Training in progress, step 24400, checkpoint

last-checkpoint/README.md

@@ -1511,6 +1511,10 @@ You can finetune this model on your own dataset.
 | 0.4259 | 24100 | 0.285         |
 | 0.4267 | 24150 | 0.4717        |
 | 0.4276 | 24200 | 0.3391        |
+| 0.4285 | 24250 | 0.2913        |
+| 0.4294 | 24300 | 0.3417        |
+| 0.4303 | 24350 | 0.2909        |
+| 0.4312 | 24400 | 0.2871        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0181c21b9f6765739bd5007a2c66971b2b61c54adeae3d64ef7c903bb8f2e6e4
+oid sha256:a38d401f5ea89e305e6df80090c6dd502f091f942a1c6fd6198f15360577d242
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6c65cd16ad4911950d1c8397919ae661398f9d0a619f0171434d20572ef27e7
+oid sha256:4ee417ff7164269027bc0f8dbaecd3a447bcdaf2df6f366192998237eb82980f
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fde7e047e37c5aa11f699d0fe33f27bebcb79d0fc8db66d93c60380391a735e
+oid sha256:84b0651531962a4d1fe7da7104f596909a3f9f4635a3127767128f052a6125b9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32780bd86329e2b09cbb8ee735964e2604497b85f5cbf997d9829eaba3fba7af
+oid sha256:6968679df555ba9a784a9188bf0ef6e39006e81ae9b7d0ac31431b960b33cd5f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be018c87a0e7096cac9e25fc24ea9075d875ad05ab63ff4844349cf5f7d7251
+oid sha256:983738f386fa95d07dae8b199fac4c31ae7f3aaf02a8d2d99fd9db8f93f6cabe
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.42762983513279496,
+  "epoch": 0.431163966001661,
   "eval_steps": 500,
-  "global_step": 24200,
+  "global_step": 24400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3396,6 +3396,34 @@
       "learning_rate": 3.180675816300485e-05,
       "loss": 0.3391,
       "step": 24200
+    },
+    {
+      "epoch": 0.4285133678500115,
+      "grad_norm": 1.3054397106170654,
+      "learning_rate": 3.1757672144666315e-05,
+      "loss": 0.2913,
+      "step": 24250
+    },
+    {
+      "epoch": 0.429396900567228,
+      "grad_norm": 1.7768748998641968,
+      "learning_rate": 3.170858612632778e-05,
+      "loss": 0.3417,
+      "step": 24300
+    },
+    {
+      "epoch": 0.43028043328444454,
+      "grad_norm": 1.2682479619979858,
+      "learning_rate": 3.1659500107989244e-05,
+      "loss": 0.2909,
+      "step": 24350
+    },
+    {
+      "epoch": 0.431163966001661,
+      "grad_norm": 1.791175365447998,
+      "learning_rate": 3.16104140896507e-05,
+      "loss": 0.2871,
+      "step": 24400
     }
   ],
   "logging_steps": 50,