Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee0127d9fe634560933ca6a3511878689b43f5a52f9f51129db0cb58b41f8611
+oid sha256:7499a74cb1079d0328d83e18964b429e0d5dcccaace438c7254894b264ab1473
 size 912734242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915eedf6705481e90f5817e55343bfdd0b9c95890d8f86fc8c1fe9b742005082
+oid sha256:cd0b39da88d704dcd2ded8aa7c4c9307f56b3d3cc5ba8c746896857a889a3a10
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11198208286674133,
+  "epoch": 0.22396416573348266,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 2.993,
       "eval_steps_per_second": 1.497,
       "step": 25
+    },
+    {
+      "epoch": 0.11646136618141098,
+      "grad_norm": NaN,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.12094064949608063,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.12541993281075028,
+      "grad_norm": NaN,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.12989921612541994,
+      "grad_norm": NaN,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.1343784994400896,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.13885778275475924,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.1433370660694289,
+      "grad_norm": NaN,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.14781634938409854,
+      "grad_norm": NaN,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.1522956326987682,
+      "grad_norm": NaN,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.15677491601343785,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.1612541993281075,
+      "grad_norm": NaN,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.16573348264277715,
+      "grad_norm": NaN,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": NaN,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.17469204927211646,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.1791713325867861,
+      "grad_norm": NaN,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.18365061590145576,
+      "grad_norm": NaN,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.1881298992161254,
+      "grad_norm": NaN,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.19260918253079506,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.19708846584546472,
+      "grad_norm": NaN,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.20156774916013437,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.20604703247480402,
+      "grad_norm": NaN,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.21500559910414332,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.21948488241881298,
+      "grad_norm": NaN,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.22396416573348266,
+      "grad_norm": NaN,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.22396416573348266,
+      "eval_loss": NaN,
+      "eval_runtime": 62.8211,
+      "eval_samples_per_second": 2.993,
+      "eval_steps_per_second": 1.496,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.746225840128e+16,
+  "total_flos": 1.1492451680256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null