Upload folder using huggingface_hub

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-multilingual-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e454d2ba077b5ec84a038c205cb4d2b7573f80f9310306dc28c2bc5f14b5126d
+size 669452284

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92390fe34d37f04f6b8b9a5cfe23c3021a604f6285ec98fe752814f355cf57a
+size 1339025658

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f9577a6d29dd0b8b33969a8f9c4b5299b13a5d5a86766b053ac56dd7eed633
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0a3bcd3d535fdd37bd63a887f0093240447dc6b76b341b99c63f5f7913ac80
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 +1,55 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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 +1,64 @@
+{
+  "best_metric": 0.06644001603126526,
+  "best_model_checkpoint": "test_training/checkpoint-1689",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1689,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.5198342214328006e-05,
+      "loss": 0.2846,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.951,
+      "eval_loss": 0.1446249932050705,
+      "eval_runtime": 2.3598,
+      "eval_samples_per_second": 423.772,
+      "eval_steps_per_second": 26.698,
+      "step": 563
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.039668442865601e-05,
+      "loss": 0.0949,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.975,
+      "eval_loss": 0.07110089808702469,
+      "eval_runtime": 2.3732,
+      "eval_samples_per_second": 421.368,
+      "eval_steps_per_second": 26.546,
+      "step": 1126
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 5.595026642984015e-06,
+      "loss": 0.0443,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.978,
+      "eval_loss": 0.06644001603126526,
+      "eval_runtime": 2.3768,
+      "eval_samples_per_second": 420.736,
+      "eval_steps_per_second": 26.506,
+      "step": 1689
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1689,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2275709307154368.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6dcd8dbf5a28624f9c1efe2e45750d1d645d3fc1e6f3c1536a5b6bb4428f98
+size 4600