coinplusfire/coinplusfire_llm

README.md

@@ -3,7 +3,7 @@ license: apache-2.0
 library_name: peft
 tags:
 - generated_from_trainer
-base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 model-index:
 - name: coinplusfire_llm
   results: []
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # coinplusfire_llm
 
-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 an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8949
+- Loss: 2.0778
 
 ## Model description
 
@@ -35,32 +35,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 4
+- learning_rate: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- total_train_batch_size: 32
 - 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: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.5942        | 0.92  | 3    | 3.9658          |
-| 4.0555        | 1.85  | 6    | 3.4516          |
-| 3.4878        | 2.77  | 9    | 3.0037          |
-| 2.2707        | 4.0   | 13   | 2.5762          |
-| 2.6976        | 4.92  | 16   | 2.3493          |
-| 2.4044        | 5.85  | 19   | 2.1719          |
-| 2.1839        | 6.77  | 22   | 2.0236          |
-| 1.5376        | 8.0   | 26   | 1.9475          |
-| 2.0032        | 8.92  | 29   | 1.9066          |
-| 1.3929        | 9.23  | 30   | 1.8949          |
+| 2.891         | 0.99  | 51   | 2.0778          |
 
 
 ### Framework versions

runs/Apr13_08-31-02_22321abdc3e0/events.out.tfevents.1712997062.22321abdc3e0.5594.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e62ded1f842ae8c7b4776e8e5b94737eacd693c7a9c2fd06bbe61d40c91854
+size 5399

runs/Apr13_08-31-02_22321abdc3e0/events.out.tfevents.1712997386.22321abdc3e0.5594.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474d2edf91e58b1045fbf17bf753790315ff0f62df4b6b536f16c9a2fd8e9b76
+size 5399

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7bb98caab6fee79d139bc154e2b7e78d735c87e2701b4e3711d66235a0b05f
+oid sha256:ae457afd3ec9ae8e7172b590111d1eb73dfe6e235d07cca6d4ee331a3356f179
 size 4856