Instructions to use ynanxiu/qwen25-3b-coffee-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ynanxiu/qwen25-3b-coffee-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "ynanxiu/qwen25-3b-coffee-lora")

Transformers

How to use ynanxiu/qwen25-3b-coffee-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ynanxiu/qwen25-3b-coffee-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ynanxiu/qwen25-3b-coffee-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ynanxiu/qwen25-3b-coffee-lora 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 ynanxiu/qwen25-3b-coffee-lora
# Run inference directly in the terminal:
llama cli -hf ynanxiu/qwen25-3b-coffee-lora

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ynanxiu/qwen25-3b-coffee-lora
# Run inference directly in the terminal:
llama cli -hf ynanxiu/qwen25-3b-coffee-lora

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 ynanxiu/qwen25-3b-coffee-lora
# Run inference directly in the terminal:
./llama-cli -hf ynanxiu/qwen25-3b-coffee-lora

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 ynanxiu/qwen25-3b-coffee-lora
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ynanxiu/qwen25-3b-coffee-lora

Use Docker

docker model run hf.co/ynanxiu/qwen25-3b-coffee-lora

LM Studio
Jan

vLLM

How to use ynanxiu/qwen25-3b-coffee-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ynanxiu/qwen25-3b-coffee-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ynanxiu/qwen25-3b-coffee-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ynanxiu/qwen25-3b-coffee-lora

SGLang

How to use ynanxiu/qwen25-3b-coffee-lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ynanxiu/qwen25-3b-coffee-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ynanxiu/qwen25-3b-coffee-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ynanxiu/qwen25-3b-coffee-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ynanxiu/qwen25-3b-coffee-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ynanxiu/qwen25-3b-coffee-lora with Ollama:
```
ollama run hf.co/ynanxiu/qwen25-3b-coffee-lora
```
Unsloth Desktop

How to use ynanxiu/qwen25-3b-coffee-lora with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ynanxiu/qwen25-3b-coffee-lora

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ynanxiu/qwen25-3b-coffee-lora"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ynanxiu/qwen25-3b-coffee-lora with Docker Model Runner:
```
docker model run hf.co/ynanxiu/qwen25-3b-coffee-lora
```

Lemonade

How to use ynanxiu/qwen25-3b-coffee-lora with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ynanxiu/qwen25-3b-coffee-lora

Run and chat with the model

lemonade run user.qwen25-3b-coffee-lora-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use ynanxiu/qwen25-3b-coffee-lora with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ynanxiu/qwen25-3b-coffee-lora

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 ynanxiu/qwen25-3b-coffee-lora

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ynanxiu/qwen25-3b-coffee-lora with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ynanxiu/qwen25-3b-coffee-lora

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 "ynanxiu/qwen25-3b-coffee-lora" \
  --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"

ynanxiu commited on Jun 29

Commit

1d6c494

verified ·

1 Parent(s): 4380377

Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

adapter_config.json +5 -5
adapter_model.safetensors +1 -1
optimizer.pt +3 -0
rng_state.pth +3 -0
scheduler.pt +3 -0
trainer_state.json +227 -283
training_args.bin +3 -0

adapter_config.json CHANGED Viewed

@@ -30,13 +30,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
-    "q_proj",
-    "down_proj",
     "gate_proj",
     "v_proj",
-    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
     "v_proj",
+    "up_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74b40061e500d01ae320e88253b40d783e924d0f58bb9d15f8cc240bff6fed3
 size 119801528

 version https://git-lfs.github.com/spec/v1
+oid sha256:50be55c540fd460b157f1d163fe6d7db7eb1f44ef1e3185d5da0de6fe152a20f
 size 119801528

optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cee0eaab38c439f095121d9d4e4b828c6f76ef24054a43c5ec75f62c68d1347a
+size 61397748

rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:567f3af81cec0d6fd174bdb3894f4963cbadb0bfdfb8d66b94b2183f22dd1750
+size 14244

scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4b576a1382f99ec79fb2cc6fa3439518381e3332418bda2826757fcf9fb2b0c7
+size 1064

trainer_state.json CHANGED Viewed

@@ -4,462 +4,406 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1284,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.046756282875511396,
-      "grad_norm": 2.6396102905273438,
-      "learning_rate": 2.9457364341085275e-05,
-      "loss": 3.770526885986328,
       "step": 20
     },
     {
-      "epoch": 0.09351256575102279,
-      "grad_norm": 1.8480104207992554,
-      "learning_rate": 6.0465116279069765e-05,
-      "loss": 2.6931344985961916,
       "step": 40
     },
     {
-      "epoch": 0.1402688486265342,
-      "grad_norm": 1.4222798347473145,
-      "learning_rate": 9.147286821705426e-05,
-      "loss": 2.0478179931640623,
       "step": 60
     },
     {
-      "epoch": 0.18702513150204558,
-      "grad_norm": 1.5602340698242188,
-      "learning_rate": 0.00012248062015503876,
-      "loss": 2.065281867980957,
       "step": 80
     },
     {
-      "epoch": 0.23378141437755698,
-      "grad_norm": 1.2624361515045166,
-      "learning_rate": 0.00015348837209302327,
-      "loss": 1.9018199920654297,
       "step": 100
     },
     {
-      "epoch": 0.2805376972530684,
-      "grad_norm": 2.0254690647125244,
-      "learning_rate": 0.00018449612403100774,
-      "loss": 1.8406829833984375,
       "step": 120
     },
     {
-      "epoch": 0.3272939801285798,
-      "grad_norm": 1.392185926437378,
-      "learning_rate": 0.00019996301045360873,
-      "loss": 1.7168672561645508,
       "step": 140
     },
     {
-      "epoch": 0.37405026300409117,
-      "grad_norm": 1.391100287437439,
-      "learning_rate": 0.00019966725824941932,
-      "loss": 1.893547821044922,
       "step": 160
     },
     {
-      "epoch": 0.4208065458796026,
-      "grad_norm": 1.342657208442688,
-      "learning_rate": 0.00019907662885836836,
-      "loss": 1.7812074661254882,
       "step": 180
     },
     {
-      "epoch": 0.46756282875511396,
-      "grad_norm": 1.5658705234527588,
-      "learning_rate": 0.00019819286972627066,
-      "loss": 1.746541976928711,
       "step": 200
     },
     {
-      "epoch": 0.5143191116306254,
-      "grad_norm": 1.2056101560592651,
-      "learning_rate": 0.00019701859555740648,
-      "loss": 1.8151447296142578,
       "step": 220
     },
     {
-      "epoch": 0.5610753945061367,
-      "grad_norm": 1.4878060817718506,
-      "learning_rate": 0.0001955572805786141,
-      "loss": 1.738751220703125,
       "step": 240
     },
     {
-      "epoch": 0.6078316773816481,
-      "grad_norm": 1.211469054222107,
-      "learning_rate": 0.0001938132482603856,
-      "loss": 1.6589984893798828,
       "step": 260
     },
     {
-      "epoch": 0.6545879602571596,
-      "grad_norm": 1.331423044204712,
-      "learning_rate": 0.00019179165852537596,
-      "loss": 1.5927919387817382,
       "step": 280
     },
     {
-      "epoch": 0.701344243132671,
-      "grad_norm": 1.503086805343628,
-      "learning_rate": 0.000189498492482171,
-      "loss": 1.687828254699707,
       "step": 300
     },
     {
-      "epoch": 0.7481005260081823,
-      "grad_norm": 1.0059964656829834,
-      "learning_rate": 0.00018694053472948156,
-      "loss": 1.5391310691833495,
       "step": 320
     },
     {
-      "epoch": 0.7948568088836937,
-      "grad_norm": 1.3163785934448242,
