Training in progress, epoch 0

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "distilroberta-base",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -24,10 +24,9 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -35,5 +34,5 @@
   "transformers_version": "4.11.3",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d8bb68777b7f1164f22a854b15e63d74a86f4b5d4261f81d79786c41132db88
-size 1112269229
+oid sha256:09dc584f4a4fe60147b24507bd4898aeefb45c05eef4f75fd696f182bf6520c6
+size 328529005

runs/Oct13_15-24-16_milo/1634135062.6294315/events.out.tfevents.1634135062.milo.23058.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79bb9d8a7823afe9f6a96bef40a84be099032b64ae91128062583e308cbdc86
+size 4627

runs/Oct13_15-24-16_milo/events.out.tfevents.1634135062.milo.23058.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eba35cafa771cbc94023bbc995a274909108d6ea9463e9216dee5e2fe56999f
+size 3909

tokenizer_config.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}
+{"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>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base", "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fbae7a2de61c3aa4d3211ad78273d3b80b70f0aebe364c3158663e08dc20370
+oid sha256:4c187cf3c366c8b0e441eb37e539a1f416f19c0fa0dce5c0d48dd120e3034e65
 size 2927