Training in progress, step 1000

config.json

@@ -14,16 +14,29 @@
   "d_model": 384,
   "decoder_attention_heads": 6,
   "decoder_ffn_dim": 1536,
-  "decoder_layerdrop": 0.0,
+  "decoder_layerdrop": 0.001,
   "decoder_layers": 4,
   "decoder_start_token_id": 50258,
-  "dropout": 0.001,
+  "dropout": 0.002,
   "encoder_attention_heads": 6,
   "encoder_ffn_dim": 1536,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 4,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50276
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "max_length": 448,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbcef5e2a7194062d61a9347991825202abe18b868b060f2ffbadf39cff4652f
+oid sha256:b5a08eabbc6c0d9d110c46d3698dcebf96be426dd9a315ad12899cda43d1cf56
 size 151097331

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ba97ab2c8a29b57887653d24c133456633e9515673a5fd3d099c5df2cd83ab
+oid sha256:c1e67d801aaa88c36784a2cf1f21d7f615ef79cd324b6fec8ebf6503a1fe78bd
 size 3567