Training in progress, step 10

config.json

@@ -24,7 +24,6 @@
   "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": true,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
@@ -45,8 +44,8 @@
   "length_penalty": 2.0,
   "max_decoder_position_embeddings": 1024,
   "max_encoder_position_embeddings": 16384,
-  "max_length": 512,
-  "min_length": 256,
+  "max_length": 256,
+  "min_length": 128,
   "model_type": "led",
   "no_repeat_ngram_size": 3,
   "num_beams": 2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a105de7a2dcc684878dea5e6b0ed2b65207019f8d813f0bd3e1bae08d56fba54
+oid sha256:b7455581ba41b997039883a26eeeed258740e22133fe84af4edd90780e1497de
 size 647614116

runs/Jul07_02-45-31_56a5d84e66da/events.out.tfevents.1720320345.56a5d84e66da.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cca0dbc4871f3166c27d952f6129dd15ca6236d4a8c44097c9be0522aa85f6e
+size 5797

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 256
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5916a8649818649a2a5f89d99b862d6173b7cc4bd8c9d8819eb325d8604b6f55
+oid sha256:518e3ea9bbfadf8f6f9a2e00e8c2f104262a2aea08ed9eb73247c938438ff5b6
 size 5240