End of training

README.md

@@ -29,7 +29,7 @@ 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/s18574s18574-/huggingface/runs/5p39svg5) 
+[<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/s18574s18574-/huggingface/runs/mrbw74ow) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,12 +1,12 @@
 {
-    "eval_runtime": 0.2379,
+    "eval_runtime": 0.2458,
     "eval_samples": 100,
-    "eval_samples_per_second": 201.753,
-    "eval_steps_per_second": 12.61,
+    "eval_samples_per_second": 195.319,
+    "eval_steps_per_second": 12.207,
     "total_flos": 541940076511232.0,
-    "train_loss": 11.106060606060606,
-    "train_runtime": 94.1702,
+    "train_loss": 11.26373106060606,
+    "train_runtime": 94.2203,
     "train_samples": 19883,
-    "train_samples_per_second": 11.225,
+    "train_samples_per_second": 11.219,
     "train_steps_per_second": 0.35
 }

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "eval_runtime": 0.2379,
+    "eval_runtime": 0.2458,
     "eval_samples": 100,
-    "eval_samples_per_second": 201.753,
-    "eval_steps_per_second": 12.61
+    "eval_samples_per_second": 195.319,
+    "eval_steps_per_second": 12.207
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a151f2bd4439693232966936e8838ed7a0f3181ee2be269d71c0f7dc5c91300
+oid sha256:e8ad15ed0e2902c8de6cf7b6a12e544269108e239df561963cb8adc1ef80c926
 size 248915448

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 541940076511232.0,
-    "train_loss": 11.106060606060606,
-    "train_runtime": 94.1702,
+    "train_loss": 11.26373106060606,
+    "train_runtime": 94.2203,
     "train_samples": 19883,
-    "train_samples_per_second": 11.225,
+    "train_samples_per_second": 11.219,
     "train_steps_per_second": 0.35
 }

trainer_state.json

@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 0.030257186081694403,
-      "grad_norm": 35.22744368526962,
+      "grad_norm": 65.58045894101673,
       "learning_rate": 1.796093065705644e-05,
-      "loss": 13.7766,
-      "mean_token_accuracy": 0.1436693400144577,
+      "loss": 13.8203,
+      "mean_token_accuracy": 0.14296866804361344,
       "step": 10
     },
     {
       "epoch": 0.060514372163388806,
-      "grad_norm": 23.6320168043645,
+      "grad_norm": 22.21860249731293,
       "learning_rate": 8.382180034472353e-06,
-      "loss": 10.65,
-      "mean_token_accuracy": 0.19171493500471115,
+      "loss": 10.8297,
+      "mean_token_accuracy": 0.18526874780654906,
       "step": 20
     },
     {
       "epoch": 0.0907715582450832,
-      "grad_norm": 15.21905964248453,
+      "grad_norm": 19.11253043223908,
       "learning_rate": 5.234682881719766e-07,
-      "loss": 9.4422,
-      "mean_token_accuracy": 0.23619858622550965,
+      "loss": 9.6797,
+      "mean_token_accuracy": 0.22612570077180863,
       "step": 30
     },
     {
       "epoch": 0.09984871406959153,
-      "mean_token_accuracy": 0.23997420817613602,
+      "mean_token_accuracy": 0.23169577370087305,
       "step": 33,
       "total_flos": 541940076511232.0,
-      "train_loss": 11.106060606060606,
-      "train_runtime": 94.1702,
-      "train_samples_per_second": 11.225,
+      "train_loss": 11.26373106060606,
+      "train_runtime": 94.2203,
+      "train_samples_per_second": 11.219,
       "train_steps_per_second": 0.35
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edbeaeb7aa6557be5c809a22a09614c50689d24c266e9e86dfcd26bb1fbec880
+oid sha256:d7e5626004e2517eec76d6d50d9b8b45f9d42ce2a5ab0b7771c40d9e4bfee538
 size 7352