End of training

README.md

@@ -4,6 +4,7 @@ license: gemma
 base_model: google/gemma-2-9b
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: hp_ablations_gemma_bsz1024
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hp_ablations_gemma_bsz1024
 
-This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5917
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 2.9946403385049365,
     "eval_loss": 0.5917297005653381,
-    "eval_runtime": 356.383,
-    "eval_samples_per_second": 33.506,
-    "eval_steps_per_second": 0.525,
+    "eval_runtime": 355.6789,
+    "eval_samples_per_second": 33.572,
+    "eval_steps_per_second": 0.526,
     "total_flos": 5052524767739904.0,
     "train_loss": 0.5641303292586612,
-    "train_runtime": 61418.5213,
-    "train_samples_per_second": 11.081,
+    "train_runtime": 61317.9429,
+    "train_samples_per_second": 11.1,
     "train_steps_per_second": 0.011
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.9946403385049365,
     "eval_loss": 0.5917297005653381,
-    "eval_runtime": 356.383,
-    "eval_samples_per_second": 33.506,
-    "eval_steps_per_second": 0.525
+    "eval_runtime": 355.6789,
+    "eval_samples_per_second": 33.572,
+    "eval_steps_per_second": 0.526
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 2.9946403385049365,
     "total_flos": 5052524767739904.0,
     "train_loss": 0.5641303292586612,
-    "train_runtime": 61418.5213,
-    "train_samples_per_second": 11.081,
+    "train_runtime": 61317.9429,
+    "train_samples_per_second": 11.1,
     "train_steps_per_second": 0.011
 }

trainer_state.json

@@ -165,9 +165,9 @@
     {
       "epoch": 0.9974612129760225,
       "eval_loss": 0.5952667593955994,
-      "eval_runtime": 354.3828,
-      "eval_samples_per_second": 33.695,
-      "eval_steps_per_second": 0.528,
+      "eval_runtime": 355.1756,
+      "eval_samples_per_second": 33.62,
+      "eval_steps_per_second": 0.527,
       "step": 221
     },
     {
@@ -327,9 +327,9 @@
     {
       "epoch": 1.9960507757404795,
       "eval_loss": 0.5866958498954773,
-      "eval_runtime": 356.554,
-      "eval_samples_per_second": 33.49,
-      "eval_steps_per_second": 0.524,
+      "eval_runtime": 355.7934,
+      "eval_samples_per_second": 33.562,
+      "eval_steps_per_second": 0.526,
       "step": 442
     },
     {
@@ -489,9 +489,9 @@
     {
       "epoch": 2.9946403385049365,
       "eval_loss": 0.5917297005653381,
-      "eval_runtime": 356.1014,
-      "eval_samples_per_second": 33.533,
-      "eval_steps_per_second": 0.525,
+      "eval_runtime": 355.5387,
+      "eval_samples_per_second": 33.586,
+      "eval_steps_per_second": 0.526,
       "step": 663
     },
     {
@@ -499,8 +499,8 @@
       "step": 663,
       "total_flos": 5052524767739904.0,
       "train_loss": 0.5641303292586612,
-      "train_runtime": 61418.5213,
-      "train_samples_per_second": 11.081,
+      "train_runtime": 61317.9429,
+      "train_samples_per_second": 11.1,
       "train_steps_per_second": 0.011
     }
   ],