bala3040/qa_bot2

README.md

@@ -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: 1.5351
+- Loss: 1.1865
 
 ## Model description
 
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4
-- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
 - num_epochs: 2
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.8113        | 1.0   | 75   | 1.5410          |
-| 1.3656        | 2.0   | 150  | 1.5351          |
+| 5.9219        | 1.0   | 75   | 1.2440          |
+| 3.9103        | 2.0   | 150  | 1.1865          |
 
 
 ### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.46.2
-- Pytorch 2.5.1+cu121
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- PEFT 0.14.0
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
+  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc6ab088a33e16b9cda8ea47ddb62bf3cafdfb95fdaa1720f37e9c3ea485f53
+oid sha256:e899be230ddf2ea1d3807304cf1df69a9f2a2f5c1e0f56fe1a7ed12bbe49c0a3
 size 8397056

runs/Jan31_12-18-54_a96bef561d82/events.out.tfevents.1738325943.a96bef561d82.354.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34cac1a24414b572ec9a29606d9f66b99ba0a24b299f9cc83e2093f37ced42a9
+size 7035

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a84ebebfb36630aa3d0671ad77a89184bcbdeef613a995c91c2f4afce756c7
+oid sha256:8740a94d3634e777fa97b62f3c3e1737f5bf7869cb1ea17fe772436c0435d839
 size 5304