Model save

README.md

@@ -1,13 +1,13 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
-- llama-duo/synth_closed_qa_dataset_dedup
+- generator
 library_name: peft
 license: llama3
 tags:
-- alignment-handbook
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: llama3.1-8b-gpt4o_100k_closedqa-k
@@ -19,9 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3.1-8b-gpt4o_100k_closedqa-k
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the llama-duo/synth_closed_qa_dataset_dedup dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.9355
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
 
 ## Model description
 
@@ -56,9 +54,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.8284        | 1.0   | 256  | 1.9355          |
 
 
 ### Framework versions

all_results.json

@@ -6,9 +6,9 @@
     "eval_samples_per_second": 5.161,
     "eval_steps_per_second": 0.86,
     "total_flos": 7.558147382936863e+17,
-    "train_loss": 0.9328742581419647,
-    "train_runtime": 2769.5152,
+    "train_loss": 0.0,
+    "train_runtime": 1.5255,
     "train_samples": 111440,
-    "train_samples_per_second": 5.905,
-    "train_steps_per_second": 0.092
+    "train_samples_per_second": 10721.267,
+    "train_steps_per_second": 167.817
 }

runs/Sep29_05-21-03_82b7fdadb1f8/events.out.tfevents.1727587393.82b7fdadb1f8.380653.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57810629ebe30478b2637206712912aa4cec264ef6f703ce288c15e3771127a1
+size 6415

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 7.558147382936863e+17,
-    "train_loss": 0.9328742581419647,
-    "train_runtime": 2769.5152,
+    "train_loss": 0.0,
+    "train_runtime": 1.5255,
     "train_samples": 111440,
-    "train_samples_per_second": 5.905,
-    "train_steps_per_second": 0.092
+    "train_samples_per_second": 10721.267,
+    "train_steps_per_second": 167.817
 }

trainer_state.json

@@ -372,22 +372,14 @@
       "loss": 0.8284,
       "step": 255
     },
-    {
-      "epoch": 1.0,
-      "eval_loss": 1.93549382686615,
-      "eval_runtime": 1.1526,
-      "eval_samples_per_second": 5.206,
-      "eval_steps_per_second": 0.868,
-      "step": 256
-    },
     {
       "epoch": 1.0,
       "step": 256,
       "total_flos": 7.558147382936863e+17,
-      "train_loss": 0.9328742581419647,
-      "train_runtime": 2769.5152,
-      "train_samples_per_second": 5.905,
-      "train_steps_per_second": 0.092
+      "train_loss": 0.0,
+      "train_runtime": 1.5255,
+      "train_samples_per_second": 10721.267,
+      "train_steps_per_second": 167.817
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb810d2219c051e2c476f04eb6fb1bc5d816e5d8f9d840bad517fb46ae2130c
+oid sha256:6f8276b5a70d47ca2b9e0a99bbf9a4f71e4152a582276acd233b0dc30d077f8d
 size 5688