-      "learning_rate": 0.00018412535328311814,
-      "loss": 1.7917730331420898,
       "step": 340
     },
     {
-      "epoch": 0.8416130917592052,
-      "grad_norm": 1.1348614692687988,
-      "learning_rate": 0.00018106127718513516,
-      "loss": 1.6579130172729493,
       "step": 360
     },
     {
-      "epoch": 0.8883693746347165,
-      "grad_norm": 1.2243685722351074,
-      "learning_rate": 0.00017775737186139038,
-      "loss": 1.665598487854004,
       "step": 380
     },
     {
-      "epoch": 0.9351256575102279,
-      "grad_norm": 1.140296220779419,
-      "learning_rate": 0.000174223412300427,
-      "loss": 1.5383720397949219,
       "step": 400
     },
     {
-      "epoch": 0.9818819403857393,
-      "grad_norm": 1.428843379020691,
-      "learning_rate": 0.00017046985413303215,
-      "loss": 1.5671328544616698,
       "step": 420
     },
     {
-      "epoch": 1.028053769725307,
-      "grad_norm": 1.312705636024475,
-      "learning_rate": 0.00016650780269803587,
-      "loss": 1.3141172409057618,
       "step": 440
     },
     {
-      "epoch": 1.0748100526008182,
-      "grad_norm": 1.358636736869812,
-      "learning_rate": 0.00016234898018587337,
-      "loss": 1.3006291389465332,
       "step": 460
     },
     {
-      "epoch": 1.1215663354763297,
-      "grad_norm": 1.2607903480529785,
-      "learning_rate": 0.00015800569095711982,
-      "loss": 1.2852769851684571,
       "step": 480
     },
     {
-      "epoch": 1.1683226183518411,
-      "grad_norm": 1.469335675239563,
-      "learning_rate": 0.00015349078513860726,
-      "loss": 1.2893740653991699,
       "step": 500
     },
     {
-      "epoch": 1.2150789012273524,
-      "grad_norm": 0.929506242275238,
-      "learning_rate": 0.00014881762060482814,
-      "loss": 1.2905136108398438,
       "step": 520
     },
     {
-      "epoch": 1.2618351841028639,
-      "grad_norm": 1.1855460405349731,
-      "learning_rate": 0.0001440000234571087,
-      "loss": 1.1688365936279297,
       "step": 540
     },
     {
-      "epoch": 1.3085914669783751,
-      "grad_norm": 1.8180115222930908,
-      "learning_rate": 0.00013905224711747844,
-      "loss": 1.3730856895446777,
       "step": 560
     },
     {
-      "epoch": 1.3553477498538866,
-      "grad_norm": 0.9414753913879395,
-      "learning_rate": 0.00013398893015826167,
-      "loss": 1.1791135787963867,
       "step": 580
     },
     {
-      "epoch": 1.4021040327293979,
-      "grad_norm": 1.4354443550109863,
-      "learning_rate": 0.0001288250529921571,
-      "loss": 1.2642309188842773,
       "step": 600
     },
     {
-      "epoch": 1.4488603156049094,
-      "grad_norm": 1.1149160861968994,
-      "learning_rate": 0.00012357589355094275,
-      "loss": 1.2251626968383789,
       "step": 620
     },
     {
-      "epoch": 1.4956165984804208,
-      "grad_norm": 1.1424580812454224,
-      "learning_rate": 0.00011825698208393619,
-      "loss": 1.3191263198852539,
       "step": 640
     },
     {
-      "epoch": 1.542372881355932,
-      "grad_norm": 1.681731939315796,
-      "learning_rate": 0.0001128840552099439,
-      "loss": 1.2504265785217286,
       "step": 660
     },
     {
-      "epoch": 1.5891291642314436,
-      "grad_norm": 0.9838011264801025,
-      "learning_rate": 0.00010747300935864243,
-      "loss": 1.3022720336914062,
       "step": 680
     },
     {
-      "epoch": 1.635885447106955,
