Upload 12 files

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "vocab_size": 30522
+}

evaluation.log

@@ -0,0 +1,6 @@
+Accuracy: 0.9977344870567322
+('People with Long COVID experience PEM.', 1, 0)
+('pharmacotherapy with amitriptyline and hochuekkito, a Japanese herbal (Kampo) medicine', 1, 0)
+('PM2.5 has implications in cardiovascular adverse events', 1, 0)
+('Small doses of prednisone block inflammation in Long COVID.', 1, 0)
+("suppression of the pituitary gland's pulsatile secretion of tropic hormones", 1, 0)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ecb413eefaba4920c61644c5002fde8137473d849700a88a062c0189efda323
+size 98470112

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d2386f70406ee6a8aa100dbad9927dc927de6b1127b72805ce9cf5b791a88a
+size 197562589

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04480b41443f43abe08b007d9f81b1cde1f8f5a62079008c358d77853cadc4d8
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e51d326d6b7287d246e4b20e262ffcde5f6050f39a442970dd3ce81768b5d4
+size 1064

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": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": 0.0006066389032639563,
+  "best_model_checkpoint": "./results/checkpoint-1500",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 37104760.0,
+      "learning_rate": 1.25e-05,
+      "loss": 1229363.12,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 41486.3671875,
+      "learning_rate": 2.5e-05,
+      "loss": 42265.33,
+      "step": 100
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.13579608296277e-06,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.8482,
+      "step": 150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.03436470404267311,
+      "learning_rate": 5e-05,
+      "loss": 1.9227,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.033596742898225784,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.0034,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.007859374396502972,
+      "eval_runtime": 3.0831,
+      "eval_samples_per_second": 324.344,
+      "eval_steps_per_second": 20.434,
+      "step": 250
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.00011137876572320238,
+      "learning_rate": 4.782608695652174e-05,
+      "loss": 0.0091,
+      "step": 300
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 6.665806722594425e-05,
+      "learning_rate": 4.673913043478261e-05,
+      "loss": 0.0072,
+      "step": 350
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.3853695893194526e-05,
+      "learning_rate": 4.565217391304348e-05,
+      "loss": 0.0296,
+      "step": 400
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 8.297997555928305e-05,
+      "learning_rate": 4.456521739130435e-05,
+      "loss": 0.0156,
+      "step": 450
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.4365089049970265e-06,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.02,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.020259028300642967,
+      "eval_runtime": 3.0938,
+      "eval_samples_per_second": 323.23,
+      "eval_steps_per_second": 20.363,
+      "step": 500
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.08514408767223358,
+      "learning_rate": 4.239130434782609e-05,
+      "loss": 0.0085,
+      "step": 550
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 6.856403222954555e-10,
+      "learning_rate": 4.130434782608696e-05,
+      "loss": 0.0055,
+      "step": 600
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.06340835243463516,
+      "learning_rate": 4.021739130434783e-05,
+      "loss": 0.0004,
+      "step": 650
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.4290629226851315e-12,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 0.0014,
+      "step": 700
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.299859962033319e-14,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.0101,
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.007910430431365967,
+      "eval_runtime": 3.113,
+      "eval_samples_per_second": 321.23,
+      "eval_steps_per_second": 20.237,
+      "step": 750
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 3.298977389931679e-05,
+      "learning_rate": 3.695652173913043e-05,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 5.847134164653142e-14,
+      "learning_rate": 3.58695652173913e-05,
+      "loss": 0.0,
+      "step": 850
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 4.566483909757002e-13,
+      "learning_rate": 3.478260869565218e-05,
+      "loss": 0.0033,
+      "step": 900
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 2.20342698753484e-07,
+      "learning_rate": 3.369565217391305e-05,
+      "loss": 0.0,
+      "step": 950
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.727204145320684e-08,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.0056,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.9520909786224365,
+      "eval_runtime": 3.0518,
+      "eval_samples_per_second": 327.672,
+      "eval_steps_per_second": 20.643,
+      "step": 1000
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 2.1178482578765312e-11,
+      "learning_rate": 3.152173913043479e-05,
+      "loss": 0.0,
+      "step": 1050
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 8.027289004530758e-05,
+      "learning_rate": 3.0434782608695656e-05,
+      "loss": 0.0163,
+      "step": 1100
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 0.0030259895138442516,
+      "learning_rate": 2.9347826086956526e-05,
+      "loss": 0.008,
+      "step": 1150
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.1572946106205156e-13,
+      "learning_rate": 2.826086956521739e-05,
+      "loss": 0.0,
+      "step": 1200
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2053489716751242e-12,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.0015,
+      "step": 1250
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.6528851985931396,
+      "eval_runtime": 3.0957,
+      "eval_samples_per_second": 323.027,
+      "eval_steps_per_second": 20.351,
+      "step": 1250
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 1.2785525947429238e-13,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 0.0022,
+      "step": 1300
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 3.6872038083370084e-13,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 1350
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 6.94073501472138e-14,
+      "learning_rate": 2.391304347826087e-05,
+      "loss": 0.0,
+      "step": 1400
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 4.947420945144998e-12,
+      "learning_rate": 2.282608695652174e-05,
+      "loss": 0.0,
+      "step": 1450
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 9.953177876071556e-14,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.0,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.0006066389032639563,
+      "eval_runtime": 3.111,
+      "eval_samples_per_second": 321.436,
+      "eval_steps_per_second": 20.25,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 376251125760000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8614583127cb28e337a0a1f67fe9053c85873ab1c66104cd4f72dceb564c1719
+size 5112