Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 13.33,
-    "total_flos": 8.7520382681131e+16,
-    "train_loss": 0.4070509672164917,
-    "train_runtime": 340.2477,
-    "train_samples_per_second": 15.342,
-    "train_steps_per_second": 0.059
+    "epoch": 8.89,
+    "total_flos": 5.786635923932774e+16,
+    "train_loss": 0.14985284606615704,
+    "train_runtime": 220.5615,
+    "train_samples_per_second": 11.833,
+    "train_steps_per_second": 0.272
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f20549ae026562cafe99e6acb0d4f97265b244202f65647251001be890fc79
+oid sha256:4563d6972195df7e6376768904924263a6abee86a55392b526b72c4e46457d08
 size 110397937

runs/Jul23_10-21-56_00db9bc3da89/events.out.tfevents.1690108534.00db9bc3da89.10544.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad00be1ecdf42cd008410747f842a33b4a7a7c6fe55a1aef7c86417e9d2f0cd
+size 551

runs/Jul23_10-21-56_00db9bc3da89/events.out.tfevents.1690109486.00db9bc3da89.10544.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79441b3af117fc3be0399cd3b7b1feb061d83a94dd24dc8d9c5e78564c652000
+size 5084

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 13.33,
-    "total_flos": 8.7520382681131e+16,
-    "train_loss": 0.4070509672164917,
-    "train_runtime": 340.2477,
-    "train_samples_per_second": 15.342,
-    "train_steps_per_second": 0.059
+    "epoch": 8.89,
+    "total_flos": 5.786635923932774e+16,
+    "train_loss": 0.14985284606615704,
+    "train_runtime": 220.5615,
+    "train_samples_per_second": 11.833,
+    "train_steps_per_second": 0.272
 }

