Upload folder using huggingface_hub

training_checkpoints/checkpoint-1286/README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: facebook/bart-base
+base_model: facebook/bart-large
 ---
 
 # Model Card for Model ID
@@ -81,7 +81,7 @@ Use the code below to get started with the model.
 
 [More Information Needed]
 
-### Training Procedure 
+### Training Procedure
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
@@ -197,8 +197,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ## Model Card Contact
 
 [More Information Needed]
-
-
 ### Framework versions
 
 - PEFT 0.10.0

training_checkpoints/checkpoint-1286/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "facebook/bart-base",
+  "base_model_name_or_path": "facebook/bart-large",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "v_proj",
     "fc1",
-    "fc2",
-    "out_proj",
     "q_proj",
-    "k_proj"
+    "dense",
+    "k_proj",
+    "out_proj",
+    "fc2",
+    "v_proj"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

training_checkpoints/checkpoint-1286/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c93bb7488d5e9223ae825c8840b5bd74209d37c7f7ddf9b3b8d71bb6b6e6ed
-size 13151448
+oid sha256:b6b8ec8961e6ac8272ea920b9692869fea0a27af675e41dd2fb5d7097bd7359f
+size 34854640

training_checkpoints/checkpoint-1286/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e988df2c5754730cc5278033010c82fe5245f6c025ba60fd682fc37e4240bc8
-size 26413626
+oid sha256:0bdea05987819bf1b4cdb358e006ce59d8b27d910992f005a9d40950dbf83fa4
+size 69927198

training_checkpoints/checkpoint-1286/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fd55bfc0ca383ba7e8bd49234e6d2dd658a683f8360da3aee4adfa6f652d46d
+oid sha256:61c40c1edd741c1e2faf6be081e9d5d99cd42d36136612b2538d0b1b19e70ff0
 size 14244

