End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: AdaptLLM/biomed-Qwen2-VL-2B-Instruct
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: qwenvl-2B-cadica-stenosis-classify-scale4-frozenVision
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwenvl-2B-cadica-stenosis-classify-scale4-frozenVision
 
-This model is a fine-tuned version of [AdaptLLM/biomed-Qwen2-VL-2B-Instruct](https://huggingface.co/AdaptLLM/biomed-Qwen2-VL-2B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [AdaptLLM/biomed-Qwen2-VL-2B-Instruct](https://huggingface.co/AdaptLLM/biomed-Qwen2-VL-2B-Instruct) on the CADICA狹窄分析選擇題scale4(TRAIN) dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8603
+- Loss: 0.6319
 - Num Input Tokens Seen: 39760664
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.750965748132887,
+    "eval_loss": 0.6319106221199036,
+    "eval_runtime": 16.1571,
+    "eval_samples_per_second": 3.714,
+    "eval_steps_per_second": 0.928,
+    "num_input_tokens_seen": 39760664,
+    "total_flos": 2232757993603072.0,
+    "train_loss": 0.5904174627801951,
+    "train_runtime": 45337.3565,
+    "train_samples_per_second": 1.8,
+    "train_steps_per_second": 0.075
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.750965748132887,
+    "eval_loss": 0.6319106221199036,
+    "eval_runtime": 16.1571,
+    "eval_samples_per_second": 3.714,
+    "eval_steps_per_second": 0.928,
+    "num_input_tokens_seen": 39760664
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.750965748132887,
+    "num_input_tokens_seen": 39760664,
+    "total_flos": 2232757993603072.0,
+    "train_loss": 0.5904174627801951,
+    "train_runtime": 45337.3565,
+    "train_samples_per_second": 1.8,
+    "train_steps_per_second": 0.075
+}