Model save

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6273
+- Loss: 1.6275
 
 ## Model description
 
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.8413        | 1.0   | 609  | 1.6335          |
-| 1.6669        | 2.0   | 1218 | 1.6158          |
-| 1.5622        | 3.0   | 1827 | 1.5574          |
-| 1.4869        | 4.0   | 2436 | 1.6425          |
-| 1.4155        | 5.0   | 3045 | 1.6174          |
-| 1.389         | 6.0   | 3654 | 1.6719          |
-| 1.3672        | 7.0   | 4263 | 1.6806          |
-| 1.3322        | 8.0   | 4872 | 1.6567          |
-| 1.306         | 9.0   | 5481 | 1.6370          |
-| 1.3152        | 10.0  | 6090 | 1.6273          |
+| 1.8412        | 1.0   | 609  | 1.6328          |
+| 1.6676        | 2.0   | 1218 | 1.6140          |
+| 1.5616        | 3.0   | 1827 | 1.5579          |
+| 1.4876        | 4.0   | 2436 | 1.6426          |
+| 1.416         | 5.0   | 3045 | 1.6180          |
+| 1.3898        | 6.0   | 3654 | 1.6720          |
+| 1.3674        | 7.0   | 4263 | 1.6823          |
+| 1.3325        | 8.0   | 4872 | 1.6565          |
+| 1.3063        | 9.0   | 5481 | 1.6364          |
+| 1.3161        | 10.0  | 6090 | 1.6275          |
 
 
 ### Framework versions

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 1.6490169763565063,
+    "eval_runtime": 3.3488,
+    "eval_samples": 1945,
+    "eval_samples_per_second": 580.811,
+    "eval_steps_per_second": 36.431,
+    "perplexity": 5.201863757919045,
+    "total_flos": 4339270626462000.0,
+    "train_loss": 1.468252067378002,
+    "train_runtime": 594.9553,
+    "train_samples": 9733,
+    "train_samples_per_second": 163.592,
+    "train_steps_per_second": 10.236
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 1.6490169763565063,
+    "eval_runtime": 3.3488,
+    "eval_samples": 1945,
+    "eval_samples_per_second": 580.811,
+    "eval_steps_per_second": 36.431,
+    "perplexity": 5.201863757919045,
+    "total_flos": 4339270626462000.0,
+    "train_loss": 1.468252067378002,
+    "train_runtime": 594.9553,
+    "train_samples": 9733,
+    "train_samples_per_second": 163.592,
+    "train_steps_per_second": 10.236
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34fe2209d68a19bead8af83947d00d558e51eeae84f788dc4d207268d29785ba
+oid sha256:4f86076a0a057228734a4ccbaa4959d4e30f7a5a6b07ad8f8e16e84d93c5cfd4
 size 438080896

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 4339270626462000.0,
+    "train_loss": 1.468252067378002,
+    "train_runtime": 594.9553,
+    "train_samples": 9733,
+    "train_samples_per_second": 163.592,
+    "train_steps_per_second": 10.236
+}

trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_metric": 1.5574235916137695,
+  "best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/OT-Entity-Extraction-Pipeline/model_outputs/Continued_pretraining/TAPT/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/Mardiyyah/TAPT_data_V2_split/tapt_llrd_only_LR-2e-05/checkpoint-1827",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 6090,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 31.118120193481445,
+      "learning_rate": 2e-05,
+      "loss": 1.8413,
+      "step": 609
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6334564685821533,
+      "eval_runtime": 3.4883,
+      "eval_samples_per_second": 557.576,
+      "eval_steps_per_second": 34.974,
+      "step": 609
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 42.714447021484375,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 1.6669,
+      "step": 1218
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.6158479452133179,
+      "eval_runtime": 3.3667,
+      "eval_samples_per_second": 577.713,
+      "eval_steps_per_second": 36.237,
+      "step": 1218
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 40.864356994628906,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 1.5622,
+      "step": 1827
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.5574235916137695,
+      "eval_runtime": 3.2481,
+      "eval_samples_per_second": 598.814,
+      "eval_steps_per_second": 37.561,
+      "step": 1827
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 36.38343048095703,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.4869,
+      "step": 2436
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.642540693283081,
+      "eval_runtime": 3.3434,
+      "eval_samples_per_second": 581.745,
+      "eval_steps_per_second": 36.49,
+      "step": 2436
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 58.19771957397461,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.4155,
+      "step": 3045
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.617448091506958,
+      "eval_runtime": 3.3597,
+      "eval_samples_per_second": 578.914,
+      "eval_steps_per_second": 36.312,
+      "step": 3045
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 25.065608978271484,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.389,
+      "step": 3654
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.6718511581420898,
+      "eval_runtime": 3.3669,
+      "eval_samples_per_second": 577.683,
+      "eval_steps_per_second": 36.235,
+      "step": 3654
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 27.623525619506836,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.3672,
+      "step": 4263
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.680617332458496,
+      "eval_runtime": 3.3669,
+      "eval_samples_per_second": 577.675,
+      "eval_steps_per_second": 36.235,
+      "step": 4263
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 35.16911697387695,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.3322,
+      "step": 4872
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.6566938161849976,
+      "eval_runtime": 3.3973,
+      "eval_samples_per_second": 572.519,
+      "eval_steps_per_second": 35.911,
+      "step": 4872
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 24.309776306152344,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.306,
+      "step": 5481
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.636995792388916,
+      "eval_runtime": 3.37,
+      "eval_samples_per_second": 577.156,
+      "eval_steps_per_second": 36.202,
+      "step": 5481
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 21.337724685668945,
+      "learning_rate": 0.0,
+      "loss": 1.3152,
+      "step": 6090
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.6272846460342407,
+      "eval_runtime": 3.4994,
+      "eval_samples_per_second": 555.806,
+      "eval_steps_per_second": 34.863,
+      "step": 6090
+    },
+    {
+      "epoch": 10.0,
+      "step": 6090,
+      "total_flos": 4339270626462000.0,
+      "train_loss": 1.468252067378002,
+      "train_runtime": 594.9553,
+      "train_samples_per_second": 163.592,
+      "train_steps_per_second": 10.236
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6090,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4339270626462000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}