Training in progress, step 500

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "facebook/m2m100_418M",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
@@ -14,7 +13,7 @@
   "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": 0.05,
@@ -23,15 +22,15 @@
   "gradient_checkpointing": false,
   "init_std": 0.02,
   "is_encoder_decoder": true,
-  "max_length": 200,
+  "max_length": null,
   "max_position_embeddings": 1024,
   "model_type": "m2m_100",
-  "num_beams": 5,
+  "num_beams": null,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.52.4",
   "use_cache": true,
   "vocab_size": 128112
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b73978afc58a5a9e0076cd830517436baea323285adcd929b1fb5d6c3ab28cf6
+oid sha256:4ee49321ce91d781660a8f2e7ce76d1a058751f05cce4a023a48979a3cf6254d
 size 1935681888

runs/Jun23_18-51-01_a9c45816e4b8/events.out.tfevents.1750704682.a9c45816e4b8.1362.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:320553b9da509238ed0a26cb6f87bed42020dee54074141a828d49c0601a07ba
+size 5559

tokenizer_config.json

@@ -936,8 +936,9 @@
     "__zu__"
   ],
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "language_codes": "m2m100",
   "model_max_length": 1024,
   "num_madeup_words": 8,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737662fe97f56b6a2a82ff756ac3d931ef5c182e19178f30481200bdb687739d
-size 5368
+oid sha256:a3248cc69d476a75b43dfdf4b8127b9685b788a88b61f6b85b3f00049b4478d5
+size 5496