Training in progress, step 32000, checkpoint

last-checkpoint/README.md

@@ -1299,6 +1299,10 @@ You can finetune this model on your own dataset.
 | 0.5602 | 31700 | 0.3578        |
 | 0.5610 | 31750 | 0.3193        |
 | 0.5619 | 31800 | 0.327         |
+| 0.5628 | 31850 | 0.3429        |
+| 0.5637 | 31900 | 0.2994        |
+| 0.5646 | 31950 | 0.3219        |
+| 0.5655 | 32000 | 0.2902        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aefeca268258dbfb0695a5597c522e31aac7733474d6d58a376815037205ed7
+oid sha256:cea8950aa6683070e22c1a564e52123795831f72f71fb839c14d7de92ee17a17
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a1ec12177bf3e7a3bcf0d2304d2b35cf56ea3e8b41cc3e1af93291a40fc7ca
+oid sha256:4ac2571e8a99f96a6e948efc2acbf6f064d1c41ef24c68243b8bfa9248b61bef
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d21026606b47fb76259886267bb47d18484b5815e94d5a5656506546687ec739
+oid sha256:ea96a97725aec5e3c937ef8955386071fe1d87cf2432c4445ce113e85618ebef
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3efc050901e150a59e85c2ab742c4d82ce79ba854a2e4dcd71f14091e10af7e2
+oid sha256:b78f9ce48aa6920e09eb307b60e2b49742b779f95ad33075f31c6652ec108e55
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ef76f1bbf004f2132ce3725824bf2705832e8a1ea3351be51debbf13b28b7d
+oid sha256:a6de4d7315ff5e38fd38a2be7f1976197684b731feeef6561c2bf9fe182bd3b1
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5619268081497057,
+  "epoch": 0.5654609390185719,
   "eval_steps": 500,
-  "global_step": 31800,
+  "global_step": 32000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4460,6 +4460,34 @@
       "learning_rate": 2.4348628536647623e-05,
       "loss": 0.327,
       "step": 31800
+    },
+    {
+      "epoch": 0.5628103408669223,
+      "grad_norm": 1.445654034614563,
+      "learning_rate": 2.4299542518309084e-05,
+      "loss": 0.3429,
+      "step": 31850
+    },
+    {
+      "epoch": 0.5636938735841388,
+      "grad_norm": 1.3795325756072998,
+      "learning_rate": 2.425045649997055e-05,
+      "loss": 0.2994,
+      "step": 31900
+    },
+    {
+      "epoch": 0.5645774063013553,
+      "grad_norm": 1.7217411994934082,
+      "learning_rate": 2.4201370481632014e-05,
+      "loss": 0.3219,
+      "step": 31950
+    },
+    {
+      "epoch": 0.5654609390185719,
+      "grad_norm": 1.3482351303100586,
+      "learning_rate": 2.4152284463293475e-05,
+      "loss": 0.2902,
+      "step": 32000
     }
   ],
   "logging_steps": 50,