Training in progress, step 38400, checkpoint

last-checkpoint/README.md

@@ -1281,6 +1281,10 @@ You can finetune this model on your own dataset.
 | 0.6733 | 38100 | 0.3039        |
 | 0.6741 | 38150 | 0.3067        |
 | 0.6750 | 38200 | 0.3072        |
+| 0.6759 | 38250 | 0.2744        |
+| 0.6768 | 38300 | 0.3098        |
+| 0.6777 | 38350 | 0.2837        |
+| 0.6786 | 38400 | 0.2998        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ff9aaaf5100bcdf47810c9aef74f277666d0563b69786a02f96d2765837422
+oid sha256:a0c033e355f6e42ff78f502c063b5b2db3a52df78665c5ff9bb6479d0c624edc
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4f4dca1f6c69a542bde78c0327dd4270176a1625067e2256ceced634a93d6c
+oid sha256:0cd783dda3b4095b4bde6c3534ce452f7dd91f5cc8116eb11d93f25b3ce7530c
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21df5a3de36303453637c6260c11dc60608b83605f06af49a76c4215097f965f
+oid sha256:e8142ca4f7ed2fe593cefee908aecc5f50a35392fb476fa2ad8c3ba0e7ec834c
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254ca1be196224bf5f7fb5303e3156f8228d188caec22f35ae76f9309a50e396
+oid sha256:2dcf7219057595bd52b15bf2951670512df99f3f40268de42603fbc194d2d20b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8546f3abee9c0d442ca93d26c327328480bf0ee1f8248e94c717f8d8cb3ba4b
+oid sha256:e9ca8a4ad9f574d1ca2310145c441ff394dd14227f12775f4424e4ebe7c06f50
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6750189959534202,
+  "epoch": 0.6785531268222862,
   "eval_steps": 500,
-  "global_step": 38200,
+  "global_step": 38400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5356,6 +5356,34 @@
       "learning_rate": 1.8068563350415268e-05,
       "loss": 0.3072,
       "step": 38200
+    },
+    {
+      "epoch": 0.6759025286706367,
+      "grad_norm": 1.8485578298568726,
+      "learning_rate": 1.8019477332076732e-05,
+      "loss": 0.2744,
+      "step": 38250
+    },
+    {
+      "epoch": 0.6767860613878532,
+      "grad_norm": 1.350595235824585,
+      "learning_rate": 1.7970391313738197e-05,
+      "loss": 0.3098,
+      "step": 38300
+    },
+    {
+      "epoch": 0.6776695941050697,
+      "grad_norm": 1.8860970735549927,
+      "learning_rate": 1.7921305295399658e-05,
+      "loss": 0.2837,
+      "step": 38350
+    },
+    {
+      "epoch": 0.6785531268222862,
+      "grad_norm": 1.3870184421539307,
+      "learning_rate": 1.7872219277061123e-05,
+      "loss": 0.2998,
+      "step": 38400
     }
   ],
   "logging_steps": 50,