training_checkpoints/checkpoint-1286/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.5755845408528306,
-  "best_model_checkpoint": "bart-base-lora/checkpoint-1286",
+  "best_metric": 0.7393184269658342,
+  "best_model_checkpoint": "bart-base-lora/checkpoint-1125",
   "epoch": 8.0,
   "eval_steps": 500,
   "global_step": 1286,
@@ -10,190 +10,190 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.611154144074361,
-      "eval_f1_macro": 0.28705545756004525,
-      "eval_f1_micro": 0.611154144074361,
-      "eval_f1_weighted": 0.5574695078229231,
-      "eval_loss": 1.3204560279846191,
-      "eval_macro_fpr": 0.046390243375546196,
-      "eval_macro_sensitivity": 0.302378554842108,
-      "eval_macro_specificity": 0.9691815961629444,
-      "eval_precision": 0.5321554731456403,
-      "eval_precision_macro": 0.2887439395071009,
-      "eval_recall": 0.611154144074361,
-      "eval_recall_macro": 0.302378554842108,
-      "eval_runtime": 45.1674,
-      "eval_samples_per_second": 28.583,
-      "eval_steps_per_second": 3.587,
-      "eval_weighted_fpr": 0.04347073086248701,
-      "eval_weighted_sensitivity": 0.611154144074361,
-      "eval_weighted_specificity": 0.9265697983698051,
+      "eval_accuracy": 0.715724244771495,
+      "eval_f1_macro": 0.3957532686340496,
+      "eval_f1_micro": 0.715724244771495,
+      "eval_f1_weighted": 0.6834645556416842,
+      "eval_loss": 0.9525313973426819,
+      "eval_macro_fpr": 0.028501626692807605,
+      "eval_macro_sensitivity": 0.4415906678049911,
+      "eval_macro_specificity": 0.9786637894661117,
+      "eval_precision": 0.6787596592263883,
+      "eval_precision_macro": 0.38751339695744513,
+      "eval_recall": 0.715724244771495,
+      "eval_recall_macro": 0.4415906678049911,
+      "eval_runtime": 120.9594,
+      "eval_samples_per_second": 10.673,
+      "eval_steps_per_second": 1.339,
+      "eval_weighted_fpr": 0.027587762158911525,
+      "eval_weighted_sensitivity": 0.715724244771495,
+      "eval_weighted_specificity": 0.9642325972201805,
       "step": 160
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6994577846630519,
-      "eval_f1_macro": 0.3947617401663212,
-      "eval_f1_micro": 0.6994577846630519,
-      "eval_f1_weighted": 0.6807748226338182,
-      "eval_loss": 0.887535810470581,
-      "eval_macro_fpr": 0.03062685085400977,
-      "eval_macro_sensitivity": 0.4253981018601158,
-      "eval_macro_specificity": 0.977359054380045,
-      "eval_precision": 0.6728416067370143,
-      "eval_precision_macro": 0.3822291983692299,
-      "eval_recall": 0.6994577846630519,
-      "eval_recall_macro": 0.4253981018601158,
-      "eval_runtime": 44.0045,
-      "eval_samples_per_second": 29.338,
-      "eval_steps_per_second": 3.681,
-      "eval_weighted_fpr": 0.02977743668457406,
-      "eval_weighted_sensitivity": 0.6994577846630519,
-      "eval_weighted_specificity": 0.9609280310376243,
+      "eval_accuracy": 0.7412858249419055,
+      "eval_f1_macro": 0.43370046411892155,
+      "eval_f1_micro": 0.7412858249419055,
+      "eval_f1_weighted": 0.7231329193382661,
+      "eval_loss": 0.7733433842658997,
+      "eval_macro_fpr": 0.025167370687133015,
+      "eval_macro_sensitivity": 0.4686708989603177,
+      "eval_macro_specificity": 0.9805374797463638,
+      "eval_precision": 0.729625861926521,
+      "eval_precision_macro": 0.4491323101141271,
+      "eval_recall": 0.7412858249419055,
+      "eval_recall_macro": 0.4686708989603177,
+      "eval_runtime": 119.8649,
+      "eval_samples_per_second": 10.77,
+      "eval_steps_per_second": 1.352,
+      "eval_weighted_fpr": 0.024322749781532187,
+      "eval_weighted_sensitivity": 0.7412858249419055,
+      "eval_weighted_specificity": 0.9667763712535515,
       "step": 321
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7064291247095275,
-      "eval_f1_macro": 0.39687975393644837,
-      "eval_f1_micro": 0.7064291247095275,
-      "eval_f1_weighted": 0.6751887743731854,
-      "eval_loss": 0.842707633972168,
-      "eval_macro_fpr": 0.029525759570689643,
-      "eval_macro_sensitivity": 0.44418263304043937,
-      "eval_macro_specificity": 0.9780349023882488,
-      "eval_precision": 0.6951917464608133,
-      "eval_precision_macro": 0.4131313886422618,
-      "eval_recall": 0.7064291247095275,
-      "eval_recall_macro": 0.44418263304043937,
-      "eval_runtime": 44.2756,
-      "eval_samples_per_second": 29.158,
-      "eval_steps_per_second": 3.659,
-      "eval_weighted_fpr": 0.02882786947592607,
-      "eval_weighted_sensitivity": 0.7064291247095275,
-      "eval_weighted_specificity": 0.9640944111142056,
+      "eval_accuracy": 0.7738187451587917,
+      "eval_f1_macro": 0.5270593942960143,
+      "eval_f1_micro": 0.7738187451587917,
+      "eval_f1_weighted": 0.7610767338978833,
+      "eval_loss": 0.7104586958885193,
+      "eval_macro_fpr": 0.021211805484311928,
+      "eval_macro_sensitivity": 0.5407847836684627,
