Model save

README.md

@@ -0,0 +1,73 @@
+---
+license: llama3
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+model-index:
+- name: unaligned
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# unaligned
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0226
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1024
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.1627        | 0.1109 | 100  | 0.1143          |
+| 0.0663        | 0.2218 | 200  | 0.0420          |
+| 0.0557        | 0.3326 | 300  | 0.0340          |
+| 0.0166        | 0.4435 | 400  | 0.0294          |
+| 0.032         | 0.5544 | 500  | 0.0277          |
+| 0.0463        | 0.6653 | 600  | 0.0260          |
+| 0.0443        | 0.7762 | 700  | 0.0247          |
+| 0.0414        | 0.8870 | 800  | 0.0239          |
+| 0.0295        | 0.9979 | 900  | 0.0234          |
+| 0.0266        | 1.1088 | 1000 | 0.0226          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -1,12 +1,8 @@
 {
-    "epoch": 0.655150351887396,
-    "eval_loss": 1.4878435134887695,
-    "eval_runtime": 103.7194,
-    "eval_samples_per_second": 48.207,
-    "eval_steps_per_second": 1.514,
-    "total_flos": 3.6685588640169984e+17,
-    "train_loss": 1.622293347492814,
-    "train_runtime": 4726.6516,
-    "train_samples_per_second": 6.933,
-    "train_steps_per_second": 0.108
+    "epoch": 1.1354123354123353,
+    "total_flos": 8.990983532408832e+17,
+    "train_loss": 0.273499660730522,
+    "train_runtime": 17033.1365,
+    "train_samples_per_second": 3.848,
+    "train_steps_per_second": 0.06
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.655150351887396,
-    "total_flos": 3.6685588640169984e+17,
-    "train_loss": 1.622293347492814,
-    "train_runtime": 4726.6516,
-    "train_samples_per_second": 6.933,
-    "train_steps_per_second": 0.108
+    "epoch": 1.1354123354123353,
+    "total_flos": 8.990983532408832e+17,
+    "train_loss": 0.273499660730522,
+    "train_runtime": 17033.1365,
+    "train_samples_per_second": 3.848,
+    "train_steps_per_second": 0.06
 }