Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/long-t5-local-base",
+  "_name_or_path": "google/long-t5-tglobal-base",
   "architectures": [
     "LongT5ForConditionalGeneration"
   ],
@@ -9,7 +9,7 @@
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
-  "encoder_attention_type": "local",
+  "encoder_attention_type": "transient-global",
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
   "global_block_size": 16,
@@ -29,7 +29,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
+  "transformers_version": "4.46.3",
   "use_cache": true,
   "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46e3719aa0aa1269fd478f3d9078fc4462d377f129b12526e870c1deb8ac5439
-size 1089042632
+oid sha256:5262ebc1956a5e5e53b4a46ffdb877dee40648cb4599bb18c1b98aef9b7da640
+size 1187780840

runs/Dec05_17-59-04_d9d9476b9d67/events.out.tfevents.1733421547.d9d9476b9d67.401.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5d75ca27173e129d58bce63f1b5ee5ace78fff67aca569b064a68bfd71fb56
+size 5445

runs/Dec05_17-59-44_d9d9476b9d67/events.out.tfevents.1733421585.d9d9476b9d67.401.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6cffe45ba9c0481edceb681385037e080189360c9b0a1f86d28f78a6f5cd7a0
+size 5445

runs/Dec05_17-59-54_d9d9476b9d67/events.out.tfevents.1733421594.d9d9476b9d67.401.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2c05b0cb99a7cce77bf89926b74453c083178b1d37bbb26e62fe2bc97af0fd
+size 5656

tokenizer.json

@@ -6,7 +6,16 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": null,
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66011c3e63c388754f2df284173a6a1c49a892d57c0842d8233534140d3ffd4e
-size 5432
+oid sha256:5cf3645329d5931c4d7daa763a415555ae15d0f7cd1141faadbb249ecf09de18
+size 5496