End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/electra-base-generator](https://huggingface.co/google/electra-base-generator) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.9361
+- Loss: 5.6760
 
 ## Model description
 
@@ -35,8 +35,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -46,14 +46,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 12.9603       | 1.0   | 267  | 8.5366          |
-| 6.5052        | 2.0   | 534  | 6.1080          |
-| 6.1269        | 3.0   | 801  | 5.9361          |
+| No log        | 1.0   | 45   | 8.7550          |
+| No log        | 2.0   | 90   | 6.2685          |
+| 8.9094        | 3.0   | 135  | 5.6760          |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.1+cu118
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -8,16 +8,19 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 32,
   "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
-    "value"
+    "value",
+    "query"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b61cb66324c468e5bd3f86a4970d3b98bcf14c8f3c5a558cea810804eb46545d
+oid sha256:0f0a210070cd7eccc4dea28f1f6a451bccf1546126c0e5e75cfed7077811e0b2
 size 400008

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b9c52e7bf80a1fbeb4f62b10e7f74e92c88fb4432802fd594d3e87464b011c9
+oid sha256:f3cc76a081aac8a4202cc5b0476b3dfd5fb7a5130326588a258494b199649096
 size 4536