Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d6f610cac3847211b288a7eaabd00cbdf875b117c12f341a233f3ff1fd2b140
+oid sha256:aa8c9d689006f6c8dcd32fa089b70d2e3fbd3e741cb8f1fe76ae975d5d69919c
 size 67209940

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a427adcb42a5e21efe60aeff1fc331ce48c7ff904cf00d837fab2409ae1ed3f
+oid sha256:702327b551c4e20ef5af863061e25c1972735379504477c4bd2355e08bc4820d
 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": 0.0032939884710403516,
+  "epoch": 0.004940982706560527,
   "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": 6.339,
       "eval_steps_per_second": 3.174,
       "step": 6
+    },
+    {
+      "epoch": 0.0038429865495470767,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0043919846280538015,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.004940982706560527,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.004940982706560527,
+      "eval_loss": NaN,
+      "eval_runtime": 119.4896,
+      "eval_samples_per_second": 6.419,
+      "eval_steps_per_second": 3.214,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2039145195110400.0,
+  "total_flos": 3058717792665600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null