Upload folder using huggingface_hub

checkpoint-1179/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "Dosage-Drug-Positive",
+    "1": "Frequency-Drug-Positive",
+    "2": "Route-Drug-Negative",
+    "3": "Form-Drug-Negative",
+    "4": "Strength-Drug-Positive",
+    "5": "ADE-Drug-Positive",
+    "6": "Frequency-Drug-Negative",
+    "7": "Reason-Drug-Negative",
+    "8": "ADE-Drug-Negative",
+    "9": "Reason-Drug-Positive",
+    "10": "Strength-Drug-Negative",
+    "11": "Dosage-Drug-Negative",
+    "12": "Form-Drug-Positive",
+    "13": "Route-Drug-Positive",
+    "14": "Duration-Drug-Negative",
+    "15": "Duration-Drug-Positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "ADE-Drug-Negative": 8,
+    "ADE-Drug-Positive": 5,
+    "Dosage-Drug-Negative": 11,
+    "Dosage-Drug-Positive": 0,
+    "Duration-Drug-Negative": 14,
+    "Duration-Drug-Positive": 15,
+    "Form-Drug-Negative": 3,
+    "Form-Drug-Positive": 12,
+    "Frequency-Drug-Negative": 6,
+    "Frequency-Drug-Positive": 1,
+    "Reason-Drug-Negative": 7,
+    "Reason-Drug-Positive": 9,
+    "Route-Drug-Negative": 2,
+    "Route-Drug-Positive": 13,
+    "Strength-Drug-Negative": 10,
+    "Strength-Drug-Positive": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-1179/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744b8be1ffac1ead1113028fdfb911e1917098a8aa00a38862b30fe4c2694984
+size 54235600

checkpoint-1179/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712d7e33a0ca124985c4fd42fca20a74d5203a6f5975561ea2b7f8e1d1b3f700
+size 108596363

checkpoint-1179/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4794e719a734ee9fa9dd15247f0fe5341fcf7ad5816c7231e7f4f7dfef734cab
+size 14645

checkpoint-1179/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2288c6ae9933e2902cb2f6e08f274a26ae19dd2df69adaa489604773cf6bde40
+size 1383

checkpoint-1179/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389007b36997ea0cd8b51e60e18f187275e138c78544c0319122aedc7ab0559c
+size 1465

checkpoint-1179/special_tokens_map.json

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

checkpoint-1179/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-1179/trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_global_step": 1179,
+  "best_metric": 0.32642487046632124,
+  "best_model_checkpoint": "./i2b2_model/checkpoint-1179",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1179,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08481764206955046,
+      "grad_norm": 0.8805635571479797,
+      "learning_rate": 1.966412213740458e-05,
+      "loss": 2.7221,
+      "step": 100
+    },
+    {
+      "epoch": 0.16963528413910092,
+      "grad_norm": 1.0300383567810059,
+      "learning_rate": 1.932485156912638e-05,
+      "loss": 2.5753,
+      "step": 200
+    },
+    {
+      "epoch": 0.2544529262086514,
+      "grad_norm": 1.5689030885696411,
+      "learning_rate": 1.898558100084818e-05,
+      "loss": 2.3339,
+      "step": 300
+    },
+    {
+      "epoch": 0.33927056827820185,
+      "grad_norm": 1.3848917484283447,
+      "learning_rate": 1.8646310432569977e-05,
+      "loss": 2.0873,
+      "step": 400
+    },
+    {
+      "epoch": 0.42408821034775235,
+      "grad_norm": 1.6002815961837769,
+      "learning_rate": 1.8307039864291775e-05,
+      "loss": 1.8578,
+      "step": 500
+    },
+    {
+      "epoch": 0.5089058524173028,
+      "grad_norm": 1.4675610065460205,
+      "learning_rate": 1.7967769296013573e-05,
+      "loss": 1.639,
+      "step": 600
+    },
+    {
+      "epoch": 0.5937234944868532,
+      "grad_norm": 1.510614275932312,
+      "learning_rate": 1.762849872773537e-05,
+      "loss": 1.4393,
+      "step": 700
+    },
+    {
+      "epoch": 0.6785411365564037,
+      "grad_norm": 1.4330428838729858,
+      "learning_rate": 1.7289228159457168e-05,
+      "loss": 1.2814,
+      "step": 800
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "grad_norm": 1.3979631662368774,
+      "learning_rate": 1.6949957591178966e-05,
+      "loss": 1.1749,
+      "step": 900
+    },
+    {
+      "epoch": 0.8481764206955047,
+      "grad_norm": 1.3620542287826538,
+      "learning_rate": 1.6610687022900763e-05,
+      "loss": 1.1002,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9329940627650551,
+      "grad_norm": 1.8766813278198242,
+      "learning_rate": 1.6271416454622565e-05,
+      "loss": 1.0137,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.32642487046632124,
+      "eval_f1": 0.23427617946411824,
+      "eval_loss": 2.2931675910949707,
+      "eval_precision": 0.20496833204797127,
+      "eval_recall": 0.32642487046632124,
+      "eval_runtime": 20.873,
+      "eval_samples_per_second": 1202.032,
+      "eval_steps_per_second": 18.828,
+      "step": 1179
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5895,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 428825443550208.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1179/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ecbeafe8ad87a86caca10ba72016e58071d9d73cdd450f90210669b5a66947
+size 5777

