Training in progress, step 900

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": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "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": 1024,
-  "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": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 51070
+  "vocab_size": 31341
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9c6aa1d73e1373d231c1b6cb5612f82bd9c4dd4314c71e6ea3a2c1cc279ded
-size 500271744
+oid sha256:2e8a1474d938984122ecf7be0b01b2606d51c0bf9c4fc7cd7fcf256c6bb699af
+size 440600140

runs/Apr09_22-39-15_31568ff91b58/events.out.tfevents.1712702357.31568ff91b58.3184.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bca2820a133424036b88b27cdf3da8d6cc8983cbec4e3852b5fdf608ddf91492
-size 8406
+oid sha256:d693d5ef45c114a744d18e2d9d6341a5cfe5a05771de5fe0346c3c98e1de4c4e
+size 8888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a70f2b6a179e533c99fa793a364d9663c6b941026f46b70622c86b9239a7a96
+oid sha256:44681afb04f2d287e2cffa9d1d0be9da12c281db821b82f53f4ca97b89bb481d
 size 4920