End of training

README.md

@@ -16,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-2-finetuned-abhishek
 
-This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9799
 
 ## Model description
 
@@ -36,15 +38,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- training_steps: 2000
+- lr_scheduler_warmup_ratio: 0.3
+- num_epochs: 4
+- mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.2648        | 1.0   | 779  | 1.1722          |
+| 1.0878        | 2.0   | 1558 | 1.0711          |
+| 0.9319        | 3.0   | 2338 | 0.9918          |
+| 0.8719        | 4.0   | 3116 | 0.9799          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/phi-2",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -9,19 +9,19 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "fc1",
     "Wqkv",
-    "fc2",
-    "fc1"
+    "fc2"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e800434cf63cd64d88ec4fb04496a72c4cfb8f8cfab932725eb9e3c44e49c46f
-size 104873776
+oid sha256:0f49a1ef4918b36c34af00759620a6b70fa4cdd41e038f01dc44f9890f16b976
+size 52447112

runs/Jan24_08-21-41_89b7d5a0e94a/events.out.tfevents.1706084541.89b7d5a0e94a.858.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c642c7b3606404e7f5c6cbdded49d5f695bc16c3152b1ffd33772fdcc072828
+size 5212

runs/Jan24_08-24-23_89b7d5a0e94a/events.out.tfevents.1706084671.89b7d5a0e94a.858.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5817fbf655b3843ba869774224dac38f103c8a685c8861fe756273be3975157
+size 5674

runs/Jan24_08-29-57_89b7d5a0e94a/events.out.tfevents.1706085002.89b7d5a0e94a.858.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0945de58022b91c7c884cb8841da1770ed467e5cbe359d9b9184e00e08a1c0ce
+size 5214

runs/Jan24_08-31-40_89b7d5a0e94a/events.out.tfevents.1706085102.89b7d5a0e94a.858.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab0f3f7e5e576d6ce8f6856e9b70bfce85f6296cfa83a8ee6cc379b442b2fca6
+size 5055

runs/Jan24_08-32-40_89b7d5a0e94a/events.out.tfevents.1706085163.89b7d5a0e94a.858.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a42b9ce220279014b06b3b04861281ece3153aad949685324e9099a4484353
+size 25949

special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": "                               ",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -318,7 +318,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 2048,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "                               ",
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc41746de4a3009ec01409f58e569d90e1adf855a253db41510236448bfb58c7
+oid sha256:46bd555d73b517291e231f99c32b47739d6609e277f33cfd905ae2a171d4ab4d
 size 4728