End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.920763373374939,
+    "eval_runtime": 80.7765,
+    "eval_samples": 5193,
+    "eval_samples_per_second": 64.289,
+    "eval_steps_per_second": 8.047,
+    "perplexity": 6.826167395302532,
+    "train_loss": 2.110191111022448,
+    "train_runtime": 17461.8774,
+    "train_samples": 98673,
+    "train_samples_per_second": 16.952,
+    "train_steps_per_second": 0.265
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.920763373374939,
+    "eval_runtime": 80.7765,
+    "eval_samples": 5193,
+    "eval_samples_per_second": 64.289,
+    "eval_steps_per_second": 8.047,
+    "perplexity": 6.826167395302532
+}

runs/Dec02_09-18-21_jbuhmann/events.out.tfevents.1638436734.jbuhmann.10393.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971cd8bbf212887153e69e194095bcd45c3e19685045aabb4f44bb86a3a4bdef
-size 5373
+oid sha256:5fd1b5f6464b04c4a0b1d452f1d6916402c5153a815ea3ffec6ff88c04a3b04b
+size 5727

runs/Dec02_09-18-21_jbuhmann/events.out.tfevents.1638454278.jbuhmann.10393.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0f8f06d50154896123e091f62b484cdc77edc22c7dd3d59b3d69495e40b089
+size 311

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.110191111022448,
+    "train_runtime": 17461.8774,
+    "train_samples": 98673,
+    "train_samples_per_second": 16.952,
+    "train_steps_per_second": 0.265
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 4626,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.7838305231301342e-05,
+      "loss": 2.2294,
+      "step": 500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.5676610462602683e-05,
+      "loss": 2.1683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.3514915693904023e-05,
+      "loss": 2.1713,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.009819507598877,
+      "eval_runtime": 81.3789,
+      "eval_samples_per_second": 63.813,
+      "eval_steps_per_second": 7.987,
+      "step": 1542
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.1353220925205362e-05,
+      "loss": 2.1142,
+      "step": 2000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.191526156506702e-06,
+      "loss": 2.0871,
+      "step": 2500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.029831387808041e-06,
+      "loss": 2.0736,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.9852919578552246,
+      "eval_runtime": 81.4601,
+      "eval_samples_per_second": 63.749,
+      "eval_steps_per_second": 7.979,
+      "step": 3084
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 4.8681366191093824e-06,
+      "loss": 2.0674,
+      "step": 3500
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.706441850410722e-06,
+      "loss": 2.0482,
+      "step": 4000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.447470817120623e-07,
+      "loss": 2.0543,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.013369083404541,
+      "eval_runtime": 81.3121,
+      "eval_samples_per_second": 63.865,
+      "eval_steps_per_second": 7.994,
+      "step": 4626
+    },
+    {
+      "epoch": 3.0,
+      "step": 4626,
+      "total_flos": 7.791321717294797e+16,
+      "train_loss": 2.110191111022448,
+      "train_runtime": 17461.8774,
+      "train_samples_per_second": 16.952,
+      "train_steps_per_second": 0.265
+    }
+  ],
+  "max_steps": 4626,
+  "num_train_epochs": 3,
+  "total_flos": 7.791321717294797e+16,
+  "trial_name": null,
+  "trial_params": null
+}