End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5272296667098999,
+    "eval_loss": 2.5027120113372803,
+    "eval_runtime": 10.4382,
+    "eval_samples": 1267,
+    "eval_samples_per_second": 121.381,
+    "eval_steps_per_second": 15.233,
+    "train_loss": 3.3223501191044313,
+    "train_runtime": 1362.0086,
+    "train_samples": 11651,
+    "train_samples_per_second": 25.663,
+    "train_steps_per_second": 3.209
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5272296667098999,
+    "eval_loss": 2.5027120113372803,
+    "eval_runtime": 10.4382,
+    "eval_samples": 1267,
+    "eval_samples_per_second": 121.381,
+    "eval_steps_per_second": 15.233
+}

runs/Nov18_16-55-04_6e58f70dbfc6/events.out.tfevents.1637254517.6e58f70dbfc6.2587.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f4e5c023fe135d12510a366c1edffc8fe640846d0a994627cb4f9e15ce90a4
-size 18571
+oid sha256:224985513a347c7567601114a216c2da368ea63487944a2965186cc33feea365
+size 18925

runs/Nov18_16-55-04_6e58f70dbfc6/events.out.tfevents.1637255897.6e58f70dbfc6.2587.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efcae39b34d7ee9cdcb9c653a0b30fccf2a473685555e6a02374ded29013d87
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.3223501191044313,
+    "train_runtime": 1362.0086,
+    "train_samples": 11651,
+    "train_samples_per_second": 25.663,
+    "train_steps_per_second": 3.209
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 4371,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "learning_rate": 8.85609700297415e-06,
+      "loss": 4.762,
+      "step": 500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.712194005948296e-06,
+      "loss": 4.203,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.39857932925224304,
+      "eval_loss": 3.2222137451171875,
+      "eval_runtime": 10.1814,
+      "eval_samples_per_second": 124.442,
+      "eval_steps_per_second": 15.617,
+      "step": 1457
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 6.568291008922444e-06,
+      "loss": 3.7248,
+      "step": 1500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 5.424388011896592e-06,
+      "loss": 3.3024,
+      "step": 2000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 4.28048501487074e-06,
+      "loss": 3.0923,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5051302313804626,
+      "eval_loss": 2.6549134254455566,
+      "eval_runtime": 10.1792,
+      "eval_samples_per_second": 124.469,
+      "eval_steps_per_second": 15.62,
+      "step": 2914
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 3.136582017844887e-06,
+      "loss": 2.8691,
+      "step": 3000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.992679020819035e-06,
+      "loss": 2.6311,
+      "step": 3500
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 8.487760237931825e-07,
+      "loss": 2.5685,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5272296667098999,
+      "eval_loss": 2.5027120113372803,
+      "eval_runtime": 10.1656,
+      "eval_samples_per_second": 124.635,
+      "eval_steps_per_second": 15.641,
+      "step": 4371
+    },
+    {
+      "epoch": 3.0,
+      "step": 4371,
+      "total_flos": 1151412634864512.0,
+      "train_loss": 3.3223501191044313,
+      "train_runtime": 1362.0086,
+      "train_samples_per_second": 25.663,
+      "train_steps_per_second": 3.209
+    }
+  ],
+  "max_steps": 4371,
+  "num_train_epochs": 3,
+  "total_flos": 1151412634864512.0,
+  "trial_name": null,
+  "trial_params": null
+}