Model save

README.md

@@ -0,0 +1,51 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: omop_bert
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# omop_bert
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 26723
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f797389ca3a719da256713642bdf1dd8b67bdfc4cadaa1a00be7caf82ad6aa84
+size 426395156

special_tokens_map.json

@@ -0,0 +1,53 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[DATE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[CODES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "None",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 26723
+}

test/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

test/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8923716339350df66fe7f9227fa35ee3b1bb19564f0eaf3b749d1a7f5387a7
+size 426395156

test/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37094b4aaa5a864158fdecc6c092c7cc40a62bee0c8a78954d95c087f7ffed3b
+size 852911866

test/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d17d6c11e9441491cccbcf01cce37aa88baae51c29f56eed910755747be4745
+size 14244

test/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f10014d5f6fa7cfb6822e8324cb833ec4e38e17bedf497cd8ae20f8573fd2e
+size 1064

test/special_tokens_map.json

@@ -0,0 +1,53 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[DATE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[CODES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "None",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test/tokenizer_config.json

@@ -0,0 +1,75 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "None",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CODES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[DATE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[DATE]",
+    "[CODES]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "return_special_tokens_mask": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "FixedVocabTokenizer",
+  "unk_token": "None",
+  "verbose": true
+}

test/trainer_state.json

@@ -0,0 +1,427 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9923011120615911,
+  "eval_steps": 500,
+  "global_step": 29000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.914456800684346e-05,
+      "loss": 6.549,
+      "num_input_tokens_seen": 4096000,
+      "step": 500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.828913601368692e-05,
+      "loss": 5.7273,
+      "num_input_tokens_seen": 8192000,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.7433704020530375e-05,
+      "loss": 5.4759,
+      "num_input_tokens_seen": 12288000,
+      "step": 1500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.6578272027373826e-05,
+      "loss": 5.2276,
+      "num_input_tokens_seen": 16384000,
+      "step": 2000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.572284003421728e-05,
+      "loss": 4.985,
+      "num_input_tokens_seen": 20480000,
+      "step": 2500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.486740804106074e-05,
+      "loss": 4.7303,
+      "num_input_tokens_seen": 24576000,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.40119760479042e-05,
+      "loss": 4.4866,
+      "num_input_tokens_seen": 28672000,
+      "step": 3500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.315654405474765e-05,
+      "loss": 4.2891,
+      "num_input_tokens_seen": 32768000,
+      "step": 4000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.2301112061591106e-05,
+      "loss": 4.1568,
+      "num_input_tokens_seen": 36864000,
+      "step": 4500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.1445680068434564e-05,
+      "loss": 3.9851,
+      "num_input_tokens_seen": 40960000,
+      "step": 5000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.059024807527802e-05,
+      "loss": 3.8691,
+      "num_input_tokens_seen": 45056000,
+      "step": 5500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.973481608212147e-05,
+      "loss": 3.7303,
+      "num_input_tokens_seen": 49152000,
+      "step": 6000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.887938408896493e-05,
+      "loss": 3.6247,
+      "num_input_tokens_seen": 53248000,
+      "step": 6500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.802395209580839e-05,
+      "loss": 3.5127,
+      "num_input_tokens_seen": 57344000,
+      "step": 7000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.7168520102651845e-05,
+      "loss": 3.4229,
+      "num_input_tokens_seen": 61440000,
+      "step": 7500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.6313088109495295e-05,
+      "loss": 3.4015,
+      "num_input_tokens_seen": 65536000,
+      "step": 8000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.545765611633875e-05,
+      "loss": 3.3241,
+      "num_input_tokens_seen": 69632000,
+      "step": 8500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.460222412318221e-05,
+      "loss": 3.2992,
+      "num_input_tokens_seen": 73728000,
+      "step": 9000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.374679213002567e-05,
+      "loss": 3.2067,
+      "num_input_tokens_seen": 77824000,
+      "step": 9500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.289136013686912e-05,
+      "loss": 3.187,
+      "num_input_tokens_seen": 81920000,
+      "step": 10000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.2035928143712576e-05,
+      "loss": 3.142,
+      "num_input_tokens_seen": 86016000,
+      "step": 10500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.1180496150556034e-05,
+      "loss": 3.0925,
+      "num_input_tokens_seen": 90112000,
+      "step": 11000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.032506415739949e-05,
+      "loss": 3.048,
+      "num_input_tokens_seen": 94208000,
+      "step": 11500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.9469632164242945e-05,
+      "loss": 3.0123,
+      "num_input_tokens_seen": 98304000,
+      "step": 12000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.8614200171086403e-05,
+      "loss": 2.9888,
+      "num_input_tokens_seen": 102400000,
+      "step": 12500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.7758768177929857e-05,
