9629291892051697,
	"step": 53
	},
	{
	"epoch": 0.21354424122590213,
	"grad_norm": 0.12743251025676727,
	"learning_rate": 0.00018083832335329342,
	"loss": 0.8884077668190002,
	"step": 54
	},
	{
	"epoch": 0.21749876421156697,
	"grad_norm": 0.14579665660858154,
	"learning_rate": 0.00018043912175648704,
	"loss": 1.0494593381881714,
	"step": 55
	},
	{
	"epoch": 0.22145328719723184,
	"grad_norm": 0.1444905400276184,
	"learning_rate": 0.00018003992015968066,
	"loss": 0.8838294744491577,
	"step": 56
	},
	{
	"epoch": 0.22540781018289668,
	"grad_norm": 0.13476018607616425,
	"learning_rate": 0.00017964071856287425,
	"loss": 0.9571032524108887,
	"step": 57
	},
	{
	"epoch": 0.22936233316856156,
	"grad_norm": 0.1387203335762024,
	"learning_rate": 0.00017924151696606787,
	"loss": 1.0317763090133667,
	"step": 58
	},
	{
	"epoch": 0.2333168561542264,
	"grad_norm": 0.14424876868724823,
	"learning_rate": 0.0001788423153692615,
	"loss": 1.0047612190246582,
	"step": 59
	},
	{
	"epoch": 0.23727137913989124,
	"grad_norm": 0.13895335793495178,
	"learning_rate": 0.0001784431137724551,
	"loss": 1.0508701801300049,
	"step": 60
	},
	{
	"epoch": 0.2412259021255561,
	"grad_norm": 0.1239890530705452,
	"learning_rate": 0.0001780439121756487,
	"loss": 1.003294587135315,
	"step": 61
	},
	{
	"epoch": 0.24518042511122096,
	"grad_norm": 0.13500665128231049,
	"learning_rate": 0.00017764471057884234,
	"loss": 0.9486382007598877,
	"step": 62
	},
	{
	"epoch": 0.2491349480968858,
	"grad_norm": 0.14559301733970642,
	"learning_rate": 0.00017724550898203594,
	"loss": 1.0008798837661743,
	"step": 63
	},
	{
	"epoch": 0.25308947108255064,
	"grad_norm": 0.15551623702049255,
	"learning_rate": 0.00017684630738522955,
	"loss": 0.9119284749031067,
	"step": 64
	},
	{
	"epoch": 0.25704399406821554,
	"grad_norm": 0.12912505865097046,
	"learning_rate": 0.00017644710578842317,
	"loss": 1.041481614112854,
	"step": 65
	},
	{
	"epoch": 0.2609985170538804,
	"grad_norm": 0.14489996433258057,
	"learning_rate": 0.0001760479041916168,
	"loss": 0.8673788905143738,
	"step": 66
	},
	{
	"epoch": 0.26495304003954523,
	"grad_norm": 0.14056646823883057,
	"learning_rate": 0.00017564870259481038,
	"loss": 0.9839107394218445,
	"step": 67
	},
	{
	"epoch": 0.2689075630252101,
	"grad_norm": 0.16830863058567047,
	"learning_rate": 0.000175249500998004,
	"loss": 1.0539538860321045,
	"step": 68
	},
	{
	"epoch": 0.2728620860108749,
	"grad_norm": 0.14673052728176117,
	"learning_rate": 0.00017485029940119762,
	"loss": 0.9210308790206909,
	"step": 69
	},
	{
	"epoch": 0.2768166089965398,
	"grad_norm": 0.1400182992219925,
	"learning_rate": 0.00017445109780439121,
	"loss": 0.9093458652496338,
	"step": 70
	},
	{
	"epoch": 0.28077113198220466,
	"grad_norm": 0.14567220211029053,
	"learning_rate": 0.00017405189620758483,
	"loss": 0.9801154136657715,
	"step": 71
	},
	{
	"epoch": 0.2847256549678695,
	"grad_norm": 0.15140396356582642,
	"learning_rate": 0.00017365269461077845,
	"loss": 1.0192142724990845,
	"step": 72
	},
	{
	"epoch": 0.28868017795353434,
	"grad_norm": 0.15245863795280457,
	"learning_rate": 0.00017325349301397207,
	"loss": 1.0319201946258545,
	"step": 73
	},
	{
	"epoch": 0.2926347009391992,
	"grad_norm": 0.15047654509544373,
	"learning_rate": 0.00017285429141716566,
	"loss": 1.0096640586853027,
	"step": 74
	},
	{
	"epoch": 0.2965892239248641,
	"grad_norm": 0.14069028198719025,
	"learning_rate": 0.00017245508982035928,
	"loss": 0.9506325125694275,
	"step": 75
	},
	{
	"epoch": 0.30054374691052893,
	"grad_norm": 0.13782000541687012,
	"learning_rate": 0.0001720558882235529,
	"loss": 0.8749170303344727,
	"step": 76
	},
	{
	"epoch": 0.3044982698961938,
	"grad_norm": 0.1548694223165512,
	"learning_rate": 0.00017165668662674652,
	"loss": 0.9927857518196106,
	"step": 77
	},
	{
	"epoch": 0.3084527928818586,
	"grad_norm": 0.14958986639976501,
	"learning_rate": 0.0001712574850299401,
	"loss": 0.7992951273918152,
	"step": 78
	},
	{
	"epoch": 0.31240731586752346,
	"grad_norm": 0.14522351324558258,
	"learning_rate": 0.00017085828343313376,
	"loss": 0.9930732846260071,
	"step": 79
	},
	{
	"epoch": 0.31636183885318836,
	"grad_norm": 0.14936009049415588,
	"learning_rate": 0.00017045908183632735,
	"loss": 1.0836726427078247,
	"step": 80
	},
	{
	"epoch": 0.3203163618388532,
	"grad_norm": 0.13863688707351685,
	"learning_rate": 0.00017005988023952097,
	"loss": 0.9540154933929443,
	"step": 81
	},
	{
	"epoch": 0.32427088482451805,
	"grad_norm": 0.14704303443431854,
	"learning_rate": 0.0001696606786427146,
	"loss": 1.03548002243042,
	"step": 82
	},
	{
	"epoch": 0.3282254078101829,
	"grad_norm": 0.13630537688732147,
	"learning_rate": 0.0001692614770459082,
	"loss": 0.9100798964500427,
	"step": 83
	},
	{
	"epoch": 0.33217993079584773,
	"grad_norm": 0.14166879653930664,
	"learning_rate": 0.0001688622754491018,
	"loss": 1.0137436389923096,
	"step": 84
	},
	{
	"epoch": 0.33613445378151263,
	"grad_norm": 0.14558711647987366,
	"learning_rate": 0.00016846307385229542,
	"loss": 1.0042855739593506,
	"step": 85
	},
	{
	"epoch": 0.3400889767671775,
	"grad_norm": 0.13049034774303436,
	"learning_rate": 0.00016806387225548904,
	"loss": 0.9128093123435974,
	"step": 86
	},
	{
	"epoch": 0.3440434997528423,
	"grad_norm": 0.1458376795053482,
	"learning_rate": 0.00016766467065868263,
	"loss": 0.9017834663391113,
	"step": 87
	},
	{
	"epoch": 0.34799802273850716,
	"grad_norm": 0.13847292959690094,
	"learning_rate": 0.00016726546906187625,
	"loss": 0.9473759531974792,
	"step": 88
	},
	{
	"epoch": 0.351952545724172,
	"grad_norm": 0.15093441307544708,
	"learning_rate": 0.00016686626746506987,
	"loss": 0.9916189312934875,
	"step": 89
	},
	{
	"epoch": 0.35590706870983685,
	"grad_norm": 0.1472613364458084,
	"learning_rate": 0.00016646706586826348,
	"loss": 0.9674598574638367,
	"step": 90
	},
	{
	"epoch": 0.35986159169550175,
	"grad_norm": 0.13850581645965576,
	"learning_rate": 0.00016606786427145708,
	"loss": 0.972917377948761,
	"step": 91
	},
	{
	"epoch": 0.3638161146811666,
	"grad_norm": 0.15554893016815186,
	"learning_rate": 0.00016566866267465072,
	"loss": 0.8598817586898804,
	"step": 92
	},
	{
	"epoch": 0.36777063766683143,
	"grad_norm": 0.15589317679405212,
	"learning_rate": 0.00016526946107784431,
	"loss": 1.0263655185699463,
	"step": 93
	},
	{
	"epoch": 0.3717251606524963,
	"grad_norm": 0.14788870513439178,
	"learning_rate": 0.00016487025948103793,
	"loss": 1.0757544040679932,
	"step": 94
	},
	{
	"epoch": 0.3756796836381611,
	"grad_norm": 0.15305693447589874,
	"learning_rate": 0.00016447105788423155,
	"loss": 0.9259313344955444,
	"step": 95
	},
	{
	"epoch": 0.379634206623826,
	"grad_norm": 0.14788882434368134,
	"learning_rate": 0.00016407185628742517,
	"loss": 1.0758525133132935,
	"step": 96
	},
	{
	"epoch": 0.38358872960949086,
	"grad_norm": 0.15263086557388306,
	"learning_rate": 0.00016367265469061876,
	"loss": 0.9790467023849487,
	"step": 97
	},
	{
	"epoch": 0.3875432525951557,
	"grad_norm": 0.16988050937652588,
	"learning_rate": 0.00016327345309381238,
	"loss": 1.180403470993042,
	"step": 98
	},
	{
	"epoch": 0.39149777558082055,
	"grad_norm": 0.142135351896286,
	"learning_rate": 0.000162874251497006,
	"loss": 1.0949641466140747,
	"step": 99
	},
	{
	"epoch": 0.3954522985664854,
	"grad_norm": 0.1378023624420166,
	"learning_rate": 0.00016247504990019962,
	"loss": 1.0425848960876465,
	"step": 100
	},
	{
	"epoch": 0.3994068215521503,
	"grad_norm": 0.1591092050075531,
	"learning_rate": 0.0001620758483033932,
	"loss": 0.9338038563728333,
	"step": 101
	},
	{
	"epoch": 0.40336134453781514,
	"grad_norm": 0.1520695835351944,
	"learning_rate": 0.00016167664670658683,
	"loss": 0.8926813006401062,
	"step": 102
	},
	{
	"epoch": 0.40731586752348,
	"grad_norm": 0.14733289182186127,
	"learning_rate": 0.00016127744510978045,
	"loss": 1.082033395767212,
	"step": 103
	},
	{
	"epoch": 0.4112703905091448,
	"grad_norm": 0.14460161328315735,
	"learning_rate": 0.00016087824351297407,
	"loss": 0.9306143522262573,
	"step": 104
	},
	{
	"epoch": 0.41522491349480967,
	"grad_norm": 0.16207540035247803,
	"learning_rate": 0.00016047904191616766,
	"loss": 1.0030015707015991,
	"step": 105
	},
	{
	"epoch": 0.41917943648047457,
	"grad_norm": 0.1540522575378418,
	"learning_rate": 0.0001600798403193613,
	"loss": 1.1492794752120972,
	"step": 106
	},
	{
	"epoch": 0.4231339594661394,
	"grad_norm": 0.13939417898654938,
	"learning_rate": 0.0001596806387225549,
	"loss": 0.9942459464073181,
	"step": 107
	},
	{
	"epoch": 0.42708848245180425,
	"grad_norm": 0.17469069361686707,
	"learning_rate": 0.0001592814371257485,
	"loss": 0.9437049031257629,
	"step": 108
	},
	{
	"epoch": 0.4310430054374691,
	"grad_norm": 0.15532726049423218,
	"learning_rate": 0.00015888223552894214,
	"loss": 0.8414091467857361,
	"step": 109
	},
	{
	"epoch": 0.43499752842313394,
	"grad_norm": 0.1431339681148529,
