Upload 11 files

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "csebuetnlp/banglabert",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "finetuned": true
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 32000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02beba05584c751c3d3ac175d5bec51090ef82889f9ea239302a4f078b2af324
+size 885083345

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668c4a0ad68897681e24370dde42e9a68301098659483716309e86232d28d00a
+size 442569161

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3192583f527d731f7eacd327b0ae96db503f69259f461b511d4a2debb1a4fba
+size 14657

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d9112604f9151814fbabf650061431121280f4a3332b1d5f30e0b406f999a9
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab30e4fc2dcc56bde2f92dcb3c805b8cb3b5dd1ceaf6254ac78d236527ee31b1
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": false, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "tokenizer_file": null, "name_or_path": "csebuetnlp/banglabert", "tokenizer_class": "ElectraTokenizer"}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.7233428496645763,
+  "best_model_checkpoint": "outputs/banglabert/checkpoint-1179",
+  "epoch": 3.0,
+  "global_step": 1179,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.3898305084745766e-07,
+      "loss": 1.1083,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.970782280867107e-05,
+      "loss": 0.7903,
+      "step": 393
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7364390555201021,
+      "eval_f1": 0.6591342767636649,
+      "eval_loss": 0.6260421276092529,
+      "eval_precision": 0.716418619657342,
+      "eval_recall": 0.6696257402218171,
+      "eval_runtime": 0.9075,
+      "eval_samples_per_second": 1726.789,
+      "eval_steps_per_second": 53.997,
+      "step": 393
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.4891611687087655e-05,
+      "loss": 0.5167,
+      "step": 786
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7523931078493937,
+      "eval_f1": 0.6965041241727926,
+      "eval_loss": 0.6028799414634705,
+      "eval_precision": 0.7288354571291619,
+      "eval_recall": 0.6975188399488532,
+      "eval_runtime": 0.907,
+      "eval_samples_per_second": 1727.768,
+      "eval_steps_per_second": 54.027,
+      "step": 786
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.540056550424129e-08,
+      "loss": 0.3229,
+      "step": 1179
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7587747287811104,
+      "eval_f1": 0.7233428496645763,
+      "eval_loss": 0.6502572298049927,
+      "eval_precision": 0.7325984484643606,
+      "eval_recall": 0.7204468990033644,
+      "eval_runtime": 0.9072,
+      "eval_samples_per_second": 1727.261,
+      "eval_steps_per_second": 54.011,
+      "step": 1179
+    }
+  ],
+  "max_steps": 1179,
+  "num_train_epochs": 3,
+  "total_flos": 1049740313791680.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647f0a1915874e3220e263708fb7a3b71287c2a4a078bd97b436ac66a30723a5
+size 2671