Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9484a455acb431a6cc1ba125a846aa885dc60747d55b46a456b37a2caee378c
+oid sha256:172e5fafbcdde11a71fab70027044e3f78fa5c11835bd6d1246112ea6f4bddd9
 size 61226900

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4e1c9f23a55ed2143b3e58d15a5e8031dd8ed2ff083ab8575c3c59dc607ae3b
+oid sha256:090ef891297553240c83065e4cd4979c83f1657e5636d98ea86e3e0567e61cad
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40666e7aa6cad9d8f341a808670890fa1732f793ffc8159549ffdc9d547a5ddd
+oid sha256:b59eb35f35d20aba79e923a732621fdfc71ddea68b6757c93e0f9921303cef34
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b84a3167d66da8e88dc8fcf68dda1b2681b6147b80417622071322d0576e970
+oid sha256:0dad4415fc2996662dd1c42c26ed83b93f0f72e2e365bdd98c3eef3ff2b0a25a
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a617145b46ed132ccf4f3ca5dc140f9a2ada0666dd487db52baecd2f6a56cde
+oid sha256:60e0d91ff89b35c25ff66c82c32500ea111021844fa437b018794a06a18dce8c
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9744ae6ad9b458e89cc439488a69f04b8bc842cf66bfe68ac2f1c0431955a99
+oid sha256:ba9f83e8b1613eb0e674a51d5a1373cd25880313ed1065ab3b6a7914468653b3
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d2a9a58e8d729a3d838d1423dc31a7a0df87dc992925a1cf56edc80b4521d9
+oid sha256:3ca031454e261156270cad2b2a57121ad083e0b6b417f7e8d2947572baceeebb
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6a06aa8ae0eb413a623a5d36f1b629b26a4497a5b5ff646e8d4b9cd1345340e
+oid sha256:767f6c1ed5a3304400aadfce8423146a61e103a344177686d9ce447c95d53fe7
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8619f67ea3336573945272f883d3d48fa179066c38eaaa99fbdd2e4a17d840
+oid sha256:7f05cb880c1fd1a27ffc75b16683f59eafb7f1c19abd6a7adf83ce777592a19b
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7c6b205e1552be0830a6d7bc56be5230d8f9d9a142f3205ff3e7dff8c8730a
+oid sha256:fd82e2c4dd46a0c4163e78a1bb05a9e321fb40a1c884136f2f4f92fe2449cbde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8791208791208791,
+  "epoch": 1.054945054945055,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,27 @@
       "eval_samples_per_second": 24.074,
       "eval_steps_per_second": 1.57,
       "step": 15
+    },
+    {
+      "epoch": 0.9377289377289377,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.9963369963369964,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 1.054945054945055,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 1,
@@ -158,12 +179,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.541268718157824e+17,
+  "total_flos": 4.249522461789389e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null