Training in progress, epoch 1

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "decoder_vocab_size": 50003,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "num_hidden_layers": 12,
+  "pad_token_id": 2,
+  "scale_embedding": false,
+  "share_encoder_decoder_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 50003
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21dca09bd585b42979f695eb4ca241101186fd37bac8db30eae667dab5cb881
+size 1615930756

special_tokens_map.json

@@ -1,4 +1,16 @@
 {
-  "eos_token": "|<EOS>|",
-  "pad_token": "|<PAD>|"
+  "eos_token": {
+    "content": "|<EOS>|",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "|<PAD>|",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4d852c1f0a85031cfeb451caeef21f7eb11bae659d5bb1e2494378abb9cb48
+size 6968