Training in progress, epoch 3

config.json

@@ -1,61 +1,46 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-tr-en",
-  "_num_labels": 3,
+  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-tr-en",
   "activation_dropout": 0.0,
-  "activation_function": "swish",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
+  "activation_function": "relu",
   "architectures": [
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
   "bad_words_ids": [
     [
-      62388
+      57059
     ]
   ],
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
   "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": 62388,
-  "decoder_vocab_size": 62389,
+  "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,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
+  "eos_token_id": 43741,
+  "forced_eos_token_id": 43741,
   "init_std": 0.02,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
   "max_length": 512,
-  "max_position_embeddings": 512,
+  "max_position_embeddings": 1024,
   "model_type": "marian",
-  "normalize_before": false,
   "normalize_embedding": false,
-  "num_beams": 6,
+  "num_beams": 4,
   "num_hidden_layers": 6,
-  "pad_token_id": 62388,
+  "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": 62389
+  "vocab_size": 57060
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab13d5dc0c7c86ec9f05322fa8886148b1c14987ad471d49e7ab6b2eb15bc1b7
-size 304605268
+oid sha256:74b10cff0da5eeac47b91b53e817073a940a2d0c13c1380bd4653b01b7f71c5d
+size 939405120

runs/Apr09_23-17-48_6fc8090ca396/events.out.tfevents.1712705151.6fc8090ca396.137663.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb32701eaa35c6a7b108021b1ec2f2da51e28ca1d9caf5727309720b3d6aed1
+size 401

runs/Apr09_23-33-54_6fc8090ca396/events.out.tfevents.1712705642.6fc8090ca396.137663.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c7517fec957ea51f274eed19356d19f611375662b9cfcf3e29ff3d1b07d8c6e
+size 5462

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
     },
-    "62388": {
+    "57059": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7012e9a1058cd9217c736a5c033a4f7237fd2c6b0cd53b0026a368427aa59e
+oid sha256:7fb56d7f25c1a264bbe1abde74c239acb8002eabfe92349a0be23c02b0623ad0
 size 5048