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,
@@ -16,9 +16,9 @@
   "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": 64,
   "relative_attention_num_buckets": 16,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0e7beeb9b3d714cfd4a63e0ef123d5075f8c5ae1d171c5ca98e30ffbb16713
-size 29787736
+oid sha256:d3a8e65e43b0054194dc59b9f3b489e9542fee2b3040ba2d36f8a39690590ec9
+size 10059592

runs/Nov23_07-11-01_3a71d3232b61/events.out.tfevents.1700723461.3a71d3232b61.1811.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e824d4802720ca08453c5c852969ed386472b695e49a461f6ae2f27957a37b
+size 4454

runs/Nov23_07-11-26_3a71d3232b61/events.out.tfevents.1700723487.3a71d3232b61.1811.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630cb60088d474293d43dacb5956308b19d050d6eeb9a889ea94ebe9170b407c
+size 4779

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_bos_token": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7fc95cde14b9eab8ea13f34449571c7b2f5cc1647d9677028afc6ec895ad75
+oid sha256:cf936f7f2828f9e1d0bd97fe2f711ae48980e968211c90abc22f63e8764da5fd
 size 4728