	"learning_rate": 0.00015848303393213573,
	"loss": 0.909614086151123,
	"step": 110
	},
	{
	"epoch": 0.43895205140879884,
	"grad_norm": 0.1456097513437271,
	"learning_rate": 0.00015808383233532935,
	"loss": 1.0974111557006836,
	"step": 111
	},
	{
	"epoch": 0.4429065743944637,
	"grad_norm": 0.14371022582054138,
	"learning_rate": 0.00015768463073852296,
	"loss": 1.0514923334121704,
	"step": 112
	},
	{
	"epoch": 0.4468610973801285,
	"grad_norm": 0.14185507595539093,
	"learning_rate": 0.00015728542914171658,
	"loss": 0.856088399887085,
	"step": 113
	},
	{
	"epoch": 0.45081562036579337,
	"grad_norm": 0.14548474550247192,
	"learning_rate": 0.00015688622754491018,
	"loss": 0.9919300079345703,
	"step": 114
	},
	{
	"epoch": 0.4547701433514582,
	"grad_norm": 0.1524973064661026,
	"learning_rate": 0.0001564870259481038,
	"loss": 0.8925392031669617,
	"step": 115
	},
	{
	"epoch": 0.4587246663371231,
	"grad_norm": 0.14767196774482727,
	"learning_rate": 0.0001560878243512974,
	"loss": 0.8464489579200745,
	"step": 116
	},
	{
	"epoch": 0.46267918932278795,
	"grad_norm": 0.15779703855514526,
	"learning_rate": 0.00015568862275449103,
	"loss": 1.0465806722640991,
	"step": 117
	},
	{
	"epoch": 0.4666337123084528,
	"grad_norm": 0.15219292044639587,
	"learning_rate": 0.00015528942115768462,
	"loss": 0.9196197986602783,
	"step": 118
	},
	{
	"epoch": 0.47058823529411764,
	"grad_norm": 0.15147675573825836,
	"learning_rate": 0.00015489021956087827,
	"loss": 0.9819110631942749,
	"step": 119
	},
	{
	"epoch": 0.4745427582797825,
	"grad_norm": 0.1430458277463913,
	"learning_rate": 0.00015449101796407186,
	"loss": 0.9948022365570068,
	"step": 120
	},
	{
	"epoch": 0.4784972812654474,
	"grad_norm": 0.15081898868083954,
	"learning_rate": 0.00015409181636726548,
	"loss": 0.9605839252471924,
	"step": 121
	},
	{
	"epoch": 0.4824518042511122,
	"grad_norm": 0.1469513326883316,
	"learning_rate": 0.0001536926147704591,
	"loss": 0.876885175704956,
	"step": 122
	},
	{
	"epoch": 0.48640632723677707,
	"grad_norm": 0.1487644910812378,
	"learning_rate": 0.00015329341317365272,
	"loss": 0.8893944025039673,
	"step": 123
	},
	{
	"epoch": 0.4903608502224419,
	"grad_norm": 0.1546425074338913,
	"learning_rate": 0.0001528942115768463,
	"loss": 0.8940907120704651,
	"step": 124
	},
	{
	"epoch": 0.49431537320810676,
	"grad_norm": 0.15078657865524292,
	"learning_rate": 0.00015249500998003993,
	"loss": 1.0783774852752686,
	"step": 125
	},
	{
	"epoch": 0.4982698961937716,
	"grad_norm": 0.1505594104528427,
	"learning_rate": 0.00015209580838323355,
	"loss": 0.9070993661880493,
	"step": 126
	},
	{
	"epoch": 0.5022244191794365,
	"grad_norm": 0.15631473064422607,
	"learning_rate": 0.00015169660678642714,
	"loss": 0.9393852353096008,
	"step": 127
	},
	{
	"epoch": 0.5061789421651013,
	"grad_norm": 0.1533495932817459,
	"learning_rate": 0.00015129740518962076,
	"loss": 1.0298182964324951,
	"step": 128
	},
	{
	"epoch": 0.5101334651507662,
	"grad_norm": 0.15687382221221924,
	"learning_rate": 0.00015089820359281438,
	"loss": 0.9548342227935791,
	"step": 129
	},
	{
	"epoch": 0.5140879881364311,
	"grad_norm": 0.13609541952610016,
	"learning_rate": 0.000150499001996008,
	"loss": 0.9333449602127075,
	"step": 130
	},
	{
	"epoch": 0.5180425111220959,
	"grad_norm": 0.1493511199951172,
	"learning_rate": 0.0001500998003992016,
	"loss": 0.9676602482795715,
	"step": 131
	},
	{
	"epoch": 0.5219970341077608,
	"grad_norm": 0.1547534167766571,
	"learning_rate": 0.0001497005988023952,
	"loss": 1.0927131175994873,
	"step": 132
	},
	{
	"epoch": 0.5259515570934256,
	"grad_norm": 0.155633345246315,
	"learning_rate": 0.00014930139720558883,
	"loss": 0.762495219707489,
	"step": 133
	},
	{
	"epoch": 0.5299060800790905,
	"grad_norm": 0.1558597981929779,
	"learning_rate": 0.00014890219560878245,
	"loss": 0.957042396068573,
	"step": 134
	},
	{
	"epoch": 0.5338606030647554,
	"grad_norm": 0.1418825089931488,
	"learning_rate": 0.00014850299401197604,
	"loss": 1.0327900648117065,
	"step": 135
	},
	{
	"epoch": 0.5378151260504201,
	"grad_norm": 0.1431950032711029,
	"learning_rate": 0.00014810379241516968,
	"loss": 0.9374012351036072,
	"step": 136
	},
	{
	"epoch": 0.541769649036085,
	"grad_norm": 0.16276349127292633,
	"learning_rate": 0.00014770459081836328,
	"loss": 0.9466843605041504,
	"step": 137
	},
	{
	"epoch": 0.5457241720217498,
	"grad_norm": 0.14857441186904907,
	"learning_rate": 0.0001473053892215569,
	"loss": 0.9261118769645691,
	"step": 138
	},
	{
	"epoch": 0.5496786950074147,
	"grad_norm": 0.16782596707344055,
	"learning_rate": 0.0001469061876247505,
	"loss": 1.0146270990371704,
	"step": 139
	},
	{
	"epoch": 0.5536332179930796,
	"grad_norm": 0.15024535357952118,
	"learning_rate": 0.00014650698602794413,
	"loss": 0.8856394290924072,
	"step": 140
	},
	{
	"epoch": 0.5575877409787444,
	"grad_norm": 0.1513880342245102,
	"learning_rate": 0.00014610778443113772,
	"loss": 1.0763099193572998,
	"step": 141
	},
	{
	"epoch": 0.5615422639644093,
	"grad_norm": 0.14922404289245605,
	"learning_rate": 0.00014570858283433134,
	"loss": 1.0585473775863647,
	"step": 142
	},
	{
	"epoch": 0.5654967869500741,
	"grad_norm": 0.14560917019844055,
	"learning_rate": 0.00014530938123752496,
	"loss": 0.8189446330070496,
	"step": 143
	},
	{
	"epoch": 0.569451309935739,
	"grad_norm": 0.1498928666114807,
	"learning_rate": 0.00014491017964071858,
	"loss": 0.9366933703422546,
	"step": 144
	},
	{
	"epoch": 0.5734058329214039,
	"grad_norm": 0.14731937646865845,
	"learning_rate": 0.00014451097804391217,
	"loss": 0.978458821773529,
	"step": 145
	},
	{
	"epoch": 0.5773603559070687,
	"grad_norm": 0.14156509935855865,
	"learning_rate": 0.00014411177644710582,
	"loss": 0.9639441967010498,
	"step": 146
	},
	{
	"epoch": 0.5813148788927336,
	"grad_norm": 0.17466521263122559,
	"learning_rate": 0.0001437125748502994,
	"loss": 0.9246646165847778,
	"step": 147
	},
	{
	"epoch": 0.5852694018783984,
	"grad_norm": 0.15222910046577454,
	"learning_rate": 0.000143313373253493,
	"loss": 0.9557418823242188,
	"step": 148
	},
	{
	"epoch": 0.5892239248640633,
	"grad_norm": 0.14972400665283203,
	"learning_rate": 0.00014291417165668665,
	"loss": 0.8998520970344543,
	"step": 149
	},
	{
	"epoch": 0.5931784478497282,
	"grad_norm": 0.16542503237724304,
	"learning_rate": 0.00014251497005988024,
	"loss": 0.8584086298942566,
	"step": 150
	},
	{
	"epoch": 0.597132970835393,
	"grad_norm": 0.1549108326435089,
	"learning_rate": 0.00014211576846307386,
	"loss": 0.9696409702301025,
	"step": 151
	},
	{
	"epoch": 0.6010874938210579,
	"grad_norm": 0.14827242493629456,
	"learning_rate": 0.00014171656686626745,
	"loss": 0.8613938093185425,
	"step": 152
	},
	{
	"epoch": 0.6050420168067226,
	"grad_norm": 0.15346549451351166,
	"learning_rate": 0.0001413173652694611,
	"loss": 0.7989118695259094,
	"step": 153
	},
	{
	"epoch": 0.6089965397923875,
	"grad_norm": 0.15291966497898102,
	"learning_rate": 0.0001409181636726547,
	"loss": 1.0761021375656128,
	"step": 154
	},
	{
	"epoch": 0.6129510627780524,
	"grad_norm": 0.13826234638690948,
	"learning_rate": 0.0001405189620758483,
	"loss": 0.9109746217727661,
	"step": 155
	},
	{
	"epoch": 0.6169055857637172,
	"grad_norm": 0.14913445711135864,
	"learning_rate": 0.00014011976047904193,
	"loss": 1.0017129182815552,
	"step": 156
	},
	{
	"epoch": 0.6208601087493821,
	"grad_norm": 0.1526130735874176,
	"learning_rate": 0.00013972055888223555,
	"loss": 0.8955498933792114,
	"step": 157
	},
	{
	"epoch": 0.6248146317350469,
	"grad_norm": 0.15382827818393707,
	"learning_rate": 0.00013932135728542914,
	"loss": 1.1069719791412354,
	"step": 158
	},
	{
	"epoch": 0.6287691547207118,
	"grad_norm": 0.14784258604049683,
	"learning_rate": 0.00013892215568862276,
	"loss": 0.9784612655639648,
	"step": 159
	},
	{
	"epoch": 0.6327236777063767,
	"grad_norm": 0.15217405557632446,
	"learning_rate": 0.00013852295409181638,
	"loss": 0.9924787878990173,
	"step": 160
	},
	{
	"epoch": 0.6366782006920415,
	"grad_norm": 0.17497238516807556,
	"learning_rate": 0.00013812375249501,
	"loss": 0.8755843043327332,
	"step": 161
	},
	{
	"epoch": 0.6406327236777064,
	"grad_norm": 0.15077446401119232,
	"learning_rate": 0.00013772455089820359,
	"loss": 0.9884225726127625,
	"step": 162
	},
	{
	"epoch": 0.6445872466633712,
	"grad_norm": 0.1486707627773285,
	"learning_rate": 0.00013732534930139723,
	"loss": 1.0523698329925537,
	"step": 163
	},
	{
	"epoch": 0.6485417696490361,
	"grad_norm": 0.13988643884658813,
	"learning_rate": 0.00013692614770459082,
	"loss": 0.9002912640571594,
	"step": 164
	},
	{
	"epoch": 0.652496292634701,
	"grad_norm": 0.15143455564975739,
	"learning_rate": 0.00013652694610778444,
	"loss": 0.9852843284606934,
	"step": 165
	},
	{
	"epoch": 0.6564508156203658,
	"grad_norm": 0.15765251219272614,
	"learning_rate": 0.00013612774451097806,
	"loss": 0.9757329225540161,
	"step": 166
	},
	{
