Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "UFNLP/gatortronS",
+  "architectures": [
+    "MegatronBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "megatron-bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_type": "BertWordPieceCase",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50176
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623d4e6a4cc7fde74433f6ea4008201c6c51a2adbe119cedb9de35493ee49cf4
+size 1421124256

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 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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": 2.0,
+  "eval_steps": 500,
+  "global_step": 2508,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.39872408293460926,
+      "grad_norm": 9.840682983398438,
+      "learning_rate": 4.63429565483241e-05,
+      "loss": 0.5605,
+      "step": 500
+    },
+    {
+      "epoch": 0.7974481658692185,
+      "grad_norm": 4.425215721130371,
+      "learning_rate": 3.4207917862252084e-05,
+      "loss": 0.2413,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1961722488038278,
+      "grad_norm": 0.04050261154770851,
+      "learning_rate": 1.83633111222982e-05,
+      "loss": 0.1967,
+      "step": 1500
+    },
+    {
+      "epoch": 1.594896331738437,
+      "grad_norm": 0.4518131911754608,
+      "learning_rate": 5.1924086239082456e-06,
+      "loss": 0.1003,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9936204146730463,
+      "grad_norm": 0.030251897871494293,
+      "learning_rate": 1.334930716231919e-09,
+      "loss": 0.1014,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "step": 2508,
+      "total_flos": 9345407711453184.0,
+      "train_loss": 0.239293363770066,
+      "train_runtime": 1172.3192,
+      "train_samples_per_second": 8.554,
+      "train_steps_per_second": 2.139
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2508,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1254,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9345407711453184.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe701c4ad0765573802ced6fb496a76d11e11a8cac73fcbfc66bee9bd7a7048b
+size 5048