End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 12.0,
+    "eval_loss": 1.9043171405792236,
+    "eval_runtime": 45.4284,
+    "eval_samples": 2933,
+    "eval_samples_per_second": 64.563,
+    "eval_steps_per_second": 8.079,
+    "perplexity": 6.714820783097618,
+    "train_loss": 1.903703066931344,
+    "train_runtime": 39626.2902,
+    "train_samples": 55736,
+    "train_samples_per_second": 16.878,
+    "train_steps_per_second": 0.264
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "eval_loss": 1.9043171405792236,
+    "eval_runtime": 45.4284,
+    "eval_samples": 2933,
+    "eval_samples_per_second": 64.563,
+    "eval_steps_per_second": 8.079,
+    "perplexity": 6.714820783097618
+}

runs/Dec13_11-03-21_jbuhmann/events.out.tfevents.1639393423.jbuhmann.20274.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c84c2cc4ee6659285e90560454f02d480345871e84081cc6f8428e39a26c4b59
-size 9569
+oid sha256:ef639afd4786d4340a36697fabd41518587a234295eb560172d497454c545fc2
+size 9923

runs/Dec13_11-03-21_jbuhmann/events.out.tfevents.1639433096.jbuhmann.20274.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2517466df1d030f822b7395b1ea5ceb51951b94c740b7e772f3a0408c463d8bb
+size 311

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 12.0,
+    "train_loss": 1.903703066931344,
+    "train_runtime": 39626.2902,
+    "train_samples": 55736,
+    "train_samples_per_second": 16.878,
+    "train_steps_per_second": 0.264
+}

trainer_state.json

@@ -0,0 +1,241 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "global_step": 10452,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.760811327975507e-05,
+      "loss": 2.2439,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.110177516937256,
+      "eval_runtime": 45.9444,
+      "eval_samples_per_second": 63.838,
+      "eval_steps_per_second": 7.988,
+      "step": 871
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 4.521622655951014e-05,
+      "loss": 2.1937,
+      "step": 1000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 4.282433983926522e-05,
+      "loss": 2.1235,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.0784690380096436,
+      "eval_runtime": 45.8173,
+      "eval_samples_per_second": 64.015,
+      "eval_steps_per_second": 8.01,
+      "step": 1742
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 4.043245311902029e-05,
+      "loss": 2.0744,
+      "step": 2000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 3.8040566398775356e-05,
+      "loss": 2.0709,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.068932056427002,
+      "eval_runtime": 45.8943,
+      "eval_samples_per_second": 63.908,
+      "eval_steps_per_second": 7.997,
+      "step": 2613
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 3.5648679678530425e-05,
+      "loss": 2.0033,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.056485891342163,
+      "eval_runtime": 45.834,
+      "eval_samples_per_second": 63.992,
+      "eval_steps_per_second": 8.007,
+      "step": 3484
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 3.32567929582855e-05,
+      "loss": 1.9855,
+      "step": 3500
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 3.086490623804057e-05,
+      "loss": 1.9386,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.0290322303771973,
+      "eval_runtime": 45.9319,
+      "eval_samples_per_second": 63.855,
+      "eval_steps_per_second": 7.99,
+      "step": 4355
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 2.847301951779564e-05,
+      "loss": 1.9207,
+      "step": 4500
+    },
+    {
+      "epoch": 5.74,
+      "learning_rate": 2.608113279755071e-05,
+      "loss": 1.8909,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.036613702774048,
+      "eval_runtime": 45.9715,
+      "eval_samples_per_second": 63.8,
+      "eval_steps_per_second": 7.983,
+      "step": 5226
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 2.368924607730578e-05,
+      "loss": 1.8682,
+      "step": 5500
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 2.1297359357060852e-05,
+      "loss": 1.8449,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.980948567390442,
+      "eval_runtime": 45.9924,
+      "eval_samples_per_second": 63.771,
+      "eval_steps_per_second": 7.98,
+      "step": 6097
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 1.890547263681592e-05,
+      "loss": 1.8078,
+      "step": 6500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.0176947116851807,
+      "eval_runtime": 45.9391,
+      "eval_samples_per_second": 63.845,
+      "eval_steps_per_second": 7.989,
+      "step": 6968
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 1.651358591657099e-05,
+      "loss": 1.8098,
+      "step": 7000
+    },
+    {
+      "epoch": 8.61,
+      "learning_rate": 1.4121699196326064e-05,
+      "loss": 1.7709,
+      "step": 7500
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.028904676437378,
+      "eval_runtime": 45.9139,
+      "eval_samples_per_second": 63.88,
+      "eval_steps_per_second": 7.993,
+      "step": 7839
+    },
+    {
+      "epoch": 9.18,
+      "learning_rate": 1.1729812476081135e-05,
+      "loss": 1.7691,
+      "step": 8000
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 9.337925755836204e-06,
+      "loss": 1.7516,
+      "step": 8500
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.9645367860794067,
+      "eval_runtime": 45.9103,
+      "eval_samples_per_second": 63.886,
+      "eval_steps_per_second": 7.994,
+      "step": 8710
+    },
+    {
+      "epoch": 10.33,
+      "learning_rate": 6.946039035591274e-06,
+      "loss": 1.7478,
+      "step": 9000
+    },
+    {
+      "epoch": 10.91,
+      "learning_rate": 4.554152315346345e-06,
+      "loss": 1.7354,
+      "step": 9500
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.9809770584106445,
+      "eval_runtime": 46.0471,
+      "eval_samples_per_second": 63.696,
+      "eval_steps_per_second": 7.97,
+      "step": 9581
+    },
+    {
+      "epoch": 11.48,
+      "learning_rate": 2.1622655951014164e-06,
+      "loss": 1.7073,
+      "step": 10000
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.9631489515304565,
+      "eval_runtime": 45.9378,
+      "eval_samples_per_second": 63.847,
+      "eval_steps_per_second": 7.989,
+      "step": 10452
+    },
+    {
+      "epoch": 12.0,
+      "step": 10452,
+      "total_flos": 1.760388788159447e+17,
+      "train_loss": 1.903703066931344,
+      "train_runtime": 39626.2902,
+      "train_samples_per_second": 16.878,
+      "train_steps_per_second": 0.264
+    }
+  ],
+  "max_steps": 10452,
+  "num_train_epochs": 12,
+  "total_flos": 1.760388788159447e+17,
+  "trial_name": null,
+  "trial_params": null
+}