Training in progress, step 26200, checkpoint

last-checkpoint/README.md

@@ -1547,6 +1547,10 @@ You can finetune this model on your own dataset.
 | 0.4577 | 25900 | 0.3418        |
 | 0.4586 | 25950 | 0.3351        |
 | 0.4594 | 26000 | 0.3117        |
+| 0.4603 | 26050 | 0.3197        |
+| 0.4612 | 26100 | 0.2856        |
+| 0.4621 | 26150 | 0.3668        |
+| 0.4630 | 26200 | 0.4672        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9b275662690960867e4c5004de25c023e37f1f7c4ebe3e55950090be859db5
+oid sha256:7aa3ad48db251d65c420989c1a1065641651336023e357be269465da6c52b747
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccf58858fe88830e35307ea10b8a5b6180e3bcc733d316d0262f05ad1036e132
+oid sha256:4cd5be8c20557f7368b8eca8b965e515fb0eede32019b1a858661a9114b93a2a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2ed85cbcfc26a558906734eea48312aeda57b3baa4220e882e04b5dde95173
+oid sha256:37d8388f61f2558efc37c86034b939b40258c4860b329143c81ea5c904f59277
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a1824f2390986b90c617282d9a88df5bdc60e3f12c5d84551697fb36352fa3
+oid sha256:7f427cb46047bcb3e8371ea8ff734f8d8ca109ef018f2637b4d5fa5935ce5feb
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c6214bd46d06bb31b87e2550447bf08cbff7452cc6c1e25562bc8a18251786
+oid sha256:bdb82bc459c496a0f434edcf728ea9313ee27e26d061cb72011f6899ef196598
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.45943701295258965,
+  "epoch": 0.4629711438214557,
   "eval_steps": 500,
-  "global_step": 26000,
+  "global_step": 26200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3648,6 +3648,34 @@
       "learning_rate": 3.004064322318431e-05,
       "loss": 0.3117,
       "step": 26000
+    },
+    {
+      "epoch": 0.4603205456698062,
+      "grad_norm": 1.4303230047225952,
+      "learning_rate": 2.9991557204845772e-05,
+      "loss": 0.3197,
+      "step": 26050
+    },
+    {
+      "epoch": 0.46120407838702265,
+      "grad_norm": 3.692739248275757,
+      "learning_rate": 2.9942471186507237e-05,
+      "loss": 0.2856,
+      "step": 26100
+    },
+    {
+      "epoch": 0.4620876111042392,
+      "grad_norm": 2.6494288444519043,
+      "learning_rate": 2.98933851681687e-05,
+      "loss": 0.3668,
+      "step": 26150
+    },
+    {
+      "epoch": 0.4629711438214557,
+      "grad_norm": 1.832560420036316,
+      "learning_rate": 2.9844299149830163e-05,
+      "loss": 0.4672,
+      "step": 26200
     }
   ],
   "logging_steps": 50,