+      "loss": 2.9684,
+      "num_input_tokens_seen": 106496000,
+      "step": 13000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.6903336184773314e-05,
+      "loss": 2.9042,
+      "num_input_tokens_seen": 110592000,
+      "step": 13500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.604790419161677e-05,
+      "loss": 2.8847,
+      "num_input_tokens_seen": 114688000,
+      "step": 14000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.5192472198460226e-05,
+      "loss": 2.8339,
+      "num_input_tokens_seen": 118784000,
+      "step": 14500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.433704020530368e-05,
+      "loss": 2.8091,
+      "num_input_tokens_seen": 122880000,
+      "step": 15000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3481608212147134e-05,
+      "loss": 2.6936,
+      "num_input_tokens_seen": 126976000,
+      "step": 15500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2626176218990592e-05,
+      "loss": 2.5118,
+      "num_input_tokens_seen": 131072000,
+      "step": 16000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.1770744225834046e-05,
+      "loss": 2.3521,
+      "num_input_tokens_seen": 135168000,
+      "step": 16500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.0915312232677503e-05,
+      "loss": 2.2735,
+      "num_input_tokens_seen": 139264000,
+      "step": 17000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.0059880239520957e-05,
+      "loss": 2.1603,
+      "num_input_tokens_seen": 143360000,
+      "step": 17500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.9204448246364415e-05,
+      "loss": 2.1129,
+      "num_input_tokens_seen": 147456000,
+      "step": 18000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8349016253207872e-05,
+      "loss": 2.0428,
+      "num_input_tokens_seen": 151552000,
+      "step": 18500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7493584260051327e-05,
+      "loss": 2.0321,
+      "num_input_tokens_seen": 155648000,
+      "step": 19000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.6638152266894784e-05,
+      "loss": 1.9463,
+      "num_input_tokens_seen": 159744000,
+      "step": 19500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5782720273738238e-05,
+      "loss": 1.9171,
+      "num_input_tokens_seen": 163840000,
+      "step": 20000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.4927288280581694e-05,
+      "loss": 1.9084,
+      "num_input_tokens_seen": 167936000,
+      "step": 20500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.407185628742515e-05,
+      "loss": 1.8769,
+      "num_input_tokens_seen": 172032000,
+      "step": 21000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.3216424294268606e-05,
+      "loss": 1.8426,
+      "num_input_tokens_seen": 176128000,
+      "step": 21500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.2360992301112061e-05,
+      "loss": 1.7861,
+      "num_input_tokens_seen": 180224000,
+      "step": 22000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.1505560307955517e-05,
+      "loss": 1.7839,
+      "num_input_tokens_seen": 184320000,
+      "step": 22500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.0650128314798973e-05,
+      "loss": 1.7512,
+      "num_input_tokens_seen": 188416000,
+      "step": 23000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.79469632164243e-06,
+      "loss": 1.7208,
+      "num_input_tokens_seen": 192512000,
+      "step": 23500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.939264328485886e-06,
+      "loss": 1.7213,
+      "num_input_tokens_seen": 196608000,
+      "step": 24000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.083832335329342e-06,
+      "loss": 1.715,
+      "num_input_tokens_seen": 200704000,
+      "step": 24500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.228400342172797e-06,
+      "loss": 1.696,
+      "num_input_tokens_seen": 204800000,
+      "step": 25000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.372968349016254e-06,
+      "loss": 1.7104,
+      "num_input_tokens_seen": 208896000,
+      "step": 25500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.51753635585971e-06,
+      "loss": 1.6742,
+      "num_input_tokens_seen": 212992000,
+      "step": 26000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.662104362703165e-06,
+      "loss": 1.6933,
+      "num_input_tokens_seen": 217088000,
+      "step": 26500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.8066723695466212e-06,
+      "loss": 1.6325,
+      "num_input_tokens_seen": 221184000,
+      "step": 27000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.951240376390077e-06,
+      "loss": 1.6691,
+      "num_input_tokens_seen": 225280000,
+      "step": 27500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.095808383233533e-06,
+      "loss": 1.6348,
+      "num_input_tokens_seen": 229376000,
+      "step": 28000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.240376390076989e-06,
+      "loss": 1.6348,
+      "num_input_tokens_seen": 233472000,
+      "step": 28500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.8494439692044483e-07,
+      "loss": 1.6152,
+      "num_input_tokens_seen": 237568000,
+      "step": 29000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 29225,
+  "num_input_tokens_seen": 237568000,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.22121618014208e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

test/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc9830c44dc4142c9d6027f64dc2a55e22a8378874f3a7a45f3235a63e8ba45
+size 4792

tokenizer_config.json

@@ -0,0 +1,75 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "None",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CODES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[DATE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[DATE]",
+    "[CODES]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "return_special_tokens_mask": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "FixedVocabTokenizer",
+  "unk_token": "None",
+  "verbose": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1677399b3cb2408860cab4c11ff58ab765ad04a9c9f857bac1e7614361a71365
+size 4728