Upload 10 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "SeanLee97/angle-bert-base-uncased-nli-en-v1",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce04059ac6eb49df9708239d0425c0257642a7be47b9a92da5294aae849d2d
+size 437951328

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a0b5d07f62f121e3652e95c39756950011c7b32e7df9e8bfbd7eb415f64f93
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4dd5d21261ead9d9eab7f7dc22493064d9557782331e0d6281822a76cade69
+size 1064

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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
+    }
+  },
+  "additional_special_tokens": [],
+  "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 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.444444444444445,
+  "eval_steps": 1000,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 18.646621704101562,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 12.9379,
+      "step": 100
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 15.787500381469727,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 12.4243,
+      "step": 200
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 24.62742805480957,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 12.1655,
+      "step": 300
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 22.622655868530273,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 11.9433,
+      "step": 400
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 24.53895378112793,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 11.9653,
+      "step": 500
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 29.335464477539062,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 11.8621,
+      "step": 600
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 23.47711753845215,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 11.5167,
+      "step": 700
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 21.372766494750977,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 11.3985,
+      "step": 800
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "total_flos": 1007165894833152.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0224374c51b3916102b97dddc6026a370bf994031b116366b68b4edfe6c88efb
+size 5048