checkpoint-4716/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "Dosage-Drug-Positive",
+    "1": "Frequency-Drug-Positive",
+    "2": "Route-Drug-Negative",
+    "3": "Form-Drug-Negative",
+    "4": "Strength-Drug-Positive",
+    "5": "ADE-Drug-Positive",
+    "6": "Frequency-Drug-Negative",
+    "7": "Reason-Drug-Negative",
+    "8": "ADE-Drug-Negative",
+    "9": "Reason-Drug-Positive",
+    "10": "Strength-Drug-Negative",
+    "11": "Dosage-Drug-Negative",
+    "12": "Form-Drug-Positive",
+    "13": "Route-Drug-Positive",
+    "14": "Duration-Drug-Negative",
+    "15": "Duration-Drug-Positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "ADE-Drug-Negative": 8,
+    "ADE-Drug-Positive": 5,
+    "Dosage-Drug-Negative": 11,
+    "Dosage-Drug-Positive": 0,
+    "Duration-Drug-Negative": 14,
+    "Duration-Drug-Positive": 15,
+    "Form-Drug-Negative": 3,
+    "Form-Drug-Positive": 12,
+    "Frequency-Drug-Negative": 6,
+    "Frequency-Drug-Positive": 1,
+    "Reason-Drug-Negative": 7,
+    "Reason-Drug-Positive": 9,
+    "Route-Drug-Negative": 2,
+    "Route-Drug-Positive": 13,
+    "Strength-Drug-Negative": 10,
+    "Strength-Drug-Positive": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-4716/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6791bb58895bef3f61441d83d8686372cd7f09d22e5817d4db3ef0cbe3c5db1a
+size 54235600

checkpoint-4716/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e5fe72b28557e89d2be6598de01392afbae6432762f4dbb16709e7bc23e7fb
+size 108596363

checkpoint-4716/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbbf92b0ac496935212e85c6e9a267d3a5afe9934afe4ec3eb7b4eab2f7d572
+size 14645

checkpoint-4716/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:075b2d9467021f1a0971c4a60861645c6b0b2851fad78dcaf0bf9e2039c897da
+size 1383

checkpoint-4716/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f8d2458d810faad3ef4c26d3eb3bddc895c77f2be3c493945b6696a36a62cd
+size 1465

checkpoint-4716/special_tokens_map.json

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

checkpoint-4716/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-4716/trainer_state.json

