Training in progress, epoch 1

config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed432fa3e865a1496d989e2d36a3b9a0211725fa846ee0cec1ae71ad002aeb2
-size 939405120
+oid sha256:a951e28a03d0a10b860290a28582f09af1c63ace96b73febcde881b8aeb870f7
+size 299690728

runs/Apr09_13-30-52_6fc8090ca396/events.out.tfevents.1712676267.6fc8090ca396.107.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b270f11aff5fa2429433dc2d5effa6da6c34594716ebbda4a270d35b7197567b
+size 407

runs/Apr09_16-01-21_6fc8090ca396/events.out.tfevents.1712678536.6fc8090ca396.107.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd7e969dcec26f8903f0d339eb6830d0e6c3a3e6d5ed92ccb4d9ee02a2e92f7
+size 5449

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9216fbabca75f4fb54996516356ff7dc10849e7071751bb8382530fbb269a8ed
+oid sha256:c73ae58c28a1fac29efe82c6d31706a0e180465ca8b2efde29afa788dc662363
 size 5048