daniyalfarh/NQG-model

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2328
+- Loss: 1.0976
 
 ## Model description
 
@@ -37,18 +37,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 4
+- learning_rate: 0.0001
+- 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 30
+- num_epochs: 20
 
 ### Training results
 
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 3.5924        | 2.3855  | 50   | 2.1567          |
+| 1.7564        | 4.7711  | 100  | 1.6550          |
+| 1.496         | 7.1446  | 150  | 1.3835          |
+| 1.3101        | 9.5301  | 200  | 1.2363          |
+| 1.1218        | 11.9157 | 250  | 1.1690          |
+| 1.1661        | 14.2892 | 300  | 1.1288          |
+| 1.1055        | 16.6747 | 350  | 1.1075          |
+| 1.1016        | 19.0482 | 400  | 1.0976          |
 
 
 ### Framework versions

adapter_config.json

@@ -13,7 +13,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 128,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
@@ -21,12 +21,12 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 128,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v",
-    "q"
+    "q",
+    "v"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa4bc585e732d5df1533056b4d4673b4a432f74397162f220f39de93516726dd
-size 253866264
+oid sha256:1cbec968a98dce04095ff52b06f243c050e384af794f2794241aad7331dbe92c
+size 225554512

logs/events.out.tfevents.1761729749.a6cb26f28323.37.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93bdd5e8738caa4d3ff0c55f3f31a1f9de065cd0e4ce944222b18d2e42b040ec
+size 12749

logs/events.out.tfevents.1761731722.a6cb26f28323.37.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f5176d9d304bf9b808afb3822a5474a37089a3da33fcc1256a9b7d7b06f0e6
+size 359

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc7ef01e2956ce2a0f14309dfda676e94886f7f1376eca7a76c2e0bef4f5770
+oid sha256:ce01364fa0f6e11ed132a1a3dc49e26f959d2bb93d33644ce4dd94a6f6801cce
 size 5368