Training in progress, epoch 1

config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac9d90dce8ca7a1825009709e1aa48600a306e5613ab56bf29b9479e468c0a5
-size 939405120
+oid sha256:4a718dec41bf5882bbddf8794723eb631f1677ddd33112a6cba8ccd4a0dfba2d
+size 304605268

runs/Apr07_16-19-16_eb754cce07bd/events.out.tfevents.1712507469.eb754cce07bd.278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c302932f62e6672978ab6d32c31c1d4089a28f34c341f1ee818797d75b3e9074
+size 4438

runs/Apr07_16-34-13_eb754cce07bd/events.out.tfevents.1712507734.eb754cce07bd.4453.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92fcbbec6c0a21a727b9cc883395baf28e1be1e734e25e493f3a4a35f5c26cf
+size 4438

runs/Apr07_16-41-19_eb754cce07bd/events.out.tfevents.1712508317.eb754cce07bd.5646.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f0a641e2e401455e406a96febfffc7661f5d28d199095aa8f0e7e990373e3f
+size 5694

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50e37a263eff55b2a655dd9360f068cbdc6e5c0f9014818707c66081f7d2f9f
+oid sha256:df5ff28e042be64aab8b07fa46a6d9b4fcd4f382a41b5425f45e4a9ea3b71c44
 size 5048