Training in progress, epoch 1

config.json

@@ -1,46 +1,46 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-tatoeba-en-tr",
+  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-tr-en",
   "activation_dropout": 0.0,
-  "activation_function": "swish",
+  "activation_function": "relu",
   "architectures": [
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
   "bad_words_ids": [
     [
-      59993
+      57059
     ]
   ],
   "bos_token_id": 0,
   "classifier_dropout": 0.0,
-  "d_model": 512,
-  "decoder_attention_heads": 8,
-  "decoder_ffn_dim": 2048,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
-  "decoder_start_token_id": 59993,
-  "decoder_vocab_size": 59994,
+  "decoder_start_token_id": 57059,
+  "decoder_vocab_size": 57060,
   "dropout": 0.1,
-  "encoder_attention_heads": 8,
-  "encoder_ffn_dim": 2048,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
-  "eos_token_id": 0,
-  "forced_eos_token_id": 0,
+  "eos_token_id": 43741,
+  "forced_eos_token_id": 43741,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "max_length": 512,
-  "max_position_embeddings": 512,
+  "max_position_embeddings": 1024,
   "model_type": "marian",
   "normalize_embedding": false,
-  "num_beams": 6,
+  "num_beams": 4,
   "num_hidden_layers": 6,
-  "pad_token_id": 59993,
+  "pad_token_id": 57059,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": true,
-  "vocab_size": 59994
+  "vocab_size": 57060
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9179206fcc137a755009f291c91672e97429a55c571ddf4968a60aee6e71aea2
-size 299690728
+oid sha256:6bca7c97fdca8a63727723f0c0971862308e32ed18e9bd59879cce07de2b4513
+size 939405120

runs/Apr06_19-57-59_08db7733709c/events.out.tfevents.1712434439.08db7733709c.377.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ba59cc63342e82f4fe5d55e1a3694b476b91f1a4993658ed36894fff907918
+size 401

runs/Apr06_20-17-34_08db7733709c/events.out.tfevents.1712435027.08db7733709c.377.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c347d33a849782862d0167f8f9b50f0f46e2db104af5ea932324473afda1ec
+size 5694

runs/Apr06_20-25-50_08db7733709c/events.out.tfevents.1712435275.08db7733709c.377.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372b462f7b859d76792691f3b12f071b87474e68f8be0e8e1042d2bea1acbb76
+size 5450

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "0": {
+    "43741": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "1": {
+    "52508": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "59993": {
+    "57059": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,
@@ -31,9 +31,9 @@
   "pad_token": "<pad>",
   "return_tensors": "pt",
   "separate_vocabs": false,
-  "source_lang": "eng",
+  "source_lang": "tr",
   "sp_model_kwargs": {},
-  "target_lang": "tur",
+  "target_lang": "en",
   "tokenizer_class": "MarianTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9830c7abbaf735c7203834571f6758c98bc4cb4976c245b3eee271aac032bd01
+oid sha256:bc39e69a876ecf3864e00e2c4775686df1dd01d326043ba5d702c0e670aa7340
 size 5048