Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "microsoft/codebert-base",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382b73735c2358e701c58120b12dd5686cee397d92b1f6481db19cc30310678b
+size 498661926

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.txt

@@ -0,0 +1,5 @@
+step = 3
+_metadata = ContainerMetadata(ref_type=typing.Any, object_type=<class 'dict'>, optional=True, key=None, flags={}, flags_root=False, resolver_cache=defaultdict(<class 'dict'>, {}), key_type=typing.Any, element_type=typing.Any)
+_parent = None
+_flags_cache = {'struct': None}
+_content = {'project_name': 'coq-theorem-embedding', 'experiment_name': 'infonce-file-final-1', 'log_level': 'INFO', 'dataset_path': './data/imm/', 'rankin_ds_path_statements': './data/imm/basic/Events_statements.json', 'rankin_ds_path_references': './validationSet/reference_premises.json', 'samples_from_single_anchor': 10, 'train_split': 0.8, 'val_split': 0.2, 'test_split': 0.0, 'model_name': 'microsoft/codebert-base', 'max_seq_length': 128, 'embedding_dim': 768, 'margin': 0.25, 'threshold_pos': 0.3, 'threshold_neg': 0.65, 'threshold_hard_neg': 0.45, 'k_negatives': 4, 'output_dir': './checkpoints/', 'steps': 100000, 'eval_steps': 200, 'evaluate_freq': 100, 'save_freq': 3, 'batch_size': 32, 'warmup_ratio': 0.1, 'learning_rate': 4e-06, 'random_seed': 52, 'wandb': {'enabled': True, 'project': 'coq-embeddings', 'entity': 'kozyrev-andreiii2016', 'tags': ['baseline', 'triplet']}, 'evaluation': {'k_values': [15], 'f_score_beta': 1, 'query_size_in_eval': 20}}