@@ -0,0 +1,411 @@
+{
+  "best_global_step": 1179,
+  "best_metric": 0.32642487046632124,
+  "best_model_checkpoint": "./i2b2_model/checkpoint-1179",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4716,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08481764206955046,
+      "grad_norm": 0.8805635571479797,
+      "learning_rate": 1.966412213740458e-05,
+      "loss": 2.7221,
+      "step": 100
+    },
+    {
+      "epoch": 0.16963528413910092,
+      "grad_norm": 1.0300383567810059,
+      "learning_rate": 1.932485156912638e-05,
+      "loss": 2.5753,
+      "step": 200
+    },
+    {
+      "epoch": 0.2544529262086514,
+      "grad_norm": 1.5689030885696411,
+      "learning_rate": 1.898558100084818e-05,
+      "loss": 2.3339,
+      "step": 300
+    },
+    {
+      "epoch": 0.33927056827820185,
+      "grad_norm": 1.3848917484283447,
+      "learning_rate": 1.8646310432569977e-05,
+      "loss": 2.0873,
+      "step": 400
+    },
+    {
+      "epoch": 0.42408821034775235,
+      "grad_norm": 1.6002815961837769,
+      "learning_rate": 1.8307039864291775e-05,
+      "loss": 1.8578,
+      "step": 500
+    },
+    {
+      "epoch": 0.5089058524173028,
+      "grad_norm": 1.4675610065460205,
+      "learning_rate": 1.7967769296013573e-05,
+      "loss": 1.639,
+      "step": 600
+    },
+    {
+      "epoch": 0.5937234944868532,
+      "grad_norm": 1.510614275932312,
+      "learning_rate": 1.762849872773537e-05,
+      "loss": 1.4393,
+      "step": 700
+    },
+    {
+      "epoch": 0.6785411365564037,
+      "grad_norm": 1.4330428838729858,
+      "learning_rate": 1.7289228159457168e-05,
+      "loss": 1.2814,
+      "step": 800
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "grad_norm": 1.3979631662368774,
+      "learning_rate": 1.6949957591178966e-05,
+      "loss": 1.1749,
+      "step": 900
+    },
+    {
+      "epoch": 0.8481764206955047,
+      "grad_norm": 1.3620542287826538,
+      "learning_rate": 1.6610687022900763e-05,
+      "loss": 1.1002,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9329940627650551,
+      "grad_norm": 1.8766813278198242,
+      "learning_rate": 1.6271416454622565e-05,
+      "loss": 1.0137,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.32642487046632124,
+      "eval_f1": 0.23427617946411824,
+      "eval_loss": 2.2931675910949707,
+      "eval_precision": 0.20496833204797127,
+      "eval_recall": 0.32642487046632124,
+      "eval_runtime": 20.873,
+      "eval_samples_per_second": 1202.032,
+      "eval_steps_per_second": 18.828,
+      "step": 1179
+    },
+    {
+      "epoch": 1.0178117048346056,
+      "grad_norm": 2.0241150856018066,
+      "learning_rate": 1.5932145886344362e-05,
+      "loss": 0.9752,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1026293469041561,
+      "grad_norm": 1.0047012567520142,
+      "learning_rate": 1.559287531806616e-05,
+      "loss": 0.9322,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1874469889737065,
+      "grad_norm": 2.013701915740967,
+      "learning_rate": 1.5253604749787958e-05,
+      "loss": 0.9217,
+      "step": 1400
+    },
+    {
+      "epoch": 1.272264631043257,
+      "grad_norm": 1.9003664255142212,
+      "learning_rate": 1.4914334181509755e-05,
+      "loss": 0.8991,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3570822731128076,
+      "grad_norm": 1.2886754274368286,
+      "learning_rate": 1.4575063613231553e-05,
+      "loss": 0.882,
+      "step": 1600
+    },
+    {
+      "epoch": 1.441899915182358,
+      "grad_norm": 1.268678903579712,
+      "learning_rate": 1.4235793044953352e-05,
+      "loss": 0.8684,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5267175572519083,
+      "grad_norm": 1.3230983018875122,
+      "learning_rate": 1.389652247667515e-05,
+      "loss": 0.8467,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6115351993214588,
+      "grad_norm": 1.3858022689819336,
+      "learning_rate": 1.3557251908396946e-05,
+      "loss": 0.8422,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6963528413910094,
+      "grad_norm": 2.531125545501709,
+      "learning_rate": 1.3217981340118746e-05,
+      "loss": 0.8266,
+      "step": 2000
+    },
+    {
+      "epoch": 1.78117048346056,
+      "grad_norm": 2.599006175994873,
+      "learning_rate": 1.2878710771840543e-05,
+      "loss": 0.8215,
+      "step": 2100
+    },
+    {
+      "epoch": 1.8659881255301103,
+      "grad_norm": 2.465607166290283,
+      "learning_rate": 1.2539440203562343e-05,
+      "loss": 0.8077,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9508057675996606,
+      "grad_norm": 1.6329939365386963,
+      "learning_rate": 1.220016963528414e-05,
+      "loss": 0.8002,
+      "step": 2300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2957353527301714,
+      "eval_f1": 0.19723504159983604,
+      "eval_loss": 2.6935245990753174,
+      "eval_precision": 0.15463079618041953,
+      "eval_recall": 0.2957353527301714,
+      "eval_runtime": 19.7862,
+      "eval_samples_per_second": 1268.057,
+      "eval_steps_per_second": 19.862,
+      "step": 2358
+    },
+    {
+      "epoch": 2.035623409669211,
+      "grad_norm": 3.1458687782287598,
+      "learning_rate": 1.1860899067005938e-05,