+      "eval_macro_specificity": 0.9830897092527341,
+      "eval_precision": 0.7630858215778352,
+      "eval_precision_macro": 0.5565386466479504,
+      "eval_recall": 0.7738187451587917,
+      "eval_recall_macro": 0.5407847836684627,
+      "eval_runtime": 119.5419,
+      "eval_samples_per_second": 10.8,
+      "eval_steps_per_second": 1.355,
+      "eval_weighted_fpr": 0.020451043563524302,
+      "eval_weighted_sensitivity": 0.7738187451587917,
+      "eval_weighted_specificity": 0.9725268936322198,
       "step": 482
     },
     {
       "epoch": 3.11,
       "learning_rate": 3.958333333333333e-05,
-      "loss": 1.2895,
+      "loss": 1.08,
       "step": 500
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.7273431448489543,
-      "eval_f1_macro": 0.42839565617146974,
-      "eval_f1_micro": 0.7273431448489543,
-      "eval_f1_weighted": 0.7166656051521775,
-      "eval_loss": 0.7718679904937744,
-      "eval_macro_fpr": 0.026373610346420835,
-      "eval_macro_sensitivity": 0.4597947061276887,
-      "eval_macro_specificity": 0.9797578098165848,
-      "eval_precision": 0.7132141916978711,
-      "eval_precision_macro": 0.41981312370683244,
-      "eval_recall": 0.7273431448489543,
-      "eval_recall_macro": 0.4597947061276887,
-      "eval_runtime": 44.0471,
-      "eval_samples_per_second": 29.31,
-      "eval_steps_per_second": 3.678,
-      "eval_weighted_fpr": 0.026077937472218107,
-      "eval_weighted_sensitivity": 0.7273431448489543,
-      "eval_weighted_specificity": 0.9690240023998159,
+      "eval_accuracy": 0.7575522850503486,
+      "eval_f1_macro": 0.5497163954183316,
+      "eval_f1_micro": 0.7575522850503486,
+      "eval_f1_weighted": 0.7437674055775699,
+      "eval_loss": 0.7538753151893616,
+      "eval_macro_fpr": 0.023393901824967867,
+      "eval_macro_sensitivity": 0.5613408412198008,
+      "eval_macro_specificity": 0.9817091819688993,
+      "eval_precision": 0.7583906478192325,
+      "eval_precision_macro": 0.5791225123984725,
+      "eval_recall": 0.7575522850503486,
+      "eval_recall_macro": 0.5613408412198008,
+      "eval_runtime": 120.3095,
+      "eval_samples_per_second": 10.731,
+      "eval_steps_per_second": 1.347,
+      "eval_weighted_fpr": 0.022349161013923598,
+      "eval_weighted_sensitivity": 0.7575522850503486,
+      "eval_weighted_specificity": 0.9680854444831427,
       "step": 643
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.750580945003873,
-      "eval_f1_macro": 0.5071625387211971,
-      "eval_f1_micro": 0.750580945003873,
-      "eval_f1_weighted": 0.7368350875727435,
-      "eval_loss": 0.7387559413909912,
-      "eval_macro_fpr": 0.02390193870216418,
-      "eval_macro_sensitivity": 0.5165232292614671,
-      "eval_macro_specificity": 0.9813510652812688,
-      "eval_precision": 0.739991301984922,
-      "eval_precision_macro": 0.5733174750951799,
-      "eval_recall": 0.750580945003873,
-      "eval_recall_macro": 0.5165232292614671,
-      "eval_runtime": 43.5191,
-      "eval_samples_per_second": 29.665,
-      "eval_steps_per_second": 3.723,
-      "eval_weighted_fpr": 0.023185483870967742,
-      "eval_weighted_sensitivity": 0.750580945003873,
-      "eval_weighted_specificity": 0.9696850342151593,
+      "eval_accuracy": 0.7831138652207591,
+      "eval_f1_macro": 0.6353946839596228,
+      "eval_f1_micro": 0.783113865220759,
+      "eval_f1_weighted": 0.770250750407997,
+      "eval_loss": 0.6978110074996948,
+      "eval_macro_fpr": 0.020328728105215688,
+      "eval_macro_sensitivity": 0.6491872351233146,
+      "eval_macro_specificity": 0.983610303127039,
+      "eval_precision": 0.790031827496624,
+      "eval_precision_macro": 0.7409525878258343,
+      "eval_recall": 0.7831138652207591,
+      "eval_recall_macro": 0.6491872351233146,
+      "eval_runtime": 119.9411,
+      "eval_samples_per_second": 10.764,
+      "eval_steps_per_second": 1.351,
+      "eval_weighted_fpr": 0.019398642095053348,
+      "eval_weighted_sensitivity": 0.7831138652207591,
+      "eval_weighted_specificity": 0.9710406816848265,
       "step": 803
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.7443841982958946,
-      "eval_f1_macro": 0.508766573370445,
-      "eval_f1_micro": 0.7443841982958946,
-      "eval_f1_weighted": 0.726841801268282,
-      "eval_loss": 0.7526118755340576,
-      "eval_macro_fpr": 0.024741953499129225,
-      "eval_macro_sensitivity": 0.5229557335240369,
-      "eval_macro_specificity": 0.980899976318631,
-      "eval_precision": 0.7337183019873953,
-      "eval_precision_macro": 0.5703412270657953,
-      "eval_recall": 0.7443841982958946,
-      "eval_recall_macro": 0.5229557335240369,
-      "eval_runtime": 43.7116,
-      "eval_samples_per_second": 29.534,
-      "eval_steps_per_second": 3.706,
-      "eval_weighted_fpr": 0.023940800928612886,
-      "eval_weighted_sensitivity": 0.7443841982958946,