	"epoch": 0.6604053386060307,
	"grad_norm": 0.15192811191082,
	"learning_rate": 0.00013572854291417165,
	"loss": 0.9793543815612793,
	"step": 167
	},
	{
	"epoch": 0.6643598615916955,
	"grad_norm": 0.1370113044977188,
	"learning_rate": 0.00013532934131736527,
	"loss": 0.8899397253990173,
	"step": 168
	},
	{
	"epoch": 0.6683143845773604,
	"grad_norm": 0.16300129890441895,
	"learning_rate": 0.0001349301397205589,
	"loss": 0.9691711664199829,
	"step": 169
	},
	{
	"epoch": 0.6722689075630253,
	"grad_norm": 0.1447598934173584,
	"learning_rate": 0.0001345309381237525,
	"loss": 1.0262728929519653,
	"step": 170
	},
	{
	"epoch": 0.67622343054869,
	"grad_norm": 0.1426248848438263,
	"learning_rate": 0.0001341317365269461,
	"loss": 0.8865811824798584,
	"step": 171
	},
	{
	"epoch": 0.680177953534355,
	"grad_norm": 0.1596144288778305,
	"learning_rate": 0.00013373253493013972,
	"loss": 1.041471242904663,
	"step": 172
	},
	{
	"epoch": 0.6841324765200197,
	"grad_norm": 0.16748711466789246,
	"learning_rate": 0.00013333333333333334,
	"loss": 1.060260534286499,
	"step": 173
	},
	{
	"epoch": 0.6880869995056846,
	"grad_norm": 0.14779865741729736,
	"learning_rate": 0.00013293413173652696,
	"loss": 0.9902845025062561,
	"step": 174
	},
	{
	"epoch": 0.6920415224913494,
	"grad_norm": 0.1514303982257843,
	"learning_rate": 0.00013253493013972055,
	"loss": 0.9630454778671265,
	"step": 175
	},
	{
	"epoch": 0.6959960454770143,
	"grad_norm": 0.16021154820919037,
	"learning_rate": 0.0001321357285429142,
	"loss": 0.8938897848129272,
	"step": 176
	},
	{
	"epoch": 0.6999505684626792,
	"grad_norm": 0.1604602336883545,
	"learning_rate": 0.0001317365269461078,
	"loss": 0.7806445956230164,
	"step": 177
	},
	{
	"epoch": 0.703905091448344,
	"grad_norm": 0.14814768731594086,
	"learning_rate": 0.0001313373253493014,
	"loss": 0.7236217856407166,
	"step": 178
	},
	{
	"epoch": 0.7078596144340089,
	"grad_norm": 0.13816480338573456,
	"learning_rate": 0.000130938123752495,
	"loss": 1.059952974319458,
	"step": 179
	},
	{
	"epoch": 0.7118141374196737,
	"grad_norm": 0.15320385992527008,
	"learning_rate": 0.00013053892215568865,
	"loss": 1.037667989730835,
	"step": 180
	},
	{
	"epoch": 0.7157686604053386,
	"grad_norm": 0.14675435423851013,
	"learning_rate": 0.00013013972055888224,
	"loss": 1.0143626928329468,
	"step": 181
	},
	{
	"epoch": 0.7197231833910035,
	"grad_norm": 0.13777698576450348,
	"learning_rate": 0.00012974051896207586,
	"loss": 0.8841183185577393,
	"step": 182
	},
	{
	"epoch": 0.7236777063766683,
	"grad_norm": 0.14622290432453156,
	"learning_rate": 0.00012934131736526947,
	"loss": 0.9912742376327515,
	"step": 183
	},
	{
	"epoch": 0.7276322293623332,
	"grad_norm": 0.14383630454540253,
	"learning_rate": 0.0001289421157684631,
	"loss": 1.031080722808838,
	"step": 184
	},
	{
	"epoch": 0.731586752347998,
	"grad_norm": 0.14537449181079865,
	"learning_rate": 0.00012854291417165669,
	"loss": 0.9928056001663208,
	"step": 185
	},
	{
	"epoch": 0.7355412753336629,
	"grad_norm": 0.1553298830986023,
	"learning_rate": 0.0001281437125748503,
	"loss": 1.0729012489318848,
	"step": 186
	},
	{
	"epoch": 0.7394957983193278,
	"grad_norm": 0.15434440970420837,
	"learning_rate": 0.00012774451097804392,
	"loss": 0.9299134016036987,
	"step": 187
	},
	{
	"epoch": 0.7434503213049926,
	"grad_norm": 0.1517597734928131,
	"learning_rate": 0.00012734530938123752,
	"loss": 0.8981556296348572,
	"step": 188
	},
	{
	"epoch": 0.7474048442906575,
	"grad_norm": 0.14408698678016663,
	"learning_rate": 0.00012694610778443113,
	"loss": 0.7834718227386475,
	"step": 189
	},
	{
	"epoch": 0.7513593672763222,
	"grad_norm": 0.1524432897567749,
	"learning_rate": 0.00012654690618762475,
	"loss": 0.9502565264701843,
	"step": 190
	},
	{
	"epoch": 0.7553138902619871,
	"grad_norm": 0.16056875884532928,
	"learning_rate": 0.00012614770459081837,
	"loss": 1.0030090808868408,
	"step": 191
	},
	{
	"epoch": 0.759268413247652,
	"grad_norm": 0.14580710232257843,
	"learning_rate": 0.00012574850299401196,
	"loss": 0.937939465045929,
	"step": 192
	},
	{
	"epoch": 0.7632229362333168,
	"grad_norm": 0.14517466723918915,
	"learning_rate": 0.0001253493013972056,
	"loss": 1.1117490530014038,
	"step": 193
	},
	{
	"epoch": 0.7671774592189817,
	"grad_norm": 0.15558141469955444,
	"learning_rate": 0.0001249500998003992,
	"loss": 0.8213934898376465,
	"step": 194
	},
	{
	"epoch": 0.7711319822046465,
	"grad_norm": 0.14642053842544556,
	"learning_rate": 0.00012455089820359282,
	"loss": 0.8714714646339417,
	"step": 195
	},
	{
	"epoch": 0.7750865051903114,
	"grad_norm": 0.15025141835212708,
	"learning_rate": 0.00012415169660678644,
	"loss": 1.0590744018554688,
	"step": 196
	},
	{
	"epoch": 0.7790410281759763,
	"grad_norm": 0.1296977996826172,
	"learning_rate": 0.00012375249500998006,
	"loss": 1.0535149574279785,
	"step": 197
	},
	{
	"epoch": 0.7829955511616411,
	"grad_norm": 0.15777179598808289,
	"learning_rate": 0.00012335329341317365,
	"loss": 1.0486925840377808,
	"step": 198
	},
	{
	"epoch": 0.786950074147306,
	"grad_norm": 0.13769429922103882,
	"learning_rate": 0.00012295409181636727,
	"loss": 0.9360702633857727,
	"step": 199
	},
	{
	"epoch": 0.7909045971329708,
	"grad_norm": 0.15268363058567047,
	"learning_rate": 0.0001225548902195609,
	"loss": 0.8887878656387329,
	"step": 200
	},
	{
	"epoch": 0.7948591201186357,
	"grad_norm": 0.13850852847099304,
	"learning_rate": 0.0001221556886227545,
	"loss": 1.083563208580017,
	"step": 201
	},
	{
	"epoch": 0.7988136431043006,
	"grad_norm": 0.16249485313892365,
	"learning_rate": 0.00012175648702594811,
	"loss": 1.0185102224349976,
	"step": 202
	},
	{
	"epoch": 0.8027681660899654,
	"grad_norm": 0.14542728662490845,
	"learning_rate": 0.00012135728542914173,
	"loss": 0.985219419002533,
	"step": 203
	},
	{
	"epoch": 0.8067226890756303,
	"grad_norm": 0.1401057094335556,
	"learning_rate": 0.00012095808383233534,
	"loss": 0.9981472492218018,
	"step": 204
	},
	{
	"epoch": 0.8106772120612951,
	"grad_norm": 0.16163145005702972,
	"learning_rate": 0.00012055888223552896,
	"loss": 0.9624532461166382,
	"step": 205
	},
	{
	"epoch": 0.81463173504696,
	"grad_norm": 0.1544468253850937,
	"learning_rate": 0.00012015968063872256,
	"loss": 0.9114558696746826,
	"step": 206
	},
	{
	"epoch": 0.8185862580326249,
	"grad_norm": 0.15567342936992645,
	"learning_rate": 0.00011976047904191617,
	"loss": 0.9480348825454712,
	"step": 207
	},
	{
	"epoch": 0.8225407810182896,
	"grad_norm": 0.15945857763290405,
	"learning_rate": 0.00011936127744510979,
	"loss": 0.9799912571907043,
	"step": 208
	},
	{
	"epoch": 0.8264953040039545,
	"grad_norm": 0.15980277955532074,
	"learning_rate": 0.00011896207584830339,
	"loss": 1.0797210931777954,
	"step": 209
	},
	{
	"epoch": 0.8304498269896193,
	"grad_norm": 0.14261196553707123,
	"learning_rate": 0.00011856287425149701,
	"loss": 1.0038321018218994,
	"step": 210
	},
	{
	"epoch": 0.8344043499752842,
	"grad_norm": 0.15023842453956604,
	"learning_rate": 0.00011816367265469061,
	"loss": 1.0017417669296265,
	"step": 211
	},
	{
	"epoch": 0.8383588729609491,
	"grad_norm": 0.14774499833583832,
	"learning_rate": 0.00011776447105788423,
	"loss": 1.056884765625,
	"step": 212
	},
	{
	"epoch": 0.8423133959466139,
	"grad_norm": 0.1311042457818985,
	"learning_rate": 0.00011736526946107784,
	"loss": 1.015238881111145,
	"step": 213
	},
	{
	"epoch": 0.8462679189322788,
	"grad_norm": 0.14513953030109406,
	"learning_rate": 0.00011696606786427147,
	"loss": 1.0354350805282593,
	"step": 214
	},
	{
	"epoch": 0.8502224419179436,
	"grad_norm": 0.1631115972995758,
	"learning_rate": 0.00011656686626746506,
	"loss": 0.9117772579193115,
	"step": 215
	},
	{
	"epoch": 0.8541769649036085,
	"grad_norm": 0.16442656517028809,
	"learning_rate": 0.0001161676646706587,
	"loss": 1.0395290851593018,
	"step": 216
	},
	{
	"epoch": 0.8581314878892734,
	"grad_norm": 0.14986057579517365,
	"learning_rate": 0.0001157684630738523,
	"loss": 0.9993502497673035,
	"step": 217
	},
	{
	"epoch": 0.8620860108749382,
	"grad_norm": 0.16269713640213013,
	"learning_rate": 0.00011536926147704592,
	"loss": 0.8923558592796326,
	"step": 218
	},
	{
	"epoch": 0.8660405338606031,
	"grad_norm": 0.14905333518981934,
	"learning_rate": 0.00011497005988023953,
	"loss": 0.846024751663208,
	"step": 219
	},
	{
	"epoch": 0.8699950568462679,
	"grad_norm": 0.14860469102859497,
	"learning_rate": 0.00011457085828343314,
	"loss": 0.933295488357544,
	"step": 220
	},
	{
	"epoch": 0.8739495798319328,
	"grad_norm": 0.15000364184379578,
	"learning_rate": 0.00011417165668662675,
	"loss": 0.9875235557556152,
	"step": 221
	},
	{
	"epoch": 0.8779041028175977,
	"grad_norm": 0.15674816071987152,
	"learning_rate": 0.00011377245508982037,
	"loss": 0.8917112946510315,
	"step": 222
	},
	{
	"epoch": 0.8818586258032625,
	"grad_norm": 0.16109170019626617,
	"learning_rate": 0.00011337325349301397,
	"loss": 0.9784120321273804,