+      "loss": 0.7967,
+      "step": 2400
+    },
+    {
+      "epoch": 2.1204410517387617,
+      "grad_norm": 1.5369526147842407,
+      "learning_rate": 1.1521628498727737e-05,
+      "loss": 0.7927,
+      "step": 2500
+    },
+    {
+      "epoch": 2.2052586938083123,
+      "grad_norm": 1.882670521736145,
+      "learning_rate": 1.1182357930449535e-05,
+      "loss": 0.7849,
+      "step": 2600
+    },
+    {
+      "epoch": 2.2900763358778624,
+      "grad_norm": 2.031019449234009,
+      "learning_rate": 1.0843087362171331e-05,
+      "loss": 0.7786,
+      "step": 2700
+    },
+    {
+      "epoch": 2.374893977947413,
+      "grad_norm": 2.266068458557129,
+      "learning_rate": 1.050381679389313e-05,
+      "loss": 0.7763,
+      "step": 2800
+    },
+    {
+      "epoch": 2.4597116200169635,
+      "grad_norm": 1.4232118129730225,
+      "learning_rate": 1.0164546225614928e-05,
+      "loss": 0.7736,
+      "step": 2900
+    },
+    {
+      "epoch": 2.544529262086514,
+      "grad_norm": 2.115183115005493,
+      "learning_rate": 9.825275657336728e-06,
+      "loss": 0.7593,
+      "step": 3000
+    },
+    {
+      "epoch": 2.6293469041560646,
+      "grad_norm": 1.7226656675338745,
+      "learning_rate": 9.486005089058525e-06,
+      "loss": 0.7587,
+      "step": 3100
+    },
+    {
+      "epoch": 2.714164546225615,
+      "grad_norm": 2.0967631340026855,
+      "learning_rate": 9.146734520780323e-06,
+      "loss": 0.7665,
+      "step": 3200
+    },
+    {
+      "epoch": 2.7989821882951653,
+      "grad_norm": 1.8578695058822632,
+      "learning_rate": 8.80746395250212e-06,
+      "loss": 0.7527,
+      "step": 3300
+    },
+    {
+      "epoch": 2.883799830364716,
+      "grad_norm": 2.35467267036438,
+      "learning_rate": 8.46819338422392e-06,
+      "loss": 0.7516,
+      "step": 3400
+    },
+    {
+      "epoch": 2.9686174724342664,
+      "grad_norm": 2.1662681102752686,
+      "learning_rate": 8.128922815945718e-06,
+      "loss": 0.749,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.29166998804304506,
+      "eval_f1": 0.2111020694739784,
+      "eval_loss": 2.924750804901123,
+      "eval_precision": 0.16962444026380036,
+      "eval_recall": 0.29166998804304506,
+      "eval_runtime": 20.8788,
+      "eval_samples_per_second": 1201.696,
+      "eval_steps_per_second": 18.823,
+      "step": 3537
+    },
+    {
+      "epoch": 3.053435114503817,
+      "grad_norm": 1.8867818117141724,
+      "learning_rate": 7.789652247667516e-06,
+      "loss": 0.7507,
+      "step": 3600
+    },
+    {
+      "epoch": 3.138252756573367,
+      "grad_norm": 2.129338026046753,
+      "learning_rate": 7.450381679389313e-06,
+      "loss": 0.7462,
+      "step": 3700
+    },
+    {
+      "epoch": 3.2230703986429177,
+      "grad_norm": 1.5529320240020752,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 0.7436,
+      "step": 3800
+    },
+    {
+      "epoch": 3.3078880407124682,
+      "grad_norm": 2.430915117263794,
+      "learning_rate": 6.7718405428329095e-06,
+      "loss": 0.7421,
+      "step": 3900
+    },
+    {
+      "epoch": 3.392705682782019,
+      "grad_norm": 2.0328726768493652,
+      "learning_rate": 6.432569974554708e-06,
+      "loss": 0.7397,
+      "step": 4000
+    },
+    {
+      "epoch": 3.4775233248515693,
+      "grad_norm": 1.6856147050857544,
+      "learning_rate": 6.093299406276506e-06,
+      "loss": 0.7358,
+      "step": 4100
+    },
+    {
+      "epoch": 3.5623409669211195,
+      "grad_norm": 2.0061874389648438,
+      "learning_rate": 5.754028837998304e-06,
+      "loss": 0.7355,
+      "step": 4200
+    },
+    {
+      "epoch": 3.64715860899067,
+      "grad_norm": 2.331062078475952,
+      "learning_rate": 5.414758269720102e-06,
+      "loss": 0.7433,
+      "step": 4300
+    },
+    {
+      "epoch": 3.7319762510602206,
+      "grad_norm": 2.5025064945220947,
+      "learning_rate": 5.075487701441901e-06,
+      "loss": 0.7371,
+      "step": 4400
+    },
+    {
+      "epoch": 3.816793893129771,
+      "grad_norm": 3.021045446395874,
+      "learning_rate": 4.736217133163698e-06,
+      "loss": 0.7357,
+      "step": 4500
+    },
+    {
+      "epoch": 3.9016115351993212,
+      "grad_norm": 1.7884670495986938,
+      "learning_rate": 4.396946564885497e-06,
+      "loss": 0.7366,
+      "step": 4600
+    },
+    {
+      "epoch": 3.986429177268872,
+      "grad_norm": 2.477693796157837,
+      "learning_rate": 4.0576759966072945e-06,
+      "loss": 0.7324,
+      "step": 4700
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.24192905540055798,
+      "eval_f1": 0.18676919220051297,
+      "eval_loss": 3.059746265411377,
+      "eval_precision": 0.23033226126155365,
+      "eval_recall": 0.24192905540055798,
+      "eval_runtime": 19.9179,
+      "eval_samples_per_second": 1259.67,
+      "eval_steps_per_second": 19.731,
+      "step": 4716
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5895,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1715326721312448.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4716/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ecbeafe8ad87a86caca10ba72016e58071d9d73cdd450f90210669b5a66947
+size 5777

