Instructions to use neopolita/doc-to-lora-ministral-3b-2512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neopolita/doc-to-lora-ministral-3b-2512 with Transformers:

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

pipe = pipeline("text-generation", model="neopolita/doc-to-lora-ministral-3b-2512")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("neopolita/doc-to-lora-ministral-3b-2512", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use neopolita/doc-to-lora-ministral-3b-2512 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neopolita/doc-to-lora-ministral-3b-2512"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neopolita/doc-to-lora-ministral-3b-2512",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/neopolita/doc-to-lora-ministral-3b-2512

SGLang

How to use neopolita/doc-to-lora-ministral-3b-2512 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 "neopolita/doc-to-lora-ministral-3b-2512" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neopolita/doc-to-lora-ministral-3b-2512",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "neopolita/doc-to-lora-ministral-3b-2512" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neopolita/doc-to-lora-ministral-3b-2512",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use neopolita/doc-to-lora-ministral-3b-2512 with Docker Model Runner:
```
docker model run hf.co/neopolita/doc-to-lora-ministral-3b-2512
```

neopolita commited on Mar 1

Commit

9406ffb

verified ·

1 Parent(s): 8cd1c11

Checkpoint at step 1000

Browse files

Files changed (11) hide show

checkpoint-1000/optimizer.pt +3 -0
checkpoint-1000/pytorch_model.bin +3 -0
checkpoint-1000/rng_state_0.pth +3 -0
checkpoint-1000/rng_state_1.pth +3 -0
checkpoint-1000/rng_state_2.pth +3 -0
checkpoint-1000/rng_state_3.pth +3 -0
checkpoint-1000/scheduler.pt +3 -0
checkpoint-1000/trainer_state.json +639 -0
checkpoint-1000/training_args.bin +3 -0
debug.log +7 -0
events.out.tfevents.1772350684.j-neopolita-69a3e406dfb316ac3f7c0a80-tuu1470p-784b1-cr29x.5286.0 +2 -2

checkpoint-1000/optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:38c4b193bdd744aff64353e7e9263b332f36620ce07a2571b2c70e3f7feaf3ee
+size 2881913146

checkpoint-1000/pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0b6fa713b9529f34ac322b1a72c3138b071017eb2b8dc8c48b2dd8fe179aa8
+size 1440963006

checkpoint-1000/rng_state_0.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0113c0bbf4f20ac5d2edfff2cdecb94bb9c0ac562021e7fd2e0297d603823b2
+size 15024

checkpoint-1000/rng_state_1.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e566a9c453b4872ed323c3ee9a3f18b450aff6e34ee867bd8fbeaad5298b286d
+size 15024

checkpoint-1000/rng_state_2.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3d776d66cb03536bc3e41cd28dfcf6ff2f809d1827558d658aef3f1e3293e763
+size 15024

checkpoint-1000/rng_state_3.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:76a0a2e56563f5750fab6c25a440019cdc9d9748714d076980a410b7ab119a4e
+size 15024

checkpoint-1000/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1179561b0b6f289b022cbea82305ad1b768b9b24382e4797ad4e91a448e5efa
+size 1064

