Training in progress, epoch 1

config.json

@@ -17,11 +17,11 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "num_decoder_layers": 6,
-  "num_heads": 4,
+  "num_heads": 6,
   "num_layers": 6,
   "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
+  "relative_attention_max_distance": 64,
+  "relative_attention_num_buckets": 16,
   "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 sha256:7c189e839dfced6d1345bb5db2a989b41ed09b0367e249d3606468b9a56534d5
-size 15958264
+oid sha256:1316b80c350e966fc9bfea6e3bbcb1378db66720fac6fd5018cd7b926350d829
+size 20676648

runs/Nov25_05-37-01_bb1ce505c0be/events.out.tfevents.1700890622.bb1ce505c0be.734.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4de53e80c7d0f5dce53abde89f48d5cd117af7ad94325542dea0f54dd7013f0
-size 6711
+oid sha256:53010642c0da2808407bd853251eea343977593e71c85cb5e5897d6b4ff41b07
+size 6868

runs/Nov25_05-45-55_bb1ce505c0be/events.out.tfevents.1700891155.bb1ce505c0be.734.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6426373e1f14e5aa2a900179ae3a87b6f418dc41630337e2d50504405cf721
+size 4778

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1127adc2d9f79f6c3c7cfb85b591bd76fc07939189b5452767975124ebc26031
+oid sha256:3b26ad5e730fc43a1790d6c888c85d7986e99f90f7f74ff0eaa901e46c7fcff4
 size 4728