Upload trainer_state.json

trainer_state.json

@@ -1,136 +1,72 @@
 {
-  "best_metric": 0.9636638164520264,
-  "best_model_checkpoint": "microsoft-swin-base-patch4-window7-224_bert-base-multilingual-cased_bert-base-multilingual-cased/checkpoint-4473",
-  "epoch": 9.0,
-  "global_step": 4473,
+  "best_metric": 0.8071129322052002,
+  "best_model_checkpoint": "microsoft-swin-base-patch4-window7-224_bert-base-multilingual-cased_bert-base-multilingual-cased/checkpoint-2496",
+  "epoch": 4.0,
+  "global_step": 2496,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "eval_loss": 1.1897900104522705,
-      "eval_runtime": 529.9619,
-      "eval_samples_per_second": 4.689,
-      "eval_steps_per_second": 0.236,
-      "step": 497
-    },
-    {
-      "epoch": 1.01,
-      "learning_rate": 1.8997987927565392e-05,
-      "loss": 1.4457,
+      "epoch": 0.8,
+      "learning_rate": 3.680128205128205e-05,
+      "loss": 1.2658,
       "step": 500
     },
     {
-      "epoch": 2.0,
-      "eval_loss": 1.0949503183364868,
-      "eval_runtime": 30.0349,
-      "eval_samples_per_second": 82.737,
-      "eval_steps_per_second": 4.162,
-      "step": 994
+      "epoch": 1.0,
+      "eval_loss": 0.9458033442497253,
+      "eval_runtime": 118.6535,
+      "eval_samples_per_second": 21.028,
+      "eval_steps_per_second": 1.315,
+      "step": 624
     },
     {
-      "epoch": 2.01,
-      "learning_rate": 1.799195171026157e-05,
-      "loss": 1.1664,
+      "epoch": 1.6,
+      "learning_rate": 3.359615384615385e-05,
+      "loss": 0.9614,
       "step": 1000
     },
     {
-      "epoch": 3.0,
-      "eval_loss": 1.0486524105072021,
-      "eval_runtime": 29.951,
-      "eval_samples_per_second": 82.969,
-      "eval_steps_per_second": 4.173,
-      "step": 1491
+      "epoch": 2.0,
+      "eval_loss": 0.8532279133796692,
+      "eval_runtime": 29.6586,
+      "eval_samples_per_second": 84.124,
+      "eval_steps_per_second": 5.26,
+      "step": 1248
     },
     {
-      "epoch": 3.02,
-      "learning_rate": 1.6985915492957746e-05,
-      "loss": 1.0482,
+      "epoch": 2.4,
+      "learning_rate": 3.0391025641025643e-05,
+      "loss": 0.8407,
       "step": 1500
     },
     {
-      "epoch": 4.0,
-      "eval_loss": 1.0101640224456787,
-      "eval_runtime": 29.925,
-      "eval_samples_per_second": 83.041,
-      "eval_steps_per_second": 4.177,
-      "step": 1988
+      "epoch": 3.0,
+      "eval_loss": 0.8248330354690552,
+      "eval_runtime": 29.4482,
+      "eval_samples_per_second": 84.725,
+      "eval_steps_per_second": 5.297,
+      "step": 1872
     },
     {
-      "epoch": 4.02,
-      "learning_rate": 1.5979879275653925e-05,
-      "loss": 0.9577,
+      "epoch": 3.21,
+      "learning_rate": 2.718589743589744e-05,
+      "loss": 0.7485,
       "step": 2000
     },
     {
-      "epoch": 5.0,
-      "eval_loss": 0.9930654168128967,
-      "eval_runtime": 29.9623,
-      "eval_samples_per_second": 82.938,
-      "eval_steps_per_second": 4.172,
-      "step": 2485
-    },
-    {
-      "epoch": 5.03,
-      "learning_rate": 1.4973843058350102e-05,
-      "loss": 0.8946,
-      "step": 2500
-    },
-    {
-      "epoch": 6.0,
-      "eval_loss": 0.9802634119987488,
-      "eval_runtime": 30.0215,
-      "eval_samples_per_second": 82.774,
-      "eval_steps_per_second": 4.164,
-      "step": 2982
-    },
-    {
-      "epoch": 6.04,
-      "learning_rate": 1.396780684104628e-05,
-      "loss": 0.8387,
-      "step": 3000
-    },
-    {
-      "epoch": 7.0,
-      "eval_loss": 0.9800927639007568,
-      "eval_runtime": 29.9858,
-      "eval_samples_per_second": 82.873,
-      "eval_steps_per_second": 4.169,
-      "step": 3479
-    },
-    {
-      "epoch": 7.04,
-      "learning_rate": 1.2961770623742455e-05,
-      "loss": 0.7909,
-      "step": 3500
-    },
-    {
-      "epoch": 8.0,
-      "eval_loss": 0.9686193466186523,
-      "eval_runtime": 30.1165,
-      "eval_samples_per_second": 82.513,
-      "eval_steps_per_second": 4.151,
-      "step": 3976
-    },
-    {
-      "epoch": 8.05,
-      "learning_rate": 1.1955734406438632e-05,
-      "loss": 0.7463,
-      "step": 4000
-    },
-    {
-      "epoch": 9.0,
-      "eval_loss": 0.9636638164520264,
-      "eval_runtime": 30.0385,
-      "eval_samples_per_second": 82.727,
-      "eval_steps_per_second": 4.161,
-      "step": 4473
+      "epoch": 4.0,
+      "eval_loss": 0.8071129322052002,
+      "eval_runtime": 29.4796,
+      "eval_samples_per_second": 84.635,
+      "eval_steps_per_second": 5.292,
+      "step": 2496
     }
   ],
-  "max_steps": 9940,
-  "num_train_epochs": 20,
-  "total_flos": 1.6290726869086323e+19,
+  "max_steps": 6240,
+  "num_train_epochs": 10,
+  "total_flos": 7.268007926746055e+18,
   "trial_name": null,
   "trial_params": null
 }