Training in progress, step 8, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5b7e634633e4d055a7b544a9c832d8d7d998e5100bb0e4dfa938799a582e15
+oid sha256:8e71c850cf62da549bc70f46dca63363921700a216a2d89b84791552cefd07a6
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f5366ddfcc1e211ed413d526222ac8edb0cb99abb64b9d8aecc8fa90d69cc2
+oid sha256:bed8c0843a4beca848b9d019f77125d5963e6b5d28890bbd48313e270584ab1c
 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": 8.619389316266943e-05,
+  "epoch": 0.00011492519088355923,
   "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": 8.48,
       "eval_steps_per_second": 4.24,
       "step": 6
+    },
+    {
+      "epoch": 0.00010055954202311432,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.00011492519088355923,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.00011492519088355923,
+      "eval_loss": NaN,
+      "eval_runtime": 3457.476,
+      "eval_samples_per_second": 8.477,
+      "eval_steps_per_second": 4.239,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2225661850681344.0,
+  "total_flos": 2967549134241792.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null