Upload model

README.md

@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- 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}
+- 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': 41322, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 2000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.03}
 - training_precision: mixed_bfloat16
 
 ### Training results
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.31.0
+- Transformers 4.32.0
 - TensorFlow 2.12.0
 - Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -6,9 +6,9 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 0,
+  "bos_token_id": 1,
   "embd_pdrop": 0.1,
-  "eos_token_id": 0,
+  "eos_token_id": 2,
   "id2label": {
     "0": "LABEL_0"
   },
@@ -24,7 +24,7 @@
   "n_inner": null,
   "n_layer": 6,
   "n_positions": 1024,
-  "pad_token_id": 50002,
+  "pad_token_id": 3,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -40,7 +40,7 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.32.0",
   "use_cache": true,
-  "vocab_size": 50003
+  "vocab_size": 50000
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
-  "pad_token_id": 50002,
-  "transformers_version": "4.31.0"
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.32.0"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c7beec991e6a29d32863c136116dd37bed53440e955f44d098994a1f362d3d
-size 326965192
+oid sha256:754f87b2937af6b51ff75476368851c0f5869692a890f456bda5221bb42955a2
+size 326955976