Training in progress, step 500

config.json

@@ -1,33 +1,67 @@
 {
-  "_name_or_path": "csebuetnlp/banglat5",
+  "_name_or_path": "facebook/bart-large-xsum",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
   "architectures": [
-    "T5ForConditionalGeneration"
+    "BartForConditionalGeneration"
   ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 768,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "eos_token_ids": [
+    2
+  ],
+  "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
-  "initializer_factor": 1.0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 62,
+  "max_position_embeddings": 1024,
+  "min_length": 11,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 6,
+  "num_hidden_layers": 12,
   "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "replacing_rate": 0,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "task_specific_params": {},
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,
-  "vocab_size": 32128
+  "vocab_size": 50264
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7208400272cc18fcfa646d73a1b4c8c1679e66e904307e45c2c5ab858b0b478b
-size 990345064
+oid sha256:cc83bb9c8c9c05ff8c91ab40b500ce71f0c6bad4295b7ccaf0ef7708f0c3fdf4
+size 1625422896

runs/Jan14_22-44-18_fa5bd509142b/events.out.tfevents.1705272269.fa5bd509142b.1221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5acb7a893e57421fbfff55c7f76c30e7733344e3ce17554f9e1b8be5ef1888a
+size 5473

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab9f093e7386c6ac97b1ebd953264233ff3a17bcafb3c15d9baf0b96feba019
+oid sha256:203a9f52fec6a10165a39eed09952f43f988ebc6a101a423e251dde27c4925ca
 size 4792