-      "grad_norm": 1.5329031944274902,
-      "learning_rate": 0.00010203985373914056,
-      "loss": 1.2638830184936523,
       "step": 700
     },
     {
-      "epoch": 1.6826417299824663,
-      "grad_norm": 1.5948340892791748,
-      "learning_rate": 9.660066297487022e-05,
-      "loss": 1.2015056610107422,
       "step": 720
     },
     {
-      "epoch": 1.7293980128579778,
-      "grad_norm": 1.5660204887390137,
-      "learning_rate": 9.117152954494194e-05,
-      "loss": 1.1331280708312987,
       "step": 740
     },
     {
-      "epoch": 1.7761542957334893,
-      "grad_norm": 1.4797639846801758,
-      "learning_rate": 8.57685161726715e-05,
-      "loss": 1.3372709274291992,
       "step": 760
     },
     {
-      "epoch": 1.8229105786090005,
-      "grad_norm": 1.4593443870544434,
-      "learning_rate": 8.040760830214333e-05,
-      "loss": 1.2525954246520996,
       "step": 780
     },
     {
-      "epoch": 1.869666861484512,
-      "grad_norm": 1.680131196975708,
-      "learning_rate": 7.510466680341301e-05,
-      "loss": 1.2918461799621581,
       "step": 800
     },
     {
-      "epoch": 1.9164231443600235,
-      "grad_norm": 1.698607325553894,
-      "learning_rate": 6.98753810462766e-05,
-      "loss": 1.221430206298828,
       "step": 820
     },
     {
-      "epoch": 1.9631794272355347,
-      "grad_norm": 1.3030081987380981,
-      "learning_rate": 6.47352224814436e-05,
-      "loss": 1.2619594573974608,
       "step": 840
     },
     {
-      "epoch": 2.009351256575102,
-      "grad_norm": 1.190048336982727,
-      "learning_rate": 5.969939886644884e-05,
-      "loss": 1.269164752960205,
       "step": 860
     },
     {
-      "epoch": 2.056107539450614,
-      "grad_norm": 1.8351762294769287,
-      "learning_rate": 5.478280927173145e-05,
-      "loss": 0.8597616195678711,
       "step": 880
     },
     {
-      "epoch": 2.102863822326125,
-      "grad_norm": 1.7225136756896973,
-      "learning_rate": 5.000000000000002e-05,
-      "loss": 0.8183969497680664,
       "step": 900
     },
     {
-      "epoch": 2.1496201052016364,
-      "grad_norm": 1.6294828653335571,
-      "learning_rate": 4.5365121549302914e-05,
-      "loss": 0.9339694976806641,
       "step": 920
     },
     {
-      "epoch": 2.196376388077148,
-      "grad_norm": 1.5743155479431152,
-      "learning_rate": 4.089188674713236e-05,
-      "loss": 0.8072254180908203,
       "step": 940
     },
     {
-      "epoch": 2.2431326709526593,
-      "grad_norm": 1.758355736732483,
-      "learning_rate": 3.6593530179427535e-05,
-      "loss": 0.9937071800231934,
       "step": 960
     },
     {
-      "epoch": 2.2898889538281706,
-      "grad_norm": 1.6887238025665283,
-      "learning_rate": 3.248276903451171e-05,
-      "loss": 0.8621444702148438,
       "step": 980
     },
     {
-      "epoch": 2.3366452367036823,
-      "grad_norm": 1.6778239011764526,
-      "learning_rate": 2.8571765477809643e-05,
-      "loss": 0.9298992156982422,
       "step": 1000
     },
     {
-      "epoch": 2.3834015195791936,
-      "grad_norm": 1.618106484413147,
-      "learning_rate": 2.487209066866565e-05,
-      "loss": 0.9818453788757324,
       "step": 1020
     },
     {
-      "epoch": 2.430157802454705,
-      "grad_norm": 1.5735318660736084,
-      "learning_rate": 2.139469052572127e-05,
-      "loss": 0.9037328720092773,
       "step": 1040
