Training in progress, epoch 1

config.json

@@ -3,12 +3,12 @@
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 1024,
+  "d_ff": 512,
   "d_kv": 64,
-  "d_model": 256,
+  "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_decoder_layers": 6,
   "num_heads": 4,
-  "num_layers": 4,
+  "num_layers": 6,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0912fff8c1c2396c2e6ab226095a264d0ccc8af7bd541ba692174ebc5cb02428
-size 29788248
+oid sha256:2a9426142f51f4e73a4857ab0271640c22c211aab594757d0f84bee56f6836c4
+size 15958264

runs/Nov25_05-18-14_bb1ce505c0be/events.out.tfevents.1700890527.bb1ce505c0be.734.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c6bd79ae9bbc9bfb3d4d3092a8f2a487df112aa022e89a388cb7a1b92fb32c
+size 414

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8deee2777112597eb9a4b8348dcc2a6fea79d9d560e391826e47bae939e21e8
+size 4779

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb8178db9b0c5c0660a4dd04fe52f73bb36e04355a17f935adc18fe344a7d1a
+oid sha256:1127adc2d9f79f6c3c7cfb85b591bd76fc07939189b5452767975124ebc26031
 size 4728