Training in progress, epoch 1

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/Colab Notebooks/HCI LAB/models/flan_t5_small-v4",
+  "_name_or_path": "google/flan-t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 1024,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 8,
-  "num_heads": 6,
-  "num_layers": 8,
+  "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 sha256:15c5bfcf40bae4f2e96b2bfc1b9ec6dacbc5739c4ee48c3a5689419810fd1e65
-size 307867048
+oid sha256:c58f4f5cb5cc81d56ac6bdd82f3e5baa92bc58e93b72f7e29af90e09984d2935
+size 990345064

runs/Feb06_02-14-59_9d94ef61723e/events.out.tfevents.1738808107.9d94ef61723e.540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40d1c612d51cefbd9e3a168baa4ca91df908f8f974d0a30e0049ddef7636c3a
+size 7330

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 256,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 256
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -931,16 +931,9 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "extra_special_tokens": {},
-  "max_length": 256,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544f8f3b72dee72d5784f9b5592eda50d327d094c8c8f0f55e71932c7aaea81d
+oid sha256:7f3c172a23cbf18e1e598b49be02710355f02037777a93e8259fb80c448a9549
 size 5432