checkpoint-5895/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "Dosage-Drug-Positive",
+    "1": "Frequency-Drug-Positive",
+    "2": "Route-Drug-Negative",
+    "3": "Form-Drug-Negative",
+    "4": "Strength-Drug-Positive",
+    "5": "ADE-Drug-Positive",
+    "6": "Frequency-Drug-Negative",
+    "7": "Reason-Drug-Negative",
+    "8": "ADE-Drug-Negative",
+    "9": "Reason-Drug-Positive",
+    "10": "Strength-Drug-Negative",
+    "11": "Dosage-Drug-Negative",
+    "12": "Form-Drug-Positive",
+    "13": "Route-Drug-Positive",
+    "14": "Duration-Drug-Negative",
+    "15": "Duration-Drug-Positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "ADE-Drug-Negative": 8,
+    "ADE-Drug-Positive": 5,
+    "Dosage-Drug-Negative": 11,
+    "Dosage-Drug-Positive": 0,
+    "Duration-Drug-Negative": 14,
+    "Duration-Drug-Positive": 15,
+    "Form-Drug-Negative": 3,
+    "Form-Drug-Positive": 12,
+    "Frequency-Drug-Negative": 6,
+    "Frequency-Drug-Positive": 1,
+    "Reason-Drug-Negative": 7,
+    "Reason-Drug-Positive": 9,
+    "Route-Drug-Negative": 2,
+    "Route-Drug-Positive": 13,
+    "Strength-Drug-Negative": 10,
+    "Strength-Drug-Positive": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-5895/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab8e9abb443554d3d36fd4a525b0dcf54de3d6618162391106149136d1e5e5a
+size 54235600

