End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 12.0,
+    "eval_loss": 2.036412477493286,
+    "eval_runtime": 10.0166,
+    "eval_samples": 2933,
+    "eval_samples_per_second": 292.814,
+    "eval_steps_per_second": 36.639,
+    "perplexity": 7.663068396450195,
+    "train_loss": 1.9038402734019955,
+    "train_runtime": 9444.1472,
+    "train_samples": 55736,
+    "train_samples_per_second": 70.82,
+    "train_steps_per_second": 1.107
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "eval_loss": 2.036412477493286,
+    "eval_runtime": 10.0166,
+    "eval_samples": 2933,
+    "eval_samples_per_second": 292.814,
+    "eval_steps_per_second": 36.639,
+    "perplexity": 7.663068396450195
+}

runs/Dec07_16-19-15_jbuhmann/events.out.tfevents.1638893985.jbuhmann.10905.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78da597b94ba22fc02fda90e7bba6ca935b49f74050a884b03767b7757986ba
-size 9572
+oid sha256:37464616609e3f0b0f10f42adb65a11c3fdd99dfb26b5876f8248dc3c4e8b5e1
+size 9926

runs/Dec07_16-19-15_jbuhmann/events.out.tfevents.1638903440.jbuhmann.10905.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:107e1e9a8bbbb52dd6907a2e5a2b3a8a6a64cd7d817bf5f5a92c6262763d888f
+size 311

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 12.0,
+    "train_loss": 1.9038402734019955,
+    "train_runtime": 9444.1472,
+    "train_samples": 55736,
+    "train_samples_per_second": 70.82,
+    "train_steps_per_second": 1.107
+}

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": 2.2326,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.150918960571289,
+      "eval_runtime": 10.3767,
+      "eval_samples_per_second": 282.652,
+      "eval_steps_per_second": 35.368,
+      "step": 871
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 4.521622655951014e-05,
+      "loss": 2.1995,
+      "step": 1000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 4.282433983926522e-05,
+      "loss": 2.1375,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.1088852882385254,
+      "eval_runtime": 10.4009,
+      "eval_samples_per_second": 281.994,
+      "eval_steps_per_second": 35.285,
+      "step": 1742
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 4.043245311902029e-05,
+      "loss": 2.0858,
+      "step": 2000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 3.8040566398775356e-05,
+      "loss": 2.0442,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.0654592514038086,
+      "eval_runtime": 10.4234,
+      "eval_samples_per_second": 281.386,
+      "eval_steps_per_second": 35.209,
+      "step": 2613
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 3.5648679678530425e-05,
+      "loss": 2.0116,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.0432863235473633,
+      "eval_runtime": 10.4039,
+      "eval_samples_per_second": 281.913,
+      "eval_steps_per_second": 35.275,
+      "step": 3484
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 3.32567929582855e-05,
+      "loss": 2.0013,
+      "step": 3500
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 3.086490623804057e-05,
+      "loss": 1.9346,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.0133845806121826,
+      "eval_runtime": 10.3456,
+      "eval_samples_per_second": 283.503,
+      "eval_steps_per_second": 35.474,
+      "step": 4355
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 2.847301951779564e-05,
+      "loss": 1.9208,
+      "step": 4500
+    },
+    {
+      "epoch": 5.74,
+      "learning_rate": 2.608113279755071e-05,
+      "loss": 1.9056,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.9956320524215698,
+      "eval_runtime": 10.2631,
+      "eval_samples_per_second": 285.782,
+      "eval_steps_per_second": 35.759,
+      "step": 5226
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 2.368924607730578e-05,
+      "loss": 1.866,
+      "step": 5500
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 2.1297359357060852e-05,
+      "loss": 1.8295,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.028700828552246,
+      "eval_runtime": 10.2135,
+      "eval_samples_per_second": 287.168,
+      "eval_steps_per_second": 35.933,
+      "step": 6097
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 1.890547263681592e-05,
+      "loss": 1.8204,
+      "step": 6500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.0173206329345703,
+      "eval_runtime": 10.2204,
+      "eval_samples_per_second": 286.974,
+      "eval_steps_per_second": 35.909,
+      "step": 6968
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 1.651358591657099e-05,
+      "loss": 1.7944,
+      "step": 7000
+    },
+    {
+      "epoch": 8.61,
+      "learning_rate": 1.4121699196326064e-05,
+      "loss": 1.7928,
+      "step": 7500
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.0250914096832275,
+      "eval_runtime": 10.2198,
+      "eval_samples_per_second": 286.991,
+      "eval_steps_per_second": 35.911,
+      "step": 7839
+    },
+    {
+      "epoch": 9.18,
+      "learning_rate": 1.1729812476081135e-05,
+      "loss": 1.7555,
+      "step": 8000
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 9.337925755836204e-06,
+      "loss": 1.7357,
+      "step": 8500
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.014782667160034,
+      "eval_runtime": 10.2205,
+      "eval_samples_per_second": 286.972,
+      "eval_steps_per_second": 35.908,
+      "step": 8710
+    },
+    {
+      "epoch": 10.33,
+      "learning_rate": 6.946039035591274e-06,
+      "loss": 1.7191,
+      "step": 9000
+    },
+    {
+      "epoch": 10.91,
+      "learning_rate": 4.554152315346345e-06,
+      "loss": 1.7318,
+      "step": 9500
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.9273912906646729,
+      "eval_runtime": 10.2143,
+      "eval_samples_per_second": 287.148,
+      "eval_steps_per_second": 35.93,
+      "step": 9581
+    },
+    {
+      "epoch": 11.48,
+      "learning_rate": 2.1622655951014164e-06,
+      "loss": 1.7311,
+      "step": 10000
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.931414246559143,
+      "eval_runtime": 10.2191,
+      "eval_samples_per_second": 287.011,
+      "eval_steps_per_second": 35.913,
+      "step": 10452
+    },
+    {
+      "epoch": 12.0,
+      "step": 10452,
+      "total_flos": 4.400971970398618e+16,
+      "train_loss": 1.9038402734019955,
+      "train_runtime": 9444.1472,
+      "train_samples_per_second": 70.82,
+      "train_steps_per_second": 1.107
+    }
+  ],
+  "max_steps": 10452,
+  "num_train_epochs": 12,
+  "total_flos": 4.400971970398618e+16,
+  "trial_name": null,
+  "trial_params": null
+}