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 sha256:7201735cc400072c5baa9eff27cb1e8390566694c30dda81a9a9ac59158ccdd0
+oid sha256:cdcad6b762aacbab46cc0d6e3d60816e087bd36e64e58c67e5735aaefffbd1a2
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d4cb8907d6f7bcf6fb124beb0d0daaba3adda486c1ac10d07e9e86375129ec
+oid sha256:f936d90ff803582b08e8172ade7d55b4baa55a241544b3356b2f9331bdc03ed0
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e093041dd78e062f439ba295e3cfb26694a1b53a63ec6a3eb102c61412d1f24f
+oid sha256:f6d1611ac667e6c91d720d8b0d739fa8eee9e216277179e6ae276a3b334055c7
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673ca1c395dbc1c541d80be5775e941d426f91c6f86c79b984bd6d5e9edf789a
+oid sha256:e05a959c5a6ee814eab02be23764b760f7f3a5765ea0b83ba5c4873c719caad1
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a53ddcef1a22a1cc61c82b75fbe41e1668049436361cbd15243cf1c56582aeda
+oid sha256:750ae665b5623a3bc4c6585ebfaf80114026712f93e233e13ee8b7c770e3ecaa
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea07796169a324a15ebe3061702f9bd74c208fcb4d5e31c5a0073c2dcff485d7
+oid sha256:bd805fdbd1caa66fd0c81289464f22a33eaa06472dd01f1753f43a29f4942ec1
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77cd04fcf435150250e89e99b9fb9f5ff9a3a90d029e4e412d22939583bb7318
+oid sha256:95e857f7a2f379c3e1cbca4e548ad343e1d77bf7b0ce8091fdbf0a9ed57dcfed
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116ddc4b198bbe108025deec46f73c3c30904c413304928959f53f3f79bb41b9
+oid sha256:832868e607249dfa000ab7c5688a108b18b75cf79d07ae3cf123bc3000f3be1c
 size 15984

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": 0.29304029304029305,
+  "epoch": 0.5860805860805861,
   "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": 24.025,
       "eval_steps_per_second": 1.567,
       "step": 5
+    },
+    {
+      "epoch": 0.3516483516483517,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.46886446886446886,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.5860805860805861,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.5860805860805861,
+      "eval_loss": NaN,
+      "eval_runtime": 9.58,
+      "eval_samples_per_second": 24.008,
+      "eval_steps_per_second": 1.566,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.180422906052608e+17,
+  "total_flos": 2.360845812105216e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null