checkpoint-5895/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5695d7ae2326320ad5b22fa67a9abeeb758a8812f3f881f2549b79d6c361d037
+size 108596363

checkpoint-5895/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50e2a41e52ec56c5d7705318a46fa6314b4bfd960b031214524e17584261aae
+size 14645

checkpoint-5895/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250dd993fb364cb2c424cee8189f84c61dbb791c6a32fc4c8d8b57d6cb5d28fe
+size 1383

checkpoint-5895/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21983f7b03a724e11a8bfeadce32cd7e2b7afd51fa3a6091f42e25a5fb85cae4
+size 1465

checkpoint-5895/special_tokens_map.json

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

checkpoint-5895/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-5895/trainer_state.json

@@ -0,0 +1,500 @@
+{
+  "best_global_step": 1179,
+  "best_metric": 0.32642487046632124,
+  "best_model_checkpoint": "./i2b2_model/checkpoint-1179",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5895,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08481764206955046,
+      "grad_norm": 0.8805635571479797,
+      "learning_rate": 1.966412213740458e-05,
+      "loss": 2.7221,
+      "step": 100
+    },
+    {
+      "epoch": 0.16963528413910092,
+      "grad_norm": 1.0300383567810059,
+      "learning_rate": 1.932485156912638e-05,
+      "loss": 2.5753,
+      "step": 200
+    },
+    {
+      "epoch": 0.2544529262086514,
+      "grad_norm": 1.5689030885696411,
+      "learning_rate": 1.898558100084818e-05,
+      "loss": 2.3339,
+      "step": 300
+    },
+    {
+      "epoch": 0.33927056827820185,
+      "grad_norm": 1.3848917484283447,
+      "learning_rate": 1.8646310432569977e-05,
+      "loss": 2.0873,
+      "step": 400
+    },
+    {
+      "epoch": 0.42408821034775235,
+      "grad_norm": 1.6002815961837769,
+      "learning_rate": 1.8307039864291775e-05,
+      "loss": 1.8578,
+      "step": 500
+    },
+    {
+      "epoch": 0.5089058524173028,
+      "grad_norm": 1.4675610065460205,
+      "learning_rate": 1.7967769296013573e-05,
+      "loss": 1.639,
+      "step": 600
+    },
+    {
+      "epoch": 0.5937234944868532,
+      "grad_norm": 1.510614275932312,
+      "learning_rate": 1.762849872773537e-05,
+      "loss": 1.4393,
+      "step": 700
+    },
+    {
+      "epoch": 0.6785411365564037,
+      "grad_norm": 1.4330428838729858,
+      "learning_rate": 1.7289228159457168e-05,
+      "loss": 1.2814,
+      "step": 800
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "grad_norm": 1.3979631662368774,
+      "learning_rate": 1.6949957591178966e-05,
+      "loss": 1.1749,
+      "step": 900
+    },
+    {
+      "epoch": 0.8481764206955047,
+      "grad_norm": 1.3620542287826538,
+      "learning_rate": 1.6610687022900763e-05,
+      "loss": 1.1002,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9329940627650551,
+      "grad_norm": 1.8766813278198242,
+      "learning_rate": 1.6271416454622565e-05,
+      "loss": 1.0137,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.32642487046632124,
+      "eval_f1": 0.23427617946411824,
+      "eval_loss": 2.2931675910949707,
+      "eval_precision": 0.20496833204797127,
+      "eval_recall": 0.32642487046632124,
+      "eval_runtime": 20.873,
+      "eval_samples_per_second": 1202.032,
+      "eval_steps_per_second": 18.828,
+      "step": 1179
+    },
+    {
+      "epoch": 1.0178117048346056,
+      "grad_norm": 2.0241150856018066,
+      "learning_rate": 1.5932145886344362e-05,
+      "loss": 0.9752,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1026293469041561,
+      "grad_norm": 1.0047012567520142,
+      "learning_rate": 1.559287531806616e-05,
+      "loss": 0.9322,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1874469889737065,
+      "grad_norm": 2.013701915740967,
+      "learning_rate": 1.5253604749787958e-05,
+      "loss": 0.9217,
+      "step": 1400
+    },
+    {
+      "epoch": 1.272264631043257,
+      "grad_norm": 1.9003664255142212,
+      "learning_rate": 1.4914334181509755e-05,
+      "loss": 0.8991,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3570822731128076,
+      "grad_norm": 1.2886754274368286,
+      "learning_rate": 1.4575063613231553e-05,
+      "loss": 0.882,
+      "step": 1600
+    },
+    {
+      "epoch": 1.441899915182358,
+      "grad_norm": 1.268678903579712,
+      "learning_rate": 1.4235793044953352e-05,
+      "loss": 0.8684,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5267175572519083,
+      "grad_norm": 1.3230983018875122,
+      "learning_rate": 1.389652247667515e-05,
+      "loss": 0.8467,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6115351993214588,
+      "grad_norm": 1.3858022689819336,
+      "learning_rate": 1.3557251908396946e-05,
+      "loss": 0.8422,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6963528413910094,
+      "grad_norm": 2.531125545501709,
+      "learning_rate": 1.3217981340118746e-05,
+      "loss": 0.8266,
+      "step": 2000
+    },
+    {
+      "epoch": 1.78117048346056,
+      "grad_norm": 2.599006175994873,
+      "learning_rate": 1.2878710771840543e-05,
+      "loss": 0.8215,
+      "step": 2100
+    },
+    {
+      "epoch": 1.8659881255301103,
+      "grad_norm": 2.465607166290283,
+      "learning_rate": 1.2539440203562343e-05,
+      "loss": 0.8077,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9508057675996606,
+      "grad_norm": 1.6329939365386963,
+      "learning_rate": 1.220016963528414e-05,
+      "loss": 0.8002,
+      "step": 2300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2957353527301714,
+      "eval_f1": 0.19723504159983604,
+      "eval_loss": 2.6935245990753174,
+      "eval_precision": 0.15463079618041953,
+      "eval_recall": 0.2957353527301714,
+      "eval_runtime": 19.7862,
+      "eval_samples_per_second": 1268.057,
+      "eval_steps_per_second": 19.862,
+      "step": 2358
+    },
+    {
+      "epoch": 2.035623409669211,
+      "grad_norm": 3.1458687782287598,
+      "learning_rate": 1.1860899067005938e-05,
+      "loss": 0.7967,
+      "step": 2400
+    },
+    {
+      "epoch": 2.1204410517387617,
+      "grad_norm": 1.5369526147842407,
+      "learning_rate": 1.1521628498727737e-05,
+      "loss": 0.7927,
+      "step": 2500
+    },
+    {
+      "epoch": 2.2052586938083123,
+      "grad_norm": 1.882670521736145,
+      "learning_rate": 1.1182357930449535e-05,
+      "loss": 0.7849,
+      "step": 2600
+    },
+    {
+      "epoch": 2.2900763358778624,
+      "grad_norm": 2.031019449234009,
+      "learning_rate": 1.0843087362171331e-05,
+      "loss": 0.7786,
+      "step": 2700
+    },
+    {
+      "epoch": 2.374893977947413,
+      "grad_norm": 2.266068458557129,
+      "learning_rate": 1.050381679389313e-05,
+      "loss": 0.7763,
+      "step": 2800
+    },
+    {
