Training in progress, step 20

config.json

@@ -16,7 +16,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
   "decoder_start_token_id": 50258,
-  "dropout": 0.0,
+  "dropout": 0.3,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14884ba5dcecbe7c2d376cd3fe05b3c7ef979aec299fc1d61c2a71d1a68a56f
+oid sha256:5c43ec74c68d2dc5d9a9d12bd295c108721baa3c5a69c4a74e11ee33c029d904
 size 966995080

runs/Jan03_13-49-40_e0cb327d3a71/events.out.tfevents.1735912181.e0cb327d3a71.6147.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b309643db2f478880068a5edf1f65561a8d99cd1ff830decdd3e393f7e59e957
+size 6771

runs/Jan03_14-07-02_e0cb327d3a71/events.out.tfevents.1735913227.e0cb327d3a71.6147.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bceeff5ca25560b913e01f7197486ca0718153f26528047edc162486b7649714
+size 7431

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff30720536be14e8834e0b3e78bdb93826c47bfc0fb4380ae5bd79de6164f762
+oid sha256:c2ad5e77f195784c2e73123e500dd4b5fd86f644ff29b0a011b7447081265753
 size 5496