Training in progress, epoch 1

config.json

@@ -3,12 +3,12 @@
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 512,
+  "d_ff": 1024,
   "d_kv": 16,
-  "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,
@@ -16,9 +16,9 @@
   "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,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82501c3334fb8e6973829a23d0213e59b4e7037691e9dd9985e3cdc408f9986
-size 10059592
+oid sha256:ef6cd9f1ef37fbcf6174af8206701471b3f62ca482e8506e038e750b88ec297c
+size 20350456

runs/Nov23_07-14-43_3a71d3232b61/events.out.tfevents.1700723683.3a71d3232b61.1811.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6912917d179b10a8c6fdc312fe80477e2b0045200e89fd5b0a638b60015958bd
-size 4779
+oid sha256:e6627a35cb0a568e8e4ba0803c8ddb2ba7b5dba12063d9400a379daabc800962
+size 4936

runs/Nov23_07-18-29_3a71d3232b61/events.out.tfevents.1700723910.3a71d3232b61.1811.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7571ccd91f56142cc6694c1a8b73c571c9f796d9bece9a1a8cdda4fd4ea3d44
+size 4460

runs/Nov23_07-20-21_3a71d3232b61/events.out.tfevents.1700724021.3a71d3232b61.1811.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3700cdff63c2f051cc04ae9050afc42ad0a201e69038a578e39884af71ffd05
+size 4780

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14f92b265c7ab2ddea4316dcf8aa4803b0f19d2caa9e7fb4c63b143248466f6
+oid sha256:9afbf827753644284e0289cfef0991d160e429097acde94a0a51d0a25232133a
 size 4728