Upload folder using huggingface_hub

https:/huggingface.co/mbzuai-ugrip-statement-tuning/MBERT_1e-06_32_0.1_0.01_50k/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

https:/huggingface.co/mbzuai-ugrip-statement-tuning/MBERT_1e-06_32_0.1_0.01_50k/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c9be90f1570016ef4ac68be88586b56e88a854d7d79209ff5b49e82fd036c7
+size 711443456

https:/huggingface.co/mbzuai-ugrip-statement-tuning/MBERT_1e-06_32_0.1_0.01_50k/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003d7dfccf8e92b94859db27f89202485fd0972f2060486e119ed2bd5c4b559e
+size 1423007994

https:/huggingface.co/mbzuai-ugrip-statement-tuning/MBERT_1e-06_32_0.1_0.01_50k/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:917e9b57d8cedd54a7ddddaecf7ef32c1bafae84206dd208bce761fd82d605ab
+size 14244

https:/huggingface.co/mbzuai-ugrip-statement-tuning/MBERT_1e-06_32_0.1_0.01_50k/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5aff4a518a696b984cea0adf72caacd8bef2db486461e739263aa607e0c58c
+size 1064

https:/huggingface.co/mbzuai-ugrip-statement-tuning/MBERT_1e-06_32_0.1_0.01_50k/trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_metric": 0.7009812997593038,
+  "best_model_checkpoint": "./MBERT-outputs-0610/checkpoint-5000",
+  "epoch": 5.685856432125089,
+  "eval_steps": 1000,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7107320540156361,
+      "grad_norm": 2.5960001945495605,
+      "learning_rate": 9.795972094247729e-07,
+      "loss": 0.6912,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7107320540156361,
+      "eval_accuracy": 0.5944,
+      "eval_f1": 0.618510158013544,
+      "eval_loss": 0.6674206256866455,
+      "eval_precision": 0.58840372226199,
+      "eval_recall": 0.6518636003172086,
+      "eval_runtime": 23.2535,
+      "eval_samples_per_second": 215.022,
+      "eval_steps_per_second": 6.752,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4214641080312722,
+      "grad_norm": 6.413941860198975,
+      "learning_rate": 8.479663024878241e-07,
+      "loss": 0.6339,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4214641080312722,
+      "eval_accuracy": 0.64,
+      "eval_f1": 0.6880415944540728,
+      "eval_loss": 0.5965415239334106,
+      "eval_precision": 0.6111453201970444,
+      "eval_recall": 0.7870737509912767,
+      "eval_runtime": 23.4927,
+      "eval_samples_per_second": 212.832,
+      "eval_steps_per_second": 6.683,
+      "step": 2000
+    },
+    {
+      "epoch": 2.1321961620469083,
+      "grad_norm": 5.231350421905518,
+      "learning_rate": 7.163353955508753e-07,
+      "loss": 0.5867,
+      "step": 3000
+    },
+    {
+      "epoch": 2.1321961620469083,
+      "eval_accuracy": 0.6612,
+      "eval_f1": 0.6682334508421465,
+      "eval_loss": 0.5709565281867981,
+      "eval_precision": 0.6602167182662538,
+      "eval_recall": 0.6764472640761301,
+      "eval_runtime": 23.5269,
+      "eval_samples_per_second": 212.523,
+      "eval_steps_per_second": 6.673,
+      "step": 3000
+    },
+    {
+      "epoch": 2.8429282160625444,
+      "grad_norm": 7.240601539611816,
+      "learning_rate": 5.847044886139265e-07,
+      "loss": 0.5653,
+      "step": 4000
+    },
+    {
+      "epoch": 2.8429282160625444,
+      "eval_accuracy": 0.6712,
+      "eval_f1": 0.6905120481927711,
+      "eval_loss": 0.5536222457885742,
+      "eval_precision": 0.657347670250896,
+      "eval_recall": 0.7272006344171292,
+      "eval_runtime": 23.5409,
+      "eval_samples_per_second": 212.396,
+      "eval_steps_per_second": 6.669,
+      "step": 4000
+    },
+    {
+      "epoch": 3.5536602700781805,
+      "grad_norm": 7.705725193023682,
+      "learning_rate": 4.5307358167697773e-07,
+      "loss": 0.5491,
+      "step": 5000
+    },
+    {
+      "epoch": 3.5536602700781805,
+      "eval_accuracy": 0.677,
+      "eval_f1": 0.7009812997593038,
+      "eval_loss": 0.5454647541046143,
+      "eval_precision": 0.6575199722125739,
+      "eval_recall": 0.7505947660586836,
+      "eval_runtime": 23.4282,
+      "eval_samples_per_second": 213.418,
+      "eval_steps_per_second": 6.701,
+      "step": 5000
+    },
+    {
+      "epoch": 4.264392324093817,
+      "grad_norm": 12.029255867004395,
+      "learning_rate": 3.2144267474002893e-07,
+      "loss": 0.5394,
+      "step": 6000
+    },
+    {
+      "epoch": 4.264392324093817,
+      "eval_accuracy": 0.6754,
+      "eval_f1": 0.6931366988088485,
+      "eval_loss": 0.5441898703575134,
+      "eval_precision": 0.6624503071919046,
+      "eval_recall": 0.7268041237113402,
+      "eval_runtime": 23.6136,
+      "eval_samples_per_second": 211.742,
+      "eval_steps_per_second": 6.649,
+      "step": 6000
+    },
+    {
+      "epoch": 4.975124378109452,
+      "grad_norm": 8.800444602966309,
+      "learning_rate": 1.8981176780308015e-07,
+      "loss": 0.5368,
+      "step": 7000
+    },
+    {
+      "epoch": 4.975124378109452,
+      "eval_accuracy": 0.6744,
+      "eval_f1": 0.6787687450670876,
+      "eval_loss": 0.5373261570930481,
+      "eval_precision": 0.6755695208169678,
+      "eval_recall": 0.6819984139571769,
+      "eval_runtime": 23.4171,
+      "eval_samples_per_second": 213.519,
+      "eval_steps_per_second": 6.704,
+      "step": 7000
+    },
+    {
+      "epoch": 5.685856432125089,
+      "grad_norm": 11.326841354370117,
+      "learning_rate": 5.818086086613137e-08,
+      "loss": 0.5293,
+      "step": 8000
+    },
+    {
+      "epoch": 5.685856432125089,
+      "eval_accuracy": 0.6772,
+      "eval_f1": 0.692454268292683,
+      "eval_loss": 0.5362803936004639,
+      "eval_precision": 0.6665443873807777,
+      "eval_recall": 0.7204599524187153,
+      "eval_runtime": 23.5382,
+      "eval_samples_per_second": 212.421,
+      "eval_steps_per_second": 6.67,
+      "step": 8000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8442,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.47261539595248e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

https:/huggingface.co/mbzuai-ugrip-statement-tuning/MBERT_1e-06_32_0.1_0.01_50k/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac156cbe336ba60765eec489c9f988230678e2b06e5bc4122db7d4307ec33ea
+size 5048