Training in progress, step 12, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71d8e2c9ab6ce512e4fe5f2de9bff9c5fb04e35dd7e76c6585ba2a1f7251c9f1
+oid sha256:d44e95eba41a6246a6899f74e4fa9deb61e2e866f84fa70295160965700769f0
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4bce206b4d535dc3e5a0da947635d46d61eba86f9f2bc5d6b08b01b38370047
+oid sha256:da06106ad662df46a5bbfc803eb00ea8cc26abfe20d636176f9e3fb364e20881
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008676789587852495,
+  "epoch": 0.013015184381778741,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 4.848,
       "eval_steps_per_second": 2.43,
       "step": 8
+    },
+    {
+      "epoch": 0.009761388286334056,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.010845986984815618,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.01193058568329718,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.013015184381778741,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.013015184381778741,
+      "eval_loss": NaN,
+      "eval_runtime": 50.8068,
+      "eval_samples_per_second": 7.656,
+      "eval_steps_per_second": 3.838,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2235874343387136.0,
+  "total_flos": 3353811515080704.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null