End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2244
+- Loss: 2.2492
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
+- learning_rate: 0.001
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
@@ -43,23 +43,17 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 5
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.352         | 0.4737 | 200  | 2.2613          |
-| 2.363         | 0.9473 | 400  | 2.2484          |
-| 2.3263        | 1.4210 | 600  | 2.2433          |
-| 2.3454        | 1.8946 | 800  | 2.2371          |
-| 2.3287        | 2.3683 | 1000 | 2.2321          |
-| 2.3003        | 2.8419 | 1200 | 2.2296          |
-| 2.2973        | 3.3156 | 1400 | 2.2266          |
-| 2.296         | 3.7892 | 1600 | 2.2257          |
-| 2.2924        | 4.2629 | 1800 | 2.2253          |
-| 2.2923        | 4.7365 | 2000 | 2.2244          |
+| 2.409         | 0.4737 | 200  | 2.2836          |
+| 2.3443        | 0.9473 | 400  | 2.2642          |
+| 2.3351        | 1.4210 | 600  | 2.2530          |
+| 2.337         | 1.8946 | 800  | 2.2492          |
 
 
 ### Framework versions

adapter_config.json

@@ -3,25 +3,26 @@
   "auto_mapping": null,
   "base_model_name_or_path": "gpt2",
   "bias": "none",
-  "fan_in_fan_out": false,
+  "fan_in_fan_out": true,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "c_attn",
     "c_proj",
-    "c_attn"
+    "c_fc"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca076c20175080fe270376f147690c9d184cc22ab11982f66f7b891dcfeaae67
-size 3253104
+oid sha256:20f6768414da7ab0d5171b00719e81c61a5c014e6870d4a99e2927d4a25b993e
+size 9449344

runs/Aug28_15-24-35_06851a5b4fad/events.out.tfevents.1724858676.06851a5b4fad.560.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32157e417e594816332fbbbdf0d80e76ec7858f7b6b807e55efafd0835c92541
+size 5082

runs/Aug28_15-25-19_06851a5b4fad/events.out.tfevents.1724858720.06851a5b4fad.560.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974d956360ac1f476ed26d455b3a2aaa3acc0d49c745efb92a9b64e9db58f43f
+size 5980

runs/Aug28_15-28-14_06851a5b4fad/events.out.tfevents.1724858895.06851a5b4fad.560.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439c5d53d29da397c00728f1aaba55a4fb105502d6e47aeafdba0df0a24709f3
+size 8203

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac808cdaefd151e141733b3dceead8564a92a5eebeaabd181fc0e6eec1269385
+oid sha256:6a31ea2b6ef19ba1ea8ba84f26caf2695e3fa4bfa2e5154ed7e53e451d666bd2
 size 5112