Training in progress, epoch 1

config.json

@@ -1,39 +1,26 @@
 {
-  "_name_or_path": "gpt2",
-  "activation_function": "gelu_new",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "GPT2LMHeadModel"
+    "BertForMaskedLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 0,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 0,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 128,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "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,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 128,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 52000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f10292260e08256766bb85c06db4915b3b4b7e0690eeee83e6192a9f44407fc
-size 503128704
+oid sha256:54b3631dea4e3dac43981cb75acca948e3d6c1cf754dd7bb97a2a3239b539175
+size 502967584

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eafe8d5ec94f229f3e353b80ba6ebee2ab40a681aced8d38d432d6577c74d87b
+oid sha256:a3f55e36572a40c781e1baaee5663fe0d5791919f6dc9e38668f9e242071439c
 size 4920