Training in progress, step 500

config.json

@@ -19,7 +19,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
   "decoder_start_token_id": 50258,
-  "dropout": 0.0,
+  "dropout": 0.05,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
@@ -146,7 +146,7 @@
   ],
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "use_cache": true,
+  "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e5ff453c17705ae5a7d0a7ebf1ab9e32a96a6b804a849199afdd40b666ef212
+oid sha256:336d324d6edcc050ac8f83d2c5fc03922921f692fa2495a95e3ec6a4edc051e5
 size 966995080

runs/Jun10_09-22-40_a346b6132474/events.out.tfevents.1718011371.a346b6132474.1109.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92597a46866f46586f2ff32b360a60aaeaf772834057ecbc23918375413d72e2
+size 7107

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0dc3169168839c2e89012de2922cd8bdc0676be11c955fb8211008fd579a71e
+oid sha256:0d7204b2b5c4014005cc71264b390b42580d76384589f6c7c08913c2599e81a7
 size 5240