Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5cefe576b6dc625831cf98ded0f30d5ab46b679aa44275ab0dbfb7d901449c
+oid sha256:0a5fbd69e85d1f171059fe74f946b082297f5f3dcebd4aca847806acb3db821f
 size 664589192

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48dfd27bde15e80eb98cdd2c5ba92d706502d0b25f6e76ff3f46d9990b888696
+oid sha256:a8437ce730c286a86c3621616df89ccd7634ef635d1c823d312df8131eec99ec
 size 1329387626

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 160,
-  "best_metric": 0.7793427230046949,
+  "best_metric": 0.7714285714285715,
   "best_model_checkpoint": "/content/drive/MyDrive/data/models/jigsaw/decoder_with_classification_head/checkpoint-160",
   "epoch": 1.5714285714285714,
   "eval_steps": 20,
@@ -11,130 +11,130 @@
   "log_history": [
     {
       "epoch": 0.19704433497536947,
-      "grad_norm": 125.02799224853516,
+      "grad_norm": 77.9209213256836,
       "learning_rate": 9.068627450980392e-06,
-      "loss": 1.7878,
+      "loss": 1.9571,
       "step": 20
     },
     {
       "epoch": 0.19704433497536947,
-      "eval_f1": 0.7181467181467182,
-      "eval_loss": 1.0732333660125732,
-      "eval_runtime": 4.0898,
-      "eval_samples_per_second": 49.636,
-      "eval_steps_per_second": 6.357,
+      "eval_f1": 0.6872246696035242,
+      "eval_loss": 0.8138803839683533,
+      "eval_runtime": 4.1302,
+      "eval_samples_per_second": 49.15,
+      "eval_steps_per_second": 6.295,
       "step": 20
     },
     {
       "epoch": 0.39408866995073893,
-      "grad_norm": 26.702146530151367,
+      "grad_norm": 82.646240234375,
       "learning_rate": 8.088235294117648e-06,
-      "loss": 1.9092,
+      "loss": 1.5111,
       "step": 40
     },
     {
       "epoch": 0.39408866995073893,
-      "eval_f1": 0.719626168224299,
-      "eval_loss": 0.733646810054779,
-      "eval_runtime": 4.0893,
-      "eval_samples_per_second": 49.642,
-      "eval_steps_per_second": 6.358,
+      "eval_f1": 0.6818181818181818,
+      "eval_loss": 0.8300531506538391,
+      "eval_runtime": 4.1106,
+      "eval_samples_per_second": 49.385,
+      "eval_steps_per_second": 6.325,
       "step": 40
     },
     {
       "epoch": 0.5911330049261084,
-      "grad_norm": 57.312957763671875,
+      "grad_norm": 73.47966766357422,
       "learning_rate": 7.107843137254903e-06,
-      "loss": 1.3607,
+      "loss": 1.4946,
       "step": 60
     },
     {
       "epoch": 0.5911330049261084,
-      "eval_f1": 0.700507614213198,
-      "eval_loss": 0.6013323664665222,
-      "eval_runtime": 5.2387,
-      "eval_samples_per_second": 38.75,
-      "eval_steps_per_second": 4.963,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.6204099059104919,
+      "eval_runtime": 4.1289,
+      "eval_samples_per_second": 49.166,
+      "eval_steps_per_second": 6.297,
       "step": 60
     },
     {
       "epoch": 0.7881773399014779,
-      "grad_norm": 49.63467788696289,
+      "grad_norm": 71.3563232421875,
       "learning_rate": 6.1274509803921575e-06,
-      "loss": 1.2099,
+      "loss": 1.2645,
       "step": 80
     },
     {
       "epoch": 0.7881773399014779,
-      "eval_f1": 0.6480446927374302,
-      "eval_loss": 0.6042909026145935,
-      "eval_runtime": 4.112,
