Training in progress, epoch 1

config.json

@@ -3,9 +3,9 @@
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 512,
+  "d_ff": 512,
+  "d_kv": 16,
+  "d_model": 128,
   "decoder_start_token_id": 259,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -17,11 +17,11 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "num_decoder_layers": 6,
-  "num_heads": 8,
+  "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 sha256:68154991de65d84b4f3f603dfd6ba7a0ad682e14feaf1821ae39e5c5c7d20dbd
-size 177032232
+oid sha256:504653bec37386b5ec098c3494c4a6d91de7df8f353600ac1b937c6f8c40f7a5
+size 10059592

runs/Nov22_13-30-49_0fe1d4a1022c/events.out.tfevents.1700659850.0fe1d4a1022c.209.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497d4dce39ca26e3075777a01f21232eeebb2fd739c1dd4ab4a40c31d068cd9d
+size 4778

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f226d8bdb52915bd23261dd9e3c3cea5e78144dd73f2a1d943aa51d855bf5b2
+oid sha256:0a7b51e1dcb698654b5ea04fbf183b7449b22b384c05092cb45754279f3c5175
 size 4728