End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.8787857294082642,
+    "eval_loss": 0.32322901487350464,
+    "eval_runtime": 17.6635,
+    "eval_samples": 14000,
+    "eval_samples_per_second": 792.596,
+    "eval_steps_per_second": 12.398,
+    "train_loss": 0.268575707836264,
+    "train_runtime": 1091.6903,
+    "train_samples": 345807,
+    "train_samples_per_second": 633.526,
+    "train_steps_per_second": 1.238
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.8787857294082642,
+    "eval_loss": 0.32322901487350464,
+    "eval_runtime": 17.6635,
+    "eval_samples": 14000,
+    "eval_samples_per_second": 792.596,
+    "eval_steps_per_second": 12.398
+}

runs/Oct20_14-31-37_2aa348391f22/events.out.tfevents.1634740494.2aa348391f22.3056.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ded09fc34738ba761f8131c2430c2a6e148746add7cfe9cc203851cb14243c
-size 4236
+oid sha256:216f0d932c5b77a928b7e897cfef5dcb448c9245e5da5cdc111b1ffde24540f2
+size 4590

runs/Oct20_14-31-37_2aa348391f22/events.out.tfevents.1634741614.2aa348391f22.3056.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e07284cdc4a6266cd747df3c8b39146d516a85410f4e7dfd3236a6dea2efd2
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.268575707836264,
+    "train_runtime": 1091.6903,
+    "train_samples": 345807,
+    "train_samples_per_second": 633.526,
+    "train_steps_per_second": 1.238
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 1352,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.2603550295857989e-05,
+      "loss": 0.3604,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8746428489685059,
+      "eval_loss": 0.3286072015762329,
+      "eval_runtime": 25.372,
+      "eval_samples_per_second": 551.79,
+      "eval_steps_per_second": 8.632,
+      "step": 676
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 5.207100591715976e-06,
+      "loss": 0.2243,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8787857294082642,
+      "eval_loss": 0.32322901487350464,
+      "eval_runtime": 18.0969,
+      "eval_samples_per_second": 773.613,
+      "eval_steps_per_second": 12.102,
+      "step": 1352
+    },
+    {
+      "epoch": 2.0,
+      "step": 1352,
+      "total_flos": 5691618349547520.0,
+      "train_loss": 0.268575707836264,
+      "train_runtime": 1091.6903,
+      "train_samples_per_second": 633.526,
+      "train_steps_per_second": 1.238
+    }
+  ],
+  "max_steps": 1352,
+  "num_train_epochs": 2,
+  "total_flos": 5691618349547520.0,
+  "trial_name": null,
+  "trial_params": null
+}