Training in progress, step 63, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea1a15becbe44febb5ecf9cc0f7ec7c1bf7163a216f0d13e167d214f55d1eb2a
+oid sha256:a315185e82cb1d480945c716fc194be8b5ba79d677b2510a1731a11fc5e4d92b
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaee9e6e7f084eb979a4fae1379973889d676dd05a81fe8ebfd03a9e10f90444
+oid sha256:935e93c17fec955cdc1873761997edd06c6d8451e1eced9e4c0a038e0347bdf6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002793440587657131,
+  "epoch": 0.0032590140189333195,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 14.123,
       "eval_steps_per_second": 1.766,
       "step": 54
+    },
+    {
+      "epoch": 0.0029486317314158603,
+      "grad_norm": NaN,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.00310382287517459,
+      "grad_norm": NaN,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.0032590140189333195,
+      "grad_norm": NaN,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.0032590140189333195,
+      "eval_loss": NaN,
+      "eval_runtime": 2305.4081,
+      "eval_samples_per_second": 14.122,
+      "eval_steps_per_second": 1.765,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.05735292920791e+16,
+  "total_flos": 8.233578417409229e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null