     },
     {
-      "epoch": 2.476914085330216,
-      "grad_norm": 1.780090093612671,
-      "learning_rate": 1.8149853342140645e-05,
-      "loss": 0.8262974739074707,
       "step": 1060
     },
     {
-      "epoch": 2.5236703682057278,
-      "grad_norm": 2.0739247798919678,
-      "learning_rate": 1.5147179346497664e-05,
-      "loss": 0.8792481422424316,
       "step": 1080
     },
     {
-      "epoch": 2.570426651081239,
-      "grad_norm": 1.351385235786438,
-      "learning_rate": 1.239555229938173e-05,
-      "loss": 0.8739164352416993,
       "step": 1100
     },
     {
-      "epoch": 2.6171829339567503,
-      "grad_norm": 1.5887919664382935,
-      "learning_rate": 9.903113209758096e-06,
-      "loss": 0.8695161819458008,
       "step": 1120
-    },
-    {
-      "epoch": 2.663939216832262,
-      "grad_norm": 1.5999833345413208,
-      "learning_rate": 7.677236248844855e-06,
-      "loss": 0.8116387367248535,
-      "step": 1140
-    },
-    {
-      "epoch": 2.7106954997077732,
-      "grad_norm": 2.1612422466278076,
-      "learning_rate": 5.724506932769014e-06,
-      "loss": 0.8531646728515625,
-      "step": 1160
-    },
-    {
-      "epoch": 2.7574517825832845,
-      "grad_norm": 1.3471204042434692,
-      "learning_rate": 4.050702638550275e-06,
-      "loss": 0.9993810653686523,
-      "step": 1180
-    },
-    {
-      "epoch": 2.8042080654587958,
-      "grad_norm": 1.716251015663147,
-      "learning_rate": 2.6607755110584887e-06,
-      "loss": 0.8893821716308594,
-      "step": 1200
-    },
-    {
-      "epoch": 2.8509643483343075,
-      "grad_norm": 2.210218667984009,
-      "learning_rate": 1.5588378115166669e-06,
-      "loss": 0.8101914405822754,
-      "step": 1220
-    },
-    {
-      "epoch": 2.8977206312098187,
-      "grad_norm": 2.0353686809539795,
-      "learning_rate": 7.481497508972312e-07,
-      "loss": 0.8651426315307618,
-      "step": 1240
-    },
-    {
-      "epoch": 2.94447691408533,
-      "grad_norm": 2.0257556438446045,
-      "learning_rate": 2.311098442083659e-07,
-      "loss": 0.8664233207702636,
-      "step": 1260
-    },
-    {
-      "epoch": 2.9912331969608417,
-      "grad_norm": 1.5078593492507935,
-      "learning_rate": 9.24781420816867e-09,
-      "loss": 0.8495323181152343,
-      "step": 1280
     }
   ],
   "logging_steps": 20,
-  "max_steps": 1284,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
@@ -475,7 +419,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5874974431944704e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
+  "global_step": 1137,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "epoch": 0.052805280528052806,
+      "grad_norm": 3.387005090713501,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 3.9786655426025392,
       "step": 20
     },
     {
+      "epoch": 0.10561056105610561,
+      "grad_norm": 1.8592948913574219,
+      "learning_rate": 6.842105263157895e-05,
+      "loss": 2.1792903900146485,
       "step": 40
     },
     {
+      "epoch": 0.15841584158415842,
+      "grad_norm": 1.2909832000732422,
+      "learning_rate": 0.00010350877192982457,
+      "loss": 1.5842592239379882,
       "step": 60
     },
     {
+      "epoch": 0.21122112211221122,
+      "grad_norm": 1.5900778770446777,
+      "learning_rate": 0.00013859649122807018,
+      "loss": 1.4694056510925293,
       "step": 80
     },
     {
+      "epoch": 0.264026402640264,
