Training in progress, step 47200, checkpoint

last-checkpoint/README.md

@@ -1233,6 +1233,10 @@ You can finetune this model on your own dataset.
 | 0.8288 | 46900 | 0.2756        |
 | 0.8296 | 46950 | 0.3345        |
 | 0.8305 | 47000 | 0.3016        |
+| 0.8314 | 47050 | 0.2712        |
+| 0.8323 | 47100 | 0.3721        |
+| 0.8332 | 47150 | 0.3483        |
+| 0.8341 | 47200 | 0.3002        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d215026fb98a4e80219f1300f712038cf2fa723f5168816bc64b2547a49bce2f
+oid sha256:cbf1ef32acc663cef4a7b10084a698b74270f6eb741911cc2c19a40d4c0c9fe9
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ceee43905dfe8e32b48bcbafa4954b114ed3adec82f09a2cc6c7e47d869d1b
+oid sha256:7b8fd1c7342aa7b1f5feea1cd8fd2a3cbc1f9d6821e77a4dc9f2f20c41b62f35
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370edc95f3ec87693c2f5c1d97900af678cc360f41a849a73def6dbfd862bd18
+oid sha256:cdfd2dd2386f51d8558af20986c5a837b3c2dfc1672baa40ef9d7dad6e51ec01
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5927361a532fb6c132d07b4ab7a520caf5f685a6698e2682d0ac3b35fea7ca5e
+oid sha256:424edc0ec5b25fea421881d2bc754b25bc2bf24839236dba41579726e027f84d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9635610518cbf3041eab5001840676a9398dea515bdb1588a50299a67cadbe
+oid sha256:2b9442ef8854cff06718d69b0eacec882112fefdafab14f1f997662b135eaff9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8305207541835274,
+  "epoch": 0.8340548850523934,
   "eval_steps": 500,
-  "global_step": 47000,
+  "global_step": 47200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6588,6 +6588,34 @@
       "learning_rate": 9.434332724666705e-06,
       "loss": 0.3016,
       "step": 47000
+    },
+    {
+      "epoch": 0.831404286900744,
+      "grad_norm": 2.7783117294311523,
+      "learning_rate": 9.38524670632817e-06,
+      "loss": 0.2712,
+      "step": 47050
+    },
+    {
+      "epoch": 0.8322878196179605,
+      "grad_norm": 4.626585483551025,
+      "learning_rate": 9.336160687989634e-06,
+      "loss": 0.3721,
+      "step": 47100
+    },
+    {
+      "epoch": 0.8331713523351769,
+      "grad_norm": 1.097589135169983,
+      "learning_rate": 9.287074669651097e-06,
+      "loss": 0.3483,
+      "step": 47150
+    },
+    {
+      "epoch": 0.8340548850523934,
+      "grad_norm": 1.6428859233856201,
+      "learning_rate": 9.237988651312562e-06,
+      "loss": 0.3002,
+      "step": 47200
     }
   ],
   "logging_steps": 50,