Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18bb3bf34e70c25c1d595149dffb71001b21b3d47e68a94baf8c333ee3e5c3ff
+oid sha256:1060a7fca1980d8430e89e1346e26327288872e04c64c7dc5ad730e5e819e9e7
 size 403961210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da5938c7d55b3c68276c6c08b28e4135cfa2cc196b54fd93b52c51ce0c1645e5
+oid sha256:206cbcf6b3d5e71f5f2b30af10bad2fa0e04237c3638fb1873a1d609be82d65e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
+oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9529411764705882,
+  "epoch": 1.0588235294117647,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -199,6 +199,28 @@
       "eval_samples_per_second": 69.592,
       "eval_steps_per_second": 8.757,
       "step": 81
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": NaN,
+      "learning_rate": 1.2639779077309098e-05,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": NaN,
+      "learning_rate": 5.709035061653494e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "eval_loss": NaN,
+      "eval_runtime": 4.3385,
+      "eval_samples_per_second": 69.61,
+      "eval_steps_per_second": 8.759,
+      "step": 90
     }
   ],
   "logging_steps": 5,
@@ -218,7 +240,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7278497605025792e+16,
+  "total_flos": 1.915166806297805e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null