push model to hub

README.md

@@ -0,0 +1,87 @@
+---
+library_name: transformers
+language:
+- en
+license: apache-2.0
+base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: CeLLaTe-ner-3class-pubmedbert-baseline
+  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. -->
+
+# CeLLaTe-ner-3class-pubmedbert-baseline
+
+This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) on the OTAR3088/CeLLaTe-ner-3class-iob_final dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0923
+- Precision: 0.7695
+- Recall: 0.7647
+- Micro F1: 0.7671
+- Weighted F1: 0.7667
+- Macro F1: 0.7626
+- Accuracy: 0.9829
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 3407
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Micro F1 | Weighted F1 | Macro F1 | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:-----------:|:--------:|:--------:|
+| 0.3707        | 1.0   | 263  | 0.0799          | 0.6219    | 0.5815 | 0.6010   | 0.5923      | 0.5770   | 0.9770   |
+| 0.0585        | 2.0   | 526  | 0.0618          | 0.7373    | 0.7246 | 0.7309   | 0.7313      | 0.7277   | 0.9815   |
+| 0.0354        | 3.0   | 789  | 0.0642          | 0.7269    | 0.7647 | 0.7453   | 0.7451      | 0.7433   | 0.9818   |
+| 0.0257        | 4.0   | 1052 | 0.0811          | 0.7938    | 0.7054 | 0.7470   | 0.7457      | 0.7406   | 0.9823   |
+| 0.0192        | 5.0   | 1315 | 0.0726          | 0.7556    | 0.7324 | 0.7439   | 0.7433      | 0.7413   | 0.9821   |
+| 0.0145        | 6.0   | 1578 | 0.0841          | 0.7036    | 0.7574 | 0.7295   | 0.7315      | 0.7282   | 0.9808   |
+| 0.0108        | 7.0   | 1841 | 0.0896          | 0.7809    | 0.7330 | 0.7562   | 0.7536      | 0.7491   | 0.9824   |
+| 0.0086        | 8.0   | 2104 | 0.0914          | 0.7442    | 0.7574 | 0.7508   | 0.7510      | 0.7500   | 0.9823   |
+| 0.0071        | 9.0   | 2367 | 0.0928          | 0.7695    | 0.7647 | 0.7671   | 0.7667      | 0.7626   | 0.9829   |
+| 0.0061        | 10.0  | 2630 | 0.1001          | 0.7536    | 0.7402 | 0.7468   | 0.7469      | 0.7463   | 0.9822   |
+| 0.0053        | 11.0  | 2893 | 0.0949          | 0.7722    | 0.7517 | 0.7618   | 0.7611      | 0.7580   | 0.9828   |
+| 0.0042        | 12.0  | 3156 | 0.1045          | 0.7545    | 0.7423 | 0.7484   | 0.7490      | 0.7484   | 0.9823   |
+| 0.0034        | 13.0  | 3419 | 0.1130          | 0.7660    | 0.7548 | 0.7604   | 0.7597      | 0.7571   | 0.9827   |
+| 0.0032        | 14.0  | 3682 | 0.1128          | 0.7572    | 0.7371 | 0.7470   | 0.7472      | 0.7465   | 0.9819   |
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.2
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 14.0,
+    "eval_accuracy": 0.9829432966140413,
+    "eval_loss": 0.09231310337781906,
+    "eval_macro_f1": 0.7626358851133038,
+    "eval_micro_f1": 0.7671018276762401,
+    "eval_precision": 0.7695128339444736,
+    "eval_recall": 0.7647058823529411,
+    "eval_samples": 1407,
+    "eval_weighted_f1": 0.7667324717128587,
+    "total_flos": 2981574659125788.0,
+    "train_loss": 0.040905012183057296,
+    "train_runtime": 941.9422,
+    "train_samples": 8409,
+    "train_samples_per_second": 178.546,
+    "train_steps_per_second": 5.584
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-CellLine",
+    "1": "I-CellLine",
+    "2": "B-CellType",
+    "3": "I-CellType",
+    "4": "B-Tissue",
+    "5": "I-Tissue",
+    "6": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CellLine": 0,
+    "B-CellType": 2,
+    "B-Tissue": 4,
+    "I-CellLine": 1,
+    "I-CellType": 3,
+    "I-Tissue": 5,
+    "O": 6
+  },
+  "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": "4.48.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 14.0,
+    "eval_accuracy": 0.9829432966140413,
+    "eval_loss": 0.09231310337781906,
+    "eval_macro_f1": 0.7626358851133038,
+    "eval_micro_f1": 0.7671018276762401,
+    "eval_precision": 0.7695128339444736,
+    "eval_recall": 0.7647058823529411,
+    "eval_samples": 1407,
+    "eval_weighted_f1": 0.7667324717128587,
+    "total_flos": 2981574659125788.0,
+    "train_loss": 0.040905012183057296,
+    "train_runtime": 941.9422,
+    "train_samples": 8409,
+    "train_samples_per_second": 178.546,
+    "train_steps_per_second": 5.584
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd02e1e80745cedeeb95bca3d7552942c8a23ffe65c48a14e03d2cbeffb9ffe
+size 435611468

