Upload 11 files

Added base model first try

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+vocab.txt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "ai4bharat/IndicBERTv2-alpha-SentimentClassification",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "amazon_multilingual_corpus",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 200001
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e867bc0ebec92cc75bcfc58f7dfefa1dc9f36a4527c1ebc2163c9da548afdb61
+size 1917273285

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b833ed27fedaebfc921e40ddab98b0c3a5181b1a9762ec3ede58b0e81c9e88b5
+size 958646641

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b8f9ad019c832fc01c19ce85606aea6d120663221ce84b07b17747824c5616
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60debbc550057e55e026ed0aa2e95e91ff118123c9103307f57db60b884529d
+size 627

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.6928467154502869,
+  "best_model_checkpoint": "./indicBERTClassifier/checkpoint-2000",
+  "epoch": 4.0,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7427,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6978471279144287,
+      "eval_runtime": 15.9862,
+      "eval_samples_per_second": 125.108,
+      "eval_steps_per_second": 31.277,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7037,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.701702892780304,
+      "eval_runtime": 20.3617,
+      "eval_samples_per_second": 98.224,
+      "eval_steps_per_second": 24.556,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.7023,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.698264479637146,
+      "eval_runtime": 16.271,
+      "eval_samples_per_second": 122.918,
+      "eval_steps_per_second": 30.73,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.6995,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6928467154502869,
+      "eval_runtime": 16.1542,
+      "eval_samples_per_second": 123.807,
+      "eval_steps_per_second": 30.952,
+      "step": 2000
+    }
+  ],
+  "max_steps": 2500,
+  "num_train_epochs": 5,
+  "total_flos": 526222110720000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183ad1811952870ae68d9312a2d8bc263733db126cbcfde3d87efc99c4c56af6
+size 3963

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f299a313a605cb02d720b4aeb94a9948cfcca3dec146bdf65cc907f749d805e
+size 1512865