Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71701389ecfd64f9fb2acf5b8a7437e71d5201b68fc585d4942993c072738675
+oid sha256:436fb53485955b91754ed1aa8da84143064d32cf13f93500fa1bc5b479d5e530
 size 61226900

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a64ebf9cd571b1eb0f733a35aeb41a27de323e071d19938f2e61566e872fcf50
+oid sha256:1450fd405ce8a996f339e682fa4c71d4f050ed00d5cbf4d5e0f307f00c576bf7
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a49c3b886933ee7b4df6ef0062983f09a9dda5401baf9a498838ff76280da619
+oid sha256:c3e43168a4d54e6ce53a8ab9259c7a5d142fb95551b7b745174f485aa526807e
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14692378328741965,
+  "epoch": 0.2938475665748393,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 12.656,
       "eval_steps_per_second": 3.191,
       "step": 5
+    },
+    {
+      "epoch": 0.1763085399449036,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.2056932966023875,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.23507805325987144,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.2644628099173554,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.2938475665748393,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.2938475665748393,
+      "eval_loss": NaN,
+      "eval_runtime": 18.1753,
+      "eval_samples_per_second": 12.655,
+      "eval_steps_per_second": 3.191,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.90211453026304e+16,
+  "total_flos": 1.180422906052608e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null