checkpoint-1000/trainer_state.json ADDED Viewed

	@@ -0,0 +1,639 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.081925243215566,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "gen_lora_l1_norm": 0.0009450324578210711,
+      "kl_loss": 1.9670246839523315,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "gen_lora_l1_norm": 0.0008100018021650612,
+      "kl_loss": 1.4670418500900269,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "gen_lora_l1_norm": 0.0006749311578460038,
+      "kl_loss": 1.3484277725219727,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "gen_lora_l1_norm": 0.000944959232583642,
+      "kl_loss": 1.4987092018127441,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "gen_lora_l1_norm": 0.0006748694577254355,
+      "kl_loss": 1.4152668714523315,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "gen_lora_l1_norm": 0.0012147949310019612,
+      "kl_loss": 2.2377562522888184,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "gen_lora_l1_norm": 0.001215127413161099,
+      "kl_loss": 2.319751501083374,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "gen_lora_l1_norm": 0.0009449576027691364,
+      "kl_loss": 1.9499444961547852,
+      "step": 0
+    },
+    {
+      "epoch": 0.00409626216077829,
+      "grad_norm": 5.8849639892578125,
+      "learning_rate": 0.0,
+      "loss": 1.6322,
+      "step": 1
+    },
+    {
+      "epoch": 0.00409626216077829,
+      "gen_lora_l1_norm": 0.0006627951515838504,
+      "kl_loss": 0.882428765296936,
+      "step": 1
+    },
+    {
+      "epoch": 0.00409626216077829,
+      "gen_lora_l1_norm": 0.0010608765296638012,
+      "kl_loss": 1.6865953207015991,
+      "step": 1
+    },
+    {
+      "epoch": 0.00409626216077829,
+      "gen_lora_l1_norm": 0.0010608312441036105,
+      "kl_loss": 2.0317649841308594,
+      "step": 1
+    },
+    {
+      "epoch": 0.00409626216077829,
+      "gen_lora_l1_norm": 0.0006628527189604938,
+      "kl_loss": 1.4127317667007446,
+      "step": 1
+    },
+    {
+      "epoch": 0.00409626216077829,
+      "gen_lora_l1_norm": 0.0007955919136293232,
+      "kl_loss": 1.2892097234725952,
+      "step": 1
+    },
+    {
+      "epoch": 0.00409626216077829,
+      "gen_lora_l1_norm": 0.0011936043156310916,
+      "kl_loss": 2.073559045791626,
+      "step": 1
+    },
+    {
+      "epoch": 0.00409626216077829,
+      "gen_lora_l1_norm": 0.0011929516913369298,
+      "kl_loss": 2.040735960006714,
+      "step": 1
+    },
+    {
+      "epoch": 0.00409626216077829,
+      "gen_lora_l1_norm": 0.000795479747466743,
+      "kl_loss": 1.4581172466278076,
+      "step": 1
+    },
+    {
+      "epoch": 0.409626216077829,
+      "grad_norm": 1.5062122344970703,
+      "learning_rate": 3.96e-05,
+      "loss": 1.3549,
+      "step": 100
+    },
+    {
+      "epoch": 0.409626216077829,
+      "gen_lora_l1_norm": 0.0024223378859460354,
+      "kl_loss": 1.1542384624481201,
+      "step": 100
+    },
+    {
+      "epoch": 0.409626216077829,
+      "gen_lora_l1_norm": 0.003727049333974719,
+      "kl_loss": 1.4517877101898193,
+      "step": 100
+    },
+    {
+      "epoch": 0.409626216077829,
+      "gen_lora_l1_norm": 0.0023780318442732096,
+      "kl_loss": 1.0488699674606323,
+      "step": 100
+    },
+    {
+      "epoch": 0.409626216077829,
+      "gen_lora_l1_norm": 0.002320361090824008,
+      "kl_loss": 0.9093623161315918,
+      "step": 100
+    },
+    {
+      "epoch": 0.409626216077829,
+      "gen_lora_l1_norm": 0.0022675672080367804,
+      "kl_loss": 1.0960808992385864,
+      "step": 100
+    },
+    {
+      "epoch": 0.409626216077829,
+      "gen_lora_l1_norm": 0.003854497103020549,
+      "kl_loss": 1.54759681224823,
+      "step": 100
+    },
+    {
+      "epoch": 0.409626216077829,
+      "gen_lora_l1_norm": 0.0023134942166507244,
+      "kl_loss": 1.0374772548675537,
+      "step": 100
+    },
+    {
+      "epoch": 0.409626216077829,
