Training in progress, epoch 1

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-de",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      58100
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 58100,
+  "decoder_vocab_size": 58101,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 58100,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 58101
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe58ca31c92a7d5fad3a3321b41d12373faf1e3b663a09cc19c812627730e8f
+size 295806292

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "cls_token": "<s>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "</s>",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,139 @@
+{
+  "version": "1.0",
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 128
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 70,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 70,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "[UNK]": 0,
+      "<s>": 1,
+      "</s>": 2,
+      "\"": 3,
+      "{{": 4,
+      "\":\"": 5,
+      ",": 6,
+      "}": 7,
+      "\":": 8,
+      "name": 9,
+      "{": 10,
+      "\":{": 11,
+      "id": 12,
+      "ktl": 13,
+      "pli": 14,
+      "translation": 15,
+      "}}": 16,
+      "},": 17,
+      "}}\",": 18,
+      "value": 19,
+      "}}\"": 20,
+      ":": 21,
+      "param0": 22,
+      "type0": 23,
+      "\":\"{{": 24,
+      "PROCEDURE": 25,
+      "fun": 26,
+      "return": 27,
+      "\",": 28,
+      "CALL": 29,
+      "type": 30,
+      "type1": 31,
+      "}}()\"": 32,
+      "}}({{": 33,
+      "}})\"": 34,
+      "\":\"{\"": 35,
+      "\":\"}\"": 36,
+      "(": 37,
+      "({{": 38,
+      "0": 39,
+      "1": 40,
+      "10": 41,
+      "2": 42,
+      "3": 43,
+      "4": 44,
+      "5": 45,
+      "6": 46,
+      "7": 47,
+      "8": 48,
+      "9": 49,
+      "<{{": 50,
+      "=": 51,
+      "ASSIGN": 52,
+      "DECLARE": 53,
+      "DO": 54,
+      "END": 55,
+      "IF": 56,
+      "MAIN": 57,
+      "RETURN": 58,
+      "THEN": 59,
+      "[": 60,
+      "]": 61,
+      "args": 62,
+      "data": 63,
+      "if": 64,
+      "main": 65,
+      "var": 66,
+      "}})": 67,
+      "}},{{": 68,
+      "}}>)\"": 69
+    },
+    "unk_token": "[UNK]"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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
+    },
+    "70": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "</s>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187d230b4d9c34fab1ea69380f0ea5922f9a30d4c63bf026c4f1cb31425789d7
+size 5240