End of training

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 1.0,
     "eval_loss": 0.27755075693130493,
-    "eval_runtime": 384.9632,
+    "eval_runtime": 385.5995,
     "eval_samples_per_second": 0.418,
     "eval_steps_per_second": 0.07,
     "eval_wer": 12.51522533495737,
-    "train_loss": 0.6583859201431275,
-    "train_runtime": 31239.5975,
-    "train_samples_per_second": 1.921,
-    "train_steps_per_second": 0.16
+    "train_loss": 0.00010507909137471822,
+    "train_runtime": 167.7323,
+    "train_samples_per_second": 357.713,
+    "train_steps_per_second": 29.809
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 1.0,
     "eval_loss": 0.27755075693130493,
-    "eval_runtime": 384.9632,
+    "eval_runtime": 385.5995,
     "eval_samples_per_second": 0.418,
     "eval_steps_per_second": 0.07,
     "eval_wer": 12.51522533495737

runs/Dec10_21-10-13_dante/events.out.tfevents.1670703878.dante.3904631.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd8ce3059c2b75f54be418a4e22c49836ae752e23b2eb07db72e304fbd3626e
+size 358

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.6583859201431275,
-    "train_runtime": 31239.5975,
-    "train_samples_per_second": 1.921,
-    "train_steps_per_second": 0.16
+    "train_loss": 0.00010507909137471822,
+    "train_runtime": 167.7323,
+    "train_samples_per_second": 357.713,
+    "train_steps_per_second": 29.809
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 12.51522533495737,
   "best_model_checkpoint": "./checkpoint-5000",
-  "epoch": 1.0,
-  "global_step": 5000,
+  "epoch": 1.0002,
+  "global_step": 5001,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1254,17 +1254,17 @@
     },
     {
       "epoch": 1.0,
-      "step": 5000,
-      "total_flos": 1.2739025557174354e+20,
-      "train_loss": 0.6583859201431275,
-      "train_runtime": 31239.5975,
-      "train_samples_per_second": 1.921,
-      "train_steps_per_second": 0.16
+      "step": 5001,
+      "total_flos": 1.2741573362483357e+20,
+      "train_loss": 0.00010507909137471822,
+      "train_runtime": 167.7323,
+      "train_samples_per_second": 357.713,
+      "train_steps_per_second": 29.809
     }
   ],
   "max_steps": 5000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 1.2739025557174354e+20,
+  "total_flos": 1.2741573362483357e+20,
   "trial_name": null,
   "trial_params": null
 }