Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51392ac5d2f9be62429c11f34ca6ef76d2f5f4e006030e6b71bb903cc8eb1e7d
+oid sha256:212ed95a8cee1cef3ba94b7c142942132b2eab51711aa464dcd79693524446ea
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41656c856e2a4df73637aab8ca1add18efc41bb01dff2d3e743b7b1678b8ca96
+oid sha256:a20f33989dffe3003804dd757d62c88a7f05f8903e3d773efe493f14f5224860
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012951969778737183,
+  "epoch": 0.019427954668105773,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 33.341,
       "eval_steps_per_second": 16.756,
       "step": 6
+    },
+    {
+      "epoch": 0.015110631408526714,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.017269293038316244,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.019427954668105773,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.019427954668105773,
+      "eval_loss": NaN,
+      "eval_runtime": 5.8035,
+      "eval_samples_per_second": 33.601,
+      "eval_steps_per_second": 16.886,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 411363981656064.0,
+  "total_flos": 617045972484096.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null