Training in progress, step 429

config.json

@@ -1,27 +1,39 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "RobertaForCausalLM"
+    "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-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "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": "4.46.3",
-  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 50257
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bb0bd08a47d033eac419626baed0fdb52723b25aa0104ec28e485432d07e146
-size 498813948
+oid sha256:ccc4064fdb81c87606a243027fc4fbc97c982d5b5ce8a33882318a5757e9167e
+size 497774208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67377e764091662699590b95dad0f76ee5d4efa65cc875535d91caabd2d877c8
+oid sha256:e0c75836438bf76417e230d7ea34f21252d8de0432463d0055b84f68daac69c9
 size 5304