-      "eval_samples_per_second": 49.368,
-      "eval_steps_per_second": 6.323,
+      "eval_f1": 0.5766871165644172,
+      "eval_loss": 0.6484544277191162,
+      "eval_runtime": 4.0732,
+      "eval_samples_per_second": 49.837,
+      "eval_steps_per_second": 6.383,
       "step": 80
     },
     {
       "epoch": 0.9852216748768473,
-      "grad_norm": 104.98243713378906,
+      "grad_norm": 91.21923065185547,
       "learning_rate": 5.147058823529411e-06,
-      "loss": 1.2787,
+      "loss": 1.2083,
       "step": 100
     },
     {
       "epoch": 0.9852216748768473,
-      "eval_f1": 0.7425742574257426,
-      "eval_loss": 0.5480031371116638,
-      "eval_runtime": 4.2347,
-      "eval_samples_per_second": 47.937,
-      "eval_steps_per_second": 6.14,
+      "eval_f1": 0.6844919786096256,
+      "eval_loss": 0.5715163946151733,
+      "eval_runtime": 4.1066,
+      "eval_samples_per_second": 49.433,
+      "eval_steps_per_second": 6.331,
       "step": 100
     },
     {
       "epoch": 1.1773399014778325,
-      "grad_norm": 30.004165649414062,
+      "grad_norm": 25.411664962768555,
       "learning_rate": 4.166666666666667e-06,
-      "loss": 0.6028,
+      "loss": 0.5234,
       "step": 120
     },
     {
       "epoch": 1.1773399014778325,
-      "eval_f1": 0.7647058823529411,
-      "eval_loss": 0.5726549029350281,
-      "eval_runtime": 4.383,
-      "eval_samples_per_second": 46.316,
-      "eval_steps_per_second": 5.932,
+      "eval_f1": 0.7523809523809524,
+      "eval_loss": 0.5852020978927612,
+      "eval_runtime": 4.1413,
+      "eval_samples_per_second": 49.019,
+      "eval_steps_per_second": 6.278,
       "step": 120
     },
     {
       "epoch": 1.374384236453202,
-      "grad_norm": 49.051124572753906,
+      "grad_norm": 36.53538513183594,
       "learning_rate": 3.1862745098039216e-06,
-      "loss": 0.5868,
+      "loss": 0.6668,
       "step": 140
     },
     {
       "epoch": 1.374384236453202,
-      "eval_f1": 0.74,
-      "eval_loss": 0.5683486461639404,
-      "eval_runtime": 4.1072,
-      "eval_samples_per_second": 49.425,
-      "eval_steps_per_second": 6.33,
+      "eval_f1": 0.7227722772277227,
+      "eval_loss": 0.5720672011375427,
+      "eval_runtime": 4.1311,
+      "eval_samples_per_second": 49.139,
+      "eval_steps_per_second": 6.294,
       "step": 140
     },
     {
       "epoch": 1.5714285714285714,
-      "grad_norm": 27.854595184326172,
+      "grad_norm": 27.936038970947266,
       "learning_rate": 2.2058823529411767e-06,
-      "loss": 0.4944,
+      "loss": 0.5102,
       "step": 160
     },
     {
       "epoch": 1.5714285714285714,
-      "eval_f1": 0.7793427230046949,
-      "eval_loss": 0.6091228127479553,
-      "eval_runtime": 4.1403,
-      "eval_samples_per_second": 49.031,
-      "eval_steps_per_second": 6.28,
+      "eval_f1": 0.7714285714285715,
+      "eval_loss": 0.608908474445343,
+      "eval_runtime": 4.1227,
+      "eval_samples_per_second": 49.239,
+      "eval_steps_per_second": 6.307,
       "step": 160
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99742976896f8ed6ae6659cef01de9defb910fe869ff938dc78c2198ca7b1964
+oid sha256:25a35e5b4d99ee56e3f3b0f9604cb520ca8d58557147938cf15c91dd6372b784
 size 5969