Training in progress, step 56400, checkpoint

last-checkpoint/README.md

@@ -1281,6 +1281,10 @@ You can finetune this model on your own dataset.
 | 0.9913 | 56100 | 0.2681        |
 | 0.9922 | 56150 | 0.2366        |
 | 0.9931 | 56200 | 0.2505        |
+| 0.9940 | 56250 | 0.3341        |
+| 0.9949 | 56300 | 0.3292        |
+| 0.9957 | 56350 | 0.3199        |
+| 0.9966 | 56400 | 0.284         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a32dcecc7a280e374129a3cf22989595ed2fddc46218250361b6a75860e81ea
+oid sha256:4747cc93084121a20f52f8b5b3fae00c2031a6d438b4dd7c030dc7e8652c32aa
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e902c9d495246ac0efa5a76c4a3f41b5141efdc728e2bf3190fe35a55a5b2e1
+oid sha256:2a01f3f6168f288a9f54b715fca053c4247ee3c93290ec1fa8d7523534d20340
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a835c96aac6cd628ade43289fa29f54a47dd56e61db80b153e797a52ab69e8
+oid sha256:85f4a9b315b1a20d2d787ee19f75f3a9099eeab81535c38061478be96f3a2307
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b83e73e3f126bc90ca6d8e599f4164120b914905a3300fff248d49cf0cac104
+oid sha256:122be002ed2c68d1f49408fb696a88fb75bec95372b6d4e67c49fa667ddaf90a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10cac6c490bb3f5b4fbbd2a825be2153a2b1171fe6ae7ae8be377957525cab19
+oid sha256:da795e3f463af8c3f55b378fcdaabc95ba9e2728665cb3652b390ac2ddc09ef8
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9930907741513668,
+  "epoch": 0.9966249050202329,
   "eval_steps": 500,
-  "global_step": 56200,
+  "global_step": 56400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7876,6 +7876,34 @@
       "learning_rate": 4.0643223184308187e-07,
       "loss": 0.2505,
       "step": 56200
+    },
+    {
+      "epoch": 0.9939743068685833,
+      "grad_norm": 1.548779010772705,
+      "learning_rate": 3.5734621350454537e-07,
+      "loss": 0.3341,
+      "step": 56250
+    },
+    {
+      "epoch": 0.9948578395857999,
+      "grad_norm": 1.6362569332122803,
+      "learning_rate": 3.0826019516600893e-07,
+      "loss": 0.3292,
+      "step": 56300
+    },
+    {
+      "epoch": 0.9957413723030164,
+      "grad_norm": 1.707270622253418,
+      "learning_rate": 2.591741768274725e-07,
+      "loss": 0.3199,
+      "step": 56350
+    },
+    {
+      "epoch": 0.9966249050202329,
+      "grad_norm": 2.1296205520629883,
+      "learning_rate": 2.1008815848893604e-07,
+      "loss": 0.284,
+      "step": 56400
     }
   ],
   "logging_steps": 50,