add Variant-V1 LLRD model

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a6c9229eed32130bb8b880265f8b886fb4347ef21ba3aacfe8a0e5e49924ce
+oid sha256:bda9525a3cc937b80370a391c7c6adf07484c6dcc483be1f745d253eb7ad31f3
 size 435599164

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f5b0a137201ea2b49806eb0bc8e2ac1a63abb4dfbe61a13677a91dba69378e
+oid sha256:76934c72aa799fa70772bd0518b6552ab16dd7af97db92f864db37f07a6517a9
 size 871321658

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e246631174b7e7bbbd79eb8c88be058db2e397b961adf392640d441f0303d3b3
+oid sha256:61e45edb800e9706baa914416a41d7442130659d6c2eedc62a95aae8c2ccdd31
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f2a475865a035e3e7c31a5baf48c564790f030bd32fece0a5357e648f353c3c
+oid sha256:684908b1ddccacc6a619d447e4f01151ce041a7a97eb1004119dd3b2f1c3be72
 size 1576

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.90625,
   "best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/OT-Entity-Extraction-Pipeline/model_outputs/hf/Variant_V2/reinit_llrd/4K_no_reinit_classifier_llrd0.9/BiomedNLP_BiomedBERT_base/checkpoint-1408",
-  "epoch": 4.0,
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 1408,
+  "global_step": 2464,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -83,6 +83,63 @@
       "eval_samples_per_second": 270.961,
       "eval_steps_per_second": 17.075,
       "step": 1408
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.021774714812636375,
+      "learning_rate": 1.667929292929293e-05,
+      "loss": 0.0016,
+      "step": 1760
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9981066222597349,
+      "eval_f1": 0.8957264957264958,
+      "eval_loss": 0.006704295519739389,
+      "eval_precision": 0.888135593220339,
+      "eval_recall": 0.903448275862069,
+      "eval_runtime": 4.4921,
+      "eval_samples_per_second": 268.47,
+      "eval_steps_per_second": 16.918,
+      "step": 1760
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.004604855552315712,
+      "learning_rate": 1.5568181818181822e-05,
+      "loss": 0.001,
+      "step": 2112
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9982663047197573,
+      "eval_f1": 0.9031141868512111,
+      "eval_loss": 0.0071674492210149765,
+      "eval_precision": 0.90625,
+      "eval_recall": 0.9,
+      "eval_runtime": 4.7306,
+      "eval_samples_per_second": 254.936,
+      "eval_steps_per_second": 16.066,
+      "step": 2112
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.013881128281354904,
+      "learning_rate": 1.4457070707070708e-05,
+      "loss": 0.0007,
+      "step": 2464
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9980838104797317,
+      "eval_f1": 0.9014084507042254,
+      "eval_loss": 0.00853455625474453,
+      "eval_precision": 0.920863309352518,
+      "eval_recall": 0.8827586206896552,
+      "eval_runtime": 4.4218,
+      "eval_samples_per_second": 272.737,
+      "eval_steps_per_second": 17.187,
+      "step": 2464
     }
   ],
   "logging_steps": 500,
@@ -97,7 +154,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -106,12 +163,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 460067113467108.0,
+  "total_flos": 805331029976316.0,
   "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 sha256:12b09da2fb5aa6cbf002b655c958b5c057a395831c815f26c553d07c8fd07caa
+size 5624