-      "eval_weighted_specificity": 0.9691154464835722,
+      "eval_accuracy": 0.8156467854376452,
+      "eval_f1_macro": 0.686011065139391,
+      "eval_f1_micro": 0.8156467854376452,
+      "eval_f1_weighted": 0.8087620976325791,
+      "eval_loss": 0.5920090675354004,
+      "eval_macro_fpr": 0.016634568189926056,
+      "eval_macro_sensitivity": 0.6889168814632094,
+      "eval_macro_specificity": 0.9860196319752603,
+      "eval_precision": 0.8053079350996695,
+      "eval_precision_macro": 0.7051361586363433,
+      "eval_recall": 0.8156467854376452,
+      "eval_recall_macro": 0.6889168814632094,
+      "eval_runtime": 121.4244,
+      "eval_samples_per_second": 10.632,
+      "eval_steps_per_second": 1.334,
+      "eval_weighted_fpr": 0.01588785046728972,
+      "eval_weighted_sensitivity": 0.8156467854376452,
+      "eval_weighted_specificity": 0.974647694191258,
       "step": 964
     },
     {
       "epoch": 6.22,
       "learning_rate": 2.916666666666667e-05,
-      "loss": 0.7332,
+      "loss": 0.5581,
       "step": 1000
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.7552285050348567,
-      "eval_f1_macro": 0.5608894910772386,
-      "eval_f1_micro": 0.7552285050348567,
-      "eval_f1_weighted": 0.7460771491633669,
-      "eval_loss": 0.7082085609436035,
-      "eval_macro_fpr": 0.02329269548734161,
-      "eval_macro_sensitivity": 0.5727565701904757,
-      "eval_macro_specificity": 0.9817624646436656,
-      "eval_precision": 0.7436383222975608,
-      "eval_precision_macro": 0.5665418243254761,
-      "eval_recall": 0.7552285050348567,
-      "eval_recall_macro": 0.5727565701904757,
-      "eval_runtime": 43.8592,
-      "eval_samples_per_second": 29.435,
-      "eval_steps_per_second": 3.694,
-      "eval_weighted_fpr": 0.02262637834741515,
-      "eval_weighted_sensitivity": 0.7552285050348567,
-      "eval_weighted_specificity": 0.9712084646201266,
+      "eval_accuracy": 0.8187451587916343,
+      "eval_f1_macro": 0.7393184269658342,
+      "eval_f1_micro": 0.8187451587916342,
+      "eval_f1_weighted": 0.8146848849127107,
+      "eval_loss": 0.6230757236480713,
+      "eval_macro_fpr": 0.016206558639896132,
+      "eval_macro_sensitivity": 0.7424574536250088,
+      "eval_macro_specificity": 0.9863587851767341,
+      "eval_precision": 0.8177894369587694,
+      "eval_precision_macro": 0.7626654223433325,
+      "eval_recall": 0.8187451587916343,
+      "eval_recall_macro": 0.7424574536250088,
+      "eval_runtime": 122.7775,
+      "eval_samples_per_second": 10.515,
+      "eval_steps_per_second": 1.319,
+      "eval_weighted_fpr": 0.015566790846194785,
+      "eval_weighted_sensitivity": 0.8187451587916343,
+      "eval_weighted_specificity": 0.9766366188593788,
       "step": 1125
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.7583268783888458,
-      "eval_f1_macro": 0.5755845408528306,
-      "eval_f1_micro": 0.7583268783888458,
-      "eval_f1_weighted": 0.7502605827076951,
-      "eval_loss": 0.7160602807998657,
-      "eval_macro_fpr": 0.022834923601538912,
-      "eval_macro_sensitivity": 0.5974764193374731,
-      "eval_macro_specificity": 0.9820281006961107,
-      "eval_precision": 0.7489019370925815,
-      "eval_precision_macro": 0.5641453776326693,
-      "eval_recall": 0.7583268783888458,
-      "eval_recall_macro": 0.5974764193374731,
-      "eval_runtime": 47.4544,
-      "eval_samples_per_second": 27.205,
-      "eval_steps_per_second": 3.414,
-      "eval_weighted_fpr": 0.022257098016835498,
-      "eval_weighted_sensitivity": 0.7583268783888458,
-      "eval_weighted_specificity": 0.9720946320528147,
+      "eval_accuracy": 0.8140975987606507,
+      "eval_f1_macro": 0.7328585966804847,
+      "eval_f1_micro": 0.8140975987606507,
+      "eval_f1_weighted": 0.8088643288992207,
+      "eval_loss": 0.6290707588195801,
+      "eval_macro_fpr": 0.01671628651715199,
+      "eval_macro_sensitivity": 0.730719512015592,
+      "eval_macro_specificity": 0.985990627132147,
+      "eval_precision": 0.8133783130550384,
+      "eval_precision_macro": 0.7636063765511063,
+      "eval_recall": 0.8140975987606507,
+      "eval_recall_macro": 0.730719512015592,
+      "eval_runtime": 122.8754,
+      "eval_samples_per_second": 10.507,
+      "eval_steps_per_second": 1.318,
+      "eval_weighted_fpr": 0.016049217600641968,
+      "eval_weighted_sensitivity": 0.8140975987606507,
+      "eval_weighted_specificity": 0.975761808221554,
       "step": 1286
     }
   ],
@@ -201,7 +201,7 @@
   "max_steps": 2400,
   "num_train_epochs": 15,
   "save_steps": 500,
-  "total_flos": 1.3021649087053824e+16,
+  "total_flos": 4.57713898892329e+16,
   "trial_name": null,
   "trial_params": null
 }

training_checkpoints/checkpoint-1286/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb230625284b71a8582d0495ae9a462b745f8cb976f9d7932c4f91357944609
+oid sha256:8cfeeb4079e0edbd60cad2df3b73a192a8e64f61f57cc52cfabb80fd9ff6105d
 size 4600