Training in progress, epoch 1

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: google/medgemma-4b-it
 library_name: transformers
 model_name: medgemma-4b-it-sft-lora-crc100k
 tags:
@@ -10,7 +11,7 @@ licence: license
 
 # Model Card for medgemma-4b-it-sft-lora-crc100k
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [google/medgemma-4b-it](https://huggingface.co/google/medgemma-4b-it).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -33,11 +34,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.18.1
+- TRL: 0.19.0
 - Transformers: 4.52.4
-- Pytorch: 2.7.0
+- Pytorch: 2.6.0+cu124
 - Datasets: 3.6.0
-- Tokenizers: 0.21.1
+- Tokenizers: 0.21.2
 
 ## Citations
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/nas203/ds_OpenData/medgemma/google/medgemma-4b-it",
+  "base_model_name_or_path": "google/medgemma-4b-it",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -28,15 +28,15 @@
   "revision": null,
   "target_modules": [
     "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
     "fc2",
-    "up_proj",
+    "fc1",
     "o_proj",
-    "down_proj",
-    "q_proj",
     "out_proj",
-    "v_proj",
-    "gate_proj",
-    "fc1"
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523e3e9d34c91128f8d7f71ef36d719a4a0618be72589a913017025097fadea8
+oid sha256:f2aa6d9d80e6e8d337d1c82909c4bc06ff5532e43dede28a510f2575e6d40074
 size 2839126480

runs/Jun27_14-32-05_431b06825272/events.out.tfevents.1751002327.431b06825272.260866.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3484720b25e134d2531eddb9473a20bca6637f42805f7b52d7b273f9f8b31c2d
+size 6963

runs/Jun27_14-36-44_431b06825272/events.out.tfevents.1751002606.431b06825272.267118.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e719fe497962d58f03cf16cd2e6550460fd3a205983920cabb254478d4e03ba9
+size 11000

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38dee7a9b2ffb9113573ba497cbdfecaf07f77e8f12568314d6dbf26bb745af9
-size 6097
+oid sha256:87d801503808ad5877b556b54a0a9c949be6cf97f6b25b5cfeab13c65d00d638
+size 5752