Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb6a5b8069ca1a339205a36e43f752c4763433cd61729120596e56f937c9573
+oid sha256:e644fb3353c9ec2ae9df9edcddd5e68d89fd778e1b79457746510511b3a5e692
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa48ab8e9b6bb0bba59a1d5e0f594ea45918b0cdc7a93aee2e5e315f46f923e
+oid sha256:3566d0f3480f2739487eae065857f3097d42230cf20152e3093dbbc14ff08748
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
+oid sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2917981072555205,
+  "epoch": 2.5189274447949526,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 8.696,
       "eval_steps_per_second": 4.348,
       "step": 90
+    },
+    {
+      "epoch": 2.367507886435331,
+      "grad_norm": NaN,
+      "learning_rate": 3.7544763546352834e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 2.443217665615142,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 2.5189274447949526,
+      "grad_norm": NaN,
+      "learning_rate": 7.709637592770991e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 2.5189274447949526,
+      "eval_loss": NaN,
+      "eval_runtime": 15.4262,
+      "eval_samples_per_second": 8.687,
+      "eval_steps_per_second": 4.343,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.98136135596245e+17,
+  "total_flos": 5.474402730686546e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null