Model save

README.md

@@ -2,16 +2,12 @@
 license: apache-2.0
 library_name: peft
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
 datasets:
-- HuggingFaceH4/ultrachat_200k
+- generator
 model-index:
 - name: zephyr-7b-sft-qlora
   results: []
@@ -22,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-qlora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9499
+- Loss: 0.9517
 
 ## Model description
 
@@ -48,10 +44,10 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 4
+- num_devices: 2
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 32
-- total_eval_batch_size: 32
+- total_train_batch_size: 16
+- 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
@@ -61,13 +57,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.9462        | 1.0   | 4357 | 0.9499          |
+| 0.9567        | 1.0   | 8714 | 0.9517          |
 
 
 ### Framework versions
 
 - PEFT 0.7.1
-- Transformers 4.38.2
-- Pytorch 2.1.2
-- Datasets 2.14.6
+- Transformers 4.39.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
 - Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d5963f9a1f5993302ffc19b8d9a1b6a8767fc761869a0d9ec7a7d27890d238
+oid sha256:440d938e3bc97bee5a47be212f3d9a03e01eb54c44ec61cbfb7462ae2fae7351
 size 83946192

all_results.json

@@ -1,13 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.9498828649520874,
-    "eval_runtime": 985.6149,
-    "eval_samples": 23110,
-    "eval_samples_per_second": 15.656,
-    "eval_steps_per_second": 0.49,
-    "train_loss": 0.9569843266025059,
-    "train_runtime": 33545.7523,
-    "train_samples": 207865,
-    "train_samples_per_second": 4.156,
-    "train_steps_per_second": 0.13
+    "train_loss": 0.8657062510599203,
+    "train_runtime": 31020.7888,
+    "train_samples": 207864,
+    "train_samples_per_second": 4.495,
+    "train_steps_per_second": 0.281
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.9569843266025059,
-    "train_runtime": 33545.7523,
-    "train_samples": 207865,
-    "train_samples_per_second": 4.156,
-    "train_steps_per_second": 0.13
+    "train_loss": 0.8657062510599203,
+    "train_runtime": 31020.7888,
+    "train_samples": 207864,
+    "train_samples_per_second": 4.495,
+    "train_steps_per_second": 0.281
 }