Model save

README.md

@@ -2,13 +2,12 @@
 license: apache-2.0
 library_name: peft
 tags:
-- alignment-handbook
 - 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: []
@@ -19,9 +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: 0.9543
+- Loss: 0.9524
 
 ## Model description
 
@@ -41,30 +40,29 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 2
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 4
-- total_eval_batch_size: 16
+- num_devices: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1.0
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch  | Step  | Validation Loss |
-|:-------------:|:------:|:-----:|:---------------:|
-| 0.8484        | 1.0000 | 34856 | 0.9543          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.9467        | 1.0   | 17429 | 0.9524          |
 
 
 ### Framework versions
 
 - PEFT 0.7.1
 - Transformers 4.41.0.dev0
-- Pytorch 2.0.1+cu117
+- Pytorch 2.1.2
 - Datasets 2.19.0
 - Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b554fb947e87aac90a5cbfaf43a38e0128aaf027266259ab1e31ab579766e02
+oid sha256:f72d92ea60154f7be85c721556b2f6e30aa243be84b80d01b626f9658cba8d51
 size 83946192

all_results.json

@@ -1,14 +1,9 @@
 {
-    "epoch": 0.9999856554731542,
-    "eval_loss": 0.9543404579162598,
-    "eval_runtime": 2086.5983,
-    "eval_samples": 23109,
-    "eval_samples_per_second": 7.395,
-    "eval_steps_per_second": 0.462,
-    "total_flos": 1.2236563132662678e+19,
-    "train_loss": 0.9581741800145707,
-    "train_runtime": 92834.4231,
+    "epoch": 1.0,
+    "total_flos": 1.2254844500131709e+19,
+    "train_loss": 0.9352519262663926,
+    "train_runtime": 32149.2413,
     "train_samples": 207864,
-    "train_samples_per_second": 1.502,
-    "train_steps_per_second": 0.375
+    "train_samples_per_second": 4.337,
+    "train_steps_per_second": 0.542
 }

runs/May03_23-45-29_p4d-24xl-us-west-2-st-p4d-24xl-us-west-2-5/events.out.tfevents.1714779964.p4d-24xl-us-west-2-st-p4d-24xl-us-west-2-5.46666.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcdc1afcff7602768f5cd8ae0e7f4073a56ddf12e24ad0dfc7e74fa00c48e57f
-size 723618
+oid sha256:222ad237d8ef8798ebc213ba6a6868c44228decf76b0a3f41ba8d6b760a2fe79
+size 725329

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 0.9999856554731542,
-    "total_flos": 1.2236563132662678e+19,
-    "train_loss": 0.9581741800145707,
-    "train_runtime": 92834.4231,
+    "epoch": 1.0,
+    "total_flos": 1.2254844500131709e+19,
+    "train_loss": 0.9352519262663926,
+    "train_runtime": 32149.2413,
     "train_samples": 207864,
-    "train_samples_per_second": 1.502,
-    "train_steps_per_second": 0.375
+    "train_samples_per_second": 4.337,
+    "train_steps_per_second": 0.542
 }