Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:353e891120c1f3085a4ae50d9257049196488443486294c7d54d656347135ecc
+oid sha256:498736cfc3b7e3198eb97573b245665ef3ac3881e3136784355448e7e65170e7
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fffc3385b4215ddc4b17b7cac3c79bd90653eb5a98a35e4bb807b66290d1fb8e
+oid sha256:562f684b1f296e89a1c35e1ddeb17a41dd7b79379be83f57533740e866b7bd31
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e0e0ac6f1eabf5b67226411843530a981f6de40c04be22eb48a8dcd83efb59
+oid sha256:ddbedb21e8d0c6f34164ce7a2846e4c2fae657975c960dd06d55cb655b72617d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18485237483953787,
+  "epoch": 0.20333761232349165,
   "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": 29.351,
       "eval_steps_per_second": 14.675,
       "step": 90
+    },
+    {
+      "epoch": 0.19101412066752246,
+      "grad_norm": NaN,
+      "learning_rate": 1.8772381773176416e-05,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.19717586649550706,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-06,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.20333761232349165,
+      "grad_norm": NaN,
+      "learning_rate": 3.854818796385495e-07,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.20333761232349165,
+      "eval_loss": NaN,
+      "eval_runtime": 55.8772,
+      "eval_samples_per_second": 29.35,
+      "eval_steps_per_second": 14.675,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.500747528732672e+16,
+  "total_flos": 8.25082228160594e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null