Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554c27f0adb6b0b054a2ca73f8f5d87b25104569ec7ee558389235ecc94de49f
+oid sha256:ae5b7e634633e4d055a7b544a9c832d8d7d998e5100bb0e4dfa938799a582e15
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e541f7aee48cc7ed448f7f7a74ac3c336f54829308a589e6265d77e6e70e6da
+oid sha256:65f5366ddfcc1e211ed413d526222ac8edb0cb99abb64b9d8aecc8fa90d69cc2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.7462595441779616e-05,
+  "epoch": 8.619389316266943e-05,
   "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": 8.469,
       "eval_steps_per_second": 4.234,
       "step": 4
+    },
+    {
+      "epoch": 7.182824430222452e-05,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 8.619389316266943e-05,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 8.619389316266943e-05,
+      "eval_loss": NaN,
+      "eval_runtime": 3456.2528,
+      "eval_samples_per_second": 8.48,
+      "eval_steps_per_second": 4.24,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1483774567120896.0,
+  "total_flos": 2225661850681344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null