Upload model

README.md

@@ -1,17 +1,19 @@
 ---
+license: apache-2.0
+base_model: distilgpt2
 tags:
 - generated_from_keras_callback
 model-index:
-- name: distilGPTBhai
+- name: distilGPT-Nepali
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
 probably proofread and complete it, then remove this comment. -->
 
-# distilGPTBhai
+# distilGPT-Nepali
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
 
 
@@ -32,8 +34,8 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 7623, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
-- training_precision: float32
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 41670, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}
+- training_precision: mixed_bfloat16
 
 ### Training results
 
@@ -43,5 +45,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.31.0
 - TensorFlow 2.12.0
-- Datasets 2.13.1
+- Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "raygx/distilGPTBhai",
+  "_name_or_path": "distilgpt2",
   "_num_labels": 1,
   "activation_function": "gelu_new",
   "architectures": [
@@ -10,21 +10,17 @@
   "embd_pdrop": 0.1,
   "eos_token_id": 0,
   "id2label": {
-    "0": "NEUTRAL",
-    "1": "POSITIVE",
-    "2": "NEGATIVE"
+    "0": "LABEL_0"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "NEGATIVE": 2,
-    "NEUTRAL": 0,
-    "POSITIVE": 1
+    "LABEL_0": 0
   },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,
-  "n_head": 6,
+  "n_head": 12,
   "n_inner": null,
   "n_layer": 6,
   "n_positions": 1024,

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 3,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 50002,
   "transformers_version": "4.31.0"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9faeaaa945c5f711617c85af1c061d07631d8c1e33ca18435c8ec0a0320de85d
-size 326965184
+oid sha256:45c7beec991e6a29d32863c136116dd37bed53440e955f44d098994a1f362d3d
+size 326965192