Training in progress, step 8, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d21cee069e647b1dc485876bb526cd2a034f86889d63f949f981856c2a0bf78c
+oid sha256:5611d10b1dc80593a4bdac7adf240fe7ec3afb8b0341077ac9b221743431d240
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88abfd0964de8635d40395a658f59c81d24f5a44cd2bc9d3629b24d56183e900
+oid sha256:07c8b900649e3a89c1fce9528aed431e4557d641a9f9d733e5c5a569fff76173
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00018785075257707752,
+  "epoch": 0.00025046767010277,
   "eval_steps": 2,
-  "global_step": 6,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 3.99,
       "eval_steps_per_second": 3.99,
       "step": 6
+    },
+    {
+      "epoch": 0.00021915921133992377,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.00025046767010277,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.00025046767010277,
+      "eval_loss": NaN,
+      "eval_runtime": 3267.2262,
+      "eval_samples_per_second": 4.116,
+      "eval_steps_per_second": 4.116,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4218776992088064.0,
+  "total_flos": 5625035989450752.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null