+      "gen_lora_l1_norm": 0.002758321352303028,
+      "kl_loss": 1.3237308263778687,
+      "step": 100
+    },
+    {
+      "epoch": 0.819252432155658,
+      "grad_norm": 0.8856369256973267,
+      "learning_rate": 3.993659497980699e-05,
+      "loss": 1.1874,
+      "step": 200
+    },
+    {
+      "epoch": 0.819252432155658,
+      "gen_lora_l1_norm": 0.003160437336191535,
+      "kl_loss": 1.0348540544509888,
+      "step": 200
+    },
+    {
+      "epoch": 0.819252432155658,
+      "gen_lora_l1_norm": 0.005650285631418228,
+      "kl_loss": 1.4363867044448853,
+      "step": 200
+    },
+    {
+      "epoch": 0.819252432155658,
+      "gen_lora_l1_norm": 0.0029608134645968676,
+      "kl_loss": 1.00709867477417,
+      "step": 200
+    },
+    {
+      "epoch": 0.819252432155658,
+      "gen_lora_l1_norm": 0.0032552958000451326,
+      "kl_loss": 0.9060482978820801,
+      "step": 200
+    },
+    {
+      "epoch": 0.819252432155658,
+      "gen_lora_l1_norm": 0.003243665909394622,
+      "kl_loss": 1.1517314910888672,
+      "step": 200
+    },
+    {
+      "epoch": 0.819252432155658,
+      "gen_lora_l1_norm": 0.0019695493392646313,
+      "kl_loss": 0.7201811671257019,
+      "step": 200
+    },
+    {
+      "epoch": 0.819252432155658,
+      "gen_lora_l1_norm": 0.00634480407461524,
+      "kl_loss": 1.8689466714859009,
+      "step": 200
+    },
+    {
+      "epoch": 0.819252432155658,
+      "gen_lora_l1_norm": 0.003726382739841938,
+      "kl_loss": 1.060623288154602,
+      "step": 200
+    },
+    {
+      "epoch": 1.2252944188428059,
+      "grad_norm": 0.9404332637786865,
+      "learning_rate": 3.974422423272462e-05,
+      "loss": 1.1436,
+      "step": 300
+    },
+    {
+      "epoch": 1.2252944188428059,
+      "gen_lora_l1_norm": 0.0036873684730380774,
+      "kl_loss": 0.8932405710220337,
+      "step": 300
+    },
+    {
+      "epoch": 1.2252944188428059,
+      "gen_lora_l1_norm": 0.0060583981685340405,
+      "kl_loss": 1.7955601215362549,
+      "step": 300
+    },
+    {
+      "epoch": 1.2252944188428059,
+      "gen_lora_l1_norm": 0.0036672591231763363,
+      "kl_loss": 0.9144486784934998,
+      "step": 300
+    },
+    {
+      "epoch": 1.2252944188428059,
+      "gen_lora_l1_norm": 0.0036556844133883715,
+      "kl_loss": 1.1638795137405396,
+      "step": 300
+    },
+    {
+      "epoch": 1.2252944188428059,
+      "gen_lora_l1_norm": 0.0037340312264859676,
+      "kl_loss": 1.0955017805099487,
+      "step": 300
+    },
+    {
+      "epoch": 1.2252944188428059,
+      "gen_lora_l1_norm": 0.0036459672264754772,
+      "kl_loss": 1.0169063806533813,
+      "step": 300
+    },
+    {
+      "epoch": 1.2252944188428059,
+      "gen_lora_l1_norm": 0.00370018114335835,
+      "kl_loss": 0.9743473529815674,
+      "step": 300
+    },
+    {
+      "epoch": 1.2252944188428059,
+      "gen_lora_l1_norm": 0.006841503549367189,
+      "kl_loss": 1.3890433311462402,
+      "step": 300
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "grad_norm": 0.9483956694602966,
+      "learning_rate": 3.942412888419724e-05,
+      "loss": 1.1035,
+      "step": 400
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "gen_lora_l1_norm": 0.004309813026338816,
+      "kl_loss": 0.96443772315979,
+      "step": 400
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "gen_lora_l1_norm": 0.006539575755596161,
+      "kl_loss": 1.54787278175354,
+      "step": 400
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "gen_lora_l1_norm": 0.004349768161773682,
+      "kl_loss": 1.1423686742782593,
+      "step": 400
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "gen_lora_l1_norm": 0.005183862056583166,
+      "kl_loss": 1.3069700002670288,
+      "step": 400
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "gen_lora_l1_norm": 0.004366028122603893,
+      "kl_loss": 0.9700032472610474,
+      "step": 400
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "gen_lora_l1_norm": 0.004371432587504387,
