Training in progress, epoch 1

README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: t5-small
 tags:
 - translation
 - generated_from_trainer
@@ -16,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # eng-nah-svo-translation
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0502
-- Bleu: 10.5711
-- Chrf: 51.4478
+- Loss: 0.1119
+- Bleu: 0.0
+- Chrf: 82.3094
 
 ## Model description
 

config.json

@@ -1,61 +1,62 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "eng-nah-svo-translation",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
   "architectures": [
-    "T5ForConditionalGeneration"
+    "MarianMTModel"
   ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
   "d_model": 512,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "relu",
-  "initializer_factor": 1.0,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 59513,
+  "decoder_vocab_size": 59514,
+  "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,
-  "is_gated_act": false,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 200,
-      "min_length": 30,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4,
-      "prefix": "summarize: "
-    },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
-    }
+  "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": 59513,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.32.1",
   "use_cache": true,
-  "vocab_size": 32128
+  "vocab_size": 59514
 }

generation_config.json

@@ -1,6 +1,16 @@
 {
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59513,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59513,
+  "renormalize_logits": true,
   "transformers_version": "4.32.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ded6f6ed43e284033fc377d12cd2188adb8f218a6903d83bec6c6d2521c1eaa
-size 242071641
+oid sha256:578e05d2f44d856f3b8440d0e444e5d8fbdcf3b57fee157e8f379288dce7dae9
+size 298763205

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5fbb2b6dceac1392ed18080451d18ef9e508063b3c59953c2cda47a5fa4d480
+oid sha256:aba06b4cf471697fc7cb79eaf3dcada366d5bc976c2044d699c735280b95a410
 size 4219