Training in progress, step 1000

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "M2M100ForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "model_type": "m2m_100",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "tokenizer_class": "NllbTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 256206
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a045a9f440e174caaf7368a03a477556f357b55e4b67eb70ca3e22663b4f524
+size 2460354912

runs/Jun18_12-20-29_b153835020e3/events.out.tfevents.1750249312.b153835020e3.452.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e100331086f3f67a56617bf46a99d2fd096a0202833b092becaa0904be01018b
+size 5793

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc744dd893b3c98572460035a74fd10d7c077f4b329c3b07b931d25a7368f596
+size 5496