Model save

README.md

@@ -1,11 +1,10 @@
 ---
-base_model: meta-llama/Meta-Llama-3.1-8B
+base_model: meta-llama/Meta-Llama-3-8B
 datasets:
-- llama-duo/synth_closed_qa_dataset_dedup
+- generator
 library_name: peft
-license: llama3.1
+license: llama3
 tags:
-- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -19,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3.1-8b-closedqa-gpt4o-100k
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the llama-duo/synth_closed_qa_dataset_dedup dataset.
+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.
 It achieves the following results on the evaluation set:
-- Loss: 3.8424
+- Loss: 2.1008
 
 ## Model description
 
@@ -41,14 +40,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 2
+- train_batch_size: 8
+- eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 4
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 32
-- total_eval_batch_size: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
@@ -56,18 +55,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.9422        | 0.9991 | 582  | 1.9762          |
-| 0.8939        | 2.0    | 1165 | 2.0232          |
-| 0.8255        | 2.9991 | 1747 | 2.1086          |
-| 0.7584        | 4.0    | 2330 | 2.2541          |
-| 0.6928        | 4.9991 | 2912 | 2.4424          |
-| 0.6102        | 6.0    | 3495 | 2.7089          |
-| 0.5466        | 6.9991 | 4077 | 3.0554          |
-| 0.5038        | 8.0    | 4660 | 3.4053          |
-| 0.4624        | 8.9991 | 5242 | 3.6952          |
-| 0.454         | 9.9914 | 5820 | 3.8424          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8026        | 1.0   | 256  | 2.0456          |
+| 0.7532        | 2.0   | 512  | 2.0313          |
+| 0.7198        | 3.0   | 768  | 2.0404          |
+| 0.7053        | 4.0   | 1024 | 2.0419          |
+| 0.6831        | 5.0   | 1280 | 2.0541          |
+| 0.6633        | 6.0   | 1536 | 2.0744          |
+| 0.6595        | 7.0   | 1792 | 2.0814          |
+| 0.6374        | 8.0   | 2048 | 2.0939          |
+| 0.6277        | 9.0   | 2304 | 2.0994          |
+| 0.616         | 10.0  | 2560 | 2.1008          |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,9 @@
 {
-    "epoch": 9.991416309012875,
-    "eval_loss": 3.8423588275909424,
-    "eval_runtime": 0.4239,
-    "eval_samples": 15,
-    "eval_samples_per_second": 14.156,
-    "eval_steps_per_second": 2.359,
-    "total_flos": 8.683561975386472e+18,
-    "train_loss": 0.6765515476977293,
-    "train_runtime": 24420.5896,
+    "epoch": 10.0,
+    "total_flos": 7.568434414263206e+18,
+    "train_loss": 0.7105431989766657,
+    "train_runtime": 14792.6859,
     "train_samples": 111440,
-    "train_samples_per_second": 7.63,
-    "train_steps_per_second": 0.238
+    "train_samples_per_second": 11.056,
+    "train_steps_per_second": 0.173
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 9.991416309012875,
-    "total_flos": 8.683561975386472e+18,
-    "train_loss": 0.6765515476977293,
-    "train_runtime": 24420.5896,
+    "epoch": 10.0,
+    "total_flos": 7.568434414263206e+18,
+    "train_loss": 0.7105431989766657,
+    "train_runtime": 14792.6859,
     "train_samples": 111440,
-    "train_samples_per_second": 7.63,
-    "train_steps_per_second": 0.238
+    "train_samples_per_second": 11.056,
+    "train_steps_per_second": 0.173
 }