Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11339acf79a96935564bc101bf3302f2ea49a5e79a1cb6a2b97970436c4d68a
+oid sha256:6667ce0c575c8e876d70533fd3d44fa002d0923d53924c86e6cb19dfdb2e8cc9
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97b21c7f33e6dd1250e43a1885dcf2862e9a21f89ea7c79b66b9571be9c48ccc
+oid sha256:a4024304f7a0346e1ea2dd1d3e14e932816a39584bd6329811f3108a9687b47f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007782101167315175,
+  "epoch": 0.011673151750972763,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 27.983,
       "eval_steps_per_second": 14.056,
       "step": 4
+    },
+    {
+      "epoch": 0.009727626459143969,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.011673151750972763,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.011673151750972763,
+      "eval_loss": NaN,
+      "eval_runtime": 7.6089,
+      "eval_samples_per_second": 28.519,
+      "eval_steps_per_second": 14.325,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 205873754406912.0,
+  "total_flos": 308810631610368.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null