	"step": 223
	},
	{
	"epoch": 0.8858131487889274,
	"grad_norm": 0.15252313017845154,
	"learning_rate": 0.0001129740518962076,
	"loss": 0.7924797534942627,
	"step": 224
	},
	{
	"epoch": 0.8897676717745922,
	"grad_norm": 0.15269458293914795,
	"learning_rate": 0.0001125748502994012,
	"loss": 0.9920112490653992,
	"step": 225
	},
	{
	"epoch": 0.893722194760257,
	"grad_norm": 0.17212046682834625,
	"learning_rate": 0.00011217564870259483,
	"loss": 0.9893192052841187,
	"step": 226
	},
	{
	"epoch": 0.897676717745922,
	"grad_norm": 0.15529413521289825,
	"learning_rate": 0.00011177644710578842,
	"loss": 1.0025854110717773,
	"step": 227
	},
	{
	"epoch": 0.9016312407315867,
	"grad_norm": 0.17252163589000702,
	"learning_rate": 0.00011137724550898203,
	"loss": 0.8992288112640381,
	"step": 228
	},
	{
	"epoch": 0.9055857637172516,
	"grad_norm": 0.1746063530445099,
	"learning_rate": 0.00011097804391217566,
	"loss": 0.8158121705055237,
	"step": 229
	},
	{
	"epoch": 0.9095402867029164,
	"grad_norm": 0.13989895582199097,
	"learning_rate": 0.00011057884231536925,
	"loss": 1.0338526964187622,
	"step": 230
	},
	{
	"epoch": 0.9134948096885813,
	"grad_norm": 0.16055206954479218,
	"learning_rate": 0.00011017964071856288,
	"loss": 0.9847093224525452,
	"step": 231
	},
	{
	"epoch": 0.9174493326742462,
	"grad_norm": 0.16400660574436188,
	"learning_rate": 0.00010978043912175649,
	"loss": 0.9464921951293945,
	"step": 232
	},
	{
	"epoch": 0.921403855659911,
	"grad_norm": 0.14987632632255554,
	"learning_rate": 0.00010938123752495011,
	"loss": 0.8394877910614014,
	"step": 233
	},
	{
	"epoch": 0.9253583786455759,
	"grad_norm": 0.16941316425800323,
	"learning_rate": 0.00010898203592814371,
	"loss": 0.8612609505653381,
	"step": 234
	},
	{
	"epoch": 0.9293129016312407,
	"grad_norm": 0.16219089925289154,
	"learning_rate": 0.00010858283433133733,
	"loss": 0.8607385158538818,
	"step": 235
	},
	{
	"epoch": 0.9332674246169056,
	"grad_norm": 0.1656905710697174,
	"learning_rate": 0.00010818363273453094,
	"loss": 1.0054378509521484,
	"step": 236
	},
	{
	"epoch": 0.9372219476025705,
	"grad_norm": 0.15206600725650787,
	"learning_rate": 0.00010778443113772456,
	"loss": 1.0277290344238281,
	"step": 237
	},
	{
	"epoch": 0.9411764705882353,
	"grad_norm": 0.1560627520084381,
	"learning_rate": 0.00010738522954091816,
	"loss": 0.9026745557785034,
	"step": 238
	},
	{
	"epoch": 0.9451309935739002,
	"grad_norm": 0.16465218365192413,
	"learning_rate": 0.00010698602794411178,
	"loss": 0.9656213521957397,
	"step": 239
	},
	{
	"epoch": 0.949085516559565,
	"grad_norm": 0.16291505098342896,
	"learning_rate": 0.00010658682634730539,
	"loss": 0.940356433391571,
	"step": 240
	},
	{
	"epoch": 0.9530400395452299,
	"grad_norm": 0.16686119139194489,
	"learning_rate": 0.00010618762475049902,
	"loss": 0.8976022601127625,
	"step": 241
	},
	{
	"epoch": 0.9569945625308948,
	"grad_norm": 0.1607900708913803,
	"learning_rate": 0.00010578842315369261,
	"loss": 0.9073758125305176,
	"step": 242
	},
	{
	"epoch": 0.9609490855165596,
	"grad_norm": 0.15350642800331116,
	"learning_rate": 0.00010538922155688624,
	"loss": 0.8798397779464722,
	"step": 243
	},
	{
	"epoch": 0.9649036085022245,
	"grad_norm": 0.13445277512073517,
	"learning_rate": 0.00010499001996007985,
	"loss": 0.8960294723510742,
	"step": 244
	},
	{
	"epoch": 0.9688581314878892,
	"grad_norm": 0.15072865784168243,
	"learning_rate": 0.00010459081836327347,
	"loss": 0.9184878468513489,
	"step": 245
	},
	{
	"epoch": 0.9728126544735541,
	"grad_norm": 0.1483660340309143,
	"learning_rate": 0.00010419161676646707,
	"loss": 1.000427484512329,
	"step": 246
	},
	{
	"epoch": 0.9767671774592189,
	"grad_norm": 0.16323480010032654,
	"learning_rate": 0.00010379241516966068,
	"loss": 0.9598352909088135,
	"step": 247
	},
	{
	"epoch": 0.9807217004448838,
	"grad_norm": 0.15449391305446625,
	"learning_rate": 0.0001033932135728543,
	"loss": 1.1161832809448242,
	"step": 248
	},
	{
	"epoch": 0.9846762234305487,
	"grad_norm": 0.15927913784980774,
	"learning_rate": 0.0001029940119760479,
	"loss": 0.9797319769859314,
	"step": 249
	},
	{
	"epoch": 0.9886307464162135,
	"grad_norm": 0.1711476743221283,
	"learning_rate": 0.00010259481037924152,
	"loss": 1.0162928104400635,
	"step": 250
	},
	{
	"epoch": 0.9925852694018784,
	"grad_norm": 0.15978345274925232,
	"learning_rate": 0.00010219560878243513,
	"loss": 0.8991297483444214,
	"step": 251
	},
	{
	"epoch": 0.9965397923875432,
	"grad_norm": 0.15758229792118073,
	"learning_rate": 0.00010179640718562875,
	"loss": 0.9805660843849182,
	"step": 252
	},
	{
	"epoch": 1.0,
	"grad_norm": 0.17985662817955017,
	"learning_rate": 0.00010139720558882235,
	"loss": 1.0062508583068848,
	"step": 253
	},
	{
	"epoch": 1.0039545229856648,
	"grad_norm": 0.16520218551158905,
	"learning_rate": 0.00010099800399201597,
	"loss": 1.0412254333496094,
	"step": 254
	},
	{
	"epoch": 1.0079090459713298,
	"grad_norm": 0.16414225101470947,
	"learning_rate": 0.00010059880239520958,
	"loss": 0.9039946794509888,
	"step": 255
	},
	{
	"epoch": 1.0118635689569946,
	"grad_norm": 0.15268850326538086,
	"learning_rate": 0.00010019960079840321,
	"loss": 0.9569994807243347,
	"step": 256
	},
	{
	"epoch": 1.0158180919426594,
	"grad_norm": 0.15560995042324066,
	"learning_rate": 9.98003992015968e-05,
	"loss": 1.1160976886749268,
	"step": 257
	},
	{
	"epoch": 1.0197726149283244,
	"grad_norm": 0.15324212610721588,
	"learning_rate": 9.940119760479042e-05,
	"loss": 1.0373631715774536,
	"step": 258
	},
	{
	"epoch": 1.0237271379139892,
	"grad_norm": 0.15931884944438934,
	"learning_rate": 9.900199600798404e-05,
	"loss": 0.9546667337417603,
	"step": 259
	},
	{
	"epoch": 1.027681660899654,
	"grad_norm": 0.16295117139816284,
	"learning_rate": 9.860279441117764e-05,
	"loss": 1.002548098564148,
	"step": 260
	},
	{
	"epoch": 1.0316361838853187,
	"grad_norm": 0.17251881957054138,
	"learning_rate": 9.820359281437126e-05,
	"loss": 0.922970175743103,
	"step": 261
	},
	{
	"epoch": 1.0355907068709838,
	"grad_norm": 0.1694485992193222,
	"learning_rate": 9.780439121756487e-05,
	"loss": 1.0178519487380981,
	"step": 262
	},
	{
	"epoch": 1.0395452298566485,
	"grad_norm": 0.16809332370758057,
	"learning_rate": 9.740518962075849e-05,
	"loss": 0.9237082004547119,
	"step": 263
	},
	{
	"epoch": 1.0434997528423133,
	"grad_norm": 0.16604508459568024,
	"learning_rate": 9.700598802395209e-05,
	"loss": 0.9441342353820801,
	"step": 264
	},
	{
	"epoch": 1.0474542758279783,
	"grad_norm": 0.16178838908672333,
	"learning_rate": 9.660678642714571e-05,
	"loss": 0.9563836455345154,
	"step": 265
	},
	{
	"epoch": 1.0514087988136431,
	"grad_norm": 0.17229746282100677,
	"learning_rate": 9.620758483033933e-05,
	"loss": 0.9493328928947449,
	"step": 266
	},
	{
	"epoch": 1.055363321799308,
	"grad_norm": 0.17116741836071014,
	"learning_rate": 9.580838323353294e-05,
	"loss": 0.7871612906455994,
	"step": 267
	},
	{
	"epoch": 1.0593178447849727,
	"grad_norm": 0.19620539247989655,
	"learning_rate": 9.540918163672655e-05,
	"loss": 0.7880710959434509,
	"step": 268
	},
	{
	"epoch": 1.0632723677706377,
	"grad_norm": 0.17312850058078766,
	"learning_rate": 9.500998003992016e-05,
	"loss": 0.8220570683479309,
	"step": 269
	},
	{
	"epoch": 1.0672268907563025,
	"grad_norm": 0.2012282907962799,
	"learning_rate": 9.461077844311378e-05,
	"loss": 0.8117949962615967,
	"step": 270
	},
	{
	"epoch": 1.0711814137419673,
	"grad_norm": 0.16529391705989838,
	"learning_rate": 9.42115768463074e-05,
	"loss": 1.000198483467102,
	"step": 271
	},
	{
	"epoch": 1.0751359367276323,
	"grad_norm": 0.17409488558769226,
	"learning_rate": 9.3812375249501e-05,
	"loss": 0.9956350922584534,
	"step": 272
	},
	{
	"epoch": 1.079090459713297,
	"grad_norm": 0.18472394347190857,
	"learning_rate": 9.341317365269462e-05,
	"loss": 1.0315921306610107,
	"step": 273
	},
	{
	"epoch": 1.0830449826989619,
	"grad_norm": 0.16941356658935547,
	"learning_rate": 9.301397205588823e-05,
	"loss": 0.95827716588974,
	"step": 274
	},
	{
	"epoch": 1.0869995056846269,
	"grad_norm": 0.16447168588638306,
	"learning_rate": 9.261477045908185e-05,
	"loss": 0.8616600036621094,
	"step": 275
	},
	{
	"epoch": 1.0909540286702917,
	"grad_norm": 0.19374088943004608,
	"learning_rate": 9.221556886227547e-05,
	"loss": 0.7994685173034668,
	"step": 276
	},
	{
	"epoch": 1.0949085516559565,
	"grad_norm": 0.16742141544818878,
	"learning_rate": 9.181636726546906e-05,
	"loss": 0.8132893443107605,
	"step": 277
	},
	{
	"epoch": 1.0988630746416213,
	"grad_norm": 0.20061492919921875,
	"learning_rate": 9.141716566866268e-05,
	"loss": 0.9603545665740967,
	"step": 278
	},
	{
	"epoch": 1.1028175976272863,
	"grad_norm": 0.16895346343517303,
	"learning_rate": 9.101796407185628e-05,
	"loss": 1.0123639106750488,
	"step": 279
	},
	{
	"epoch": 1.106772120612951,
	"grad_norm": 0.1848328411579132,
	"learning_rate": 9.06187624750499e-05,
