End of training

README.md

@@ -27,7 +27,7 @@ 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/h4mjpwdc) 
+[<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/j0nfe37z) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,12 +1,12 @@
 {
-    "eval_runtime": 0.2433,
+    "eval_runtime": 0.2685,
     "eval_samples": 100,
-    "eval_samples_per_second": 197.294,
-    "eval_steps_per_second": 12.331,
+    "eval_samples_per_second": 178.767,
+    "eval_steps_per_second": 11.173,
     "total_flos": 0.0,
-    "train_loss": 5.5546875,
-    "train_runtime": 94.1946,
+    "train_loss": 5.5703125,
+    "train_runtime": 94.29,
     "train_samples": 19883,
-    "train_samples_per_second": 11.223,
+    "train_samples_per_second": 11.211,
     "train_steps_per_second": 0.35
 }

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "eval_runtime": 0.2433,
+    "eval_runtime": 0.2685,
     "eval_samples": 100,
-    "eval_samples_per_second": 197.294,
-    "eval_steps_per_second": 12.331
+    "eval_samples_per_second": 178.767,
+    "eval_steps_per_second": 11.173
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7eb2e565ca142cb58857c3ef1ff8c9788eda03e52d5e253048aa975a37544c3
+oid sha256:2b2a460303c6a34aff294621d2ce5dfb7f6fbc76e0167914d64909521d616777
 size 248944286

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 5.5546875,
-    "train_runtime": 94.1946,
+    "train_loss": 5.5703125,
+    "train_runtime": 94.29,
     "train_samples": 19883,
-    "train_samples_per_second": 11.223,
+    "train_samples_per_second": 11.211,
     "train_steps_per_second": 0.35
 }

trainer_state.json

@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 0.030257186081694403,
-      "grad_norm": 18.732376748958846,
+      "grad_norm": 23.19076749983313,
       "learning_rate": 1.796093065705644e-05,
-      "loss": 6.9055,
-      "mean_token_accuracy": 0.14334678202867507,
+      "loss": 6.8891,
+      "mean_token_accuracy": 0.14328600466251373,
       "step": 10
     },
     {
       "epoch": 0.060514372163388806,
-      "grad_norm": 11.043682894738728,
+      "grad_norm": 10.552981359945921,
       "learning_rate": 8.382180034472353e-06,
-      "loss": 5.325,
-      "mean_token_accuracy": 0.19193603545427323,
+      "loss": 5.3461,
+      "mean_token_accuracy": 0.1898418039083481,
       "step": 20
     },
     {
       "epoch": 0.0907715582450832,
-      "grad_norm": 7.678457987927252,
+      "grad_norm": 8.191712743407091,
       "learning_rate": 5.234682881719766e-07,
-      "loss": 4.7141,
-      "mean_token_accuracy": 0.23722605779767036,
+      "loss": 4.75,
+      "mean_token_accuracy": 0.2335878863930702,
       "step": 30
     },
     {
       "epoch": 0.09984871406959153,
-      "mean_token_accuracy": 0.24098099519809088,
+      "mean_token_accuracy": 0.23857259502013525,
       "step": 33,
       "total_flos": 0.0,
-      "train_loss": 5.5546875,
-      "train_runtime": 94.1946,
-      "train_samples_per_second": 11.223,
+      "train_loss": 5.5703125,
+      "train_runtime": 94.29,
+      "train_samples_per_second": 11.211,
       "train_steps_per_second": 0.35
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c10a437b51b6ac5b776af8a77eca7bed409a4b430f5c14a649e28ff244060c91
+oid sha256:f5fa711d6cdcb0b2b63e61e4b8e967fec2988c80fb803ba46477961ca838fb4d
 size 7352