Training in progress, step 23500

config.json

@@ -1,31 +1,28 @@
 {
-  "_name_or_path": "facebook/opt-125m",
-  "_remove_final_layer_norm": false,
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
+  "_name_or_path": "xlm-roberta-large",
   "architectures": [
-    "OPTForCausalLM"
+    "XLMRobertaForCausalLM"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "do_layer_norm_before": true,
-  "dropout": 0.1,
-  "enable_bias": true,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
   "eos_token_id": 2,
-  "ffn_dim": 3072,
-  "hidden_size": 768,
-  "init_std": 0.02,
-  "layer_norm_elementwise_affine": true,
-  "layerdrop": 0.0,
-  "max_position_embeddings": 2048,
-  "model_type": "opt",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
   "pad_token_id": 1,
-  "prefix": "</s>",
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.33.3",
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50272,
-  "word_embed_proj_dim": 768
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6401cf0d85b8b9416cc161efe2097f7b2c670242ac336a70c66e8992808669bf
-size 501023389
+oid sha256:dfd84abd477ee9219551b714ac1eaf9b54e6393b78636c6eeb3e16f62fc03b01
+size 2240706037

special_tokens_map.json

@@ -1,30 +1,15 @@
 {
-  "bos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea44f4e9418dcfdd7c6f0ac9f445d0405e3cd75423f106c5d0bae9ff91eb8db5
-size 2108883
+oid sha256:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441
+size 17082913

tokenizer_config.json

@@ -1,40 +1,19 @@
 {
-  "add_bos_token": true,
-  "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": {
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
     "__type": "AddedToken",
-    "content": "<pad>",
-    "lstrip": false,
+    "content": "<mask>",
+    "lstrip": true,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53313092d109a391e0898b0bee6844ea392965c8c5bf148cfbb0c514976d9e88
+oid sha256:5008108e53cdb8e7f240c97ba92b03b41d129ae0ed84af3900966084794ad7c8
 size 4027