Training in progress, step 56200, checkpoint

last-checkpoint/README.md

@@ -1277,6 +1277,10 @@ You can finetune this model on your own dataset.
 | 0.9878 | 55900 | 0.241         |
 | 0.9887 | 55950 | 0.2616        |
 | 0.9896 | 56000 | 0.2572        |
+| 0.9904 | 56050 | 0.3437        |
+| 0.9913 | 56100 | 0.2681        |
+| 0.9922 | 56150 | 0.2366        |
+| 0.9931 | 56200 | 0.2505        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ce30d7aacd666933a14d83cc737c586dcae579850f877da7309f9895799d43
+oid sha256:2a32dcecc7a280e374129a3cf22989595ed2fddc46218250361b6a75860e81ea
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d280d8e79c740dc707e7398c5e14c4f2ad422cb187845da01e50e47c090ae44
+oid sha256:5e902c9d495246ac0efa5a76c4a3f41b5141efdc728e2bf3190fe35a55a5b2e1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c072afea83c70b7165bf32b5c5585de459f967b6f4f050240893f3e9f57351d0
+oid sha256:a7a835c96aac6cd628ade43289fa29f54a47dd56e61db80b153e797a52ab69e8
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4674ba66a393298737c507490cd48fcb412b9b21de3a1d3996a7109c47aaae95
+oid sha256:3b83e73e3f126bc90ca6d8e599f4164120b914905a3300fff248d49cf0cac104
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1d493f6ec6785592b7a247d7ab39afb368b0e235cf1f0840677960dedafdad
+oid sha256:10cac6c490bb3f5b4fbbd2a825be2153a2b1171fe6ae7ae8be377957525cab19
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9895566432825007,
+  "epoch": 0.9930907741513668,
   "eval_steps": 500,
-  "global_step": 56000,
+  "global_step": 56200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7848,6 +7848,34 @@
       "learning_rate": 6.027763051972277e-07,
       "loss": 0.2572,
       "step": 56000
+    },
+    {
+      "epoch": 0.9904401759997172,
+      "grad_norm": 1.814112663269043,
+      "learning_rate": 5.536902868586912e-07,
+      "loss": 0.3437,
+      "step": 56050
+    },
+    {
+      "epoch": 0.9913237087169338,
+      "grad_norm": 2.0368192195892334,
+      "learning_rate": 5.046042685201547e-07,
+      "loss": 0.2681,
+      "step": 56100
+    },
+    {
+      "epoch": 0.9922072414341503,
+      "grad_norm": 1.4389891624450684,
+      "learning_rate": 4.555182501816183e-07,
+      "loss": 0.2366,
+      "step": 56150
+    },
+    {
+      "epoch": 0.9930907741513668,
+      "grad_norm": 2.772890567779541,
+      "learning_rate": 4.0643223184308187e-07,
+      "loss": 0.2505,
+      "step": 56200
     }
   ],
   "logging_steps": 50,