Training in progress, step 63, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f53293838445a6d8e66c7909589708a708049e2eff3d9cfaaf613030a90fe346
+oid sha256:0bfc38de157b483a196afcac9a46c29141384848365c412e307d791d2a5f2008
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2425b3861618a945a0437a5dfb29ac97fcd65c047bd59e2820e3ecf2bf6b2058
+oid sha256:0f249013890690838eaacac0577330eb1ce20bd7f29839b9b80b34a4939f21da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f68b4a4ba4603d307a8be653dd70e693a9f3506ea1af5f24d2d241dc54cfcb1
+oid sha256:d85eac2daddfe8e3f78a5d6ef1e9ba13c04651694635a9ed76369a20726389db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0605359957961114,
+  "epoch": 0.07062532842879664,
   "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": 8.272,
       "eval_steps_per_second": 4.137,
       "step": 54
+    },
+    {
+      "epoch": 0.06389910667367314,
+      "grad_norm": NaN,
+      "learning_rate": 8.381530480933783e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.06726221755123489,
+      "grad_norm": NaN,
+      "learning_rate": 7.5e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.07062532842879664,
+      "grad_norm": NaN,
+      "learning_rate": 6.618469519066217e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.07062532842879664,
+      "eval_loss": NaN,
+      "eval_runtime": 363.3706,
+      "eval_samples_per_second": 8.27,
+      "eval_steps_per_second": 4.136,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4913289161303654e+17,
+  "total_flos": 4.082542199470817e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null