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 sha256:7e6a3f7ca97fb77f113c075842f0d291872cbee94e37d922b91f817da8bd0b01
+size 2460354912

runs/May14_21-49-50_9639917d017a/events.out.tfevents.1747259404.9639917d017a.6035.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8665452c7a52c2cecaf3761e8950237663e5731295291ebb54305bb4082f4b
+size 5849

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617400f6484e94dc55a95e08641de4ab395cf85955c4684aa4ba1f3d7402280a
+size 5496