+      "grad_norm": 1.1479384899139404,
+      "learning_rate": 0.0001736842105263158,
+      "loss": 1.4147757530212401,
       "step": 100
     },
     {
+      "epoch": 0.31683168316831684,
+      "grad_norm": 1.1772419214248657,
+      "learning_rate": 0.000199988211733156,
+      "loss": 1.3961140632629394,
       "step": 120
     },
     {
+      "epoch": 0.3696369636963696,
+      "grad_norm": 1.2219910621643066,
+      "learning_rate": 0.00019970543226920288,
+      "loss": 1.3594454765319823,
       "step": 140
     },
     {
+      "epoch": 0.42244224422442245,
+      "grad_norm": 1.2809395790100098,
+      "learning_rate": 0.00019904665028066894,
+      "loss": 1.2906615257263183,
       "step": 160
     },
     {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 1.0857222080230713,
+      "learning_rate": 0.00019801435012257082,
+      "loss": 1.278927993774414,
       "step": 180
     },
     {
+      "epoch": 0.528052805280528,
+      "grad_norm": 1.1999471187591553,
+      "learning_rate": 0.00019661242473691508,
+      "loss": 1.2647177696228027,
       "step": 200
     },
     {
+      "epoch": 0.5808580858085809,
+      "grad_norm": 1.2492403984069824,
+      "learning_rate": 0.0001948461609718933,
+      "loss": 1.262906837463379,
       "step": 220
     },
     {
+      "epoch": 0.6336633663366337,
+      "grad_norm": 1.2875385284423828,
+      "learning_rate": 0.0001927222196444701,
+      "loss": 1.2704970359802246,
       "step": 240
     },
     {
+      "epoch": 0.6864686468646864,
+      "grad_norm": 1.1071441173553467,
+      "learning_rate": 0.0001902486104215513,
+      "loss": 1.2264627456665038,
       "step": 260
     },
     {
+      "epoch": 0.7392739273927392,
+      "grad_norm": 1.1471881866455078,
+      "learning_rate": 0.00018743466161445823,
+      "loss": 1.344072151184082,
       "step": 280
     },
     {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 1.3447649478912354,
+      "learning_rate": 0.00018429098500061798,
+      "loss": 1.2709327697753907,
       "step": 300
     },
     {
+      "epoch": 0.8448844884488449,
+      "grad_norm": 1.248130440711975,
+      "learning_rate": 0.00018082943580513083,
+      "loss": 1.1969389915466309,
       "step": 320
     },
     {
+      "epoch": 0.8976897689768977,
+      "grad_norm": 1.097252368927002,
+      "learning_rate": 0.00017706306799313026,
+      "loss": 1.1848082542419434,
       "step": 340
     },
     {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 1.4637950658798218,
+      "learning_rate": 0.00017300608504153405,
+      "loss": 1.1622210502624513,
       "step": 360
     },
     {
+      "epoch": 1.0026402640264027,
+      "grad_norm": 1.013732671737671,
+      "learning_rate": 0.00016867378637583252,
+      "loss": 1.1062444686889648,
       "step": 380
     },
     {
+      "epoch": 1.0554455445544555,
+      "grad_norm": 1.1227339506149292,
+      "learning_rate": 0.00016408250967390805,
+      "loss": 0.950930118560791,
       "step": 400
     },
     {
+      "epoch": 1.1082508250825083,
+      "grad_norm": 1.4735091924667358,
+      "learning_rate": 0.00015924956925446614,
+      "loss": 0.926474666595459,
       "step": 420
     },
     {
+      "epoch": 1.161056105610561,
+      "grad_norm": 1.264074444770813,
+      "learning_rate": 0.00015419319078242288,
+      "loss": 0.9251585006713867,
       "step": 440
     },