	"loss": 0.9767408967018127,
	"step": 280
	},
	{
	"epoch": 1.1107266435986158,
	"grad_norm": 0.1762303113937378,
	"learning_rate": 9.021956087824352e-05,
	"loss": 1.0461487770080566,
	"step": 281
	},
	{
	"epoch": 1.1146811665842808,
	"grad_norm": 0.18317660689353943,
	"learning_rate": 8.982035928143712e-05,
	"loss": 0.8694061636924744,
	"step": 282
	},
	{
	"epoch": 1.1186356895699456,
	"grad_norm": 0.275339812040329,
	"learning_rate": 8.942115768463074e-05,
	"loss": 0.859940767288208,
	"step": 283
	},
	{
	"epoch": 1.1225902125556104,
	"grad_norm": 0.18906059861183167,
	"learning_rate": 8.902195608782435e-05,
	"loss": 0.9108320474624634,
	"step": 284
	},
	{
	"epoch": 1.1265447355412754,
	"grad_norm": 0.1821734756231308,
	"learning_rate": 8.862275449101797e-05,
	"loss": 0.8772467970848083,
	"step": 285
	},
	{
	"epoch": 1.1304992585269402,
	"grad_norm": 0.1746835559606552,
	"learning_rate": 8.822355289421159e-05,
	"loss": 0.9596457481384277,
	"step": 286
	},
	{
	"epoch": 1.134453781512605,
	"grad_norm": 0.17881642282009125,
	"learning_rate": 8.782435129740519e-05,
	"loss": 0.9305652379989624,
	"step": 287
	},
	{
	"epoch": 1.1384083044982698,
	"grad_norm": 0.18960846960544586,
	"learning_rate": 8.742514970059881e-05,
	"loss": 0.9538063406944275,
	"step": 288
	},
	{
	"epoch": 1.1423628274839348,
	"grad_norm": 0.17049920558929443,
	"learning_rate": 8.702594810379242e-05,
	"loss": 0.8245007395744324,
	"step": 289
	},
	{
	"epoch": 1.1463173504695996,
	"grad_norm": 0.18376107513904572,
	"learning_rate": 8.662674650698604e-05,
	"loss": 0.888431966304779,
	"step": 290
	},
	{
	"epoch": 1.1502718734552644,
	"grad_norm": 0.1948973834514618,
	"learning_rate": 8.622754491017964e-05,
	"loss": 0.9021210074424744,
	"step": 291
	},
	{
	"epoch": 1.1542263964409294,
	"grad_norm": 0.2063995599746704,
	"learning_rate": 8.582834331337326e-05,
	"loss": 0.9560433030128479,
	"step": 292
	},
	{
	"epoch": 1.1581809194265942,
	"grad_norm": 0.1944153606891632,
	"learning_rate": 8.542914171656688e-05,
	"loss": 0.9102143049240112,
	"step": 293
	},
	{
	"epoch": 1.162135442412259,
	"grad_norm": 0.19204482436180115,
	"learning_rate": 8.502994011976048e-05,
	"loss": 0.8926071524620056,
	"step": 294
	},
	{
	"epoch": 1.1660899653979238,
	"grad_norm": 0.20266790688037872,
	"learning_rate": 8.46307385229541e-05,
	"loss": 1.0379507541656494,
	"step": 295
	},
	{
	"epoch": 1.1700444883835888,
	"grad_norm": 0.18556608259677887,
	"learning_rate": 8.423153692614771e-05,
	"loss": 0.8484141826629639,
	"step": 296
	},
	{
	"epoch": 1.1739990113692536,
	"grad_norm": 0.20597191154956818,
	"learning_rate": 8.383233532934131e-05,
	"loss": 0.7798240780830383,
	"step": 297
	},
	{
	"epoch": 1.1779535343549183,
	"grad_norm": 0.18532755970954895,
	"learning_rate": 8.343313373253493e-05,
	"loss": 0.8546709418296814,
	"step": 298
	},
	{
	"epoch": 1.1819080573405834,
	"grad_norm": 0.19410572946071625,
	"learning_rate": 8.303393213572854e-05,
	"loss": 1.0295960903167725,
	"step": 299
	},
	{
	"epoch": 1.1858625803262481,
	"grad_norm": 0.1959802806377411,
	"learning_rate": 8.263473053892216e-05,
	"loss": 0.8178250193595886,
	"step": 300
	},
	{
	"epoch": 1.189817103311913,
	"grad_norm": 0.1843615621328354,
	"learning_rate": 8.223552894211578e-05,
	"loss": 0.9791051745414734,
	"step": 301
	},
	{
	"epoch": 1.193771626297578,
	"grad_norm": 0.19072717428207397,
	"learning_rate": 8.183632734530938e-05,
	"loss": 0.8327443599700928,
	"step": 302
	},
	{
	"epoch": 1.1977261492832427,
	"grad_norm": 0.18121100962162018,
	"learning_rate": 8.1437125748503e-05,
	"loss": 0.9626063704490662,
	"step": 303
	},
	{
	"epoch": 1.2016806722689075,
	"grad_norm": 0.1815863400697708,
	"learning_rate": 8.10379241516966e-05,
	"loss": 0.9914010763168335,
	"step": 304
	},
	{
	"epoch": 1.2056351952545725,
	"grad_norm": 0.17102938890457153,
	"learning_rate": 8.063872255489022e-05,
	"loss": 0.8116806149482727,
	"step": 305
	},
	{
	"epoch": 1.2095897182402373,
	"grad_norm": 0.18805690109729767,
	"learning_rate": 8.023952095808383e-05,
	"loss": 0.8748471140861511,
	"step": 306
	},
	{
	"epoch": 1.213544241225902,
	"grad_norm": 0.18052758276462555,
	"learning_rate": 7.984031936127745e-05,
	"loss": 0.9938658475875854,
	"step": 307
	},
	{
	"epoch": 1.2174987642115669,
	"grad_norm": 0.19235683977603912,
	"learning_rate": 7.944111776447107e-05,
	"loss": 1.1100804805755615,
	"step": 308
	},
	{
	"epoch": 1.221453287197232,
	"grad_norm": 0.18457858264446259,
	"learning_rate": 7.904191616766467e-05,
	"loss": 0.9189471006393433,
	"step": 309
	},
	{
	"epoch": 1.2254078101828967,
	"grad_norm": 0.18914006650447845,
	"learning_rate": 7.864271457085829e-05,
	"loss": 0.8920475840568542,
	"step": 310
	},
	{
	"epoch": 1.2293623331685615,
	"grad_norm": 0.19251829385757446,
	"learning_rate": 7.82435129740519e-05,
	"loss": 0.939852774143219,
	"step": 311
	},
	{
	"epoch": 1.2333168561542265,
	"grad_norm": 0.17629219591617584,
	"learning_rate": 7.784431137724552e-05,
	"loss": 1.0373430252075195,
	"step": 312
	},
	{
	"epoch": 1.2372713791398913,
	"grad_norm": 0.18412235379219055,
	"learning_rate": 7.744510978043914e-05,
	"loss": 0.9560478329658508,
	"step": 313
	},
	{
	"epoch": 1.241225902125556,
	"grad_norm": 0.191380113363266,
	"learning_rate": 7.704590818363274e-05,
	"loss": 0.8593218326568604,
	"step": 314
	},
	{
	"epoch": 1.2451804251112208,
	"grad_norm": 0.18198034167289734,
	"learning_rate": 7.664670658682636e-05,
	"loss": 0.8392094969749451,
	"step": 315
	},
	{
	"epoch": 1.2491349480968859,
	"grad_norm": 0.18671447038650513,
	"learning_rate": 7.624750499001996e-05,
	"loss": 0.9436869621276855,
	"step": 316
	},
	{
	"epoch": 1.2530894710825506,
	"grad_norm": 0.17818371951580048,
	"learning_rate": 7.584830339321357e-05,
	"loss": 0.886319100856781,
	"step": 317
	},
	{
	"epoch": 1.2570439940682157,
	"grad_norm": 0.18418045341968536,
	"learning_rate": 7.544910179640719e-05,
	"loss": 0.8711346983909607,
	"step": 318
	},
	{
	"epoch": 1.2609985170538804,
	"grad_norm": 0.18546275794506073,
	"learning_rate": 7.50499001996008e-05,
	"loss": 0.9372309446334839,
	"step": 319
	},
	{
	"epoch": 1.2649530400395452,
	"grad_norm": 0.19021575152873993,
	"learning_rate": 7.465069860279441e-05,
	"loss": 0.9252364039421082,
	"step": 320
	},
	{
	"epoch": 1.26890756302521,
	"grad_norm": 0.185474693775177,
	"learning_rate": 7.425149700598802e-05,
	"loss": 0.8521521687507629,
	"step": 321
	},
	{
	"epoch": 1.2728620860108748,
	"grad_norm": 0.20583201944828033,
	"learning_rate": 7.385229540918164e-05,
	"loss": 0.9617403149604797,
	"step": 322
	},
	{
	"epoch": 1.2768166089965398,
	"grad_norm": 0.19673901796340942,
	"learning_rate": 7.345309381237526e-05,
	"loss": 1.0314775705337524,
	"step": 323
	},
	{
	"epoch": 1.2807711319822046,
	"grad_norm": 0.18468639254570007,
	"learning_rate": 7.305389221556886e-05,
	"loss": 0.9060774445533752,
	"step": 324
	},
	{
	"epoch": 1.2847256549678696,
	"grad_norm": 0.18173182010650635,
	"learning_rate": 7.265469061876248e-05,
	"loss": 0.7989869117736816,
	"step": 325
	},
	{
	"epoch": 1.2886801779535344,
	"grad_norm": 0.1873815804719925,
	"learning_rate": 7.225548902195609e-05,
	"loss": 0.980597972869873,
	"step": 326
	},
	{
	"epoch": 1.2926347009391992,
	"grad_norm": 0.19111032783985138,
	"learning_rate": 7.18562874251497e-05,
	"loss": 0.9921055436134338,
	"step": 327
	},
	{
	"epoch": 1.296589223924864,
	"grad_norm": 0.1846132129430771,
	"learning_rate": 7.145708582834332e-05,
	"loss": 0.9843934178352356,
	"step": 328
	},
	{
	"epoch": 1.300543746910529,
	"grad_norm": 0.23496906459331512,
	"learning_rate": 7.105788423153693e-05,
	"loss": 1.000301480293274,
	"step": 329
	},
	{
	"epoch": 1.3044982698961938,
	"grad_norm": 0.1931312382221222,
	"learning_rate": 7.065868263473055e-05,
	"loss": 0.8303369283676147,
	"step": 330
	},
	{
	"epoch": 1.3084527928818586,
	"grad_norm": 0.185639426112175,
	"learning_rate": 7.025948103792415e-05,
	"loss": 0.898432731628418,
	"step": 331
	},
	{
	"epoch": 1.3124073158675236,
	"grad_norm": 0.20121130347251892,
	"learning_rate": 6.986027944111777e-05,
	"loss": 0.9152477383613586,
	"step": 332
	},
	{
	"epoch": 1.3163618388531884,
	"grad_norm": 0.21694481372833252,
	"learning_rate": 6.946107784431138e-05,
	"loss": 0.82918781042099,
	"step": 333
	},
	{
	"epoch": 1.3203163618388531,
	"grad_norm": 0.1961311399936676,
	"learning_rate": 6.9061876247505e-05,
	"loss": 0.7353627681732178,
	"step": 334
	},
	{
	"epoch": 1.324270884824518,
	"grad_norm": 0.18697749078273773,
	"learning_rate": 6.866267465069862e-05,
	"loss": 0.9976124167442322,
	"step": 335
	},
	{
	"epoch": 1.328225407810183,
	"grad_norm": 0.20015275478363037,
	"learning_rate": 6.826347305389222e-05,
	"loss": 0.9885960221290588,
	"step": 336
	},
	{
	"epoch": 1.3321799307958477,
	"grad_norm": 0.170740008354187,
	"learning_rate": 6.786427145708583e-05,
