Upload folder using huggingface_hub

training_checkpoints/checkpoint-482/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-482/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-482/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c199fbb228a83b13abb5344bab7f80b4a68294f6c426e291525627e882339e17
-size 13151448
+oid sha256:c719daa23e1d81c0b2ff0e360aec48ddf2bcf0ebc592f710cb51c40fdbe4f484
+size 34854640

training_checkpoints/checkpoint-482/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e362dd74f75ff456ef0651b2dd565518b09d655aeaf4f0d3e2700807ff6a9540
-size 26413626
+oid sha256:fd4bb4f409c45c7ad2f65d2862e1bda289f8d754e1de606dea26a3b13e3bd840
+size 69927198

training_checkpoints/checkpoint-482/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86500ec09f2ca351f4fd67cf7f0aa06f34c0c4aedda09477ff2fce8239cfd608
+oid sha256:cf6d16d5ffd16bb406bd25889a9f70b6ee3da19a14c665fcae6ea26c561db5f5
 size 14244

training_checkpoints/checkpoint-482/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.39687975393644837,
+  "best_metric": 0.5270593942960143,
   "best_model_checkpoint": "bart-base-lora/checkpoint-482",
   "epoch": 2.998444790046656,
   "eval_steps": 500,
@@ -10,68 +10,68 @@
   "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
     }
   ],
@@ -79,7 +79,7 @@
   "max_steps": 2400,
   "num_train_epochs": 15,
   "save_steps": 500,
-  "total_flos": 4883118407645184.0,
+  "total_flos": 1.7164271208462336e+16,
   "trial_name": null,
   "trial_params": null
 }

training_checkpoints/checkpoint-482/training_args.bin

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