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
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 14.0,
+    "total_flos": 2981574659125788.0,
+    "train_loss": 0.040905012183057296,
+    "train_runtime": 941.9422,
+    "train_samples": 8409,
+    "train_samples_per_second": 178.546,
+    "train_steps_per_second": 5.584
+}

trainer_state.json

@@ -0,0 +1,303 @@
+{
+  "best_metric": 0.7626358851133038,
+  "best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/Ner_Pipeline/src/ner_pipeline/model_outputs/NER/CeLLaTe_3_Class_1.0/BiomedNLP_BiomedBERT_base_uncased_abstract_fulltext/BaseStrategy/StandardNerHead/BaseTrainer/no_data_aug/checkpoint-2367",
+  "epoch": 14.0,
+  "eval_steps": 100,
+  "global_step": 3682,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4862927198410034,
+      "learning_rate": 1.9204916458613406e-05,
+      "loss": 0.3707,
+      "step": 263
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9770208301605835,
+      "eval_loss": 0.079874187707901,
+      "eval_macro_f1": 0.5769987323644276,
+      "eval_micro_f1": 0.6010223298358892,
+      "eval_precision": 0.6219376391982183,
+      "eval_recall": 0.5814679854242581,
+      "eval_weighted_f1": 0.592280710950957,
+      "step": 263
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9079930782318115,
+      "learning_rate": 1.819473785289034e-05,
+      "loss": 0.0585,
+      "step": 526
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9815049833324873,
+      "eval_loss": 0.06179345026612282,
+      "eval_macro_f1": 0.7277089050124769,
+      "eval_micro_f1": 0.7309004988185875,
+      "eval_precision": 0.7372881355932204,
+      "eval_recall": 0.7246225923997918,
+      "eval_weighted_f1": 0.7313446348142951,
+      "step": 526
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0678396224975586,
+      "learning_rate": 1.7184559247167276e-05,
+      "loss": 0.0354,
+      "step": 789
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9818434099869706,
+      "eval_loss": 0.06418469548225403,
+      "eval_macro_f1": 0.7432720323562445,
+      "eval_micro_f1": 0.7453069507864029,
+      "eval_precision": 0.7268678871845621,
+      "eval_recall": 0.7647058823529411,
+      "eval_weighted_f1": 0.7451202973389662,
+      "step": 789
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.2629636824131012,
+      "learning_rate": 1.617438064144421e-05,
+      "loss": 0.0257,
+      "step": 1052
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9822664433050747,
+      "eval_loss": 0.08105488121509552,
+      "eval_macro_f1": 0.7405963948143229,
+      "eval_micro_f1": 0.74696802646086,
+      "eval_precision": 0.7937902753368483,
+      "eval_recall": 0.7053617907339927,
+      "eval_weighted_f1": 0.7457498165560936,
+      "step": 1052
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.4527699947357178,
+      "learning_rate": 1.5164202035721145e-05,
+      "loss": 0.0192,
+      "step": 1315
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9820633873123847,
+      "eval_loss": 0.07257022708654404,
+      "eval_macro_f1": 0.7412864283559636,
+      "eval_micro_f1": 0.7438540840602695,
+      "eval_precision": 0.7556390977443609,
+      "eval_recall": 0.7324310255075481,
+      "eval_weighted_f1": 0.7433335893250815,
+      "step": 1315
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.020912302657961845,
+      "learning_rate": 1.415402342999808e-05,
+      "loss": 0.0145,
+      "step": 1578
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.980760444692624,
+      "eval_loss": 0.08405586332082748,
+      "eval_macro_f1": 0.728176283051415,
+      "eval_micro_f1": 0.729506141890198,
+      "eval_precision": 0.7035783365570599,
+      "eval_recall": 0.7574180114523685,
+      "eval_weighted_f1": 0.731476982530679,
+      "step": 1578
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.8371907472610474,
+      "learning_rate": 1.3143844824275017e-05,
+      "loss": 0.0108,
+      "step": 1841
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9824356566323164,
+      "eval_loss": 0.08958898484706879,
+      "eval_macro_f1": 0.7491220181673697,
+      "eval_micro_f1": 0.7561761546723953,
+      "eval_precision": 0.7809206877426511,
