Training in progress, step 1100

config.json

@@ -1,26 +1,39 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "BertForMaskedLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "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": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "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
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 31341
+  "vocab_size": 51070
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05cfb2d65242513ace20a2ac0856371cf45271c03042e7144b8988f9d73d9b5b
-size 440600140
+oid sha256:74774a9d777039d076f8dcc31bfe1a963f77b40f30913805676dfcb6e8918ada
+size 500271744

runs/Apr09_22-38-39_f5af74300b2b/events.out.tfevents.1712702334.f5af74300b2b.1622.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff981322f0fa60e19a03d2f54cfd7fe14328de1ddd468196e8745f568b4bde6
-size 9128
+oid sha256:e3c11e71a3cb7ba89d228e0cdf21b23b22a86a2f3eeeeea498073ddac2966a56
+size 10092

training_args.bin

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