+      "kl_loss": 0.8293535113334656,
+      "step": 400
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "gen_lora_l1_norm": 0.0036595307756215334,
+      "kl_loss": 1.2910619974136353,
+      "step": 400
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "gen_lora_l1_norm": 0.004372357856482267,
+      "kl_loss": 0.9109727740287781,
+      "step": 400
+    },
+    {
+      "epoch": 2.040962621607783,
+      "grad_norm": 0.913838803768158,
+      "learning_rate": 3.8978384875390766e-05,
+      "loss": 1.0673,
+      "step": 500
+    },
+    {
+      "epoch": 2.040962621607783,
+      "gen_lora_l1_norm": 0.00400135712698102,
+      "kl_loss": 0.7898850440979004,
+      "step": 500
+    },
+    {
+      "epoch": 2.040962621607783,
+      "gen_lora_l1_norm": 0.00573880085721612,
+      "kl_loss": 1.0935029983520508,
+      "step": 500
+    },
+    {
+      "epoch": 2.040962621607783,
+      "gen_lora_l1_norm": 0.004075320437550545,
+      "kl_loss": 0.7592037916183472,
+      "step": 500
+    },
+    {
+      "epoch": 2.040962621607783,
+      "gen_lora_l1_norm": 0.007495749741792679,
+      "kl_loss": 1.3880740404129028,
+      "step": 500
+    },
+    {
+      "epoch": 2.040962621607783,
+      "gen_lora_l1_norm": 0.0047694905661046505,
+      "kl_loss": 0.9538154602050781,
+      "step": 500
+    },
+    {
+      "epoch": 2.040962621607783,
+      "gen_lora_l1_norm": 0.004024278372526169,
+      "kl_loss": 1.0414124727249146,
+      "step": 500
+    },
+    {
+      "epoch": 2.040962621607783,
+      "gen_lora_l1_norm": 0.005740255583077669,
+      "kl_loss": 1.3348419666290283,
+      "step": 500
+    },
+    {
+      "epoch": 2.040962621607783,
+      "gen_lora_l1_norm": 0.004882144276052713,
+      "kl_loss": 1.056125283241272,
+      "step": 500
+    },
+    {
+      "epoch": 2.4505888376856118,
+      "grad_norm": 0.9659350514411926,
+      "learning_rate": 3.840988302724834e-05,
+      "loss": 1.0139,
+      "step": 600
+    },
+    {
+      "epoch": 2.4505888376856118,
+      "gen_lora_l1_norm": 0.005276651121675968,
+      "kl_loss": 1.2098764181137085,
+      "step": 600
+    },
+    {
+      "epoch": 2.4505888376856118,
+      "gen_lora_l1_norm": 0.005354944616556168,
+      "kl_loss": 1.2536226511001587,
+      "step": 600
+    },
+    {
+      "epoch": 2.4505888376856118,
+      "gen_lora_l1_norm": 0.006087795365601778,
+      "kl_loss": 1.4725929498672485,
+      "step": 600
+    },
+    {
+      "epoch": 2.4505888376856118,
+      "gen_lora_l1_norm": 0.004386508837342262,
+      "kl_loss": 0.6955914497375488,
+      "step": 600
+    },
+    {
+      "epoch": 2.4505888376856118,
+      "gen_lora_l1_norm": 0.006141394842416048,
+      "kl_loss": 1.1263651847839355,
+      "step": 600
+    },
+    {
+      "epoch": 2.4505888376856118,
+      "gen_lora_l1_norm": 0.0034647039137780666,
+      "kl_loss": 0.9702500700950623,
+      "step": 600
+    },
+    {
+      "epoch": 2.4505888376856118,
+      "gen_lora_l1_norm": 0.005230437032878399,
+      "kl_loss": 1.1107494831085205,
+      "step": 600
+    },
+    {
+      "epoch": 2.4505888376856118,
+      "gen_lora_l1_norm": 0.0052700042724609375,
+      "kl_loss": 0.9291554689407349,
+      "step": 600
+    },
+    {
+      "epoch": 2.860215053763441,
+      "grad_norm": 0.8220306038856506,
+      "learning_rate": 3.772231029240728e-05,
+      "loss": 1.0036,
+      "step": 700
+    },
+    {
+      "epoch": 2.860215053763441,
+      "gen_lora_l1_norm": 0.006512848194688559,
+      "kl_loss": 1.1565109491348267,
+      "step": 700
+    },
+    {
+      "epoch": 2.860215053763441,
+      "gen_lora_l1_norm": 0.00398235023021698,
+      "kl_loss": 0.7244017124176025,
+      "step": 700
+    },
+    {
+      "epoch": 2.860215053763441,
+      "gen_lora_l1_norm": 0.003980782348662615,
+      "kl_loss": 0.7359597086906433,
+      "step": 700
+    },
+    {
+      "epoch": 2.860215053763441,
