End of training

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: hishab/titulm-1b-enbn-v1
 tags:
 - generated_from_trainer
-base_model: hishab/titulm-1b-enbn-v1
 model-index:
 - name: bn_llm
   results: []
@@ -15,7 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [hishab/titulm-1b-enbn-v1](https://huggingface.co/hishab/titulm-1b-enbn-v1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9683
+- eval_loss: 1.9963
+- eval_runtime: 12.117
+- eval_samples_per_second: 8.253
+- eval_steps_per_second: 4.126
+- epoch: 0.01
+- step: 60
 
 ## Model description
 
@@ -38,30 +43,16 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 6
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 0.03
 - training_steps: 100
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 2.9884        | 0.0   | 10   | 2.5847          |
-| 2.2947        | 0.0   | 20   | 2.1460          |
-| 1.9811        | 0.0   | 30   | 2.0387          |
-| 2.1339        | 0.0   | 40   | 2.0084          |
-| 2.13          | 0.0   | 50   | 1.9940          |
-| 2.071         | 0.0   | 60   | 1.9842          |
-| 2.0213        | 0.0   | 70   | 1.9764          |
-| 1.872         | 0.0   | 80   | 1.9717          |
-| 2.0046        | 0.0   | 90   | 1.9691          |
-| 2.1022        | 0.0   | 100  | 1.9683          |
-
-
 ### Framework versions
 
-- Transformers 4.38.2
-- Pytorch 2.2.1+cu121
+- Transformers 4.39.3
+- Pytorch 2.1.2
 - Datasets 2.18.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -20,7 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "Wqkv"
+    "out_proj",
+    "Wqkv",
+    "up_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33180fef4d60c421e4e17b8a404eb3b2fe56e4e60be173f9ebc20df93e5ec0a
-size 6297744
+oid sha256:1f63d6500dd91faf121aaf9a6e27f994623b3757f700bdb37063eaafd54205a1
+size 25191632

generation_config.json

@@ -1,5 +1,5 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.39.3",
   "use_cache": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bbb8c7bd1829058e155fc57852a5737e774d15a5ad039f36da7dba01c1e29bb
-size 4920
+oid sha256:6fdb68de174bb19d9cd9c8e651d67abdb4ea5ecd85bc245c71e94c24121b7859
+size 4984