End of training

all_results.json

@@ -1,7 +1,12 @@
 {
-    "epoch": 0.97,
-    "train_loss": 0.4665303599834442,
-    "train_runtime": 6285.9399,
-    "train_samples_per_second": 1.018,
-    "train_steps_per_second": 0.032
+    "epoch": 1.45,
+    "eval_loss": 0.46850404143333435,
+    "eval_runtime": 2554.9052,
+    "eval_samples_per_second": 1.292,
+    "eval_steps_per_second": 0.081,
+    "eval_wer": 26.980130911344357,
+    "train_loss": 0.08693385044733683,
+    "train_runtime": 3481.8761,
+    "train_samples_per_second": 2.757,
+    "train_steps_per_second": 0.086
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.45,
+    "eval_loss": 0.46850404143333435,
+    "eval_runtime": 2554.9052,
+    "eval_samples_per_second": 1.292,
+    "eval_steps_per_second": 0.081,
+    "eval_wer": 26.980130911344357
+}

runs/Dec11_14-58-14_150-136-41-252/events.out.tfevents.1670777055.150-136-41-252.369844.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c821bdf4fc61a8c11243fa75bd5c3fb6af8cfd4899b9a8d23d8f3f8cfcd9e3b
+size 358

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 0.97,
-    "train_loss": 0.4665303599834442,
-    "train_runtime": 6285.9399,
-    "train_samples_per_second": 1.018,
-    "train_steps_per_second": 0.032
+    "epoch": 1.45,
+    "train_loss": 0.08693385044733683,
+    "train_runtime": 3481.8761,
+    "train_samples_per_second": 2.757,
+    "train_steps_per_second": 0.086
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 26.980130911344357,
   "best_model_checkpoint": "./checkpoint-200",
-  "epoch": 0.966183574879227,
-  "global_step": 200,
+  "epoch": 1.4492753623188406,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -146,18 +146,87 @@
       "step": 200
     },
     {
-      "epoch": 0.97,
-      "step": 200,
-      "total_flos": 6.531871408128e+18,
-      "train_loss": 0.4665303599834442,
-      "train_runtime": 6285.9399,
-      "train_samples_per_second": 1.018,
-      "train_steps_per_second": 0.032
+      "epoch": 1.01,
+      "learning_rate": 3.538461538461539e-06,
+      "loss": 0.3721,
+      "step": 210
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.153846153846154e-06,
+      "loss": 0.2392,
+      "step": 220
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.7692307692307697e-06,
+      "loss": 0.2854,
+      "step": 230
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.384615384615385e-06,
+      "loss": 0.2517,
+      "step": 240
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.2506,
+      "step": 250
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.6153846153846157e-06,
+      "loss": 0.2462,
+      "step": 260
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.230769230769231e-06,
+      "loss": 0.2179,
+      "step": 270
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 8.461538461538463e-07,
+      "loss": 0.2579,
+      "step": 280
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.615384615384616e-07,
+      "loss": 0.2446,
+      "step": 290
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 7.692307692307694e-08,
+      "loss": 0.2426,
+      "step": 300
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.4635893404483795,
+      "eval_runtime": 2857.1857,
+      "eval_samples_per_second": 1.156,
+      "eval_steps_per_second": 0.072,
+      "eval_wer": 28.502265773267748,
+      "step": 300
+    },
+    {
+      "epoch": 1.45,
+      "step": 300,
+      "total_flos": 9.77943622385664e+18,
+      "train_loss": 0.08693385044733683,
+      "train_runtime": 3481.8761,
+      "train_samples_per_second": 2.757,
+      "train_steps_per_second": 0.086
     }
   ],
-  "max_steps": 200,
-  "num_train_epochs": 1,
-  "total_flos": 6.531871408128e+18,
+  "max_steps": 300,
+  "num_train_epochs": 2,
+  "total_flos": 9.77943622385664e+18,
   "trial_name": null,
   "trial_params": null
 }