Training in progress, step 31800, checkpoint

last-checkpoint/README.md

@@ -1295,6 +1295,10 @@ You can finetune this model on your own dataset.
 | 0.5566 | 31500 | 0.3329        |
 | 0.5575 | 31550 | 0.2794        |
 | 0.5584 | 31600 | 0.4189        |
+| 0.5593 | 31650 | 0.3643        |
+| 0.5602 | 31700 | 0.3578        |
+| 0.5610 | 31750 | 0.3193        |
+| 0.5619 | 31800 | 0.327         |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:037af2d441f69bccfeb282dafbe011432348a180c3a824cdedd50370b13aa3f5
+oid sha256:2aefeca268258dbfb0695a5597c522e31aac7733474d6d58a376815037205ed7
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0170e06425554bee01ebe42a564ab7255970144350ac51e311ccbc99405281
+oid sha256:30a1ec12177bf3e7a3bcf0d2304d2b35cf56ea3e8b41cc3e1af93291a40fc7ca
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a18c03e60472d4b8f510c853a2c7471950a1574efd6c20fb49cc26f42e6d1dd
+oid sha256:d21026606b47fb76259886267bb47d18484b5815e94d5a5656506546687ec739
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c19235faf86fc7b488d049c5de2dd9270a2ad7d80400a9f4692705e68f0f698f
+oid sha256:3efc050901e150a59e85c2ab742c4d82ce79ba854a2e4dcd71f14091e10af7e2
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a676db8a1d42fae190e3de7197b8ccb119e27d8c3e860a70915ea0b98f39452b
+oid sha256:79ef76f1bbf004f2132ce3725824bf2705832e8a1ea3351be51debbf13b28b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5583926772808397,
+  "epoch": 0.5619268081497057,
   "eval_steps": 500,
-  "global_step": 31600,
+  "global_step": 31800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4432,6 +4432,34 @@
       "learning_rate": 2.4544972610001768e-05,
       "loss": 0.4189,
       "step": 31600
+    },
+    {
+      "epoch": 0.5592762099980563,
+      "grad_norm": 1.5030118227005005,
+      "learning_rate": 2.4495886591663232e-05,
+      "loss": 0.3643,
+      "step": 31650
+    },
+    {
+      "epoch": 0.5601597427152728,
+      "grad_norm": 1.3483951091766357,
+      "learning_rate": 2.4446800573324697e-05,
+      "loss": 0.3578,
+      "step": 31700
+    },
+    {
+      "epoch": 0.5610432754324892,
+      "grad_norm": 1.5314035415649414,
+      "learning_rate": 2.439771455498616e-05,
+      "loss": 0.3193,
+      "step": 31750
+    },
+    {
+      "epoch": 0.5619268081497057,
+      "grad_norm": 1.1020389795303345,
+      "learning_rate": 2.4348628536647623e-05,
+      "loss": 0.327,
+      "step": 31800
     }
   ],
   "logging_steps": 50,