End of training

README.md

@@ -32,7 +32,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 128
+- train_batch_size: 32
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

config.json

@@ -1,26 +1,31 @@
 {
+  "activation_function": "gelu_new",
   "architectures": [
-    "RobertaForMaskedLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 514,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.32.0",
-  "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 52000
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "pad_token_id": 1,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.32.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17a6bf7cf93e0f8c7061c628c92c1c4b9d960f5c3b74c9f79485b3c65f9c0c2
-size 334053941
+oid sha256:d2a54da3a79c5d622a28985f4a3fddee954251b7b458fad654901499e7d50842
+size 331462549

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2fa3eb73136e929282d01b85aba563e6b493761b2ed67a57c8d3f5aabbd709b
+oid sha256:cd9f37f3003f669d389650c4c24378a2e3a556924b4b5b2887c369f0a38e840d
 size 4091