End of training

README.md

@@ -4,6 +4,8 @@ license: llama3.2
 base_model: meta-llama/Llama-3.2-1B
 tags:
 - generated_from_trainer
+datasets:
+- squad
 model-index:
 - name: squad_llama_finetuned
   results: []
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # squad_llama_finetuned
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -2,14 +2,14 @@
     "epoch": 8.0,
     "eval_exact_match": 0.34058656575212864,
     "eval_f1": 4.476693191916602,
-    "eval_runtime": 250.4299,
+    "eval_runtime": 249.3188,
     "eval_samples": 10787,
-    "eval_samples_per_second": 43.074,
-    "eval_steps_per_second": 5.387,
+    "eval_samples_per_second": 43.266,
+    "eval_steps_per_second": 5.411,
     "total_flos": 1.5884920525342925e+18,
     "train_loss": 5.578120173746451,
-    "train_runtime": 16920.9894,
+    "train_runtime": 16751.1125,
     "train_samples": 88559,
-    "train_samples_per_second": 41.869,
-    "train_steps_per_second": 0.327
+    "train_samples_per_second": 42.294,
+    "train_steps_per_second": 0.33
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 8.0,
     "eval_exact_match": 0.34058656575212864,
     "eval_f1": 4.476693191916602,
-    "eval_runtime": 250.4299,
+    "eval_runtime": 249.3188,
     "eval_samples": 10787,
-    "eval_samples_per_second": 43.074,
-    "eval_steps_per_second": 5.387
+    "eval_samples_per_second": 43.266,
+    "eval_steps_per_second": 5.411
 }

runs/Dec21_14-10-52_xgpi8/events.out.tfevents.1734778573.xgpi8.2575093.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1f0504604b856d63136e1709089d2957f5ee92aff9d5b0756f2135722116ffd
+size 412

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 8.0,
     "total_flos": 1.5884920525342925e+18,
     "train_loss": 5.578120173746451,
-    "train_runtime": 16920.9894,
+    "train_runtime": 16751.1125,
     "train_samples": 88559,
-    "train_samples_per_second": 41.869,
-    "train_steps_per_second": 0.327
+    "train_samples_per_second": 42.294,
+    "train_steps_per_second": 0.33
 }

trainer_state.json

@@ -90,9 +90,9 @@
       "step": 5536,
       "total_flos": 1.5884920525342925e+18,
       "train_loss": 5.578120173746451,
-      "train_runtime": 16920.9894,
-      "train_samples_per_second": 41.869,
-      "train_steps_per_second": 0.327
+      "train_runtime": 16751.1125,
+      "train_samples_per_second": 42.294,
+      "train_steps_per_second": 0.33
     }
   ],
   "logging_steps": 500,