Training in progress, step 500

config.json

@@ -1,31 +1,31 @@
 {
-  "_name_or_path": "csebuetnlp/banglat5",
+  "_name_or_path": "csebuetnlp/banglat5_small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
+  "dense_act_fn": "relu",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
+  "feed_forward_proj": "relu",
   "gradient_checkpointing": false,
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
+  "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7208400272cc18fcfa646d73a1b4c8c1679e66e904307e45c2c5ab858b0b478b
-size 990345064
+oid sha256:896d81c9c2f8bda740e8c1212864462b807d19499856e756b34ba07afb231c61
+size 242041896

runs/Jan15_05-31-41_0049146a7df3/events.out.tfevents.1705296715.0049146a7df3.984.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d99bb53d88530274a3f4f4bee862fbac80256d52691fbb3b04dbeecf7fba5c
+size 4727

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5863b96e667eabb03e543c22c33e2a4098d0f8fd1e8c7a1253877c40fe862e41
+oid sha256:4a039a243671d41d92ba8efedd684e7b6cce617f9786522e1f14831bf35ee6ea
 size 4792