Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5da7acd1cac13024a271168c83760a13ae67564d1c7b0ddc97f52c215217d171
+oid sha256:3f5cefe576b6dc625831cf98ded0f30d5ab46b679aa44275ab0dbfb7d901449c
 size 664589192

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038c8ad99b2958a5827041bd76e8692e8a42b7776cb293cf0f4bb0b36502b38f
+oid sha256:48dfd27bde15e80eb98cdd2c5ba92d706502d0b25f6e76ff3f46d9990b888696
 size 1329387626

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfaff6034b3e88f47d71910c8ef42dca596bcda39bcce22412efadf633b79b2a
+oid sha256:2506b128006f22177f21af93946838684cc0529e555580cf9c85d69ecdc19101
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70c8af470d16cae8adab12055155c2988464b9af430aed08af74c6c7f742ad5
+oid sha256:caa8735e913ec0329447586ccdb6cd32d9c59dc4b7fad0d79ebba902846bf7d7
 size 1465

trainer_state.json

@@ -1,65 +1,145 @@
 {
-  "best_global_step": 60,
-  "best_metric": 0.6956521739130435,
-  "best_model_checkpoint": "/content/drive/MyDrive/data/models/jigsaw/decoder_with_classification_head/checkpoint-60",
-  "epoch": 1.1764705882352942,
+  "best_global_step": 160,
+  "best_metric": 0.7793427230046949,
+  "best_model_checkpoint": "/content/drive/MyDrive/data/models/jigsaw/decoder_with_classification_head/checkpoint-160",
+  "epoch": 1.5714285714285714,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.39215686274509803,
-      "grad_norm": 24.615467071533203,
-      "learning_rate": 8.137254901960784e-06,
-      "loss": 0.9527,
+      "epoch": 0.19704433497536947,
+      "grad_norm": 125.02799224853516,
+      "learning_rate": 9.068627450980392e-06,
+      "loss": 1.7878,
       "step": 20
     },
     {
-      "epoch": 0.39215686274509803,
-      "eval_f1": 0.6091370558375635,
-      "eval_loss": 0.8214746713638306,
-      "eval_runtime": 1.3683,
-      "eval_samples_per_second": 148.361,
-      "eval_steps_per_second": 5.116,
+      "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,
       "step": 20
     },
     {
-      "epoch": 0.7843137254901961,
-      "grad_norm": 17.757286071777344,
-      "learning_rate": 6.176470588235295e-06,
-      "loss": 0.6754,
+      "epoch": 0.39408866995073893,
+      "grad_norm": 26.702146530151367,
+      "learning_rate": 8.088235294117648e-06,
+      "loss": 1.9092,
       "step": 40
     },
     {
-      "epoch": 0.7843137254901961,
-      "eval_f1": 0.6504854368932039,
-      "eval_loss": 0.7166364789009094,
-      "eval_runtime": 1.3196,
-      "eval_samples_per_second": 153.84,
-      "eval_steps_per_second": 5.305,
+      "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,
       "step": 40
     },
     {
-      "epoch": 1.1764705882352942,
-      "grad_norm": 12.719354629516602,
-      "learning_rate": 4.215686274509805e-06,
-      "loss": 0.5274,
+      "epoch": 0.5911330049261084,
+      "grad_norm": 57.312957763671875,
+      "learning_rate": 7.107843137254903e-06,
+      "loss": 1.3607,
       "step": 60
     },
     {
-      "epoch": 1.1764705882352942,
-      "eval_f1": 0.6956521739130435,
-      "eval_loss": 0.6729336380958557,
-      "eval_runtime": 1.325,
-      "eval_samples_per_second": 153.203,
-      "eval_steps_per_second": 5.283,
+      "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,
       "step": 60
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 49.63467788696289,
+      "learning_rate": 6.1274509803921575e-06,
+      "loss": 1.2099,
+      "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,
+      "step": 80
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 104.98243713378906,
+      "learning_rate": 5.147058823529411e-06,
+      "loss": 1.2787,
+      "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,
+      "step": 100
+    },
+    {
+      "epoch": 1.1773399014778325,
+      "grad_norm": 30.004165649414062,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6028,
+      "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,
+      "step": 120
+    },
+    {
+      "epoch": 1.374384236453202,
+      "grad_norm": 49.051124572753906,
+      "learning_rate": 3.1862745098039216e-06,
+      "loss": 0.5868,
+      "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,
+      "step": 140
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 27.854595184326172,
+      "learning_rate": 2.2058823529411767e-06,
+      "loss": 0.4944,
+      "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,
+      "step": 160
     }
   ],
   "logging_steps": 20,
-  "max_steps": 102,
+  "max_steps": 204,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
@@ -75,8 +155,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 3446524437064704.0,
-  "train_batch_size": 32,
+  "total_flos": 3638557364465664.0,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:141ef824b762321620a7c611dcf4dd379131d8d4bb8c7ebfbb498fca352f2776
+oid sha256:99742976896f8ed6ae6659cef01de9defb910fe869ff938dc78c2198ca7b1964
 size 5969