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": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 256206
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d81a6d0aa33f08a49059855a38a33b4b87c9392ae7b35d568caa460f5c5c3b
+size 2460354912

runs/May09_12-17-06_874cfdf5b297/events.out.tfevents.1746793046.874cfdf5b297.177.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b330cca7cc151596a66849870eaab0f38c3203e6ce6168c273a1f0d102984d0
+size 5845

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d7a553d45ae22a5380a10aa6d385268544b99f52d5b95e3917532f686b6ae0
+size 5496