+      "epoch": 2.4597116200169635,
+      "grad_norm": 1.4232118129730225,
+      "learning_rate": 1.0164546225614928e-05,
+      "loss": 0.7736,
+      "step": 2900
+    },
+    {
+      "epoch": 2.544529262086514,
+      "grad_norm": 2.115183115005493,
+      "learning_rate": 9.825275657336728e-06,
+      "loss": 0.7593,
+      "step": 3000
+    },
+    {
+      "epoch": 2.6293469041560646,
+      "grad_norm": 1.7226656675338745,
+      "learning_rate": 9.486005089058525e-06,
+      "loss": 0.7587,
+      "step": 3100
+    },
+    {
+      "epoch": 2.714164546225615,
+      "grad_norm": 2.0967631340026855,
+      "learning_rate": 9.146734520780323e-06,
+      "loss": 0.7665,
+      "step": 3200
+    },
+    {
+      "epoch": 2.7989821882951653,
+      "grad_norm": 1.8578695058822632,
+      "learning_rate": 8.80746395250212e-06,
+      "loss": 0.7527,
+      "step": 3300
+    },
+    {
+      "epoch": 2.883799830364716,
+      "grad_norm": 2.35467267036438,
+      "learning_rate": 8.46819338422392e-06,
+      "loss": 0.7516,
+      "step": 3400
+    },
+    {
+      "epoch": 2.9686174724342664,
+      "grad_norm": 2.1662681102752686,
+      "learning_rate": 8.128922815945718e-06,
+      "loss": 0.749,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.29166998804304506,
+      "eval_f1": 0.2111020694739784,
+      "eval_loss": 2.924750804901123,
+      "eval_precision": 0.16962444026380036,
+      "eval_recall": 0.29166998804304506,
+      "eval_runtime": 20.8788,
+      "eval_samples_per_second": 1201.696,
+      "eval_steps_per_second": 18.823,
+      "step": 3537
+    },
+    {
+      "epoch": 3.053435114503817,
+      "grad_norm": 1.8867818117141724,
+      "learning_rate": 7.789652247667516e-06,
+      "loss": 0.7507,
+      "step": 3600
+    },
+    {
+      "epoch": 3.138252756573367,
+      "grad_norm": 2.129338026046753,
+      "learning_rate": 7.450381679389313e-06,
+      "loss": 0.7462,
+      "step": 3700
+    },
+    {
+      "epoch": 3.2230703986429177,
+      "grad_norm": 1.5529320240020752,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 0.7436,
+      "step": 3800
+    },
+    {
+      "epoch": 3.3078880407124682,
+      "grad_norm": 2.430915117263794,
+      "learning_rate": 6.7718405428329095e-06,
+      "loss": 0.7421,
+      "step": 3900
+    },
+    {
+      "epoch": 3.392705682782019,
+      "grad_norm": 2.0328726768493652,
+      "learning_rate": 6.432569974554708e-06,
+      "loss": 0.7397,
+      "step": 4000
+    },
+    {
+      "epoch": 3.4775233248515693,
+      "grad_norm": 1.6856147050857544,
+      "learning_rate": 6.093299406276506e-06,
+      "loss": 0.7358,
+      "step": 4100
+    },
+    {
+      "epoch": 3.5623409669211195,
+      "grad_norm": 2.0061874389648438,
+      "learning_rate": 5.754028837998304e-06,
+      "loss": 0.7355,
+      "step": 4200
+    },
+    {
+      "epoch": 3.64715860899067,
+      "grad_norm": 2.331062078475952,
+      "learning_rate": 5.414758269720102e-06,
+      "loss": 0.7433,
+      "step": 4300
+    },
+    {
+      "epoch": 3.7319762510602206,
+      "grad_norm": 2.5025064945220947,
+      "learning_rate": 5.075487701441901e-06,
+      "loss": 0.7371,
+      "step": 4400
+    },
+    {
+      "epoch": 3.816793893129771,
+      "grad_norm": 3.021045446395874,
+      "learning_rate": 4.736217133163698e-06,
+      "loss": 0.7357,
+      "step": 4500
+    },
+    {
+      "epoch": 3.9016115351993212,
+      "grad_norm": 1.7884670495986938,
+      "learning_rate": 4.396946564885497e-06,
+      "loss": 0.7366,
+      "step": 4600
+    },
+    {
+      "epoch": 3.986429177268872,
+      "grad_norm": 2.477693796157837,
+      "learning_rate": 4.0576759966072945e-06,
+      "loss": 0.7324,
+      "step": 4700
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.24192905540055798,
+      "eval_f1": 0.18676919220051297,
+      "eval_loss": 3.059746265411377,
+      "eval_precision": 0.23033226126155365,
+      "eval_recall": 0.24192905540055798,
+      "eval_runtime": 19.9179,
+      "eval_samples_per_second": 1259.67,
+      "eval_steps_per_second": 19.731,
+      "step": 4716
+    },
+    {
+      "epoch": 4.071246819338422,
+      "grad_norm": 2.0766072273254395,
+      "learning_rate": 3.7184054283290927e-06,
+      "loss": 0.7299,
+      "step": 4800
+    },
+    {
+      "epoch": 4.156064461407973,
+      "grad_norm": 2.57733416557312,
+      "learning_rate": 3.3791348600508912e-06,
+      "loss": 0.7316,
+      "step": 4900
+    },
+    {
+      "epoch": 4.2408821034775235,
+      "grad_norm": 2.095597267150879,
+      "learning_rate": 3.039864291772689e-06,
+      "loss": 0.7343,
+      "step": 5000
+    },
+    {
+      "epoch": 4.325699745547074,
+      "grad_norm": 1.9832748174667358,
+      "learning_rate": 2.7005937234944875e-06,
+      "loss": 0.7298,
+      "step": 5100
+    },
+    {
+      "epoch": 4.410517387616625,
+      "grad_norm": 2.461386203765869,
+      "learning_rate": 2.361323155216285e-06,
+      "loss": 0.7292,
+      "step": 5200
+    },
+    {
+      "epoch": 4.495335029686174,
+      "grad_norm": 2.768099546432495,
+      "learning_rate": 2.0220525869380833e-06,
+      "loss": 0.7277,
+      "step": 5300
+    },
+    {
+      "epoch": 4.580152671755725,
+      "grad_norm": 1.4862111806869507,
+      "learning_rate": 1.6827820186598814e-06,
+      "loss": 0.7303,
+      "step": 5400
+    },
+    {
+      "epoch": 4.664970313825275,
+      "grad_norm": 2.281935214996338,
+      "learning_rate": 1.3435114503816796e-06,
+      "loss": 0.7287,
+      "step": 5500
+    },
+    {
+      "epoch": 4.749787955894826,
+      "grad_norm": 1.5928317308425903,
+      "learning_rate": 1.0042408821034775e-06,
+      "loss": 0.7237,
+      "step": 5600
+    },
+    {
+      "epoch": 4.8346055979643765,
+      "grad_norm": 2.170006275177002,
+      "learning_rate": 6.649703138252757e-07,
+      "loss": 0.7271,
+      "step": 5700
+    },
+    {
+      "epoch": 4.919423240033927,
+      "grad_norm": 2.7832131385803223,
+      "learning_rate": 3.256997455470738e-07,
+      "loss": 0.7245,
+      "step": 5800
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.24814667198086887,
+      "eval_f1": 0.2479496923119951,
+      "eval_loss": 3.093135356903076,
+      "eval_precision": 0.3335291041205902,
+      "eval_recall": 0.24814667198086887,
+      "eval_runtime": 19.8549,
+      "eval_samples_per_second": 1263.666,
+      "eval_steps_per_second": 19.794,
+      "step": 5895
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5895,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 2144050881888768.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5895/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ecbeafe8ad87a86caca10ba72016e58071d9d73cdd450f90210669b5a66947
+size 5777

