Training in progress, step 26400, checkpoint

last-checkpoint/README.md

@@ -1551,6 +1551,10 @@ You can finetune this model on your own dataset.
 | 0.4612 | 26100 | 0.2856        |
 | 0.4621 | 26150 | 0.3668        |
 | 0.4630 | 26200 | 0.4672        |
+| 0.4639 | 26250 | 0.373         |
+| 0.4647 | 26300 | 0.3232        |
+| 0.4656 | 26350 | 0.3461        |
+| 0.4665 | 26400 | 0.2937        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa3ad48db251d65c420989c1a1065641651336023e357be269465da6c52b747
+oid sha256:95db985db084a74db34108a18955cb2f94475e94d71ba1394dc6711c0773d4b7
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd5be8c20557f7368b8eca8b965e515fb0eede32019b1a858661a9114b93a2a
+oid sha256:99edc411ece53670a76daae12b850cb27d05b6b28f0e1abb1039884ae4ec4d91
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d8388f61f2558efc37c86034b939b40258c4860b329143c81ea5c904f59277
+oid sha256:c3c74149b9485dd85a90bddde2fb89338979661fdbddb3f61abad71930d1b347
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f427cb46047bcb3e8371ea8ff734f8d8ca109ef018f2637b4d5fa5935ce5feb
+oid sha256:5aa35335d6835971914c8cd5a825891507e75318afb8a7d46177ecba5e7044a7
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb82bc459c496a0f434edcf728ea9313ee27e26d061cb72011f6899ef196598
+oid sha256:d8741bd796701c3df080c6afd4a635df632277d4edf7423e34ebd4e6d1a562aa
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4629711438214557,
+  "epoch": 0.46650527469032177,
   "eval_steps": 500,
-  "global_step": 26200,
+  "global_step": 26400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3676,6 +3676,34 @@
       "learning_rate": 2.9844299149830163e-05,
       "loss": 0.4672,
       "step": 26200
+    },
+    {
+      "epoch": 0.46385467653867224,
+      "grad_norm": 3.4169373512268066,
+      "learning_rate": 2.9795213131491627e-05,
+      "loss": 0.373,
+      "step": 26250
+    },
+    {
+      "epoch": 0.46473820925588877,
+      "grad_norm": 1.5430257320404053,
+      "learning_rate": 2.974612711315309e-05,
+      "loss": 0.3232,
+      "step": 26300
+    },
+    {
+      "epoch": 0.46562174197310524,
+      "grad_norm": 1.674177646636963,
+      "learning_rate": 2.9697041094814553e-05,
+      "loss": 0.3461,
+      "step": 26350
+    },
+    {
+      "epoch": 0.46650527469032177,
+      "grad_norm": 1.7116457223892212,
+      "learning_rate": 2.9647955076476018e-05,
+      "loss": 0.2937,
+      "step": 26400
     }
   ],
   "logging_steps": 50,