End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9099395936298736,
+    "eval_loss": 0.39857929944992065,
+    "eval_runtime": 56.1502,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 97.293,
+    "eval_steps_per_second": 12.164,
+    "train_loss": 0.21717328177007758,
+    "train_runtime": 9622.4325,
+    "train_samples": 104743,
+    "train_samples_per_second": 32.656,
+    "train_steps_per_second": 2.041
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9099395936298736,
+    "eval_loss": 0.39857929944992065,
+    "eval_runtime": 56.1502,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 97.293,
+    "eval_steps_per_second": 12.164
+}

runs/Sep17_14-24-47_patrick-general-gpu/events.out.tfevents.1631888732.patrick-general-gpu.282818.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15eb957929d8687b25f1324428b52c655e937ef578c121fb8577a82b83b344c9
-size 4695
+oid sha256:2fb7a66b82165962b6b3b874a7e78ffad641c2a7c3a0513a98596dba28a7a04d
+size 5055

runs/Sep17_14-24-47_patrick-general-gpu/events.out.tfevents.1631898419.patrick-general-gpu.282818.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58208204412082970299db6181aaa14ffad439e7a1414399089bddfc7d7d19f0
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.21717328177007758,
+    "train_runtime": 9622.4325,
+    "train_samples": 104743,
+    "train_samples_per_second": 32.656,
+    "train_steps_per_second": 2.041
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 19641,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.337,
+      "step": 6547
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9013362621270364,
+      "eval_loss": 0.24480287730693817,
+      "eval_runtime": 55.721,
+      "eval_samples_per_second": 98.042,
+      "eval_steps_per_second": 12.258,
+      "step": 6547
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1971,
+      "step": 13094
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.914332784184514,
+      "eval_loss": 0.28385764360427856,
+      "eval_runtime": 55.6845,
+      "eval_samples_per_second": 98.106,
+      "eval_steps_per_second": 12.266,
+      "step": 13094
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1175,
+      "step": 19641
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9099395936298736,
+      "eval_loss": 0.39857929944992065,
+      "eval_runtime": 55.8016,
+      "eval_samples_per_second": 97.9,
+      "eval_steps_per_second": 12.24,
+      "step": 19641
+    },
+    {
+      "epoch": 3.0,
+      "step": 19641,
+      "total_flos": 8.267712381471744e+16,
+      "train_loss": 0.21717328177007758,
+      "train_runtime": 9622.4325,
+      "train_samples_per_second": 32.656,
+      "train_steps_per_second": 2.041
+    }
+  ],
+  "max_steps": 19641,
+  "num_train_epochs": 3,
+  "total_flos": 8.267712381471744e+16,
+  "trial_name": null,
+  "trial_params": null
+}