Training in progress, epoch 1

config.json

@@ -1,62 +1,61 @@
 {
-  "_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,
+  "_name_or_path": "t5-small",
   "architectures": [
-    "MarianMTModel"
+    "T5ForConditionalGeneration"
   ],
-  "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_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,
+  "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,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
+  "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: "
+    }
   },
-  "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": 59514
+  "vocab_size": 32128
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d47a1cc2e60868ac41949876ae4414602220c0f0abc912bf94b841b07cbc37b
-size 298763205
+oid sha256:55cfb5ae7b93a5499ceef834bbc0c0b4a9975a74f5c7655d56813f1ca47b889a
+size 242071641

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cadf2eac4af493f42b6bd05f86b10fb313a7e14664f191d04f1b7fbe3656ae63
+oid sha256:0e6cbb7cd36fdffcdde6c48b673afba42196198891272e129ee3d025abe81c1d
 size 4219