Training in progress, step 1000

config.json

@@ -1,46 +1,61 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-ko",
+  "_name_or_path": "Helsinki-NLP/opus-mt-ko-en",
   "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": [
     [
-      32000
+      65000
     ]
   ],
   "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": 32000,
-  "decoder_vocab_size": 32001,
+  "decoder_start_token_id": 65000,
+  "decoder_vocab_size": 65001,
   "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": 2,
-  "forced_eos_token_id": 2,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 65001,
+  "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": 32000,
+  "pad_token_id": 65000,
   "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": 32001
+  "vocab_size": 65001
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa9d18b1a5093ed5cfe5c2949dd5d57427390358fa12d62fe0f998b09b7d2d2
-size 836663220
+oid sha256:b0b4add4f0cf65b0af2359c06d0fffdd96119531dc68cd0301cd47c29cbed886
+size 309965092

runs/Mar16_20-02-21_4b27bba79272/events.out.tfevents.1710619342.4b27bba79272.329.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2685d65735f41baac8ee6d712bee34c3a667134b164da214f18f1eccf22a9250
+size 6249

tokenizer_config.json

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "1": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32000": {
+    "65000": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,
@@ -30,9 +30,9 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "separate_vocabs": false,
-  "source_lang": "en",
+  "source_lang": "kor",
   "sp_model_kwargs": {},
-  "target_lang": "ko",
+  "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 sha256:5303b8abc353822dde0c2d92f1c47094cd571c6c5af88789f2e782b5b23c4b70
+oid sha256:fd74e14f3871d8f882cc8d16da6b9d64171e5ff0f933b622ec9c1e1d7f631244
 size 5048