Upload 7 files

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a24023cc6c46dd166b1fdbd0c2279c2ac131964234801d28f0e5db34de8a7535
+oid sha256:2dbbe18d76df09c22fa36f245fba82f2fe9a2b4776d99c603305bc23ef70fd21
 size 13553

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620a2c6044c4ec2a4dcd175f5fe80f8acb66bb949178847e0257327ae79e1185
+oid sha256:183a7ce17aefcfb041aca645cba320fd6d7d899b8807bffb9a11937d9e30ac58
 size 627

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 3.395401954650879,
   "best_model_checkpoint": "/content/drive/MyDrive/ICModel/arabertVit/checkpoint-726",
-  "epoch": 2.0,
-  "global_step": 726,
+  "epoch": 4.0,
+  "global_step": 1452,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -106,11 +106,117 @@
       "eval_samples_per_second": 5.563,
       "eval_steps_per_second": 0.088,
       "step": 726
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 2.4173553719008264e-05,
+      "loss": 3.0104,
+      "step": 750
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 2.2451790633608817e-05,
+      "loss": 2.8998,
+      "step": 800
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.073002754820937e-05,
+      "loss": 2.8714,
+      "step": 850
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.900826446280992e-05,
+      "loss": 2.8648,
+      "step": 900
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.728650137741047e-05,
+      "loss": 2.8893,
+      "step": 950
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.5564738292011018e-05,
+      "loss": 2.8479,
+      "step": 1000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.3842975206611573e-05,
+      "loss": 2.8732,
+      "step": 1050
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.4181885719299316,
+      "eval_runtime": 474.579,
+      "eval_samples_per_second": 5.441,
+      "eval_steps_per_second": 0.086,
+      "step": 1089
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 2.8077,
+      "step": 1100
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 1.0399449035812673e-05,
+      "loss": 2.6918,
+      "step": 1150
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 8.677685950413224e-06,
+      "loss": 2.6974,
+      "step": 1200
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 6.955922865013774e-06,
+      "loss": 2.6855,
+      "step": 1250
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 5.234159779614326e-06,
+      "loss": 2.6727,
+      "step": 1300
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 3.5123966942148763e-06,
+      "loss": 2.6863,
+      "step": 1350
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 1.7906336088154272e-06,
+      "loss": 2.6866,
+      "step": 1400
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 6.887052341597797e-08,
+      "loss": 2.6622,
+      "step": 1450
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.4961369037628174,
+      "eval_runtime": 465.9454,
+      "eval_samples_per_second": 5.541,
+      "eval_steps_per_second": 0.088,
+      "step": 1452
     }
   ],
   "max_steps": 1452,
   "num_train_epochs": 4,
-  "total_flos": 8.411884290016543e+18,
+  "total_flos": 1.6823768580033085e+19,
   "trial_name": null,
   "trial_params": null
 }