     {
+      "epoch": 1.2138613861386138,
+      "grad_norm": 1.78537917137146,
+      "learning_rate": 0.00014893244253748436,
+      "loss": 0.9181754112243652,
       "step": 460
     },
     {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 1.7237722873687744,
+      "learning_rate": 0.00014348716350511272,
+      "loss": 0.8821272850036621,
       "step": 480
     },
     {
+      "epoch": 1.3194719471947196,
+      "grad_norm": 1.561103105545044,
+      "learning_rate": 0.0001378778885610576,
+      "loss": 0.8810061454772949,
       "step": 500
     },
     {
+      "epoch": 1.3722772277227722,
+      "grad_norm": 0.8485727310180664,
+      "learning_rate": 0.00013212577103159258,
+      "loss": 0.8872846603393555,
       "step": 520
     },
     {
+      "epoch": 1.4250825082508252,
+      "grad_norm": 1.5448591709136963,
+      "learning_rate": 0.0001262525029214915,
+      "loss": 0.882346248626709,
       "step": 540
     },
     {
+      "epoch": 1.477887788778878,
+      "grad_norm": 1.4128762483596802,
+      "learning_rate": 0.00012028023311057641,
+      "loss": 0.9044669151306153,
       "step": 560
     },
     {
+      "epoch": 1.5306930693069307,
+      "grad_norm": 2.1570534706115723,
+      "learning_rate": 0.00011423148382732853,
+      "loss": 0.9163276672363281,
       "step": 580
     },
     {
+      "epoch": 1.5834983498349835,
+      "grad_norm": 1.7017725706100464,
+      "learning_rate": 0.00010812906571455128,
+      "loss": 0.8167492866516113,
       "step": 600
     },
     {
+      "epoch": 1.6363036303630363,
+      "grad_norm": 1.5086382627487183,
+      "learning_rate": 0.00010199599180738462,
+      "loss": 0.8773318290710449,
       "step": 620
     },
     {
+      "epoch": 1.689108910891089,
+      "grad_norm": 1.29973304271698,
+      "learning_rate": 9.585539074807047e-05,
+      "loss": 0.9067516326904297,
       "step": 640
     },
     {
+      "epoch": 1.7419141914191418,
+      "grad_norm": 1.2764034271240234,
+      "learning_rate": 8.973041956474861e-05,
+      "loss": 0.8765406608581543,
       "step": 660
     },
     {
+      "epoch": 1.7947194719471948,
+      "grad_norm": 1.8195858001708984,
+      "learning_rate": 8.364417634320538e-05,
+      "loss": 0.879486083984375,
       "step": 680
     },
     {
+      "epoch": 1.8475247524752474,
+      "grad_norm": 1.3113222122192383,
+      "learning_rate": 7.761961312090174e-05,
+      "loss": 0.9121587753295899,
       "step": 700
     },
     {
+      "epoch": 1.9003300330033004,
+      "grad_norm": 1.0956863164901733,
+      "learning_rate": 7.16794493317696e-05,
+      "loss": 0.8715014457702637,
       "step": 720
     },
     {
+      "epoch": 1.9531353135313532,
+      "grad_norm": 1.7764663696289062,
+      "learning_rate": 6.584608612818651e-05,
+      "loss": 0.8537203788757324,
       "step": 740
     },
     {
+      "epoch": 2.0052805280528054,
+      "grad_norm": 1.2446659803390503,
+      "learning_rate": 6.0141521903233235e-05,
+      "loss": 0.8911971092224121,
       "step": 760
     },
     {
+      "epoch": 2.058085808580858,
+      "grad_norm": 1.6061584949493408,
+      "learning_rate": 5.458726933181022e-05,
+      "loss": 0.6473441600799561,
       "step": 780
     },
     {
+      "epoch": 2.110891089108911,
+      "grad_norm": 1.5538922548294067,
+      "learning_rate": 4.920427424346239e-05,
+      "loss": 0.5273653507232666,
