Training in progress, step 10

config.json

@@ -5,7 +5,7 @@
   "architectures": [
     "LEDForConditionalGeneration"
   ],
-  "attention_dropout": 0.2,
+  "attention_dropout": 0.5,
   "attention_window": [
     1024,
     1024,
@@ -23,14 +23,14 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
   "decoder_start_token_id": 2,
-  "dropout": 0.2,
+  "dropout": 0.5,
   "early_stopping": true,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 2,
-  "hidden_dropout_prob": 0.2,
+  "hidden_dropout_prob": 0.5,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6833928fd94296676788b3ae5bcb5badd92764adfdcae811254374a0bc23e72
+oid sha256:d0048b65168afc9cc7f51d62d32fda59f3224feff210052f29ba87932c6b1685
 size 647614116

runs/Jul21_15-34-15_77dc08e62a58/events.out.tfevents.1721576137.77dc08e62a58.100.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c851789e153773ba034289d069f0c9f15de256aa55f162adae2515d065916e57
+size 6130

runs/Jul21_15-46-22_77dc08e62a58/events.out.tfevents.1721576786.77dc08e62a58.100.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e190c9b0be35062ebc69133ac4fdcf058f2dc990f49d467e143eccd234f88c78
+size 5664

runs/Jul21_15-46-56_77dc08e62a58/events.out.tfevents.1721576819.77dc08e62a58.100.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f272328770ebbbfff3388a9e6507f3fce216f33af16d3716282e35c3639e89f9
+size 5871

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b9662da31dee40c02605d22ff6f526f002746b819796f8b23a77ef89bcd8d8
+oid sha256:4fb17a8c6e4947fa0cfcdbf7ba857b306e58c048e8e9a9acea2558a78d8cbc94
 size 5304