End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9231651376146789,
+    "eval_loss": 0.36485353112220764,
+    "eval_runtime": 8.9446,
+    "eval_samples": 872,
+    "eval_samples_per_second": 97.489,
+    "eval_steps_per_second": 12.186,
+    "train_loss": 0.14529220810600998,
+    "train_runtime": 6136.5168,
+    "train_samples": 67349,
+    "train_samples_per_second": 32.925,
+    "train_steps_per_second": 2.058
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9231651376146789,
+    "eval_loss": 0.36485353112220764,
+    "eval_runtime": 8.9446,
+    "eval_samples": 872,
+    "eval_samples_per_second": 97.489,
+    "eval_steps_per_second": 12.186
+}

runs/Sep19_05-56-28_patrick-general-gpu/events.out.tfevents.1632031020.patrick-general-gpu.459415.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a701d8a2d7493a3c991a2cc95f5a5792ce7192794bf18bfb3eefbe52ec24aee8
-size 4670
+oid sha256:2bba44f4a64c2e9892d086917a712f4edb27766f272e53cdf2ac4bad44af7280
+size 5024

runs/Sep19_05-56-28_patrick-general-gpu/events.out.tfevents.1632037174.patrick-general-gpu.459415.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b5fcef719d6da57bc3f653d00169dd6bc19e9725dbbd8d0874d3168a38f63b
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.14529220810600998,
+    "train_runtime": 6136.5168,
+    "train_samples": 67349,
+    "train_samples_per_second": 32.925,
+    "train_steps_per_second": 2.058
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 12630,
+  "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": 0.233,
+      "step": 4210
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9174311926605505,
+      "eval_loss": 0.28414297103881836,
+      "eval_runtime": 8.9563,
+      "eval_samples_per_second": 97.362,
+      "eval_steps_per_second": 12.17,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1261,
+      "step": 8420
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9277522935779816,
+      "eval_loss": 0.3310103714466095,
+      "eval_runtime": 8.9528,
+      "eval_samples_per_second": 97.399,
+      "eval_steps_per_second": 12.175,
+      "step": 8420
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0768,
+      "step": 12630
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9231651376146789,
+      "eval_loss": 0.36485353112220764,
+      "eval_runtime": 8.9701,
+      "eval_samples_per_second": 97.212,
+      "eval_steps_per_second": 12.152,
+      "step": 12630
+    },
+    {
+      "epoch": 3.0,
+      "step": 12630,
+      "total_flos": 5.316079940232192e+16,
+      "train_loss": 0.14529220810600998,
+      "train_runtime": 6136.5168,
+      "train_samples_per_second": 32.925,
+      "train_steps_per_second": 2.058
+    }
+  ],
+  "max_steps": 12630,
+  "num_train_epochs": 3,
+  "total_flos": 5.316079940232192e+16,
+  "trial_name": null,
+  "trial_params": null
+}