sujithatz/finbot-transofrmer-based-phi3.5_adapter

README.md

@@ -17,8 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
 # phi-3-mini-LoRA
 
 This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.4630
 
 ## Model description
 
@@ -37,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.0002
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -45,63 +43,10 @@ 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: linear
-- lr_scheduler_warmup_ratio: 0.2
-- training_steps: 250
+- training_steps: 90
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss |
-|:-------------:|:-------:|:----:|:---------------:|
-| 1.6578        | 1.3333  | 5    | 1.6863          |
-| 1.6277        | 2.6667  | 10   | 1.6771          |
-| 1.615         | 4.0     | 15   | 1.6615          |
-| 1.5879        | 5.3333  | 20   | 1.6372          |
-| 1.5835        | 6.6667  | 25   | 1.6028          |
-| 1.5908        | 8.0     | 30   | 1.5586          |
-| 1.5143        | 9.3333  | 35   | 1.5012          |
-| 1.4633        | 10.6667 | 40   | 1.4352          |
-| 1.3414        | 12.0    | 45   | 1.3606          |
-| 1.3229        | 13.3333 | 50   | 1.2811          |
-| 1.2218        | 14.6667 | 55   | 1.2119          |
-| 1.1352        | 16.0    | 60   | 1.1488          |
-| 1.0852        | 17.3333 | 65   | 1.0885          |
-| 0.9989        | 18.6667 | 70   | 1.0299          |
-| 0.9959        | 20.0    | 75   | 0.9757          |
-| 0.921         | 21.3333 | 80   | 0.9205          |
-| 0.8727        | 22.6667 | 85   | 0.8683          |
-| 0.8067        | 24.0    | 90   | 0.8200          |
-| 0.7785        | 25.3333 | 95   | 0.7783          |
-| 0.7139        | 26.6667 | 100  | 0.7396          |
-| 0.7081        | 28.0    | 105  | 0.7095          |
-| 0.6705        | 29.3333 | 110  | 0.6824          |
-| 0.6177        | 30.6667 | 115  | 0.6613          |
-| 0.6106        | 32.0    | 120  | 0.6418          |
-| 0.575         | 33.3333 | 125  | 0.6239          |
-| 0.5904        | 34.6667 | 130  | 0.6083          |
-| 0.5917        | 36.0    | 135  | 0.5927          |
-| 0.5051        | 37.3333 | 140  | 0.5801          |
-| 0.5169        | 38.6667 | 145  | 0.5656          |
-| 0.5442        | 40.0    | 150  | 0.5542          |
-| 0.5112        | 41.3333 | 155  | 0.5432          |
-| 0.5061        | 42.6667 | 160  | 0.5321          |
-| 0.5071        | 44.0    | 165  | 0.5234          |
-| 0.4373        | 45.3333 | 170  | 0.5119          |
-| 0.4476        | 46.6667 | 175  | 0.5049          |
-| 0.3914        | 48.0    | 180  | 0.4972          |
-| 0.465         | 49.3333 | 185  | 0.4914          |
-| 0.4122        | 50.6667 | 190  | 0.4890          |
-| 0.4209        | 52.0    | 195  | 0.4837          |
-| 0.3933        | 53.3333 | 200  | 0.4784          |
-| 0.3583        | 54.6667 | 205  | 0.4760          |
-| 0.3952        | 56.0    | 210  | 0.4727          |
-| 0.3858        | 57.3333 | 215  | 0.4708          |
-| 0.3433        | 58.6667 | 220  | 0.4707          |
-| 0.4041        | 60.0    | 225  | 0.4680          |
-| 0.3558        | 61.3333 | 230  | 0.4665          |
-| 0.382         | 62.6667 | 235  | 0.4650          |
-| 0.3625        | 64.0    | 240  | 0.4638          |
-| 0.3513        | 65.3333 | 245  | 0.4644          |
-| 0.3541        | 66.6667 | 250  | 0.4630          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,6 +1,9 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "Phi3ForCausalLM",
+    "parent_library": "transformers_modules.microsoft.Phi-3.5-mini-instruct.af0dfb8029e8a74545d0736d30cb6b58d2f0f3f0.modeling_phi3"
+  },
   "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
   "bias": "none",
   "fan_in_fan_out": false,
@@ -21,11 +24,11 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "o_proj",
     "gate_up_proj",
+    "o_proj",
     "qkv_proj"
   ],
-  "task_type": "CAUSAL_LM",
+  "task_type": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34328d550a8b27f1ce0567efebc0753762b2e56158e73fcf2fbfe056028991de
+oid sha256:07f56375e6cce0d9c0438b48860300a5fb4928e1613e15ea2ffd123ca4e0f2fb
 size 100697728

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 2048,
+    "max_length": 300,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3083cc2b7d42aa4e26b73ee560dd2185afd1e4c08af814236bcfcf5a7c7f3fb3
+oid sha256:d0e2d4fdfa338331d313dd64d51a403616f18a6a2dd45381ee57bc1641693d1c
 size 5432