End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7674938974776241,
+    "eval_loss": 0.6443182229995728,
+    "eval_runtime": 71.2392,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 138.014,
+    "eval_steps_per_second": 17.252,
+    "train_loss": 0.5575872004317077,
+    "train_runtime": 24054.786,
+    "train_samples": 392702,
+    "train_samples_per_second": 48.976,
+    "train_steps_per_second": 3.061
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7674938974776241,
+    "eval_loss": 0.6443182229995728,
+    "eval_runtime": 71.2392,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 138.014,
+    "eval_steps_per_second": 17.252
+}

runs/Sep17_07-10-01_patrick-general-gpu/events.out.tfevents.1631862669.patrick-general-gpu.234538.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3871425bb15e7db46c7147304c2c5cd013aee069a74aa20784346ab0e17185db
-size 4687
+oid sha256:37a793684abf6ecf70fdd5d1a80578fe36d6641dbdb812ad3fe37d9aaa5683e6
+size 5047

runs/Sep17_07-10-01_patrick-general-gpu/events.out.tfevents.1631886799.patrick-general-gpu.234538.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ab1fd20f96662ded228db6fd5690e71fa29fb0baae51532890e781a8c44c2b
+size 698

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.5575872004317077,
+    "train_runtime": 24054.786,
+    "train_samples": 392702,
+    "train_samples_per_second": 48.976,
+    "train_steps_per_second": 3.061
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 73632,
+  "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": 0.7143,
+      "step": 24544
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7503820682628629,
+      "eval_loss": 0.6168540120124817,
+      "eval_runtime": 71.4698,
+      "eval_samples_per_second": 137.331,
+      "eval_steps_per_second": 17.168,
+      "step": 24544
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5407,
+      "step": 49088
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7627101375445746,
+      "eval_loss": 0.6218484044075012,
+      "eval_runtime": 71.2675,
+      "eval_samples_per_second": 137.72,
+      "eval_steps_per_second": 17.217,
+      "step": 49088
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.4178,
+      "step": 73632
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7657666836474784,
+      "eval_loss": 0.6564478278160095,
+      "eval_runtime": 71.6262,
+      "eval_samples_per_second": 137.031,
+      "eval_steps_per_second": 17.131,
+      "step": 73632
+    },
+    {
+      "epoch": 3.0,
+      "step": 73632,
+      "total_flos": 2.095159996537344e+17,
+      "train_loss": 0.5575872004317077,
+      "train_runtime": 24054.786,
+      "train_samples_per_second": 48.976,
+      "train_steps_per_second": 3.061
+    }
+  ],
+  "max_steps": 73632,
+  "num_train_epochs": 3,
+  "total_flos": 2.095159996537344e+17,
+  "trial_name": null,
+  "trial_params": null
+}