+      "gen_lora_l1_norm": 0.006494825705885887,
+      "kl_loss": 1.1472868919372559,
+      "step": 700
+    },
+    {
+      "epoch": 2.860215053763441,
+      "gen_lora_l1_norm": 0.004660531412810087,
+      "kl_loss": 0.7635590434074402,
+      "step": 700
+    },
+    {
+      "epoch": 2.860215053763441,
+      "gen_lora_l1_norm": 0.005749559495598078,
+      "kl_loss": 0.9587411880493164,
+      "step": 700
+    },
+    {
+      "epoch": 2.860215053763441,
+      "gen_lora_l1_norm": 0.0039028008468449116,
+      "kl_loss": 0.5627914071083069,
+      "step": 700
+    },
+    {
+      "epoch": 2.860215053763441,
+      "gen_lora_l1_norm": 0.007235225290060043,
+      "kl_loss": 1.289211630821228,
+      "step": 700
+    },
+    {
+      "epoch": 3.266257040450589,
+      "grad_norm": 0.9872245788574219,
+      "learning_rate": 3.692012584389641e-05,
+      "loss": 0.9615,
+      "step": 800
+    },
+    {
+      "epoch": 3.266257040450589,
+      "gen_lora_l1_norm": 0.005679607857018709,
+      "kl_loss": 0.8019008040428162,
+      "step": 800
+    },
+    {
+      "epoch": 3.266257040450589,
+      "gen_lora_l1_norm": 0.00867470819503069,
+      "kl_loss": 1.5495558977127075,
+      "step": 800
+    },
+    {
+      "epoch": 3.266257040450589,
+      "gen_lora_l1_norm": 0.00566524313762784,
+      "kl_loss": 0.9215335249900818,
+      "step": 800
+    },
+    {
+      "epoch": 3.266257040450589,
+      "gen_lora_l1_norm": 0.005784123670309782,
+      "kl_loss": 1.0987138748168945,
+      "step": 800
+    },
+    {
+      "epoch": 3.266257040450589,
+      "gen_lora_l1_norm": 0.004819593392312527,
+      "kl_loss": 0.9064775705337524,
+      "step": 800
+    },
+    {
+      "epoch": 3.266257040450589,
+      "gen_lora_l1_norm": 0.004847296047955751,
+      "kl_loss": 0.8540226221084595,
+      "step": 800
+    },
+    {
+      "epoch": 3.266257040450589,
+      "gen_lora_l1_norm": 0.0028415124397724867,
+      "kl_loss": 0.5352403521537781,
+      "step": 800
+    },
+    {
+      "epoch": 3.266257040450589,
+      "gen_lora_l1_norm": 0.005715073551982641,
+      "kl_loss": 0.9670476317405701,
+      "step": 800
+    },
+    {
+      "epoch": 3.675883256528418,
+      "grad_norm": 0.8288973569869995,
+      "learning_rate": 3.600853215568783e-05,
+      "loss": 0.943,
+      "step": 900
+    },
+    {
+      "epoch": 3.675883256528418,
+      "gen_lora_l1_norm": 0.005058944225311279,
+      "kl_loss": 0.8599977493286133,
+      "step": 900
+    },
+    {
+      "epoch": 3.675883256528418,
+      "gen_lora_l1_norm": 0.003312613582238555,
+      "kl_loss": 0.5305082201957703,
+      "step": 900
+    },
+    {
+      "epoch": 3.675883256528418,
+      "gen_lora_l1_norm": 0.004963682033121586,
+      "kl_loss": 0.8053346872329712,
+      "step": 900
+    },
+    {
+      "epoch": 3.675883256528418,
+      "gen_lora_l1_norm": 0.008336002007126808,
+      "kl_loss": 1.3062776327133179,
+      "step": 900
+    },
+    {
+      "epoch": 3.675883256528418,
+      "gen_lora_l1_norm": 0.003407533746212721,
+      "kl_loss": 0.5421016812324524,
+      "step": 900
+    },
+    {
+      "epoch": 3.675883256528418,
+      "gen_lora_l1_norm": 0.005902859847992659,
+      "kl_loss": 0.8554947376251221,
+      "step": 900
+    },
+    {
+      "epoch": 3.675883256528418,
+      "gen_lora_l1_norm": 0.006641158368438482,
+      "kl_loss": 1.0285379886627197,
+      "step": 900
+    },
+    {
+      "epoch": 3.675883256528418,
+      "gen_lora_l1_norm": 0.006653614342212677,
+      "kl_loss": 1.1064549684524536,
+      "step": 900
+    },
+    {
+      "epoch": 4.081925243215566,
+      "grad_norm": 0.8488938212394714,
+      "learning_rate": 3.4993441262656855e-05,
+      "loss": 0.9306,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 17,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:82bfa23cfa703dfd984caf3ec0567ad70c88e206a8ae4381d28bfed0bd0da4d0
+size 5496

