End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: microsoft/Phi-3-mini-4k-instruct
+base_model: google/gemma-3-1b-pt
 library_name: transformers
 model_name: phi3-mini-SAMbot
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for phi3-mini-SAMbot
 
-This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
+This model is a fine-tuned version of [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -34,10 +34,10 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.16.0
-- Transformers: 4.50.0
+- TRL: 0.15.2
+- Transformers: 4.50.0.dev0
 - Pytorch: 2.6.0+cu124
-- Datasets: 3.5.0
+- Datasets: 3.3.2
 - Tokenizers: 0.21.1
 
 ## Citations

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "base_model_name_or_path": "google/gemma-3-1b-pt",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "o_proj",
-    "qkv_proj",
-    "gate_up_proj"
+    "gate_up_proj",
+    "down_proj",
+    "qkv_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c37ef470254545070a6557781333d10e0a35469507b5c5a48a577411b20234d
-size 62948960
+oid sha256:75e42c5c84fde95588a513f3dac097e7dc01a8d4bcd2f0e794db60b68fe36fc5
+size 10663272

added_tokens.json

@@ -1,13 +1,3 @@
 {
-  "<|assistant|>": 32001,
-  "<|endoftext|>": 32000,
-  "<|end|>": 32007,
-  "<|placeholder1|>": 32002,
-  "<|placeholder2|>": 32003,
-  "<|placeholder3|>": 32004,
-  "<|placeholder4|>": 32005,
-  "<|placeholder5|>": 32008,
-  "<|placeholder6|>": 32009,
-  "<|system|>": 32006,
-  "<|user|>": 32010
+  "<image_soft_token>": 262144
 }

special_tokens_map.json

@@ -1,20 +1,23 @@
 {
+  "boi_token": "<start_of_image>",
   "bos_token": {
-    "content": "<s>",
+    "content": "<bos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "eoi_token": "<end_of_image>",
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<eos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "image_token": "<image_soft_token>",
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6064f9beb06153ff16b06b7e93115092fbd119e1b8e789e20a80cfb89e8fff4
+oid sha256:f596bfdfb6093cb53d1a5deffcc6063f36e1172b2de027ca0b706e06b77fc92f
 size 5560