Training in progress, epoch 5

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 2.98,
+    "epoch": 4.99,
     "eval_accuracy": 0.796875,
     "eval_loss": 0.776684582233429,
-    "eval_runtime": 43.6376,
-    "eval_samples_per_second": 36.666,
-    "eval_steps_per_second": 0.573,
-    "total_flos": 1.1739110279510753e+18,
-    "train_loss": 1.9657008977646524,
-    "train_runtime": 10337.147,
-    "train_samples_per_second": 3.501,
-    "train_steps_per_second": 0.014
+    "eval_runtime": 45.0682,
+    "eval_samples_per_second": 35.502,
+    "eval_steps_per_second": 0.555,
+    "total_flos": 1.971449904436347e+18,
+    "train_loss": 0.42377444733964637,
+    "train_runtime": 1020.3883,
+    "train_samples_per_second": 59.12,
+    "train_steps_per_second": 0.23
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.98,
+    "epoch": 4.99,
     "eval_accuracy": 0.796875,
     "eval_loss": 0.776684582233429,
-    "eval_runtime": 43.6376,
-    "eval_samples_per_second": 36.666,
-    "eval_steps_per_second": 0.573
+    "eval_runtime": 45.0682,
+    "eval_samples_per_second": 35.502,
+    "eval_steps_per_second": 0.555
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f63348280f49b98c911a27eb5955ea9592b6eb23308bf0fb4b6f8dc927e1854a
+oid sha256:dfea6cb0efd41a3bbeb51e4e8f232c2e8ca4897a1818f093bb00bb6ac447036f
 size 110552801

runs/Apr21_21-14-33_25733e00f35f/events.out.tfevents.1682124684.25733e00f35f.544.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97fd33c8ed6c3599f399a0585b73fa157abe660142f2370d3745c62b2d7cd634
-size 22446
+oid sha256:d4330b04eab97d38e0feaf1228792cc07c5c03af9efce91173859d97bfc64b5c
+size 22800

runs/Apr21_21-14-33_25733e00f35f/events.out.tfevents.1682128540.25733e00f35f.544.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fadbdcd72d7e00add7fa3dfe857424f73b0e110de461fcf5faeb51886be835
+size 411

runs/Apr22_01-57-25_25733e00f35f/1682128678.0475118/events.out.tfevents.1682128678.25733e00f35f.544.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b509999c3568745e7f46e7e23ad9c7f73bd6285456d6bbe32b3805694b30ee
+size 5961

runs/Apr22_01-57-25_25733e00f35f/events.out.tfevents.1682128678.25733e00f35f.544.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e3574c9d3be163606e7c48c7169ecc2e8d7d3169f01a45adb104a3a5bfb389
+size 7802

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.98,
-    "total_flos": 1.1739110279510753e+18,
-    "train_loss": 1.9657008977646524,
-    "train_runtime": 10337.147,
-    "train_samples_per_second": 3.501,
-    "train_steps_per_second": 0.014
+    "epoch": 4.99,
+    "total_flos": 1.971449904436347e+18,
+    "train_loss": 0.42377444733964637,
+    "train_runtime": 1020.3883,
+    "train_samples_per_second": 59.12,
+    "train_steps_per_second": 0.23
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 0.796875,
   "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-thai/checkpoint-141",
-  "epoch": 2.984126984126984,
-  "global_step": 141,
+  "epoch": 4.98941798941799,
+  "global_step": 235,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,18 +119,90 @@
       "step": 141
     },
     {
-      "epoch": 2.98,
-      "step": 141,
-      "total_flos": 1.1739110279510753e+18,
-      "train_loss": 1.9657008977646524,
-      "train_runtime": 10337.147,
-      "train_samples_per_second": 3.501,
-      "train_steps_per_second": 0.014
+      "epoch": 3.19,
+      "learning_rate": 0.0,
+      "loss": 1.092,
+      "step": 150
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.0,
+      "loss": 1.0781,
+      "step": 160
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.0,
+      "loss": 1.0461,
+      "step": 170
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 0.0,
+      "loss": 1.0487,
+      "step": 180
+    },
+    {
+      "epoch": 3.99,
+      "eval_accuracy": 0.796875,
+      "eval_loss": 0.776684582233429,
+      "eval_runtime": 43.5371,
+      "eval_samples_per_second": 36.75,
+      "eval_steps_per_second": 0.574,
+      "step": 188
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 0.0,
+      "loss": 1.0316,
+      "step": 190
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 0.0,
+      "loss": 1.06,
+      "step": 200
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.0,
+      "loss": 1.0528,
+      "step": 210
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 0.0,
+      "loss": 1.0339,
+      "step": 220
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 0.0,
+      "loss": 1.0889,
+      "step": 230
+    },
+    {
+      "epoch": 4.99,
+      "eval_accuracy": 0.796875,
+      "eval_loss": 0.776684582233429,
+      "eval_runtime": 43.9225,
+      "eval_samples_per_second": 36.428,
+      "eval_steps_per_second": 0.569,
+      "step": 235
+    },
+    {
+      "epoch": 4.99,
+      "step": 235,
+      "total_flos": 1.971449904436347e+18,
+      "train_loss": 0.42377444733964637,
+      "train_runtime": 1020.3883,
+      "train_samples_per_second": 59.12,
+      "train_steps_per_second": 0.23
     }
   ],
-  "max_steps": 141,
-  "num_train_epochs": 3,
-  "total_flos": 1.1739110279510753e+18,
+  "max_steps": 235,
+  "num_train_epochs": 5,
+  "total_flos": 1.971449904436347e+18,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88f8d9e6e17864b2fbdc5786aa50c38e06a595f903bf942228e7ba7bd33fe7a
+oid sha256:3c3c0fd013aeeb31c04363116eb17010e8356d94af1eff566cd9e2e854b96dc9
 size 3643