End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.624345064163208,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 22.8358,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 45.674,
+    "eval_steps_per_second": 5.737,
+    "train_loss": 0.6174308222552717,
+    "train_runtime": 2113.9292,
+    "train_samples": 8551,
+    "train_samples_per_second": 12.135,
+    "train_steps_per_second": 3.034
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.624345064163208,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 22.8358,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 45.674,
+    "eval_steps_per_second": 5.737
+}

runs/Oct10_04-22-52_patrick-general-gpu/events.out.tfevents.1633840393.patrick-general-gpu.74835.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e66e66a8b5374cc1f5b3122c19301723d6a6da6be3d181641347104b5c4689c
-size 4745
+oid sha256:c9350a023f8ff61db5c9baab7ccb38efe93926d044cd91c270dab26ced0f26a2
+size 5099

runs/Oct10_04-22-52_patrick-general-gpu/events.out.tfevents.1633842549.patrick-general-gpu.74835.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31372d78b0f769dedca80b2a907147c37938e9d98143b96c90fbc13a8983dbbc
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.6174308222552717,
+    "train_runtime": 2113.9292,
+    "train_samples": 8551,
+    "train_samples_per_second": 12.135,
+    "train_steps_per_second": 3.034
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6414,
+  "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": 0.6195,
+      "step": 2138
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6526795029640198,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.8335,
+      "eval_samples_per_second": 45.678,
+      "eval_steps_per_second": 5.737,
+      "step": 2138
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6168,
+      "step": 4276
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6258916258811951,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7299,
+      "eval_samples_per_second": 45.887,
+      "eval_steps_per_second": 5.763,
+      "step": 4276
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.616,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.624345064163208,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7295,
+      "eval_samples_per_second": 45.888,
+      "eval_steps_per_second": 5.763,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0,
+      "step": 6414,
+      "total_flos": 1.6048929796061184e+16,
+      "train_loss": 0.6174308222552717,
+      "train_runtime": 2113.9292,
+      "train_samples_per_second": 12.135,
+      "train_steps_per_second": 3.034
+    }
+  ],
+  "max_steps": 6414,
+  "num_train_epochs": 3,
+  "total_flos": 1.6048929796061184e+16,
+  "trial_name": null,
+  "trial_params": null
+}