End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.2106219083070755,
+    "eval_runtime": 6.8481,
+    "eval_samples": 99,
+    "eval_samples_per_second": 14.457,
+    "eval_steps_per_second": 0.584,
+    "eval_wer": 0.8585858585858586,
+    "train_loss": 1.5815124033636587,
+    "train_runtime": 17545.769,
+    "train_samples": 48997,
+    "train_samples_per_second": 13.963,
+    "train_steps_per_second": 0.109
+}

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 5.0,
-    "eval_loss": 0.23142604529857635,
-    "eval_runtime": 3.4384,
-    "eval_samples": 100,
-    "eval_samples_per_second": 29.083,
-    "eval_steps_per_second": 1.163,
-    "eval_wer": 0.64
+    "eval_loss": 0.2106219083070755,
+    "eval_runtime": 6.8481,
+    "eval_samples": 99,
+    "eval_samples_per_second": 14.457,
+    "eval_steps_per_second": 0.584,
+    "eval_wer": 0.8585858585858586
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d3bcf0e6d452dc75e1431acc832f9cb297aa692db17a7a039bde02a0c603c3
+oid sha256:e0bb6f93e9d8b335cbc2ce6b3981f13f2061d7f1378d897fa37f285780bc6f80
 size 1262104049

runs/Jan27_08-47-37_job-05b2a883-27c6-492e-87b7-30be04252f5c/events.out.tfevents.1643276165.job-05b2a883-27c6-492e-87b7-30be04252f5c.3432238.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0bac00a6ff9e3e1679515b1ee7e78f93bbe9d52dabb061fbfdb9ab4c8e5e0eb
-size 5391
+oid sha256:75e8ed02940b1f34dd22ecc975cfcf27515e44fdff20f682b92b07208cac3f6b
+size 5745

runs/Jan27_08-47-37_job-05b2a883-27c6-492e-87b7-30be04252f5c/events.out.tfevents.1643293720.job-05b2a883-27c6-492e-87b7-30be04252f5c.3432238.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d04224cb03cc0a4aa4754efb683b32413de168a1ea82f41e92fe20710393e357
+size 358

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 1.5815124033636587,
+    "train_runtime": 17545.769,
+    "train_samples": 48997,
+    "train_samples_per_second": 13.963,
+    "train_steps_per_second": 0.109
+}

trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 1915,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.000995,
+      "loss": 2.1093,
+      "step": 1000
+    },
+    {
+      "epoch": 2.61,
+      "eval_loss": 0.257192462682724,
+      "eval_runtime": 6.7241,
+      "eval_samples_per_second": 14.723,
+      "eval_steps_per_second": 0.595,
+      "eval_wer": 0.9292929292929293,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "step": 1915,
+      "total_flos": 4.985190246992067e+19,
+      "train_loss": 1.5815124033636587,
+      "train_runtime": 17545.769,
+      "train_samples_per_second": 13.963,
+      "train_steps_per_second": 0.109
+    }
+  ],
+  "max_steps": 1915,
+  "num_train_epochs": 5,
+  "total_flos": 4.985190246992067e+19,
+  "trial_name": null,
+  "trial_params": null
+}