Training in progress, step 500

config.json

@@ -1,33 +1,61 @@
 {
-  "_name_or_path": "google/mt5-base",
+  "_name_or_path": "Helsinki-NLP/opus-mt-sla-en",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
   "architectures": [
-    "MT5ForConditionalGeneration"
+    "MarianMTModel"
   ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      58815
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 768,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
-  "initializer_factor": 1.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 58815,
+  "decoder_vocab_size": 58816,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 58816,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "mt5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "tokenizer_class": "T5Tokenizer",
+  "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": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 58815,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
   "use_cache": true,
-  "vocab_size": 250112
+  "vocab_size": 58816
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c5f036c184ab68dfb1b7282a377edc1552b79d442cd03ed44839cbfac772c66
-size 2329638768
+oid sha256:cb4bb4dd7a77fdf64b0ca0af9c62214fd09c2e4bdbafff2d5f48ba17a694af8a
+size 297273472

runs/May20_05-28-47_f0c1ec067eb7/events.out.tfevents.1716182936.f0c1ec067eb7.3757.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3677dc2ab576ad7a1f12aa9cb396827fee4fe333b798fa62600ccee5a268aa94
+size 5808

special_tokens_map.json

@@ -1,23 +1,5 @@
 {
-  "eos_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
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,8 +1,7 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,15 +9,15 @@
       "special": true
     },
     "1": {
-      "content": "</s>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "<unk>",
+    "58815": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -26,14 +25,14 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
-  "extra_ids": 0,
-  "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "sla",
   "sp_model_kwargs": {},
-  "tokenizer_class": "T5Tokenizer",
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c999ab2f1d4429eb8e08139f6bcc8645101824a0334ea427d2fb0ae61f11b5
+oid sha256:c3834c82800b7d360129e1ba1f22f4076cfd92b7b76230b14eb39aca7436b6f1
 size 5176