Training in progress, step 500

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",
@@ -8,6 +9,7 @@
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
+  "bos_token_id": 0,
   "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
   "d_model": 512,
@@ -18,7 +20,6 @@
   "decoder_start_token_id": 59513,
   "decoder_vocab_size": 59514,
   "dropout": 0.1,
-  "dtype": "float32",
   "encoder_attention_heads": 8,
   "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
@@ -49,7 +50,8 @@
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
-  "transformers_version": "4.57.0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "vocab_size": 59514
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89be58fcd3cdb715d98a0e9736f958fc00d0b141aa13a172adfae8f9e0d5a47
+oid sha256:13d62c1ba27a40972927b375990da3f51f19c6fdb2ae23cd6a82b52924fc43ab
 size 298705768

tokenizer_config.json

@@ -27,7 +27,6 @@
   },
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "extra_special_tokens": {},
   "model_max_length": 512,
   "pad_token": "<pad>",
   "return_tensors": "pt",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06989971985e80e8e736b53d0658f55e396e9585f1d85de49bfc03cf20ce3c8
-size 6033
+oid sha256:442fc8b18145f882b2228f9118e934e3d0cbc859baa2c87a520b210a63f6e337
+size 5841