Upload 6 files

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4387073d5cd79b938534425d0aa69cce8f595db74ecffbf675f6722c658c7047
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde0284e691744cab21aa0a7258284d8a47c7dd85f1dc68f2c3313211592bd3f
+size 627

trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": 3.395401954650879,
+  "best_model_checkpoint": "/content/drive/MyDrive/ICModel/arabertVit/checkpoint-726",
+  "epoch": 3.0,
+  "global_step": 1089,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.8278236914600555e-05,
+      "loss": 6.668,
+      "step": 50
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.65564738292011e-05,
+      "loss": 4.4106,
+      "step": 100
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.4834710743801654e-05,
+      "loss": 4.0868,
+      "step": 150
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.311294765840221e-05,
+      "loss": 3.8562,
+      "step": 200
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.139118457300275e-05,
+      "loss": 3.7648,
+      "step": 250
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.9669421487603306e-05,
+      "loss": 3.6757,
+      "step": 300
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.794765840220386e-05,
+      "loss": 3.6014,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.510687828063965,
+      "eval_runtime": 447.4802,
+      "eval_samples_per_second": 5.77,
+      "eval_steps_per_second": 0.092,
+      "step": 363
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.622589531680441e-05,
+      "loss": 3.3528,
+      "step": 400
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.4504132231404964e-05,
+      "loss": 3.2424,
+      "step": 450
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 3.278236914600551e-05,
+      "loss": 3.1979,
+      "step": 500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 3.106060606060606e-05,
+      "loss": 3.2015,
+      "step": 550
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.9338842975206616e-05,
+      "loss": 3.1945,
+      "step": 600
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.7617079889807162e-05,
+      "loss": 3.1473,
+      "step": 650
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 2.5895316804407715e-05,
+      "loss": 3.171,
+      "step": 700
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.395401954650879,
+      "eval_runtime": 464.1391,
+      "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
+    }
+  ],
+  "max_steps": 1452,
+  "num_train_epochs": 4,
+  "total_flos": 1.2617826435024814e+19,
+  "trial_name": null,
+  "trial_params": null
+}