config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "Dosage-Drug-Positive",
+    "1": "Frequency-Drug-Positive",
+    "2": "Route-Drug-Negative",
+    "3": "Form-Drug-Negative",
+    "4": "Strength-Drug-Positive",
+    "5": "ADE-Drug-Positive",
+    "6": "Frequency-Drug-Negative",
+    "7": "Reason-Drug-Negative",
+    "8": "ADE-Drug-Negative",
+    "9": "Reason-Drug-Positive",
+    "10": "Strength-Drug-Negative",
+    "11": "Dosage-Drug-Negative",
+    "12": "Form-Drug-Positive",
+    "13": "Route-Drug-Positive",
+    "14": "Duration-Drug-Negative",
+    "15": "Duration-Drug-Positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "ADE-Drug-Negative": 8,
+    "ADE-Drug-Positive": 5,
+    "Dosage-Drug-Negative": 11,
+    "Dosage-Drug-Positive": 0,
+    "Duration-Drug-Negative": 14,
+    "Duration-Drug-Positive": 15,
+    "Form-Drug-Negative": 3,
+    "Form-Drug-Positive": 12,
+    "Frequency-Drug-Negative": 6,
+    "Frequency-Drug-Positive": 1,
+    "Reason-Drug-Negative": 7,
+    "Reason-Drug-Positive": 9,
+    "Route-Drug-Negative": 2,
+    "Route-Drug-Positive": 13,
+    "Strength-Drug-Negative": 10,
+    "Strength-Drug-Positive": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

evaluation_results.txt

@@ -0,0 +1,10 @@
+Evaluation Results:
+eval_loss: 2.2932
+eval_accuracy: 0.3264
+eval_f1: 0.2343
+eval_precision: 0.2050
+eval_recall: 0.3264
+eval_runtime: 20.1358
+eval_samples_per_second: 1246.0390
+eval_steps_per_second: 19.5170
+epoch: 5.0000

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744b8be1ffac1ead1113028fdfb911e1917098a8aa00a38862b30fe4c2694984
+size 54235600

runs/Oct03_23-16-17_3cb83e6cc4fa/events.out.tfevents.1759533380.3cb83e6cc4fa.306.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9302be9a9c83e2a462e74bea385038df84c1acb15ad467f46a68aee178c9a1
+size 21124

runs/Oct03_23-16-17_3cb83e6cc4fa/events.out.tfevents.1759534206.3cb83e6cc4fa.306.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f726f80d1e5ce8ac14e0c5d92e03ab36139023cf61f9ff464017094768691cfe
+size 560

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ecbeafe8ad87a86caca10ba72016e58071d9d73cdd450f90210669b5a66947
+size 5777