Training in progress, step 25800, checkpoint

last-checkpoint/README.md

@@ -1539,6 +1539,10 @@ You can finetune this model on your own dataset.
 | 0.4506 | 25500 | 0.3245        |
 | 0.4515 | 25550 | 0.2978        |
 | 0.4524 | 25600 | 0.3397        |
+| 0.4533 | 25650 | 0.4655        |
+| 0.4541 | 25700 | 0.2669        |
+| 0.4550 | 25750 | 0.3316        |
+| 0.4559 | 25800 | 0.3395        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4c41f05edc2d7e0e5b6aa96c7280a269723970b3d9f5db97a908d698c18e46
+oid sha256:bd62d182588cf8dcdefa578689850921060508dd744c2b3d5b8b216b2f913c93
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad0f634d22e8d985415b64b93836e5380971e245fef96c6b35c06a87043b680
+oid sha256:c66245bb4fd1461fe3283febbf948bf75039365f0ad45b5077d2a510d710e8d9
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d11ea4dc06732960ed6abb1d44f0f58d98e38680260f859b6e949eb007dff1
+oid sha256:8a2d25e27ed0772b40c719933dfce361fb32d9594edb2389a78ead3d7c0f02d3
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f87f293944d5e456973842209f35aaec89127a12621bc86fb62b420000afe5
+oid sha256:5ed2d3227321b546366709c7d41896c93e3aed6b33762555946b5ad3ddd21662
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0157ec5a2cd87b323072c019eeb626da0770a47c34b4436db6020558b163b6ea
+oid sha256:2352e4a13b9010953b7c8382f227a4c5da82a9b4a73a8c91fe1b7aa1258dd370
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4523687512148575,
+  "epoch": 0.45590288208372354,
   "eval_steps": 500,
-  "global_step": 25600,
+  "global_step": 25800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3592,6 +3592,34 @@
       "learning_rate": 3.0433331369892604e-05,
       "loss": 0.3397,
       "step": 25600
+    },
+    {
+      "epoch": 0.453252283932074,
+      "grad_norm": 3.319705009460449,
+      "learning_rate": 3.0384245351554065e-05,
+      "loss": 0.4655,
+      "step": 25650
+    },
+    {
+      "epoch": 0.45413581664929054,
+      "grad_norm": 1.3729950189590454,
+      "learning_rate": 3.033515933321553e-05,
+      "loss": 0.2669,
+      "step": 25700
+    },
+    {
+      "epoch": 0.45501934936650706,
+      "grad_norm": 1.3527820110321045,
+      "learning_rate": 3.028607331487699e-05,
+      "loss": 0.3316,
+      "step": 25750
+    },
+    {
+      "epoch": 0.45590288208372354,
+      "grad_norm": 1.4500503540039062,
+      "learning_rate": 3.0236987296538455e-05,
+      "loss": 0.3395,
+      "step": 25800
     }
   ],
   "logging_steps": 50,