Model save

README.md

@@ -26,7 +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/aethersura/huggingface/runs/9lvrpehp)
+[<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/aethersura/huggingface/runs/k0mab5n8)
 
 This model was trained with SFT.
 

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.9915110356536503,
     "total_flos": 30674119557120.0,
-    "train_loss": 0.7169299482488308,
-    "train_runtime": 2062.2629,
-    "train_samples": 19711,
-    "train_samples_per_second": 4.564,
-    "train_steps_per_second": 0.143
+    "train_loss": 0.0,
+    "train_runtime": 0.8452,
+    "train_samples": 197,
+    "train_samples_per_second": 113.582,
+    "train_steps_per_second": 2.366
 }

runs/Feb20_06-01-02_ip-10-0-18-140/events.out.tfevents.1740031329.ip-10-0-18-140.111102.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f385e3c7bf8aa5a4f53ca5304f11a91b470a18a622cca4713be78b991934cae
+size 6504

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.9915110356536503,
     "total_flos": 30674119557120.0,
-    "train_loss": 0.7169299482488308,
-    "train_runtime": 2062.2629,
-    "train_samples": 19711,
-    "train_samples_per_second": 4.564,
-    "train_steps_per_second": 0.143
+    "train_loss": 0.0,
+    "train_runtime": 0.8452,
+    "train_samples": 197,
+    "train_samples_per_second": 113.582,
+    "train_steps_per_second": 2.366
 }

trainer_state.json

@@ -441,14 +441,14 @@
       "epoch": 1.9915110356536503,
       "step": 294,
       "total_flos": 30674119557120.0,
-      "train_loss": 0.7169299482488308,
-      "train_runtime": 2062.2629,
-      "train_samples_per_second": 4.564,
-      "train_steps_per_second": 0.143
+      "train_loss": 0.0,
+      "train_runtime": 0.8452,
+      "train_samples_per_second": 113.582,
+      "train_steps_per_second": 2.366
     }
   ],
   "logging_steps": 5,
-  "max_steps": 294,
+  "max_steps": 2,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 500,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e478913fbbcd8c92804d4ed10b6f0940d4285debd340b542a6df904bfc6e29b0
+oid sha256:7964c8765ef28cec74f9e5bf45638faf250410fc75d233c41f53ac41fd213864
 size 6968