Model save

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: meta-llama/Llama-3.2-1B
 library_name: transformers
-model_name: Llama-3.2-1B-MS-MARCO-Qlora
+model_name: results
 tags:
 - generated_from_trainer
 - trl

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 6.6440677966101696,
-    "eval_loss": 2.681103229522705,
-    "eval_runtime": 16.2756,
-    "eval_samples_per_second": 43.501,
-    "eval_steps_per_second": 5.468,
+    "eval_loss": 2.677806854248047,
+    "eval_runtime": 16.1742,
+    "eval_samples_per_second": 43.774,
+    "eval_steps_per_second": 5.503,
     "total_flos": 5.749859310737818e+16,
     "train_loss": 0.9609878695740992,
     "train_runtime": 1272.9991,

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 6.6440677966101696,
-    "eval_loss": 2.681103229522705,
-    "eval_runtime": 16.2756,
-    "eval_samples_per_second": 43.501,
-    "eval_steps_per_second": 5.468
+    "eval_loss": 2.677806854248047,
+    "eval_runtime": 16.1742,
+    "eval_samples_per_second": 43.774,
+    "eval_steps_per_second": 5.503
 }

trainer_state.json

@@ -175,6 +175,14 @@
       "eval_samples_per_second": 43.753,
       "eval_steps_per_second": 5.5,
       "step": 98
+    },
+    {
+      "epoch": 6.6440677966101696,
+      "eval_loss": 2.681103229522705,
+      "eval_runtime": 16.2756,
+      "eval_samples_per_second": 43.501,
+      "eval_steps_per_second": 5.468,
+      "step": 98
     }
   ],
   "logging_steps": 10,