	"loss": 0.8704991936683655,
	"step": 337
	},
	{
	"epoch": 1.3361344537815127,
	"grad_norm": 0.2036600261926651,
	"learning_rate": 6.746506986027945e-05,
	"loss": 0.8373860120773315,
	"step": 338
	},
	{
	"epoch": 1.3400889767671775,
	"grad_norm": 0.1967741847038269,
	"learning_rate": 6.706586826347305e-05,
	"loss": 0.9344059228897095,
	"step": 339
	},
	{
	"epoch": 1.3440434997528423,
	"grad_norm": 0.18084974586963654,
	"learning_rate": 6.666666666666667e-05,
	"loss": 0.9507811069488525,
	"step": 340
	},
	{
	"epoch": 1.347998022738507,
	"grad_norm": 0.1890396773815155,
	"learning_rate": 6.626746506986028e-05,
	"loss": 0.9278057217597961,
	"step": 341
	},
	{
	"epoch": 1.351952545724172,
	"grad_norm": 0.20094835758209229,
	"learning_rate": 6.58682634730539e-05,
	"loss": 0.9359115362167358,
	"step": 342
	},
	{
	"epoch": 1.355907068709837,
	"grad_norm": 0.19261251389980316,
	"learning_rate": 6.54690618762475e-05,
	"loss": 0.9001166820526123,
	"step": 343
	},
	{
	"epoch": 1.3598615916955017,
	"grad_norm": 0.19089815020561218,
	"learning_rate": 6.506986027944112e-05,
	"loss": 0.9219706654548645,
	"step": 344
	},
	{
	"epoch": 1.3638161146811667,
	"grad_norm": 0.20358265936374664,
	"learning_rate": 6.467065868263474e-05,
	"loss": 0.8198409080505371,
	"step": 345
	},
	{
	"epoch": 1.3677706376668315,
	"grad_norm": 0.20188573002815247,
	"learning_rate": 6.427145708582834e-05,
	"loss": 0.9551017880439758,
	"step": 346
	},
	{
	"epoch": 1.3717251606524963,
	"grad_norm": 0.18636231124401093,
	"learning_rate": 6.387225548902196e-05,
	"loss": 1.007879376411438,
	"step": 347
	},
	{
	"epoch": 1.375679683638161,
	"grad_norm": 0.20502787828445435,
	"learning_rate": 6.347305389221557e-05,
	"loss": 0.7461677193641663,
	"step": 348
	},
	{
	"epoch": 1.379634206623826,
	"grad_norm": 0.1991313099861145,
	"learning_rate": 6.307385229540919e-05,
	"loss": 0.9965579509735107,
	"step": 349
	},
	{
	"epoch": 1.3835887296094909,
	"grad_norm": 0.18065449595451355,
	"learning_rate": 6.26746506986028e-05,
	"loss": 0.7860137820243835,
	"step": 350
	},
	{
	"epoch": 1.3875432525951557,
	"grad_norm": 0.1943470537662506,
	"learning_rate": 6.227544910179641e-05,
	"loss": 0.9140808582305908,
	"step": 351
	},
	{
	"epoch": 1.3914977755808207,
	"grad_norm": 0.18946987390518188,
	"learning_rate": 6.187624750499003e-05,
	"loss": 0.813644289970398,
	"step": 352
	},
	{
	"epoch": 1.3954522985664854,
	"grad_norm": 0.18935807049274445,
	"learning_rate": 6.147704590818363e-05,
	"loss": 0.7775428891181946,
	"step": 353
	},
	{
	"epoch": 1.3994068215521502,
	"grad_norm": 0.17212191224098206,
	"learning_rate": 6.107784431137725e-05,
	"loss": 0.791588306427002,
	"step": 354
	},
	{
	"epoch": 1.403361344537815,
	"grad_norm": 0.1845926195383072,
	"learning_rate": 6.0678642714570866e-05,
	"loss": 0.8854494690895081,
	"step": 355
	},
	{
	"epoch": 1.40731586752348,
	"grad_norm": 0.19545923173427582,
	"learning_rate": 6.027944111776448e-05,
	"loss": 0.9289248585700989,
	"step": 356
	},
	{
	"epoch": 1.4112703905091448,
	"grad_norm": 0.23064754903316498,
	"learning_rate": 5.988023952095808e-05,
	"loss": 0.8877400755882263,
	"step": 357
	},
	{
	"epoch": 1.4152249134948096,
	"grad_norm": 0.18640878796577454,
	"learning_rate": 5.9481037924151695e-05,
	"loss": 0.8007562160491943,
	"step": 358
	},
	{
	"epoch": 1.4191794364804746,
	"grad_norm": 0.196823850274086,
	"learning_rate": 5.908183632734531e-05,
	"loss": 0.9147028923034668,
	"step": 359
	},
	{
	"epoch": 1.4231339594661394,
	"grad_norm": 0.18492864072322845,
	"learning_rate": 5.868263473053892e-05,
	"loss": 1.0567796230316162,
	"step": 360
	},
	{
	"epoch": 1.4270884824518042,
	"grad_norm": 0.19871287047863007,
	"learning_rate": 5.828343313373253e-05,
	"loss": 0.858993411064148,
	"step": 361
	},
	{
	"epoch": 1.431043005437469,
	"grad_norm": 0.1865636110305786,
	"learning_rate": 5.788423153692615e-05,
	"loss": 0.9598185420036316,
	"step": 362
	},
	{
	"epoch": 1.434997528423134,
	"grad_norm": 0.1950787603855133,
	"learning_rate": 5.748502994011976e-05,
	"loss": 0.866109311580658,
	"step": 363
	},
	{
	"epoch": 1.4389520514087988,
	"grad_norm": 0.19537241756916046,
	"learning_rate": 5.7085828343313375e-05,
	"loss": 0.9231923818588257,
	"step": 364
	},
	{
	"epoch": 1.4429065743944638,
	"grad_norm": 0.1848801076412201,
	"learning_rate": 5.668662674650699e-05,
	"loss": 0.9152354001998901,
	"step": 365
	},
	{
	"epoch": 1.4468610973801286,
	"grad_norm": 0.19516348838806152,
	"learning_rate": 5.62874251497006e-05,
	"loss": 0.9022656679153442,
	"step": 366
	},
	{
	"epoch": 1.4508156203657934,
	"grad_norm": 0.1875586360692978,
	"learning_rate": 5.588822355289421e-05,
	"loss": 0.9204172492027283,
	"step": 367
	},
	{
	"epoch": 1.4547701433514582,
	"grad_norm": 0.19239316880702972,
	"learning_rate": 5.548902195608783e-05,
	"loss": 0.9383366107940674,
	"step": 368
	},
	{
	"epoch": 1.4587246663371232,
	"grad_norm": 0.19720111787319183,
	"learning_rate": 5.508982035928144e-05,
	"loss": 0.961857795715332,
	"step": 369
	},
	{
	"epoch": 1.462679189322788,
	"grad_norm": 0.213732048869133,
	"learning_rate": 5.4690618762475055e-05,
	"loss": 0.8472163081169128,
	"step": 370
	},
	{
	"epoch": 1.4666337123084527,
	"grad_norm": 0.1938932090997696,
	"learning_rate": 5.429141716566867e-05,
	"loss": 0.8686806559562683,
	"step": 371
	},
	{
	"epoch": 1.4705882352941178,
	"grad_norm": 0.19152139127254486,
	"learning_rate": 5.389221556886228e-05,
	"loss": 0.8825725317001343,
	"step": 372
	},
	{
	"epoch": 1.4745427582797825,
	"grad_norm": 0.19953249394893646,
	"learning_rate": 5.349301397205589e-05,
	"loss": 1.0075819492340088,
	"step": 373
	},
	{
	"epoch": 1.4784972812654473,
	"grad_norm": 0.19870170950889587,
	"learning_rate": 5.309381237524951e-05,
	"loss": 0.8033257126808167,
	"step": 374
	},
	{
	"epoch": 1.4824518042511121,
	"grad_norm": 0.21190565824508667,
	"learning_rate": 5.269461077844312e-05,
	"loss": 0.9029344916343689,
	"step": 375
	},
	{
	"epoch": 1.4864063272367771,
	"grad_norm": 0.20307143032550812,
	"learning_rate": 5.2295409181636734e-05,
	"loss": 0.9491141438484192,
	"step": 376
	},
	{
	"epoch": 1.490360850222442,
	"grad_norm": 0.21230387687683105,
	"learning_rate": 5.189620758483034e-05,
	"loss": 0.9077959060668945,
	"step": 377
	},
	{
	"epoch": 1.4943153732081067,
	"grad_norm": 0.20202863216400146,
	"learning_rate": 5.149700598802395e-05,
	"loss": 0.9439913630485535,
	"step": 378
	},
	{
	"epoch": 1.4982698961937717,
	"grad_norm": 0.1929042786359787,
	"learning_rate": 5.1097804391217564e-05,
	"loss": 0.9769095778465271,
	"step": 379
	},
	{
	"epoch": 1.5022244191794365,
	"grad_norm": 0.21215690672397614,
	"learning_rate": 5.0698602794411176e-05,
	"loss": 0.7954482436180115,
	"step": 380
	},
	{
	"epoch": 1.5061789421651013,
	"grad_norm": 0.19395476579666138,
	"learning_rate": 5.029940119760479e-05,
	"loss": 0.8338028192520142,
	"step": 381
	},
	{
	"epoch": 1.510133465150766,
	"grad_norm": 0.2140199989080429,
	"learning_rate": 4.99001996007984e-05,
	"loss": 0.7927234172821045,
	"step": 382
	},
	{
	"epoch": 1.514087988136431,
	"grad_norm": 0.20886200666427612,
	"learning_rate": 4.950099800399202e-05,
	"loss": 0.9537109136581421,
	"step": 383
	},
	{
	"epoch": 1.5180425111220959,
	"grad_norm": 0.21319736540317535,
	"learning_rate": 4.910179640718563e-05,
	"loss": 0.7856256365776062,
	"step": 384
	},
	{
	"epoch": 1.5219970341077609,
	"grad_norm": 0.21167606115341187,
	"learning_rate": 4.8702594810379244e-05,
	"loss": 0.9939818978309631,
	"step": 385
	},
	{
	"epoch": 1.5259515570934257,
	"grad_norm": 0.20061740279197693,
	"learning_rate": 4.8303393213572856e-05,
	"loss": 0.9484026432037354,
	"step": 386
	},
	{
	"epoch": 1.5299060800790905,
	"grad_norm": 0.2059990018606186,
	"learning_rate": 4.790419161676647e-05,
	"loss": 0.8519854545593262,
	"step": 387
	},
	{
	"epoch": 1.5338606030647552,
	"grad_norm": 0.1978318989276886,
	"learning_rate": 4.750499001996008e-05,
	"loss": 0.8361144065856934,
	"step": 388
	},
	{
	"epoch": 1.53781512605042,
	"grad_norm": 0.2057390809059143,
	"learning_rate": 4.71057884231537e-05,
	"loss": 0.8409650325775146,
	"step": 389
	},
	{
	"epoch": 1.541769649036085,
	"grad_norm": 0.1905912309885025,
	"learning_rate": 4.670658682634731e-05,
	"loss": 0.8437705039978027,
	"step": 390
	},
	{
	"epoch": 1.5457241720217498,
	"grad_norm": 0.23166270554065704,
	"learning_rate": 4.630738522954092e-05,
	"loss": 1.1090465784072876,
	"step": 391
	},
	{
	"epoch": 1.5496786950074148,
	"grad_norm": 0.19709770381450653,
	"learning_rate": 4.590818363273453e-05,
	"loss": 0.9146186709403992,
	"step": 392
	},
	{
	"epoch": 1.5536332179930796,
	"grad_norm": 0.24494928121566772,
	"learning_rate": 4.550898203592814e-05,
	"loss": 0.8773439526557922,
	"step": 393
	},
	{
	"epoch": 1.5575877409787444,
	"grad_norm": 0.1936318725347519,
	"learning_rate": 4.510978043912176e-05,
