Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f95b17010e269997f37a0d67711b1270e8a524670a56c596b4bf3c9edb022172
+oid sha256:3da1c3d0998205b7918e96407fdc928aa5dfccb4b65b5fdbac83c076c274537b
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e213d932a8575a36a5a5c1f1103ea32d86293e36ed6cf75132ccafd4c553635
+oid sha256:c5e19bcf35158f6b3d0b3937cad49f6cb041e5c5d18c53e90b18e34f58228c4d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03376477208778841,
+  "epoch": 0.03714124929656725,
   "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": 10.816,
       "eval_steps_per_second": 1.354,
       "step": 90
+    },
+    {
+      "epoch": 0.03489026449071469,
+      "grad_norm": NaN,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.03601575689364097,
+      "grad_norm": NaN,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.03714124929656725,
+      "grad_norm": NaN,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.03714124929656725,
+      "eval_loss": NaN,
+      "eval_runtime": 414.9211,
+      "eval_samples_per_second": 10.821,
+      "eval_steps_per_second": 1.354,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.733245975532667e+17,
+  "total_flos": 1.891453011838894e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null