Upload 11 files

checkpoint-6378/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Emergency",
+    "1": "Urgent",
+    "2": "Non-Urgent",
+    "3": "Routine",
+    "4": "Follow-up"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Emergency": 0,
+    "Follow-up": 4,
+    "Non-Urgent": 2,
+    "Routine": 3,
+    "Urgent": 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,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-6378/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a32027d80f03544cb668c61a921e561d1bcec80a8f406f85a9a24443670db82
+size 433279996

checkpoint-6378/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c3a18d0fa83d91f81d7d0a729605551fbefd4307e5a6c2aa8d336d4922a153
+size 866675450

checkpoint-6378/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3142eb9ef29f39c1056feaba012d70697a15cdef061694ac7929853189d9ee94
+size 13990

checkpoint-6378/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d09625be2a05e159fd29265bdc81fd5545deb31161b59e2885ce6d7adc35803
+size 1064

checkpoint-6378/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-6378/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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]"
+}

checkpoint-6378/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6378,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23518344308560676,
+      "grad_norm": 4.934643745422363,
+      "learning_rate": 1.8435246158670432e-05,
+      "loss": 0.5796,
+      "step": 500
+    },
+    {
+      "epoch": 0.4703668861712135,
+      "grad_norm": 2.5223684310913086,
+      "learning_rate": 1.686735653809972e-05,
+      "loss": 0.5163,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7055503292568204,
+      "grad_norm": 4.723271369934082,
+      "learning_rate": 1.5299466917529008e-05,
+      "loss": 0.5031,
+      "step": 1500
+    },
+    {
+      "epoch": 0.940733772342427,
+      "grad_norm": 4.584543704986572,
+      "learning_rate": 1.3731577296958296e-05,
+      "loss": 0.4881,
+      "step": 2000
+    },
+    {
+      "epoch": 1.175917215428034,
+      "grad_norm": 3.5594470500946045,
+      "learning_rate": 1.2163687676387584e-05,
+      "loss": 0.4445,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4111006585136407,
+      "grad_norm": 4.399453639984131,
+      "learning_rate": 1.059579805581687e-05,
+      "loss": 0.4356,
+      "step": 3000
+    },
+    {
+      "epoch": 1.6462841015992473,
+      "grad_norm": 12.899914741516113,
+      "learning_rate": 9.02790843524616e-06,
+      "loss": 0.4308,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8814675446848543,
+      "grad_norm": 5.3025946617126465,
+      "learning_rate": 7.460018814675447e-06,
+      "loss": 0.4247,
+      "step": 4000
+    },
+    {
+      "epoch": 2.116650987770461,
+      "grad_norm": 8.840332984924316,
+      "learning_rate": 5.892129194104735e-06,
+      "loss": 0.3799,
+      "step": 4500
+    },
+    {
+      "epoch": 2.351834430856068,
+      "grad_norm": 12.173576354980469,
+      "learning_rate": 4.324239573534023e-06,
+      "loss": 0.3278,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5870178739416745,
+      "grad_norm": 9.838640213012695,
+      "learning_rate": 2.7563499529633112e-06,
+      "loss": 0.3335,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8222013170272815,
+      "grad_norm": 5.874736309051514,
+      "learning_rate": 1.1884603323925998e-06,
+      "loss": 0.3284,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6378,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 6711486018900480.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6378/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a42a47958dccd16f9779b31d84670c8435e4da34f240a66c815410b7fd0b46e
+size 5432