	"loss": 0.8627104163169861,
	"step": 394
	},
	{
	"epoch": 1.5615422639644092,
	"grad_norm": 0.1917494237422943,
	"learning_rate": 4.471057884231537e-05,
	"loss": 0.9282490015029907,
	"step": 395
	},
	{
	"epoch": 1.565496786950074,
	"grad_norm": 0.20790532231330872,
	"learning_rate": 4.4311377245508984e-05,
	"loss": 0.9672350883483887,
	"step": 396
	},
	{
	"epoch": 1.569451309935739,
	"grad_norm": 0.21338993310928345,
	"learning_rate": 4.3912175648702596e-05,
	"loss": 0.9289650321006775,
	"step": 397
	},
	{
	"epoch": 1.573405832921404,
	"grad_norm": 0.20963947474956512,
	"learning_rate": 4.351297405189621e-05,
	"loss": 0.9762122631072998,
	"step": 398
	},
	{
	"epoch": 1.5773603559070688,
	"grad_norm": 0.20937083661556244,
	"learning_rate": 4.311377245508982e-05,
	"loss": 0.9213401079177856,
	"step": 399
	},
	{
	"epoch": 1.5813148788927336,
	"grad_norm": 0.20903795957565308,
	"learning_rate": 4.271457085828344e-05,
	"loss": 0.9836536645889282,
	"step": 400
	},
	{
	"epoch": 1.5852694018783984,
	"grad_norm": 0.20544159412384033,
	"learning_rate": 4.231536926147705e-05,
	"loss": 0.8152018785476685,
	"step": 401
	},
	{
	"epoch": 1.5892239248640632,
	"grad_norm": 0.1830497533082962,
	"learning_rate": 4.191616766467066e-05,
	"loss": 0.9987653493881226,
	"step": 402
	},
	{
	"epoch": 1.5931784478497282,
	"grad_norm": 0.1913018822669983,
	"learning_rate": 4.151696606786427e-05,
	"loss": 0.867318332195282,
	"step": 403
	},
	{
	"epoch": 1.597132970835393,
	"grad_norm": 0.19043081998825073,
	"learning_rate": 4.111776447105789e-05,
	"loss": 0.8715974688529968,
	"step": 404
	},
	{
	"epoch": 1.601087493821058,
	"grad_norm": 0.18875691294670105,
	"learning_rate": 4.07185628742515e-05,
	"loss": 0.904281735420227,
	"step": 405
	},
	{
	"epoch": 1.6050420168067228,
	"grad_norm": 0.2014741152524948,
	"learning_rate": 4.031936127744511e-05,
	"loss": 0.9567676186561584,
	"step": 406
	},
	{
	"epoch": 1.6089965397923875,
	"grad_norm": 0.17751306295394897,
	"learning_rate": 3.9920159680638724e-05,
	"loss": 0.8185122013092041,
	"step": 407
	},
	{
	"epoch": 1.6129510627780523,
	"grad_norm": 0.20318663120269775,
	"learning_rate": 3.9520958083832336e-05,
	"loss": 0.9554027318954468,
	"step": 408
	},
	{
	"epoch": 1.6169055857637171,
	"grad_norm": 0.1872302144765854,
	"learning_rate": 3.912175648702595e-05,
	"loss": 0.9051477313041687,
	"step": 409
	},
	{
	"epoch": 1.6208601087493821,
	"grad_norm": 0.21332977712154388,
	"learning_rate": 3.872255489021957e-05,
	"loss": 0.944547712802887,
	"step": 410
	},
	{
	"epoch": 1.624814631735047,
	"grad_norm": 0.18820840120315552,
	"learning_rate": 3.832335329341318e-05,
	"loss": 0.9271795749664307,
	"step": 411
	},
	{
	"epoch": 1.628769154720712,
	"grad_norm": 0.2146555483341217,
	"learning_rate": 3.7924151696606785e-05,
	"loss": 0.8307335376739502,
	"step": 412
	},
	{
	"epoch": 1.6327236777063767,
	"grad_norm": 0.2196199744939804,
	"learning_rate": 3.75249500998004e-05,
	"loss": 0.8816962242126465,
	"step": 413
	},
	{
	"epoch": 1.6366782006920415,
	"grad_norm": 0.1986646205186844,
	"learning_rate": 3.712574850299401e-05,
	"loss": 0.9725742936134338,
	"step": 414
	},
	{
	"epoch": 1.6406327236777063,
	"grad_norm": 0.18679843842983246,
	"learning_rate": 3.672654690618763e-05,
	"loss": 0.9385328888893127,
	"step": 415
	},
	{
	"epoch": 1.644587246663371,
	"grad_norm": 0.18637174367904663,
	"learning_rate": 3.632734530938124e-05,
	"loss": 0.9450833201408386,
	"step": 416
	},
	{
	"epoch": 1.648541769649036,
	"grad_norm": 0.20110389590263367,
	"learning_rate": 3.592814371257485e-05,
	"loss": 0.9009251594543457,
	"step": 417
	},
	{
	"epoch": 1.652496292634701,
	"grad_norm": 0.22820661962032318,
	"learning_rate": 3.5528942115768465e-05,
	"loss": 0.9610739350318909,
	"step": 418
	},
	{
	"epoch": 1.656450815620366,
	"grad_norm": 0.20116274058818817,
	"learning_rate": 3.512974051896208e-05,
	"loss": 0.9576656818389893,
	"step": 419
	},
	{
	"epoch": 1.6604053386060307,
	"grad_norm": 0.19964101910591125,
	"learning_rate": 3.473053892215569e-05,
	"loss": 0.9899635314941406,
	"step": 420
	},
	{
	"epoch": 1.6643598615916955,
	"grad_norm": 0.21723447740077972,
	"learning_rate": 3.433133732534931e-05,
	"loss": 0.7412058115005493,
	"step": 421
	},
	{
	"epoch": 1.6683143845773603,
	"grad_norm": 0.21164871752262115,
	"learning_rate": 3.393213572854291e-05,
	"loss": 1.107064127922058,
	"step": 422
	},
	{
	"epoch": 1.6722689075630253,
	"grad_norm": 0.20853902399539948,
	"learning_rate": 3.3532934131736525e-05,
	"loss": 1.0325095653533936,
	"step": 423
	},
	{
	"epoch": 1.67622343054869,
	"grad_norm": 0.1993069052696228,
	"learning_rate": 3.313373253493014e-05,
	"loss": 0.8811869621276855,
	"step": 424
	},
	{
	"epoch": 1.680177953534355,
	"grad_norm": 0.2086590826511383,
	"learning_rate": 3.273453093812375e-05,
	"loss": 0.8045269846916199,
	"step": 425
	},
	{
	"epoch": 1.6841324765200198,
	"grad_norm": 0.19502981007099152,
	"learning_rate": 3.233532934131737e-05,
	"loss": 1.0250900983810425,
	"step": 426
	},
	{
	"epoch": 1.6880869995056846,
	"grad_norm": 0.1864766627550125,
	"learning_rate": 3.193612774451098e-05,
	"loss": 0.7248687744140625,
	"step": 427
	},
	{
	"epoch": 1.6920415224913494,
	"grad_norm": 0.20849153399467468,
	"learning_rate": 3.153692614770459e-05,
	"loss": 0.8926454186439514,
	"step": 428
	},
	{
	"epoch": 1.6959960454770142,
	"grad_norm": 0.20903082191944122,
	"learning_rate": 3.1137724550898205e-05,
	"loss": 0.8962099552154541,
	"step": 429
	},
	{
	"epoch": 1.6999505684626792,
	"grad_norm": 0.1925486922264099,
	"learning_rate": 3.073852295409182e-05,
	"loss": 0.9962249994277954,
	"step": 430
	},
	{
	"epoch": 1.703905091448344,
	"grad_norm": 0.20653171837329865,
	"learning_rate": 3.0339321357285433e-05,
	"loss": 0.8618420958518982,
	"step": 431
	},
	{
	"epoch": 1.707859614434009,
	"grad_norm": 0.21909548342227936,
	"learning_rate": 2.994011976047904e-05,
	"loss": 1.0019207000732422,
	"step": 432
	},
	{
	"epoch": 1.7118141374196738,
	"grad_norm": 0.1952063888311386,
	"learning_rate": 2.9540918163672654e-05,
	"loss": 0.7654832005500793,
	"step": 433
	},
	{
	"epoch": 1.7157686604053386,
	"grad_norm": 0.20689325034618378,
	"learning_rate": 2.9141716566866266e-05,
	"loss": 0.9330834746360779,
	"step": 434
	},
	{
	"epoch": 1.7197231833910034,
	"grad_norm": 0.20880067348480225,
	"learning_rate": 2.874251497005988e-05,
	"loss": 0.9945483803749084,
	"step": 435
	},
	{
	"epoch": 1.7236777063766682,
	"grad_norm": 0.18159128725528717,
	"learning_rate": 2.8343313373253494e-05,
	"loss": 0.9131766557693481,
	"step": 436
	},
	{
	"epoch": 1.7276322293623332,
	"grad_norm": 0.19038815796375275,
	"learning_rate": 2.7944111776447106e-05,
	"loss": 0.8274218440055847,
	"step": 437
	},
	{
	"epoch": 1.731586752347998,
	"grad_norm": 0.20182478427886963,
	"learning_rate": 2.754491017964072e-05,
	"loss": 0.8425199389457703,
	"step": 438
	},
	{
	"epoch": 1.735541275333663,
	"grad_norm": 0.20511551201343536,
	"learning_rate": 2.7145708582834333e-05,
	"loss": 0.8865355253219604,
	"step": 439
	},
	{
	"epoch": 1.7394957983193278,
	"grad_norm": 0.2129596769809723,
	"learning_rate": 2.6746506986027946e-05,
	"loss": 0.9642688035964966,
	"step": 440
	},
	{
	"epoch": 1.7434503213049926,
	"grad_norm": 0.20142444968223572,
	"learning_rate": 2.634730538922156e-05,
	"loss": 1.0012695789337158,
	"step": 441
	},
	{
	"epoch": 1.7474048442906573,
	"grad_norm": 0.20275944471359253,
	"learning_rate": 2.594810379241517e-05,
	"loss": 0.8509343266487122,
	"step": 442
	},
	{
	"epoch": 1.7513593672763221,
	"grad_norm": 0.20978280901908875,
	"learning_rate": 2.5548902195608782e-05,
	"loss": 0.8017287850379944,
	"step": 443
	},
	{
	"epoch": 1.7553138902619871,
	"grad_norm": 0.2030046135187149,
	"learning_rate": 2.5149700598802394e-05,
	"loss": 0.9278156757354736,
	"step": 444
	},
	{
	"epoch": 1.7592684132476522,
	"grad_norm": 0.2252151072025299,
	"learning_rate": 2.475049900199601e-05,
	"loss": 0.9012824296951294,
	"step": 445
	},
	{
	"epoch": 1.763222936233317,
	"grad_norm": 0.20253197848796844,
	"learning_rate": 2.4351297405189622e-05,
	"loss": 0.8817086815834045,
	"step": 446
	},
	{
	"epoch": 1.7671774592189817,
	"grad_norm": 0.22054298222064972,
	"learning_rate": 2.3952095808383234e-05,
	"loss": 0.9003196954727173,
	"step": 447
	},
	{
	"epoch": 1.7711319822046465,
	"grad_norm": 0.2037447839975357,
	"learning_rate": 2.355289421157685e-05,
	"loss": 0.8119622468948364,
	"step": 448
	},
	{
	"epoch": 1.7750865051903113,
	"grad_norm": 0.21892541646957397,
	"learning_rate": 2.315369261477046e-05,
	"loss": 0.9405473470687866,
	"step": 449
	},
	{
	"epoch": 1.7790410281759763,
	"grad_norm": 0.20719027519226074,
	"learning_rate": 2.275449101796407e-05,
	"loss": 0.8205680847167969,
	"step": 450
	},
	{
	"epoch": 1.782995551161641,
	"grad_norm": 0.20699091255664825,
