Training in progress, step 53600, checkpoint

last-checkpoint/README.md

@@ -1225,6 +1225,10 @@ You can finetune this model on your own dataset.
 | 0.9418 | 53300 | 0.234         |
 | 0.9427 | 53350 | 0.2244        |
 | 0.9436 | 53400 | 0.2736        |
+| 0.9445 | 53450 | 0.3088        |
+| 0.9454 | 53500 | 0.3135        |
+| 0.9463 | 53550 | 0.2813        |
+| 0.9471 | 53600 | 0.2333        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c1a96a93254cf31ffb70f6814ad348fc844266fcb793b7212c9e8b11daf19d
+oid sha256:46322e2fdae84cb4d149624b40324ba603107423e0ed811b11c103af6014e1e4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b5b98b6da8546e8a7a2cc62e31dd4b93cce07de3e6e6f9ce4ce52ad9cdab9b
+oid sha256:068f22c1d711e17dfced7140337b436095f34a8fa926c1703ed0a4e7970380ec
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca41761b8d788c104936e19f7e170bfd0a6d6a882f10f2b6319094786889629a
+oid sha256:738e43c027de9571a26dc41c2c90188ad15bc024b7fa4548c553209c415b7ff9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe990ada4836e3b8da06b332bb1effcb8ba00456aa80c3ca264f6cde84a1b18
+oid sha256:41033b29e66c9e9264898026bd8259ffc51d8197a6199f012e6c4fab4d2b8853
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b096fb0b9d4b123e0ea98d85fa01bcdb3622620e30def8e03e9a27f4fc9f25b
+oid sha256:225f37a4049625453028403228c6e91c80694c7d0b9a5b2f9a1f983bafdfc1df
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9436129419872418,
+  "epoch": 0.9471470728561079,
   "eval_steps": 500,
-  "global_step": 53400,
+  "global_step": 53600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7484,6 +7484,34 @@
       "learning_rate": 3.1542675384343524e-06,
       "loss": 0.2736,
       "step": 53400
+    },
+    {
+      "epoch": 0.9444964747044583,
+      "grad_norm": 1.7333183288574219,
+      "learning_rate": 3.105181520095816e-06,
+      "loss": 0.3088,
+      "step": 53450
+    },
+    {
+      "epoch": 0.9453800074216748,
+      "grad_norm": 1.5718059539794922,
+      "learning_rate": 3.0560955017572796e-06,
+      "loss": 0.3135,
+      "step": 53500
+    },
+    {
+      "epoch": 0.9462635401388914,
+      "grad_norm": 1.3086848258972168,
+      "learning_rate": 3.007009483418743e-06,
+      "loss": 0.2813,
+      "step": 53550
+    },
+    {
+      "epoch": 0.9471470728561079,
+      "grad_norm": 1.3118650913238525,
+      "learning_rate": 2.9579234650802064e-06,
+      "loss": 0.2333,
+      "step": 53600
     }
   ],
   "logging_steps": 50,