       "step": 800
     },
     {
+      "epoch": 2.1636963696369635,
+      "grad_norm": 1.59296452999115,
+      "learning_rate": 4.401283663285355e-05,
+      "loss": 0.5859078884124755,
       "step": 820
     },
     {
+      "epoch": 2.2165016501650165,
+      "grad_norm": 1.875257134437561,
+      "learning_rate": 3.903253410577088e-05,
+      "loss": 0.5635562896728515,
       "step": 840
     },
     {
+      "epoch": 2.2693069306930695,
+      "grad_norm": 1.8543015718460083,
+      "learning_rate": 3.4282148049353824e-05,
+      "loss": 0.5485569477081299,
       "step": 860
     },
     {
+      "epoch": 2.322112211221122,
+      "grad_norm": 0.991675615310669,
+      "learning_rate": 2.977959280497068e-05,
+      "loss": 0.5272461891174316,
       "step": 880
     },
     {
+      "epoch": 2.374917491749175,
+      "grad_norm": 1.6339776515960693,
+      "learning_rate": 2.5541848110840517e-05,
+      "loss": 0.5180594444274902,
       "step": 900
     },
     {
+      "epoch": 2.4277227722772277,
+      "grad_norm": 1.5920040607452393,
+      "learning_rate": 2.158489506916874e-05,
+      "loss": 0.592043399810791,
       "step": 920
     },
     {
+      "epoch": 2.4805280528052807,
+      "grad_norm": 1.6994235515594482,
+      "learning_rate": 1.7923655879272393e-05,
+      "loss": 0.5419695854187012,
       "step": 940
     },
     {
+      "epoch": 2.533333333333333,
+      "grad_norm": 2.0405519008636475,
+      "learning_rate": 1.4571937563970184e-05,
+      "loss": 0.5323679924011231,
       "step": 960
     },
     {
+      "epoch": 2.586138613861386,
+      "grad_norm": 1.509047508239746,
+      "learning_rate": 1.1542379901452382e-05,
+      "loss": 0.5415875911712646,
       "step": 980
     },
     {
+      "epoch": 2.638943894389439,
+      "grad_norm": 2.0958621501922607,
+      "learning_rate": 8.846407758985886e-06,
+      "loss": 0.5498926639556885,
       "step": 1000
     },
     {
+      "epoch": 2.6917491749174918,
+      "grad_norm": 1.9577443599700928,
+      "learning_rate": 6.494188008211432e-06,
+      "loss": 0.6058428764343262,
       "step": 1020
     },
     {
+      "epoch": 2.7445544554455443,
+      "grad_norm": 1.9752472639083862,
+      "learning_rate": 4.4945911845104326e-06,
+      "loss": 0.5456490516662598,
       "step": 1040
     },
     {
+      "epoch": 2.7973597359735973,
+      "grad_norm": 1.4467875957489014,
+      "learning_rate": 2.8551580350291817e-06,
+      "loss": 0.5644352436065674,
       "step": 1060
     },
     {
+      "epoch": 2.8501650165016503,
+      "grad_norm": 1.31772780418396,
+      "learning_rate": 1.5820710815125484e-06,
+      "loss": 0.5065171718597412,
       "step": 1080
     },
     {
+      "epoch": 2.902970297029703,
+      "grad_norm": 1.9897189140319824,
+      "learning_rate": 6.801313051873259e-07,
+      "loss": 0.5483640670776367,
       "step": 1100
     },
     {
+      "epoch": 2.955775577557756,
+      "grad_norm": 1.9058332443237305,
+      "learning_rate": 1.5274004161970335e-07,
+      "loss": 0.5132439613342286,
       "step": 1120
     }
   ],
   "logging_steps": 20,
+  "max_steps": 1137,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
       "attributes": {}
     }
   },
+  "total_flos": 9020460442411008.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:06ad98e5b9349d4cbdb048c769849a56d4fee9f9738d509cc3b909c9c324141f
+size 5048