🍻 cheers

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.8985,
+    "eval_loss": 0.4420098662376404,
+    "eval_runtime": 101.557,
+    "eval_samples_per_second": 98.467,
+    "eval_steps_per_second": 12.308,
+    "total_flos": 1.55120108322816e+19,
+    "train_loss": 0.41695240966796876,
+    "train_runtime": 5380.0705,
+    "train_samples_per_second": 37.174,
+    "train_steps_per_second": 2.323
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.8985,
+    "eval_loss": 0.4420098662376404,
+    "eval_runtime": 101.557,
+    "eval_samples_per_second": 98.467,
+    "eval_steps_per_second": 12.308
+}

runs/May18_23-36-34_12b95d1959eb/events.out.tfevents.1652922962.12b95d1959eb.80.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044cf088baf5800f91124434264f543418e3c43ab118ea10cfe370fa6ec4ddee
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 1.55120108322816e+19,
+    "train_loss": 0.41695240966796876,
+    "train_runtime": 5380.0705,
+    "train_samples_per_second": 37.174,
+    "train_steps_per_second": 2.323
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 12500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.000150048,
+      "loss": 1.08,
+      "step": 3125
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8262,
+      "eval_loss": 0.6196413040161133,
+      "eval_runtime": 100.3985,
+      "eval_samples_per_second": 99.603,
+      "eval_steps_per_second": 12.45,
+      "step": 3125
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.000100048,
+      "loss": 0.3816,
+      "step": 6250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8555,
+      "eval_loss": 0.5322445034980774,
+      "eval_runtime": 99.8169,
+      "eval_samples_per_second": 100.183,
+      "eval_steps_per_second": 12.523,
+      "step": 6250
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.0064e-05,
+      "loss": 0.1619,
+      "step": 9375
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8765,
+      "eval_loss": 0.4817411005496979,
+      "eval_runtime": 100.5682,
+      "eval_samples_per_second": 99.435,
+      "eval_steps_per_second": 12.429,
+      "step": 9375
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.600000000000001e-08,
+      "loss": 0.0443,
+      "step": 12500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8985,
+      "eval_loss": 0.4420098662376404,
+      "eval_runtime": 101.737,
+      "eval_samples_per_second": 98.293,
+      "eval_steps_per_second": 12.287,
+      "step": 12500
+    },
+    {
+      "epoch": 4.0,
+      "step": 12500,
+      "total_flos": 1.55120108322816e+19,
+      "train_loss": 0.41695240966796876,
+      "train_runtime": 5380.0705,
+      "train_samples_per_second": 37.174,
+      "train_steps_per_second": 2.323
+    }
+  ],
+  "max_steps": 12500,
+  "num_train_epochs": 4,
+  "total_flos": 1.55120108322816e+19,
+  "trial_name": null,
+  "trial_params": null
+}