Upload folder using huggingface_hub

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "yikuan8/Clinical-Longformer",
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aba72b6161ae1eeabd427c3be571876c76fe70dd53ea3752d93aafe229f96c8
+size 1189502522

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4da4f1d4d6f0ef4db8385ad2d7d4504a9d6947044de9dfdf69de28970907be0
+size 594732814

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d32051101ec51c2b04c4ee6a6d2c7f40562e56836cbb02d6e6e3126490484d
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4141bd82293fbad58a7034a6164e1b15ebb3bd98a6108d37ca224bb15d7ee5f0
+size 1064

trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": 0.9671150655371568,
+  "best_model_checkpoint": "models/longformer_classifier/checkpoint-6544",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 13088,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9235941320293402e-05,
+      "loss": 7.0429,
+      "step": 500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.84718826405868e-05,
+      "loss": 6.7762,
+      "step": 1000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7707823960880196e-05,
+      "loss": 6.3278,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6943765281173596e-05,
+      "loss": 5.1982,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.6179706601466993e-05,
+      "loss": 6.9234,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.5415647921760393e-05,
+      "loss": 3.3308,
+      "step": 3000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4651589242053792e-05,
+      "loss": 11.0545,
+      "step": 3500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.3887530562347189e-05,
+      "loss": 11.4149,
+      "step": 4000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.3123471882640589e-05,
+      "loss": 3.9411,
+      "step": 4500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.2359413202933986e-05,
+      "loss": 5.0606,
+      "step": 5000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.1595354523227385e-05,
+      "loss": 4.0193,
+      "step": 5500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.0831295843520783e-05,
+      "loss": 6.3164,
+      "step": 6000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.006723716381418e-05,
+      "loss": 10.0802,
+      "step": 6500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9671150655371568,
+      "eval_loss": 6.602837085723877,
+      "eval_precision": 0.9564744352317358,
+      "eval_recall": 0.9779951100244498,
+      "eval_runtime": 1373.3102,
+      "eval_samples_per_second": 1.191,
+      "eval_steps_per_second": 1.191,
+      "step": 6544
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.30317848410758e-06,
+      "loss": 6.419,
+      "step": 7000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.539119804400979e-06,
+      "loss": 3.2558,
+      "step": 7500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.775061124694378e-06,
+      "loss": 6.4214,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 7.011002444987775e-06,
+      "loss": 5.2197,
+      "step": 8500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 6.246943765281174e-06,
+      "loss": 7.7577,
+      "step": 9000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.482885085574573e-06,
+      "loss": 4.2541,
+      "step": 9500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.718826405867971e-06,
+      "loss": 6.9299,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.954767726161369e-06,
+      "loss": 4.4269,
+      "step": 10500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.190709046454768e-06,
+      "loss": 4.4276,
+      "step": 11000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.4266503667481666e-06,
+      "loss": 4.2753,
+      "step": 11500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.6625916870415647e-06,
+      "loss": 4.9898,
+      "step": 12000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 8.985330073349634e-07,
+      "loss": 5.014,
+      "step": 12500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.3447432762836187e-07,
+      "loss": 4.3745,
+      "step": 13000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9671150655371568,
+      "eval_loss": 5.483180999755859,
+      "eval_precision": 0.9564744352317358,
+      "eval_recall": 0.9779951100244498,
+      "eval_runtime": 9134.9046,
+      "eval_samples_per_second": 0.179,
+      "eval_steps_per_second": 0.179,
+      "step": 13088
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13088,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 3.3581297093376e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba1f3ee7607380d609e013b7589d291fd66597877e88b392866198029930237
+size 4536