Training in progress, epoch 1

config.json

@@ -4,7 +4,7 @@
   ],
   "classifier_dropout": 0.0,
   "d_ff": 1024,
-  "d_kv": 16,
+  "d_kv": 64,
   "d_model": 256,
   "decoder_start_token_id": 259,
   "dense_act_fn": "relu",
@@ -20,8 +20,8 @@
   "num_heads": 4,
   "num_layers": 4,
   "pad_token_id": 0,
-  "relative_attention_max_distance": 64,
-  "relative_attention_num_buckets": 16,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5a70ba296b3dc067cca4f7ad8ebddd6b199e562bc55b375df682295a0b1bb4
-size 20350456
+oid sha256:45e850bdc2efb424588e8f58e310c64847be7cee47fe7a18f7ef240ee6577b45
+size 29788248

runs/Nov25_04-58-25_bb1ce505c0be/events.out.tfevents.1700888314.bb1ce505c0be.734.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5afa36a0c35b47fe366e25432cf662ce7448d09efe19fe63648e97e65809949
+size 4184

runs/Nov25_04-59-07_bb1ce505c0be/events.out.tfevents.1700888348.bb1ce505c0be.734.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137dd70814716f28f12680e614fba276ec6716cc0725b188acbaedf0766a5c66
+size 4782

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d0fe48c281bb738d90c4b1a6d0b7ad84e16adee5a55dc9be65c85575416b0e5
+oid sha256:c1747bc837d2be6c84a8f287ae7842474654dac5218d6f08edacbb3ccdd5abb3
 size 4728