Training in progress, epoch 0

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a372fe22b8e62bcfc2dfcbcccee830d1aaf62f1325f034fa546e3bb5f416a30
-size 242041896
+oid sha256:2ab1c621694f35c47e1db4448de4d08907ea1abfedd5cb3b4db368d1f225c803
+size 891644712

runs/May16_15-58-34_66e3db6fc9ff/events.out.tfevents.1715875115.66e3db6fc9ff.2789.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e2ea0d6fd1fc4c9de5e6eca7e2db0df42a75594dcfac4aba809509faf9518f
+size 6047

tokenizer_config.json

@@ -932,7 +932,7 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "legacy": true,
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd18fc8c8283fcfcf856036769c291053042398b8b48c736cdc814771be9a822
+oid sha256:b4a898fbfaf959d51a55447a3dcae239cac48c34938fca93cf64ef0663b40727
 size 5176