Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/bart-large",
+  "_name_or_path": "facebook/bart-base",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,
@@ -11,18 +11,18 @@
   "bos_token_id": 0,
   "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
   "early_stopping": true,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 6,
   "eos_token_id": 2,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
@@ -43,8 +43,9 @@
   "model_type": "bart",
   "no_repeat_ngram_size": 3,
   "normalize_before": false,
+  "normalize_embedding": true,
   "num_beams": 4,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
   "task_specific_params": {

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6a180c498eceeed8d4f55e7583519142bd96cd71d94347855fc73033ba8993
-size 1625426996
+oid sha256:0de2e2b119385f61efe50e026b9fb5ffe6765bab41548c4cd12a9ec96547c139
+size 557912620

runs/Apr11_13-00-37_86457e1bc633/events.out.tfevents.1712840438.86457e1bc633.25.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce6f4a16bd632471f07edfa2fe2fd23d0b07ea2973e38b456f0d9f47721fb03
+size 6016

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7ffad5565cb40d9f93c977ef583fe9576dfdb95495aa31210dcbf4b6d054ae
+oid sha256:444927edb1b349de9e01397c79fe58ea8fff3d496f44843bb4256094d35a403d
 size 5048