Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa3aa295baa3b91a6c1f8d28e4e65514a3167e05f7e1e8884216aae66d72db6
+oid sha256:6d7fef61ed8fc003bc69709538acc7f5589febeec068f1933e01c925e4437048
 size 456603682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87529415d1384de86b6c0ef3c2ad137cb25008da08d2beb470ea0c8312f17a07
+oid sha256:8eebf46c637860d2d83b972830e5b9a43e1c9eadfc67be12d4f719787f3ef07d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040b95482c646935022d148ebc91f462fbf2195cfa3365adbbe3bd6ca1f35a74
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028421202216853774,
+  "epoch": 0.05684240443370755,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 2.955,
       "eval_steps_per_second": 1.48,
       "step": 25
+    },
+    {
+      "epoch": 0.029558050305527925,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.030694898394202075,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.031831746482876226,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.03296859457155037,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.03410544266022453,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03410544266022453,
+      "eval_loss": NaN,
+      "eval_runtime": 250.7795,
+      "eval_samples_per_second": 2.955,
+      "eval_steps_per_second": 1.479,
+      "step": 30
+    },
+    {
+      "epoch": 0.03524229074889868,
+      "grad_norm": NaN,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.03637913883757283,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.03751598692624698,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.03865283501492113,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.039789683103595284,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.039789683103595284,
+      "eval_loss": NaN,
+      "eval_runtime": 250.7402,
+      "eval_samples_per_second": 2.955,
+      "eval_steps_per_second": 1.48,
+      "step": 35
+    },
+    {
+      "epoch": 0.04092653119226943,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.042063379280943586,
+      "grad_norm": NaN,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.04320022736961773,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.04433707545829189,
+      "grad_norm": NaN,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.045473923546966034,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.045473923546966034,
+      "eval_loss": NaN,
+      "eval_runtime": 250.704,
+      "eval_samples_per_second": 2.956,
+      "eval_steps_per_second": 1.48,
+      "step": 40
+    },
+    {
+      "epoch": 0.04661077163564019,
+      "grad_norm": NaN,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.047747619724314336,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.04888446781298849,
+      "grad_norm": NaN,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.05002131590166264,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.05115816399033679,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.05115816399033679,
+      "eval_loss": NaN,
+      "eval_runtime": 250.5933,
+      "eval_samples_per_second": 2.957,
+      "eval_steps_per_second": 1.48,
+      "step": 45
+    },
+    {
+      "epoch": 0.052295012079010945,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.05343186016768509,
+      "grad_norm": NaN,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.05456870825635925,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.055705556345033394,
+      "grad_norm": NaN,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.05684240443370755,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05684240443370755,
+      "eval_loss": NaN,
+      "eval_runtime": 250.3891,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 1.482,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.86115620798464e+16,
+  "total_flos": 1.1665130404184064e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null