debug.log CHANGED Viewed

@@ -2839,3 +2839,10 @@ Device: cuda:3
 2026-03-01 09:08:23 DEBUG: https://huggingface.co:443 "POST /api/models/neopolita/doc-to-lora-ministral-3b-2512/preupload/main HTTP/1.1" 200 4127
 2026-03-01 09:08:23 DEBUG: https://huggingface.co:443 "GET /api/models/neopolita/doc-to-lora-ministral-3b-2512/revision/main?expand=xetEnabled HTTP/1.1" 200 99
 2026-03-01 09:08:23 DEBUG: https://huggingface.co:443 "GET /api/models/neopolita/doc-to-lora-ministral-3b-2512/xet-write-token/main HTTP/1.1" 200 386

 2026-03-01 09:08:23 DEBUG: https://huggingface.co:443 "POST /api/models/neopolita/doc-to-lora-ministral-3b-2512/preupload/main HTTP/1.1" 200 4127
 2026-03-01 09:08:23 DEBUG: https://huggingface.co:443 "GET /api/models/neopolita/doc-to-lora-ministral-3b-2512/revision/main?expand=xetEnabled HTTP/1.1" 200 99
 2026-03-01 09:08:23 DEBUG: https://huggingface.co:443 "GET /api/models/neopolita/doc-to-lora-ministral-3b-2512/xet-write-token/main HTTP/1.1" 200 386
+2026-03-01 09:08:40 DEBUG: https://huggingface.co:443 "POST /api/models/neopolita/doc-to-lora-ministral-3b-2512/commit/main HTTP/1.1" 200 212
+2026-03-01 09:08:40 INFO: Checkpoint uploaded to https://huggingface.co/neopolita/doc-to-lora-ministral-3b-2512
+2026-03-01 09:38:09 INFO: Uploading checkpoint at step 1000 to neopolita/doc-to-lora-ministral-3b-2512...
+2026-03-01 09:38:49 DEBUG: Resetting dropped connection: huggingface.co
+2026-03-01 09:38:49 DEBUG: https://huggingface.co:443 "POST /api/models/neopolita/doc-to-lora-ministral-3b-2512/preupload/main HTTP/1.1" 200 5512
+2026-03-01 09:38:49 DEBUG: https://huggingface.co:443 "GET /api/models/neopolita/doc-to-lora-ministral-3b-2512/revision/main?expand=xetEnabled HTTP/1.1" 200 99
+2026-03-01 09:38:49 DEBUG: https://huggingface.co:443 "GET /api/models/neopolita/doc-to-lora-ministral-3b-2512/xet-write-token/main HTTP/1.1" 200 386

events.out.tfevents.1772350684.j-neopolita-69a3e406dfb316ac3f7c0a80-tuu1470p-784b1-cr29x.5286.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c61af00e3414f2d6fdb9e0e11814a0be35a0ae9e40be700a0a51ccf446bce215
-size 18836

 version https://git-lfs.github.com/spec/v1
+oid sha256:f987697e07c09870e5cdf9a5a3e84506fa2c9b6870effa5dc0e693d7c801a872
+size 22077