bala3040/finally_done

README.md

@@ -1,9 +1,9 @@
 ---
-license: apache-2.0
+base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
 library_name: peft
+license: apache-2.0
 tags:
 - generated_from_trainer
-base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
 model-index:
 - name: balagpt-ft2
   results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5969
+- Loss: 0.8438
 
 ## Model description
 
@@ -44,29 +44,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 10
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 2.5007        | 1.0   | 5    | 2.0719          |
-| 1.8713        | 2.0   | 10   | 1.5969          |
-| 1.4159        | 3.0   | 15   | 1.2384          |
-| 1.0399        | 4.0   | 20   | 0.9500          |
-| 0.7569        | 5.0   | 25   | 0.7594          |
-| 0.59          | 6.0   | 30   | 0.6689          |
-| 0.5004        | 7.0   | 35   | 0.6295          |
-| 0.4488        | 8.0   | 40   | 0.6123          |
-| 0.4119        | 9.0   | 45   | 0.5994          |
-| 0.386         | 10.0  | 50   | 0.5969          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.1065        | 0.9231 | 9    | 1.4824          |
+| 1.1553        | 1.9487 | 19   | 0.9793          |
+| 0.7704        | 2.7692 | 27   | 0.8438          |
 
 
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.38.2
+- PEFT 0.11.1
+- Transformers 4.41.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b5ef7e77573cd180bdfb58950cdb99dbd6e99eedcdb45fcda8eac35081fcdc
+oid sha256:8f21bfdf96de82956129050d87fc5b7f6e8852f47eab987307fba0efb9a44295
 size 8397056

runs/Jul17_14-32-58_cc8519d491ae/events.out.tfevents.1721226783.cc8519d491ae.284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aac2a61168dd97edb916cf31a39778988c54eeb808fce9a7735ed800ddfb499
+size 10535

runs/Jul17_15-31-39_cc8519d491ae/events.out.tfevents.1721230305.cc8519d491ae.284.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05c567f9ce866587412638e36823b7821f4bfee6fb6aaa013f15565c6767d08
+size 7223

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3830df37fb9742ae81ecd72f7d2180409ce95de1c4c24a4981091be978ca3675
-size 4920
+oid sha256:b7c5ddd89521a4abe1dbfc0eab0fce560afe5656bc5823edcef32529e5547385
+size 5112