8 epochs of training

.gitattributes

@@ -16,3 +16,4 @@
 *.pth filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 nohup.out filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "./",
   "architectures": [
     "RobertaForMaskedLM"
   ],
@@ -18,6 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
   "transformers_version": "4.9.0.dev0",
   "type_vocab_size": 1,
   "use_cache": true,

flax_to_torch.py

@@ -0,0 +1,7 @@
+from transformers import RobertaForMaskedLM, AutoTokenizer
+
+model = RobertaForMaskedLM.from_pretrained("./", from_flax=True)
+model.save_pretrained("./")
+
+tokenizer = AutoTokenizer.from_pretrained("./")
+tokenizer.save_pretrained("./")

nohup.out

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c9571bb69f151d306a7ad2f06eef318d7029e1e59af5690b0f70956f372972
-size 16226324
+oid sha256:aa9fffea38d0dacea94cfb0e33cf554ebdbaeff9521b45dbcb37d812928152ca
+size 16228479

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843ba5529934bfa14c528bb50647d74e9836326d686510660c2836e15a218ed2
+size 498858859

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "RobertaTokenizer"}