	"learning_rate": 2.2355289421157686e-05,
	"loss": 0.8950562477111816,
	"step": 451
	},
	{
	"epoch": 1.7869500741473061,
	"grad_norm": 0.19834667444229126,
	"learning_rate": 2.1956087824351298e-05,
	"loss": 0.8222463130950928,
	"step": 452
	},
	{
	"epoch": 1.790904597132971,
	"grad_norm": 0.19083131849765778,
	"learning_rate": 2.155688622754491e-05,
	"loss": 0.9506749510765076,
	"step": 453
	},
	{
	"epoch": 1.7948591201186357,
	"grad_norm": 0.21305403113365173,
	"learning_rate": 2.1157684630738526e-05,
	"loss": 0.833589494228363,
	"step": 454
	},
	{
	"epoch": 1.7988136431043005,
	"grad_norm": 0.21756337583065033,
	"learning_rate": 2.0758483033932134e-05,
	"loss": 0.7631924152374268,
	"step": 455
	},
	{
	"epoch": 1.8027681660899653,
	"grad_norm": 0.20038093626499176,
	"learning_rate": 2.035928143712575e-05,
	"loss": 1.037887692451477,
	"step": 456
	},
	{
	"epoch": 1.8067226890756303,
	"grad_norm": 0.20598313212394714,
	"learning_rate": 1.9960079840319362e-05,
	"loss": 0.9344784617424011,
	"step": 457
	},
	{
	"epoch": 1.810677212061295,
	"grad_norm": 0.19507546722888947,
	"learning_rate": 1.9560878243512974e-05,
	"loss": 0.9052549600601196,
	"step": 458
	},
	{
	"epoch": 1.81463173504696,
	"grad_norm": 0.20818522572517395,
	"learning_rate": 1.916167664670659e-05,
	"loss": 0.8613417148590088,
	"step": 459
	},
	{
	"epoch": 1.8185862580326249,
	"grad_norm": 0.18870945274829865,
	"learning_rate": 1.87624750499002e-05,
	"loss": 0.793246865272522,
	"step": 460
	},
	{
	"epoch": 1.8225407810182896,
	"grad_norm": 0.21497206389904022,
	"learning_rate": 1.8363273453093814e-05,
	"loss": 0.9714541435241699,
	"step": 461
	},
	{
	"epoch": 1.8264953040039544,
	"grad_norm": 0.21383772790431976,
	"learning_rate": 1.7964071856287426e-05,
	"loss": 1.0128012895584106,
	"step": 462
	},
	{
	"epoch": 1.8304498269896192,
	"grad_norm": 0.21303774416446686,
	"learning_rate": 1.756487025948104e-05,
	"loss": 0.8802911639213562,
	"step": 463
	},
	{
	"epoch": 1.8344043499752842,
	"grad_norm": 0.18445076048374176,
	"learning_rate": 1.7165668662674654e-05,
	"loss": 1.0024535655975342,
	"step": 464
	},
	{
	"epoch": 1.8383588729609492,
	"grad_norm": 0.20212195813655853,
	"learning_rate": 1.6766467065868263e-05,
	"loss": 1.1197216510772705,
	"step": 465
	},
	{
	"epoch": 1.842313395946614,
	"grad_norm": 0.2088390588760376,
	"learning_rate": 1.6367265469061875e-05,
	"loss": 0.9632558226585388,
	"step": 466
	},
	{
	"epoch": 1.8462679189322788,
	"grad_norm": 0.20784492790699005,
	"learning_rate": 1.596806387225549e-05,
	"loss": 0.734897255897522,
	"step": 467
	},
	{
	"epoch": 1.8502224419179436,
	"grad_norm": 0.19716675579547882,
	"learning_rate": 1.5568862275449103e-05,
	"loss": 0.9311115145683289,
	"step": 468
	},
	{
	"epoch": 1.8541769649036084,
	"grad_norm": 0.20142972469329834,
	"learning_rate": 1.5169660678642716e-05,
	"loss": 0.9369468688964844,
	"step": 469
	},
	{
	"epoch": 1.8581314878892734,
	"grad_norm": 0.20825821161270142,
	"learning_rate": 1.4770459081836327e-05,
	"loss": 1.135632038116455,
	"step": 470
	},
	{
	"epoch": 1.8620860108749382,
	"grad_norm": 0.20531900227069855,
	"learning_rate": 1.437125748502994e-05,
	"loss": 0.817120373249054,
	"step": 471
	},
	{
	"epoch": 1.8660405338606032,
	"grad_norm": 0.2101070135831833,
	"learning_rate": 1.3972055888223553e-05,
	"loss": 0.8993910551071167,
	"step": 472
	},
	{
	"epoch": 1.869995056846268,
	"grad_norm": 0.1841268241405487,
	"learning_rate": 1.3572854291417167e-05,
	"loss": 0.9081541299819946,
	"step": 473
	},
	{
	"epoch": 1.8739495798319328,
	"grad_norm": 0.19929905235767365,
	"learning_rate": 1.317365269461078e-05,
	"loss": 0.8846563696861267,
	"step": 474
	},
	{
	"epoch": 1.8779041028175976,
	"grad_norm": 0.21067850291728973,
	"learning_rate": 1.2774451097804391e-05,
	"loss": 0.8508776426315308,
	"step": 475
	},
	{
	"epoch": 1.8818586258032624,
	"grad_norm": 0.19630905985832214,
	"learning_rate": 1.2375249500998005e-05,
	"loss": 0.9228495359420776,
	"step": 476
	},
	{
	"epoch": 1.8858131487889274,
	"grad_norm": 0.22471991181373596,
	"learning_rate": 1.1976047904191617e-05,
	"loss": 0.8360285758972168,
	"step": 477
	},
	{
	"epoch": 1.8897676717745922,
	"grad_norm": 0.18797798454761505,
	"learning_rate": 1.157684630738523e-05,
	"loss": 0.8709227442741394,
	"step": 478
	},
	{
	"epoch": 1.8937221947602572,
	"grad_norm": 0.20813153684139252,
	"learning_rate": 1.1177644710578843e-05,
	"loss": 1.0134263038635254,
	"step": 479
	},
	{
	"epoch": 1.897676717745922,
	"grad_norm": 0.20971933007240295,
	"learning_rate": 1.0778443113772455e-05,
	"loss": 0.8753843307495117,
	"step": 480
	},
	{
	"epoch": 1.9016312407315867,
	"grad_norm": 0.19115358591079712,
	"learning_rate": 1.0379241516966067e-05,
	"loss": 0.8529820442199707,
	"step": 481
	},
	{
	"epoch": 1.9055857637172515,
	"grad_norm": 0.23405560851097107,
	"learning_rate": 9.980039920159681e-06,
	"loss": 0.9483686685562134,
	"step": 482
	},
	{
	"epoch": 1.9095402867029163,
	"grad_norm": 0.23471501469612122,
	"learning_rate": 9.580838323353295e-06,
	"loss": 0.9428390860557556,
	"step": 483
	},
	{
	"epoch": 1.9134948096885813,
	"grad_norm": 0.21804015338420868,
	"learning_rate": 9.181636726546907e-06,
	"loss": 0.8681425452232361,
	"step": 484
	},
	{
	"epoch": 1.9174493326742463,
	"grad_norm": 0.20593298971652985,
	"learning_rate": 8.78243512974052e-06,
	"loss": 0.9854474067687988,
	"step": 485
	},
	{
	"epoch": 1.9214038556599111,
	"grad_norm": 0.20268182456493378,
	"learning_rate": 8.383233532934131e-06,
	"loss": 0.8769013285636902,
	"step": 486
	},
	{
	"epoch": 1.925358378645576,
	"grad_norm": 0.20166848599910736,
	"learning_rate": 7.984031936127745e-06,
	"loss": 0.8038483262062073,
	"step": 487
	},
	{
	"epoch": 1.9293129016312407,
	"grad_norm": 0.20438715815544128,
	"learning_rate": 7.584830339321358e-06,
	"loss": 0.8820595741271973,
	"step": 488
	},
	{
	"epoch": 1.9332674246169055,
	"grad_norm": 0.22562836110591888,
	"learning_rate": 7.18562874251497e-06,
	"loss": 0.8607326745986938,
	"step": 489
	},
	{
	"epoch": 1.9372219476025705,
	"grad_norm": 0.24032363295555115,
	"learning_rate": 6.786427145708583e-06,
	"loss": 0.9563621878623962,
	"step": 490
	},
	{
	"epoch": 1.9411764705882353,
	"grad_norm": 0.22053006291389465,
	"learning_rate": 6.3872255489021955e-06,
	"loss": 0.9206818342208862,
	"step": 491
	},
	{
	"epoch": 1.9451309935739003,
	"grad_norm": 0.201730415225029,
	"learning_rate": 5.9880239520958085e-06,
	"loss": 0.8101902604103088,
	"step": 492
	},
	{
	"epoch": 1.949085516559565,
	"grad_norm": 0.2032587230205536,
	"learning_rate": 5.5888223552894215e-06,
	"loss": 0.8570499420166016,
	"step": 493
	},
	{
	"epoch": 1.9530400395452299,
	"grad_norm": 0.21162763237953186,
	"learning_rate": 5.189620758483034e-06,
	"loss": 0.8345759510993958,
	"step": 494
	},
	{
	"epoch": 1.9569945625308947,
	"grad_norm": 0.19271045923233032,
	"learning_rate": 4.7904191616766475e-06,
	"loss": 0.9391037821769714,
	"step": 495
	},
	{
	"epoch": 1.9609490855165594,
	"grad_norm": 0.20637477934360504,
	"learning_rate": 4.39121756487026e-06,
	"loss": 0.8780249953269958,
	"step": 496
	},
	{
	"epoch": 1.9649036085022245,
	"grad_norm": 0.20201361179351807,
	"learning_rate": 3.992015968063873e-06,
	"loss": 0.9155791997909546,
	"step": 497
	},
	{
	"epoch": 1.9688581314878892,
	"grad_norm": 0.21115684509277344,
	"learning_rate": 3.592814371257485e-06,
	"loss": 0.7178623676300049,
	"step": 498
	},
	{
	"epoch": 1.9728126544735543,
	"grad_norm": 0.22672364115715027,
	"learning_rate": 3.1936127744510977e-06,
	"loss": 0.8261544704437256,
	"step": 499
	},
	{
	"epoch": 1.976767177459219,
	"grad_norm": 0.18823912739753723,
	"learning_rate": 2.7944111776447107e-06,
	"loss": 0.8679497241973877,
	"step": 500
	},
	{
	"epoch": 1.9807217004448838,
	"grad_norm": 0.2101755440235138,
	"learning_rate": 2.3952095808383237e-06,
	"loss": 0.950539231300354,
	"step": 501
	},
	{
	"epoch": 1.9846762234305486,
	"grad_norm": 0.21033525466918945,
	"learning_rate": 1.9960079840319363e-06,
	"loss": 0.7960910797119141,
	"step": 502
	},
	{
	"epoch": 1.9886307464162134,
	"grad_norm": 0.21546964347362518,
	"learning_rate": 1.5968063872255489e-06,
	"loss": 0.9860714077949524,
	"step": 503
	},
	{
	"epoch": 1.9925852694018784,
	"grad_norm": 0.19765757024288177,
	"learning_rate": 1.1976047904191619e-06,
	"loss": 1.025565505027771,
	"step": 504
	},
	{
	"epoch": 1.9965397923875432,
	"grad_norm": 0.20392237603664398,
	"learning_rate": 7.984031936127744e-07,
	"loss": 0.8897353410720825,
	"step": 505
	},
	{
	"epoch": 2.0,
	"grad_norm": 0.2248964011669159,
	"learning_rate": 3.992015968063872e-07,
	"loss": 0.7869975566864014,
	"step": 506
	}
	],
	"logging_steps": 1,
	"max_steps": 506,
	"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": 2.5380020501658665e+18,
	"train_batch_size": 8,
	"trial_name": null,
	"trial_params": null
	}