Training in progress, epoch 1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "dokyoungkim/wmt19-finetuned-it-de-to-en-2",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "FSMTForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "d_model": 1024,
+  "decoder": {
+    "bos_token_id": 2,
+    "model_type": "fsmt_decoder",
+    "vocab_size": 42024
+  },
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.2,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "langs": [
+    "de",
+    "en"
+  ],
+  "length_penalty": 1.1,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "fsmt",
+  "num_beams": 5,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "src_vocab_size": 42024,
+  "tgt_vocab_size": 42024,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34af2827767d0dd3acd2cd581d6d1cdf600de63cdf3b28980372e6f628425264
+size 1087419504

runs/Mar20_10-54-39_gpusvr021320/events.out.tfevents.1710899684.gpusvr021320.2621941.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6578c75ddeea879211a462c7082461bcd798d80d488a12682690bd91558cdc5
+size 6790

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "langs": [
+    "de",
+    "en"
+  ],
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "FSMTTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7e37a3806adc1197f88d6cef8871d9024b8e5e5fa87f41cd8bbc957781351f
+size 4475