Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:436fb53485955b91754ed1aa8da84143064d32cf13f93500fa1bc5b479d5e530
+oid sha256:e9484a455acb431a6cc1ba125a846aa885dc60747d55b46a456b37a2caee378c
 size 61226900

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdcad6b762aacbab46cc0d6e3d60816e087bd36e64e58c67e5735aaefffbd1a2
+oid sha256:a4e1c9f23a55ed2143b3e58d15a5e8031dd8ed2ff083ab8575c3c59dc607ae3b
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f936d90ff803582b08e8172ade7d55b4baa55a241544b3356b2f9331bdc03ed0
+oid sha256:40666e7aa6cad9d8f341a808670890fa1732f793ffc8159549ffdc9d547a5ddd
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d1611ac667e6c91d720d8b0d739fa8eee9e216277179e6ae276a3b334055c7
+oid sha256:6b84a3167d66da8e88dc8fcf68dda1b2681b6147b80417622071322d0576e970
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05a959c5a6ee814eab02be23764b760f7f3a5765ea0b83ba5c4873c719caad1
+oid sha256:8a617145b46ed132ccf4f3ca5dc140f9a2ada0666dd487db52baecd2f6a56cde
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:750ae665b5623a3bc4c6585ebfaf80114026712f93e233e13ee8b7c770e3ecaa
+oid sha256:b9744ae6ad9b458e89cc439488a69f04b8bc842cf66bfe68ac2f1c0431955a99
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd805fdbd1caa66fd0c81289464f22a33eaa06472dd01f1753f43a29f4942ec1
+oid sha256:e1d2a9a58e8d729a3d838d1423dc31a7a0df87dc992925a1cf56edc80b4521d9
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e857f7a2f379c3e1cbca4e548ad343e1d77bf7b0ce8091fdbf0a9ed57dcfed
+oid sha256:a6a06aa8ae0eb413a623a5d36f1b629b26a4497a5b5ff646e8d4b9cd1345340e
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832868e607249dfa000ab7c5688a108b18b75cf79d07ae3cf123bc3000f3be1c
+oid sha256:eb8619f67ea3336573945272f883d3d48fa179066c38eaaa99fbdd2e4a17d840
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:2b7c6b205e1552be0830a6d7bc56be5230d8f9d9a142f3205ff3e7dff8c8730a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5860805860805861,
+  "epoch": 0.8791208791208791,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 24.008,
       "eval_steps_per_second": 1.566,
       "step": 10
+    },
+    {
+      "epoch": 0.6446886446886447,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.7032967032967034,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "eval_loss": NaN,
+      "eval_runtime": 9.5539,
+      "eval_samples_per_second": 24.074,
+      "eval_steps_per_second": 1.57,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.360845812105216e+17,
+  "total_flos": 3.541268718157824e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null