🍻 cheers

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.5,
+    "eval_loss": 0.977874755859375,
+    "eval_runtime": 0.7061,
+    "eval_samples_per_second": 14.162,
+    "eval_steps_per_second": 2.832,
+    "total_flos": 2.479765892825088e+16,
+    "train_loss": 0.2677663803100586,
+    "train_runtime": 23.2011,
+    "train_samples_per_second": 13.792,
+    "train_steps_per_second": 0.862
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.5,
+    "eval_loss": 0.977874755859375,
+    "eval_runtime": 0.7061,
+    "eval_samples_per_second": 14.162,
+    "eval_steps_per_second": 2.832
+}

runs/Jul17_18-52-36_7bd92b54aad6/events.out.tfevents.1689620073.7bd92b54aad6.189.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a081d3de5fb69959b8878abcbdd86a569b8f520d534fe25306e235f9c1274c2f
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 2.479765892825088e+16,
+    "train_loss": 0.2677663803100586,
+    "train_runtime": 23.2011,
+    "train_samples_per_second": 13.792,
+    "train_steps_per_second": 0.862
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001,
+      "loss": 0.3999,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.1356,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "step": 20,
+      "total_flos": 2.479765892825088e+16,
+      "train_loss": 0.2677663803100586,
+      "train_runtime": 23.2011,
+      "train_samples_per_second": 13.792,
+      "train_steps_per_second": 0.862
+    }
+  ],
+  "max_steps": 20,
+  "num_train_epochs": 4,
+  "total_flos": 2.479765892825088e+16,
+  "trial_name": null,
+  "trial_params": null
+}