+      "eval_recall": 0.7329515877147319,
+      "eval_weighted_f1": 0.7535894817666166,
+      "step": 1841
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.036153607070446014,
+      "learning_rate": 1.213366621855195e-05,
+      "loss": 0.0086,
+      "step": 2104
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.982300285970523,
+      "eval_loss": 0.09140016883611679,
+      "eval_macro_f1": 0.7499882167101145,
+      "eval_micro_f1": 0.7507739938080494,
+      "eval_precision": 0.7442455242966752,
+      "eval_recall": 0.7574180114523685,
+      "eval_weighted_f1": 0.7510494149917656,
+      "step": 2104
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6101483106613159,
+      "learning_rate": 1.1123487612828885e-05,
+      "loss": 0.0071,
+      "step": 2367
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9829432966140413,
+      "eval_loss": 0.09278572350740433,
+      "eval_macro_f1": 0.7626358851133038,
+      "eval_micro_f1": 0.7671018276762401,
+      "eval_precision": 0.7695128339444736,
+      "eval_recall": 0.7647058823529411,
+      "eval_weighted_f1": 0.7667324717128587,
+      "step": 2367
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.0035175979137420654,
+      "learning_rate": 1.011330900710582e-05,
+      "loss": 0.0061,
+      "step": 2630
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9821818366414539,
+      "eval_loss": 0.10011798143386841,
+      "eval_macro_f1": 0.7462770455304736,
+      "eval_micro_f1": 0.7468487394957983,
+      "eval_precision": 0.753577106518283,
+      "eval_recall": 0.7402394586153045,
+      "eval_weighted_f1": 0.7468672605156849,
+      "step": 2630
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.0037437197752296925,
+      "learning_rate": 9.103130401382755e-06,
+      "loss": 0.0053,
+      "step": 2893
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.9827910046195238,
+      "eval_loss": 0.09489310532808304,
+      "eval_macro_f1": 0.7580331495732254,
+      "eval_micro_f1": 0.7618042732788183,
+      "eval_precision": 0.772192513368984,
+      "eval_recall": 0.7516918271733473,
+      "eval_weighted_f1": 0.7611300880366612,
+      "step": 2893
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.33181801438331604,
+      "learning_rate": 8.092951795659689e-06,
+      "loss": 0.0042,
+      "step": 3156
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.9823172073032472,
+      "eval_loss": 0.10447186231613159,
+      "eval_macro_f1": 0.74837113461728,
+      "eval_micro_f1": 0.7483600104959328,
+      "eval_precision": 0.7544973544973544,
+      "eval_recall": 0.7423217074440396,
+      "eval_weighted_f1": 0.7490474113274579,
+      "step": 3156
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.046197082847356796,
+      "learning_rate": 7.082773189936625e-06,
+      "loss": 0.0034,
+      "step": 3419
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.9826894766231788,
+      "eval_loss": 0.11298680305480957,
+      "eval_macro_f1": 0.7570912941995157,
+      "eval_micro_f1": 0.7603565810173047,
+      "eval_precision": 0.7659799260433174,
+      "eval_recall": 0.7548152004164498,
+      "eval_weighted_f1": 0.7597214121014263,
+      "step": 3419
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.02146022580564022,
+      "learning_rate": 6.072594584213559e-06,
+      "loss": 0.0032,
+      "step": 3682
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.9819110953178672,
+      "eval_loss": 0.11282865703105927,
+      "eval_macro_f1": 0.7464972293717181,
+      "eval_micro_f1": 0.7470324452651016,
+      "eval_precision": 0.7572192513368984,
+      "eval_recall": 0.737116085372202,
+      "eval_weighted_f1": 0.7472486799694477,
+      "step": 3682
+    },
+    {
+      "epoch": 14.0,
+      "step": 3682,
+      "total_flos": 2981574659125788.0,
+      "train_loss": 0.040905012183057296,
+      "train_runtime": 941.9422,
+      "train_samples_per_second": 178.546,
+      "train_steps_per_second": 5.584
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5260,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2981574659125788.0,
+  "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 sha256:17a170b9e623987daf76056a24fc0016d9520717b7969d1e9ad9e26465224fdd
+size 5816