Training in progress, step 500

config.json

@@ -19,7 +19,7 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": true,
+  "early_stopping": null,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
@@ -39,12 +39,12 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_length": 200,
+  "max_length": null,
   "max_position_embeddings": 1024,
   "model_type": "mbart",
   "normalize_before": true,
   "normalize_embedding": true,
-  "num_beams": 5,
+  "num_beams": null,
   "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
@@ -52,7 +52,7 @@
   "static_position_embeddings": false,
   "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.47.1",
   "use_cache": true,
   "vocab_size": 250054
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fcf37a910b0311b01f94b85ab2cb38ee289434f30d446d17932891b26406438
+oid sha256:4e91e1090a321cd6430ddacb75230d4cb2de08fec68ac5281c3fcc01b11662c0
 size 2444578688

runs/Jan07_11-37-45_86c481aef8d4/events.out.tfevents.1736249898.86c481aef8d4.1286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f576b178f1e090a5fad2214e024051d1b56db1004b5ab2685aa3def0c20b0357
+size 5960

runs/Jan07_11-38-39_86c481aef8d4/events.out.tfevents.1736249927.86c481aef8d4.1286.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95d49efc3911473849ce90c1e9c627af75df798fa4accc1811717a3ac85691c
+size 5960

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9472a5f3613a4d5b4fc0bc78c944dd2edbcb2ceed3defe1c760efdc0ffc0fded
-size 17110041
+oid sha256:ef126060ddcab67250020d3e4fff2150e3946ba9e7cea24b2a18dd969e0469da
+size 17110019

tokenizer_config.json

@@ -512,9 +512,10 @@
     "sl_SI"
   ],
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "<s>",
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "mask_token": "<mask>",
   "model_max_length": 1024,
   "pad_token": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:350625b1a49e4228e404a4c08183efaf9d5f5b0229a0c9c5b08ef012d3fd67d6
-size 5048
+oid sha256:6988008c2aa4b2c21252735654501e234b333b261d48eceb344f74e201e3b4d1
+size 5432