End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6747468709945679,
+    "eval_matthews_correlation": 0.5956649094312695,
+    "eval_runtime": 10.7534,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 96.992,
+    "eval_steps_per_second": 12.182,
+    "train_loss": 0.31777251056421585,
+    "train_runtime": 860.3783,
+    "train_samples": 8551,
+    "train_samples_per_second": 29.816,
+    "train_steps_per_second": 1.865
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6747468709945679,
+    "eval_matthews_correlation": 0.5956649094312695,
+    "eval_runtime": 10.7534,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 96.992,
+    "eval_steps_per_second": 12.182
+}

runs/Sep16_18-47-00_patrick-general-gpu/events.out.tfevents.1631818036.patrick-general-gpu.195949.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c447af10216b49105989d4df5e3389964565ffe80b87aa63e1eddc7f19ce119
-size 4718
+oid sha256:c9fc7eb5b1138270bd5d18acbcb5002eaea759fdf30f5ababfd8560c2b98770c
+size 5072

runs/Sep16_18-47-00_patrick-general-gpu/events.out.tfevents.1631818916.patrick-general-gpu.195949.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276eb0da7ff9200cf723312841b212a3e00546cf8720229a8897ace088f81186
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.31777251056421585,
+    "train_runtime": 860.3783,
+    "train_samples": 8551,
+    "train_samples_per_second": 29.816,
+    "train_steps_per_second": 1.865
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1605,
+  "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": 0.4921,
+      "step": 535
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5283351540565491,
+      "eval_matthews_correlation": 0.5068375331988826,
+      "eval_runtime": 10.6748,
+      "eval_samples_per_second": 97.706,
+      "eval_steps_per_second": 12.272,
+      "step": 535
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.2837,
+      "step": 1070
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5132979154586792,
+      "eval_matthews_correlation": 0.5521390429003941,
+      "eval_runtime": 10.6848,
+      "eval_samples_per_second": 97.616,
+      "eval_steps_per_second": 12.26,
+      "step": 1070
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1775,
+      "step": 1605
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6747468709945679,
+      "eval_matthews_correlation": 0.5956649094312695,
+      "eval_runtime": 10.6837,
+      "eval_samples_per_second": 97.625,
+      "eval_steps_per_second": 12.262,
+      "step": 1605
+    },
+    {
+      "epoch": 3.0,
+      "step": 1605,
+      "total_flos": 6749587903150080.0,
+      "train_loss": 0.31777251056421585,
+      "train_runtime": 860.3783,
+      "train_samples_per_second": 29.816,
+      "train_steps_per_second": 1.865
+    }
+  ],
+  "max_steps": 1605,
+  "num_train_epochs": 3,
+  "total_flos": 6749587903150080.0,
+  "trial_name": null,
+  "trial_params": null
+}