Training in progress, step 500

config.json

@@ -1,39 +1,27 @@
 {
-  "_name_or_path": "gpt2",
-  "activation_function": "gelu_new",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "GPT2LMHeadModel"
+    "RobertaForMaskedLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "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,
   "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.21.0.dev0",
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34348841821f56b1d0fc28b6cbabfbbd943aad7c3b57a1c4b62e6a588275842b
-size 510396521
+oid sha256:1d42e9a687c60d3408e900229d950007b21ab653fe08650e937a7c427b38ac0e
+size 498861675

special_tokens_map.json

@@ -1,5 +1,15 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,10 +1,16 @@
 {
   "add_prefix_space": false,
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "name_or_path": "gpt2",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
   "special_tokens_map_file": null,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf542b4cd5d15d87f091671d0ff9e0bdd3aade90ed4d3aca497dfe22a131222
+oid sha256:575bcba0894481f4037e50524a1f5075c00aee78d8fb66f2ff5db9891bebe1db
 size 3311