Training in progress, epoch 1

config.json

@@ -3,12 +3,12 @@
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 1024,
-  "d_kv": 64,
-  "d_model": 256,
+  "d_ff": 512,
+  "d_kv": 16,
+  "d_model": 128,
   "decoder_start_token_id": 259,
   "dense_act_fn": "relu",
-  "dropout_rate": 0.3,
+  "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
@@ -16,12 +16,12 @@
   "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
-  "num_decoder_layers": 4,
-  "num_heads": 4,
-  "num_layers": 4,
+  "num_decoder_layers": 6,
+  "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:fd98d82a7e5109bd0f51c905d5aa8743443adfe05ef7f7d34de0063de93438b2
-size 29788248
+oid sha256:38e6028f018e88b8025753bd0a59403fb6f73c033aecf4d1272301b74379dc85
+size 10059592

runs/Nov22_13-12-50_0fe1d4a1022c/events.out.tfevents.1700658779.0fe1d4a1022c.209.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:002c492abc5288cee7c020efb66705a807a622ae97f72f57aabafac16e72e3e6
-size 5263
+oid sha256:05fcfd6185d972dd871d7048585b7ca0effdf0781b00ce71e57794a59046275c
+size 5420

runs/Nov22_13-17-15_0fe1d4a1022c/events.out.tfevents.1700659035.0fe1d4a1022c.209.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c79c994185e1879ba8a9b2e5d703480ba74b732fba34a4847d16ced1916d07
+size 4778

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29c28dea34de8b442d7d8e56cf451763e23d7bfe7c865b0fe5eaaae7a589890
+oid sha256:1574c3c6dfa0ee6a479410ff442ed0cd293fcdc7e4f95f0da9b2fc131d2c1535
 size 4728