trainer_state.json

@@ -1,163 +1,169 @@
 {
-  "best_metric": 0.896551724137931,
-  "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-13",
-  "epoch": 13.333333333333334,
-  "global_step": 20,
+  "best_metric": 1.0,
+  "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-6",
+  "epoch": 8.88888888888889,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.27586206896551724,
-      "eval_loss": 1.1699918508529663,
-      "eval_runtime": 1.1929,
-      "eval_samples_per_second": 24.31,
-      "eval_steps_per_second": 0.838,
-      "step": 1
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.3793103448275862,
-      "eval_loss": 1.0350514650344849,
-      "eval_runtime": 0.7976,
-      "eval_samples_per_second": 36.36,
-      "eval_steps_per_second": 1.254,
-      "step": 3
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.5172413793103449,
-      "eval_loss": 0.9730662107467651,
-      "eval_runtime": 0.8014,
-      "eval_samples_per_second": 36.186,
-      "eval_steps_per_second": 1.248,
-      "step": 5
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.5172413793103449,
-      "eval_loss": 0.9361577033996582,
-      "eval_runtime": 1.0363,
-      "eval_samples_per_second": 27.984,
-      "eval_steps_per_second": 0.965,
+      "epoch": 0.89,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.04543434828519821,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 0.9849,
+      "eval_samples_per_second": 29.446,
+      "eval_steps_per_second": 3.046,
       "step": 6
     },
     {
-      "epoch": 5.0,
-      "eval_accuracy": 0.5517241379310345,
-      "eval_loss": 0.8889826536178589,
-      "eval_runtime": 0.7918,
-      "eval_samples_per_second": 36.624,
-      "eval_steps_per_second": 1.263,
-      "step": 7
-    },
-    {
-      "epoch": 6.0,
-      "eval_accuracy": 0.7586206896551724,
-      "eval_loss": 0.7596346735954285,
-      "eval_runtime": 0.8269,
-      "eval_samples_per_second": 35.071,
-      "eval_steps_per_second": 1.209,
-      "step": 9
-    },
-    {
-      "epoch": 6.67,
-      "learning_rate": 2.777777777777778e-05,
-      "loss": 0.5024,
+      "epoch": 1.48,
+      "learning_rate": 1.992337164750958e-05,
+      "loss": 0.1558,
       "step": 10
     },
     {
-      "epoch": 7.0,
-      "eval_accuracy": 0.8620689655172413,
-      "eval_loss": 0.6531320810317993,
-      "eval_runtime": 0.7953,
-      "eval_samples_per_second": 36.466,
-      "eval_steps_per_second": 1.257,
-      "step": 11
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.8620689655172413,
-      "eval_loss": 0.6170477271080017,
-      "eval_runtime": 1.0429,
-      "eval_samples_per_second": 27.806,
-      "eval_steps_per_second": 0.959,
-      "step": 12
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.896551724137931,
-      "eval_loss": 0.5878463387489319,
-      "eval_runtime": 0.7888,
-      "eval_samples_per_second": 36.767,
-      "eval_steps_per_second": 1.268,
+      "epoch": 1.93,
+      "eval_accuracy": 0.9655172413793104,
+      "eval_f1": 0.964683592269799,
+      "eval_loss": 0.08155026286840439,
+      "eval_precision": 0.9674329501915708,
+      "eval_recall": 0.9655172413793104,
+      "eval_runtime": 0.7233,
+      "eval_samples_per_second": 40.093,
+      "eval_steps_per_second": 4.148,
       "step": 13
     },
     {
-      "epoch": 10.0,
-      "eval_accuracy": 0.8620689655172413,
-      "eval_loss": 0.5418170094490051,
-      "eval_runtime": 0.8158,
-      "eval_samples_per_second": 35.546,
-      "eval_steps_per_second": 1.226,
-      "step": 15
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.8620689655172413,
-      "eval_loss": 0.5121886730194092,
-      "eval_runtime": 0.8148,
-      "eval_samples_per_second": 35.592,
-      "eval_steps_per_second": 1.227,
-      "step": 17
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.8620689655172413,
-      "eval_loss": 0.5020919442176819,
-      "eval_runtime": 1.0894,
-      "eval_samples_per_second": 26.62,
-      "eval_steps_per_second": 0.918,
-      "step": 18
-    },
-    {
-      "epoch": 13.0,
-      "eval_accuracy": 0.8620689655172413,
-      "eval_loss": 0.4927540421485901,
-      "eval_runtime": 0.8053,
-      "eval_samples_per_second": 36.014,
-      "eval_steps_per_second": 1.242,
-      "step": 19
+      "epoch": 2.96,
+      "learning_rate": 1.9846743295019158e-05,
+      "loss": 0.1727,
+      "step": 20
     },
     {
-      "epoch": 13.33,
-      "learning_rate": 0.0,
-      "loss": 0.3117,
+      "epoch": 2.96,
+      "eval_accuracy": 0.9655172413793104,
+      "eval_f1": 0.964683592269799,
+      "eval_loss": 0.07752516865730286,
+      "eval_precision": 0.9674329501915708,
+      "eval_recall": 0.9655172413793104,
+      "eval_runtime": 0.9304,
+      "eval_samples_per_second": 31.17,
+      "eval_steps_per_second": 3.225,
       "step": 20
     },
     {
-      "epoch": 13.33,
-      "eval_accuracy": 0.8620689655172413,
-      "eval_loss": 0.4871620237827301,
-      "eval_runtime": 0.7941,
-      "eval_samples_per_second": 36.521,
-      "eval_steps_per_second": 1.259,
-      "step": 20
+      "epoch": 4.0,
+      "eval_accuracy": 0.9655172413793104,
+      "eval_f1": 0.964683592269799,
+      "eval_loss": 0.04428544268012047,
+      "eval_precision": 0.9674329501915708,
+      "eval_recall": 0.9655172413793104,
+      "eval_runtime": 0.7055,
+      "eval_samples_per_second": 41.107,
+      "eval_steps_per_second": 4.252,
+      "step": 27
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 1.9770114942528737e-05,
+      "loss": 0.1299,
+      "step": 30
+    },
+    {
+      "epoch": 4.89,
+      "eval_accuracy": 0.9655172413793104,
+      "eval_f1": 0.964683592269799,
+      "eval_loss": 0.053459376096725464,
+      "eval_precision": 0.9674329501915708,
+      "eval_recall": 0.9655172413793104,
+      "eval_runtime": 0.7107,
+      "eval_samples_per_second": 40.805,
+      "eval_steps_per_second": 4.221,
+      "step": 33
+    },
+    {
+      "epoch": 5.93,
+      "learning_rate": 1.9693486590038315e-05,
+      "loss": 0.1808,
+      "step": 40
+    },
+    {
+      "epoch": 5.93,
+      "eval_accuracy": 0.9655172413793104,
+      "eval_f1": 0.964683592269799,
+      "eval_loss": 0.029818205162882805,
+      "eval_precision": 0.9674329501915708,
+      "eval_recall": 0.9655172413793104,
+      "eval_runtime": 0.932,
+      "eval_samples_per_second": 31.115,
+      "eval_steps_per_second": 3.219,
+      "step": 40
+    },
+    {
+      "epoch": 6.96,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.019522428512573242,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 0.699,
+      "eval_samples_per_second": 41.486,
+      "eval_steps_per_second": 4.292,
+      "step": 47
+    },
+    {
+      "epoch": 7.41,
+      "learning_rate": 1.9616858237547893e-05,
+      "loss": 0.1406,
+      "step": 50
     },
     {
-      "epoch": 13.33,
-      "step": 20,
-      "total_flos": 8.7520382681131e+16,
-      "train_loss": 0.4070509672164917,
-      "train_runtime": 340.2477,
-      "train_samples_per_second": 15.342,
-      "train_steps_per_second": 0.059
+      "epoch": 8.0,
+      "eval_accuracy": 0.9655172413793104,
+      "eval_f1": 0.964683592269799,
+      "eval_loss": 0.05264897271990776,
+      "eval_precision": 0.9674329501915708,
+      "eval_recall": 0.9655172413793104,
+      "eval_runtime": 0.6927,
+      "eval_samples_per_second": 41.863,
+      "eval_steps_per_second": 4.331,
+      "step": 54
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 1.9540229885057475e-05,
+      "loss": 0.1193,
+      "step": 60
+    },
+    {
+      "epoch": 8.89,
+      "eval_accuracy": 0.9655172413793104,
+      "eval_f1": 0.964683592269799,
+      "eval_loss": 0.14525191485881805,
+      "eval_precision": 0.9674329501915708,
+      "eval_recall": 0.9655172413793104,
+      "eval_runtime": 0.9816,
+      "eval_samples_per_second": 29.543,
+      "eval_steps_per_second": 3.056,
+      "step": 60
+    },
+    {
+      "epoch": 8.89,
+      "step": 60,
+      "total_flos": 5.786635923932774e+16,
+      "train_loss": 0.14985284606615704,
+      "train_runtime": 220.5615,
+      "train_samples_per_second": 11.833,
+      "train_steps_per_second": 0.272
     }
   ],
-  "max_steps": 20,
-  "num_train_epochs": 20,
-  "total_flos": 8.7520382681131e+16,
+  "max_steps": 60,
+  "num_train_epochs": 10,
+  "total_flos": 5.786635923932774e+16,
   "trial_name": null,
   "trial_params": null
 }