Training in progress, step 47000, checkpoint

last-checkpoint/README.md

@@ -1229,6 +1229,10 @@ You can finetune this model on your own dataset.
 | 0.8252 | 46700 | 0.2965        |
 | 0.8261 | 46750 | 0.2506        |
 | 0.8270 | 46800 | 0.2258        |
+| 0.8279 | 46850 | 0.2209        |
+| 0.8288 | 46900 | 0.2756        |
+| 0.8296 | 46950 | 0.3345        |
+| 0.8305 | 47000 | 0.3016        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c3f18fa41ad103d30f8534ab7132db4ee0061b54edf40285b4af72b13eb56f
+oid sha256:d215026fb98a4e80219f1300f712038cf2fa723f5168816bc64b2547a49bce2f
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd6c1d98fe362a0c2eb43d38b5cdf5892278019bdee6a0ede5aba69437e6bc1
+oid sha256:10ceee43905dfe8e32b48bcbafa4954b114ed3adec82f09a2cc6c7e47d869d1b
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc474fa5fa7ccd3f751905ccba31cf8241a798bcffde04ca50c28aabfb2c8fc4
+oid sha256:370edc95f3ec87693c2f5c1d97900af678cc360f41a849a73def6dbfd862bd18
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f4d5223b0e67d5c0eb5511f7b2157df3119d42796d741c478e1b9dd9b2daa03
+oid sha256:5927361a532fb6c132d07b4ab7a520caf5f685a6698e2682d0ac3b35fea7ca5e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb3a6b85091a07e122d9b08dbed39a677740be0c318acc9f799b2491273dc34
+oid sha256:4d9635610518cbf3041eab5001840676a9398dea515bdb1588a50299a67cadbe
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8269866233146613,
+  "epoch": 0.8305207541835274,
   "eval_steps": 500,
-  "global_step": 46800,
+  "global_step": 47000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6560,6 +6560,34 @@
       "learning_rate": 9.629695077654082e-06,
       "loss": 0.2258,
       "step": 46800
+    },
+    {
+      "epoch": 0.8278701560318779,
+      "grad_norm": 1.71811842918396,
+      "learning_rate": 9.580609059315546e-06,
+      "loss": 0.2209,
+      "step": 46850
+    },
+    {
+      "epoch": 0.8287536887490944,
+      "grad_norm": 3.2347002029418945,
+      "learning_rate": 9.53152304097701e-06,
+      "loss": 0.2756,
+      "step": 46900
+    },
+    {
+      "epoch": 0.8296372214663109,
+      "grad_norm": 2.865858554840088,
+      "learning_rate": 9.483418743005244e-06,
+      "loss": 0.3345,
+      "step": 46950
+    },
+    {
+      "epoch": 0.8305207541835274,
+      "grad_norm": 1.4720476865768433,
+      "learning_rate": 9.434332724666705e-06,
+      "loss": 0.3016,
+      "step": 47000
     }
   ],
   "logging_steps": 50,