Training in progress, epoch 1

config.json

@@ -3,12 +3,12 @@
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 512,
+  "d_ff": 1024,
   "d_kv": 64,
-  "d_model": 128,
+  "d_model": 256,
   "decoder_start_token_id": 259,
   "dense_act_fn": "relu",
-  "dropout_rate": 0.1,
+  "dropout_rate": 0.3,
   "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": 6,
-  "num_heads": 6,
-  "num_layers": 6,
+  "num_decoder_layers": 4,
+  "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:bc7ca6985fa913392b3af5d0f22cbf126ee5a39d2404b65ed1dcda7ace1865e6
-size 20676648
+oid sha256:64074984c82564ad116c77016899f10b8efdc8459f5fbbc88c43d5cb392cc30c
+size 29788248

runs/Nov27_07-09-33_3b954b0fb60c/events.out.tfevents.1701069321.3b954b0fb60c.460.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c94fb65c620c86a2ddcfcc3073a445cc329d7b568733b246c1c3224040afc7c
+size 414

runs/Nov27_07-16-15_3b954b0fb60c/events.out.tfevents.1701069375.3b954b0fb60c.460.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d041161f4c1251c55caf0cf134797917c6d285d0e966f6ac79702fc5f2f6df
+size 4781

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060cfd4299329132d56f829b7ad06ac79475d6a85f01581584c908d291a7a6ad
+oid sha256:01dd869cc1356eed4d5106befc1b218a9847b77edd623fa7a2118d00d63d8a78
 size 4728