Training in progress, step 68, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a27096981255da323876810b71d4d0fa75aff2a623be29237e8cc96f237ee80
+oid sha256:3c755a8afd91ffba478a86b1819c20d2a43b7da45950356efc27abffb3b3be7b
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dcfd7c73f8b512c49d9750d648bdf1702116da4421461a4a4bd0b6a13ab5b60
+oid sha256:33b475a076fd9434f2dd13dd7dd07097656597c66a04650e8cfe678812f89c14
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c86702c0a3caad6c51746e54805a7289de03dff9cc5abc148a58966cf1f4d339
+oid sha256:3f4e77fd2a3bb3f08929494d77da2f57f8781f91a45852bcf8f71a5777dd088c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010175895846713098,
+  "epoch": 0.013567861128950798,
   "eval_steps": 50,
-  "global_step": 51,
+  "global_step": 68,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -380,6 +380,125 @@
       "learning_rate": 0.00013928754755265842,
       "loss": 0.0,
       "step": 51
+    },
+    {
+      "epoch": 0.010375423216256492,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013860360721173193,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.010574950585799886,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001379002925959068,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.010774477955343281,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001371778179416281,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.010974005324886675,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013643640332167438,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.011173532694430069,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.011373060063973463,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013489766325354695,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.011572587433516857,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013410080652050412,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.01177211480306025,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001332859471092728,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.011971642172603644,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013245333323392333,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.01217116954214704,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001316032185167079,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.012370696911690434,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013073586191080457,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.012570224281233828,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012985152762143778,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.012769751650777221,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012895048502539882,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.012969279020320615,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012803300858899104,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.013168806389864009,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001270993777844248,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.013368333759407403,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001261498770046874,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.013567861128950798,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012518479547691435,
+      "loss": 0.0,
+      "step": 68
     }
   ],
   "logging_steps": 1,
@@ -399,7 +518,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0437226448316006e+17,
+  "total_flos": 4.0582968597754675e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null