End of training

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 5.0,
-    "eval_loss": 3.648160934448242,
-    "eval_runtime": 152.0262,
-    "eval_samples": 856,
-    "eval_samples_per_second": 5.631,
-    "eval_steps_per_second": 0.704,
+    "eval_loss": 3.558051109313965,
+    "eval_runtime": 13.048,
+    "eval_samples": 198,
+    "eval_samples_per_second": 15.175,
+    "eval_steps_per_second": 1.916,
     "eval_wer": 1.0,
-    "train_loss": 3.8949092686733353,
-    "train_runtime": 4254.8706,
-    "train_samples": 3420,
-    "train_samples_per_second": 4.019,
-    "train_steps_per_second": 0.126
+    "train_loss": 5.393351091657366,
+    "train_runtime": 232.952,
+    "train_samples": 221,
+    "train_samples_per_second": 4.743,
+    "train_steps_per_second": 1.202
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 5.0,
-    "eval_loss": 3.648160934448242,
-    "eval_runtime": 152.0262,
-    "eval_samples": 856,
-    "eval_samples_per_second": 5.631,
-    "eval_steps_per_second": 0.704,
+    "eval_loss": 3.558051109313965,
+    "eval_runtime": 13.048,
+    "eval_samples": 198,
+    "eval_samples_per_second": 15.175,
+    "eval_steps_per_second": 1.916,
     "eval_wer": 1.0
 }

runs/Jun19_14-50-47_bf13bc1f00ad/events.out.tfevents.1687186799.bf13bc1f00ad.6820.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb97e20f5258381c3ca659542eb803a96d149a894074ff1f1d8ed44df9476178
+size 406

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "train_loss": 3.8949092686733353,
-    "train_runtime": 4254.8706,
-    "train_samples": 3420,
-    "train_samples_per_second": 4.019,
-    "train_steps_per_second": 0.126
+    "train_loss": 5.393351091657366,
+    "train_runtime": 232.952,
+    "train_samples": 221,
+    "train_samples_per_second": 4.743,
+    "train_steps_per_second": 1.202
 }

trainer_state.json

@@ -2,75 +2,42 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 5.0,
-  "global_step": 535,
+  "global_step": 280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "eval_loss": 3.6305501461029053,
-      "eval_runtime": 149.517,
-      "eval_samples_per_second": 5.725,
-      "eval_steps_per_second": 0.716,
+      "epoch": 1.79,
+      "eval_loss": 3.634540557861328,
+      "eval_runtime": 13.2676,
+      "eval_samples_per_second": 14.924,
+      "eval_steps_per_second": 1.884,
       "eval_wer": 1.0,
-      "step": 107
+      "step": 100
     },
     {
-      "epoch": 2.0,
-      "eval_loss": 3.6398332118988037,
-      "eval_runtime": 149.6843,
-      "eval_samples_per_second": 5.719,
-      "eval_steps_per_second": 0.715,
+      "epoch": 3.57,
+      "eval_loss": 3.6708743572235107,
+      "eval_runtime": 14.3938,
+      "eval_samples_per_second": 13.756,
+      "eval_steps_per_second": 1.737,
       "eval_wer": 1.0,
-      "step": 214
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 3.6339974403381348,
-      "eval_runtime": 149.3998,
-      "eval_samples_per_second": 5.73,
-      "eval_steps_per_second": 0.716,
-      "eval_wer": 1.0,
-      "step": 321
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 3.6450517177581787,
-      "eval_runtime": 148.6995,
-      "eval_samples_per_second": 5.757,
-      "eval_steps_per_second": 0.72,
-      "eval_wer": 1.0,
-      "step": 428
-    },
-    {
-      "epoch": 4.67,
-      "learning_rate": 8.96551724137931e-05,
-      "loss": 3.9157,
-      "step": 500
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": 3.648160934448242,
-      "eval_runtime": 149.436,
-      "eval_samples_per_second": 5.728,
-      "eval_steps_per_second": 0.716,
-      "eval_wer": 1.0,
-      "step": 535
+      "step": 200
     },
     {
       "epoch": 5.0,
-      "step": 535,
-      "total_flos": 4.1064521881054213e+18,
-      "train_loss": 3.8949092686733353,
-      "train_runtime": 4254.8706,
-      "train_samples_per_second": 4.019,
-      "train_steps_per_second": 0.126
+      "step": 280,
+      "total_flos": 1.211109110220672e+17,
+      "train_loss": 5.393351091657366,
+      "train_runtime": 232.952,
+      "train_samples_per_second": 4.743,
+      "train_steps_per_second": 1.202
     }
   ],
-  "max_steps": 535,
+  "max_steps": 280,
   "num_train_epochs": 5,
-  "total_flos": 4.1064521881054213e+18,
+  "total_flos": 1.211109110220672e+17,
   "trial_name": null,
   "trial_params": null
 }