Model save

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: Qwen/Qwen2.5-7B-Instruct
 library_name: transformers
 model_name: PreThink_MemAgent
 tags:
@@ -11,7 +10,7 @@ licence: license
 
 # Model Card for PreThink_MemAgent
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -27,7 +26,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mingzeli/PreThink_MemAgent/runs/kprp9gb7) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mingzeli/PreThink_MemAgent/runs/9q53vlm5) 
 
 
 This model was trained with SFT.
@@ -37,7 +36,7 @@ This model was trained with SFT.
 - TRL: 0.18.0
 - Transformers: 4.52.3
 - Pytorch: 2.7.0
-- Datasets: 4.4.1
+- Datasets: 4.3.0
 - Tokenizers: 0.21.4
 
 ## Citations

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 2.2203599102840668e+18,
-    "train_loss": 0.3945140190995656,
-    "train_runtime": 7938.1861,
-    "train_samples": 79626,
-    "train_samples_per_second": 20.062,
-    "train_steps_per_second": 0.079
+    "total_flos": 3.064163325664297e+17,
+    "train_loss": 0.4129233885510468,
+    "train_runtime": 3035.4475,
+    "train_samples": 27456,
+    "train_samples_per_second": 27.135,
+    "train_steps_per_second": 0.107
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 2.2203599102840668e+18,
-    "train_loss": 0.3945140190995656,
-    "train_runtime": 7938.1861,
-    "train_samples": 79626,
-    "train_samples_per_second": 20.062,
-    "train_steps_per_second": 0.079
+    "total_flos": 3.064163325664297e+17,
+    "train_loss": 0.4129233885510468,
+    "train_runtime": 3035.4475,
+    "train_samples": 27456,
+    "train_samples_per_second": 27.135,
+    "train_steps_per_second": 0.107
 }