Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9f689fc9544e7558c323eae470fd996b4266b03f0f1cfb5eb9f28e0d5ed452
+oid sha256:316aba2930a94308e4d1089240557ace753e60365be956e20a6ddbf0ef1dfb77
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b382193a63f277550380fa02274faa8cf1e6c79dd0ecf9c90fffe399fc53ea
+oid sha256:87f0e2407d179965d787b2279a15aa2d551e9fb96b47dcd427c868bf47913b56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7e91af1a79d7676619e959cc4b5dde54a9e2ec825d24c1c34fe5387a27894f
+oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.039721946375372394,
+  "epoch": 0.07944389275074479,
   "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": 4.199,
       "eval_steps_per_second": 2.1,
       "step": 25
+    },
+    {
+      "epoch": 0.04131082423038729,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001537299608346824,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.04289970208540218,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.04448857994041708,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014617486132350343,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.04607745779543198,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014226182617406996,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.047666335650446874,
+      "grad_norm": NaN,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.04925521350546177,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.05084409136047666,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013007057995042732,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.05243296921549156,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.05402184707050645,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012164396139381029,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.05561072492552135,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.05719960278053625,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011305261922200519,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.058788480635551144,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010871557427476583,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.06037735849056604,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010436193873653361,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.06196623634558093,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.06355511420059583,
+      "grad_norm": NaN,
+      "learning_rate": 9.563806126346642e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.06514399205561072,
+      "grad_norm": NaN,
+      "learning_rate": 9.128442572523417e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.06673286991062562,
+      "grad_norm": NaN,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.06832174776564051,
+      "grad_norm": NaN,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.0699106256206554,
+      "grad_norm": NaN,
+      "learning_rate": 7.835603860618972e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.07149950347567031,
+      "grad_norm": NaN,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.07308838133068521,
+      "grad_norm": NaN,
+      "learning_rate": 6.992942004957271e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.0746772591857001,
+      "grad_norm": NaN,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.076266137040715,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.0778550148957299,
+      "grad_norm": NaN,
+      "learning_rate": 5.773817382593008e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.07944389275074479,
+      "grad_norm": NaN,
+      "learning_rate": 5.382513867649663e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.07944389275074479,
+      "eval_loss": NaN,
+      "eval_runtime": 126.0889,
+      "eval_samples_per_second": 4.203,
+      "eval_steps_per_second": 2.102,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4633306041483264e+16,
+  "total_flos": 6.926661208296653e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null