Upload 11 files

config.json

@@ -0,0 +1,44 @@
+{
+  "_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,
+  "id2label": {
+    "0": "Mixed",
+    "1": "Positive",
+    "2": "Neutral",
+    "3": "Negative"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Mixed": 0,
+    "Negative": 3,
+    "Neutral": 2,
+    "Positive": 1
+  },
+  "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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac7e242ff163ef4dbd73c8ab293a8d223763ede1a1891c6d6f70e6b9a5845ab
+size 711449608

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6010baabbefd5d61ed5b783c7c34484bd905958a40f6ecfa5ce00c0db5212eb4
+size 1423020282

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e6a8a18325b04a29271914f5ccd3a9a6f2e06aeaa5c16b1e80b47040657a1c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e287a805c03d24771cc35d2be4d04d38171db0ebfbeeb6562a4a6c64af5b3d67
+size 1064

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 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": 0.6061349693251534,
+  "best_model_checkpoint": "bert-finetuned-sem_eval-georgian/checkpoint-2110",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.45023696682464454,
+      "eval_f1": 0.5087014725568942,
+      "eval_loss": 0.4644582271575928,
+      "eval_roc_auc": 0.6718009478672986,
+      "eval_runtime": 12.4119,
+      "eval_samples_per_second": 33.999,
+      "eval_steps_per_second": 4.27,
+      "step": 422
+    },
+    {
+      "epoch": 1.1848341232227488,
+      "grad_norm": 5.8598737716674805,
+      "learning_rate": 1.5260663507109007e-05,
+      "loss": 0.4952,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.523696682464455,
+      "eval_f1": 0.5441176470588235,
+      "eval_loss": 0.47526419162750244,
+      "eval_roc_auc": 0.6951026856240126,
+      "eval_runtime": 12.3933,
+      "eval_samples_per_second": 34.051,
+      "eval_steps_per_second": 4.277,
+      "step": 844
+    },
+    {
+      "epoch": 2.3696682464454977,
+      "grad_norm": 2.699039936065674,
+      "learning_rate": 1.052132701421801e-05,
+      "loss": 0.3968,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5616113744075829,
+      "eval_f1": 0.6025316455696202,
+      "eval_loss": 0.43833649158477783,
+      "eval_roc_auc": 0.7306477093206951,
+      "eval_runtime": 12.4177,
+      "eval_samples_per_second": 33.984,
+      "eval_steps_per_second": 4.268,
+      "step": 1266
+    },
+    {
+      "epoch": 3.5545023696682465,
+      "grad_norm": 6.871908664703369,
+      "learning_rate": 5.7819905213270145e-06,
+      "loss": 0.3198,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5734597156398105,
+      "eval_f1": 0.6,
+      "eval_loss": 0.49058645963668823,
+      "eval_roc_auc": 0.7306477093206951,
+      "eval_runtime": 12.4414,
+      "eval_samples_per_second": 33.919,
+      "eval_steps_per_second": 4.26,
+      "step": 1688
+    },
+    {
+      "epoch": 4.739336492890995,
+      "grad_norm": 3.2302420139312744,
+      "learning_rate": 1.042654028436019e-06,
+      "loss": 0.2409,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5829383886255924,
+      "eval_f1": 0.6061349693251534,
+      "eval_loss": 0.4966834783554077,
+      "eval_roc_auc": 0.7349921011058452,
+      "eval_runtime": 12.2307,
+      "eval_samples_per_second": 34.503,
+      "eval_steps_per_second": 4.333,
+      "step": 2110
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2110,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4440078789120000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9289e7ed2d6b6be882ea170903f05dfb5f32879370ff87bc6bad6dfb3529cc
+size 5368