End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 666.67,
+    "eval_loss": 3.8433420658111572,
+    "eval_runtime": 5.4398,
+    "eval_samples": 142,
+    "eval_samples_per_second": 26.104,
+    "eval_steps_per_second": 3.309,
+    "eval_wer": 0.985178727114211,
+    "train_loss": 0.3888468391895294,
+    "train_runtime": 14986.9731,
+    "train_samples": 378,
+    "train_samples_per_second": 17.082,
+    "train_steps_per_second": 0.133
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 666.67,
+    "eval_loss": 3.8433420658111572,
+    "eval_runtime": 5.4398,
+    "eval_samples": 142,
+    "eval_samples_per_second": 26.104,
+    "eval_steps_per_second": 3.309,
+    "eval_wer": 0.985178727114211
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a45d2822bb91bb974d2b31bca68deb636d59da4ce6e50856a6d192d1bccd6f
+oid sha256:c682e1bb0700134f686d26b075c5572f761a09b187c8e8a9acacbbba67037762
 size 1262149169

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 666.67,
+    "train_loss": 0.3888468391895294,
+    "train_runtime": 14986.9731,
+    "train_samples": 378,
+    "train_samples_per_second": 17.082,
+    "train_steps_per_second": 0.133
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 666.6666666666666,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 166.67,
+      "learning_rate": 0.00022529999999999997,
+      "loss": 1.468,
+      "step": 500
+    },
+    {
+      "epoch": 166.67,
+      "eval_loss": 3.02618145942688,
+      "eval_runtime": 5.3514,
+      "eval_samples_per_second": 26.535,
+      "eval_steps_per_second": 3.364,
+      "eval_wer": 1.003487358326068,
+      "step": 500
+    },
+    {
+      "epoch": 333.33,
+      "learning_rate": 0.0001503,
+      "loss": 0.0572,
+      "step": 1000
+    },
+    {
+      "epoch": 333.33,
+      "eval_loss": 3.535200834274292,
+      "eval_runtime": 5.4028,
+      "eval_samples_per_second": 26.283,
+      "eval_steps_per_second": 3.332,
+      "eval_wer": 0.972101133391456,
+      "step": 1000
+    },
+    {
+      "epoch": 500.0,
+      "learning_rate": 7.529999999999999e-05,
+      "loss": 0.0209,
+      "step": 1500
+    },
+    {
+      "epoch": 500.0,
+      "eval_loss": 3.726599931716919,
+      "eval_runtime": 5.4408,
+      "eval_samples_per_second": 26.099,
+      "eval_steps_per_second": 3.308,
+      "eval_wer": 0.983435047951177,
+      "step": 1500
+    },
+    {
+      "epoch": 666.67,
+      "learning_rate": 3e-07,
+      "loss": 0.0092,
+      "step": 2000
+    },
+    {
+      "epoch": 666.67,
+      "eval_loss": 3.8433420658111572,
+      "eval_runtime": 5.3563,
+      "eval_samples_per_second": 26.511,
+      "eval_steps_per_second": 3.361,
+      "eval_wer": 0.985178727114211,
+      "step": 2000
+    },
+    {
+      "epoch": 666.67,
+      "step": 2000,
+      "total_flos": 5.0698303474476155e+19,
+      "train_loss": 0.3888468391895294,
+      "train_runtime": 14986.9731,
+      "train_samples_per_second": 17.082,
+      "train_steps_per_second": 0.133
+    }
+  ],
+  "max_steps": 2000,
+  "num_train_epochs": 667,
+  "total_flos": 5.0698303474476155e+19,
+  "trial_name": null,
+  "trial_params": null
+}