OpOp1/TI-GPT-735M

README.md

@@ -1,9 +1,9 @@
 ---
-license: other
+license: cc-by-nc-4.0
 library_name: peft
 tags:
 - generated_from_trainer
-base_model: google/gemma-2b-it
+base_model: MBZUAI/LaMini-GPT-774M
 model-index:
 - name: shawgpt-ft
   results: []
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # shawgpt-ft
 
-This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on an unknown dataset.
+This model is a fine-tuned version of [MBZUAI/LaMini-GPT-774M](https://huggingface.co/MBZUAI/LaMini-GPT-774M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7817
+- Loss: 1.4635
 
 ## Model description
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.063         | 1.0   | 10   | 3.5780          |
-| 3.31          | 2.0   | 20   | 3.0259          |
-| 2.8245        | 3.0   | 30   | 2.5810          |
-| 2.4092        | 4.0   | 40   | 2.2151          |
-| 2.1057        | 5.0   | 50   | 1.9864          |
-| 1.9341        | 6.0   | 60   | 1.8753          |
-| 1.8583        | 7.0   | 70   | 1.8140          |
-| 1.7906        | 8.0   | 80   | 1.7611          |
-| 1.7858        | 9.0   | 90   | 1.7852          |
-| 1.7948        | 10.0  | 100  | 1.7817          |
+| 3.5991        | 1.0   | 5    | 3.4306          |
+| 3.3522        | 2.0   | 10   | 3.0302          |
+| 2.9388        | 3.0   | 15   | 2.6452          |
+| 2.621         | 4.0   | 20   | 2.3555          |
+| 2.3501        | 5.0   | 25   | 2.1047          |
+| 2.1243        | 6.0   | 30   | 1.8846          |
+| 1.9309        | 7.0   | 35   | 1.6957          |
+| 1.7786        | 8.0   | 40   | 1.5726          |
+| 1.6718        | 9.0   | 45   | 1.4961          |
+| 1.6283        | 10.0  | 50   | 1.4635          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-2b-it",
+  "base_model_name_or_path": "MBZUAI/LaMini-GPT-774M",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,7 +20,7 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj"
+    "c_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a093ecf135bad9fd1e1ebb7c3ea83e0e0af4f097b473775303233f1539a943d3
-size 2364032
+oid sha256:af6f0d7bf8f3b5b58143633d46df622bbb118957f496b1cf34bd9a0d73cca5b8
+size 10340256

runs/Apr11_18-22-57_4c15467c46e6/events.out.tfevents.1712859780.4c15467c46e6.7200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e6a799a862a08aa382d1811f13f7c409d2df244e3eafbd52bd592f69bbdcfa
+size 10355

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc24de6a7360e87caadd0feaf93abc73aaa0d2eacf9acbb786807cc86a0012f4
+oid sha256:dc4897ca3e2228ef1fe3dc1b55f4565f261a9c7fef6d507548504092b908bdcb
 size 4856