Training in progress, step 16600, checkpoint

last-checkpoint/README.md

@@ -1355,6 +1355,10 @@ You can finetune this model on your own dataset.
 | 0.2880 | 16300 | 0.3508        |
 | 0.2889 | 16350 | 0.3443        |
 | 0.2898 | 16400 | 0.4346        |
+| 0.2907 | 16450 | 0.4262        |
+| 0.2916 | 16500 | 0.3065        |
+| 0.2924 | 16550 | 0.4003        |
+| 0.2933 | 16600 | 0.5295        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72204e50bc6a729a9530dbec2c2b7b58645a458ae9d80bb5e58884f5987fcb41
+oid sha256:bdc8b58e69308ebfbfc0eb50f8d94cc9702cadcdc42e3254287236a6a1b09a4e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb1ec3cd79155004f27b637dbdf8248d31df7a7e6b9271ef520a45273a071c7
+oid sha256:705df85026bb51643b710bf960103e3bb1661185afb2f1e06a383d34dc56e4bf
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0290ac5f04e55c88614a5fc8876370d93a593987208fcc581fc642918b1da8ba
+oid sha256:f891a9e7af458bc02af6e87abb160c7f8d056d1f22f1437aa987e99557c38c6d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9ee0ff1940dd91113eeb7613899018df3dbdd59112c1db2a4ee540aa7411d1
+oid sha256:3ec9685408ff856249d18165c59f9d1d95d1e000415171f3550ac55d011d4b84
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d25210b544040bb154d351b7b54b39ff9c98281c0d9fc772c1d1b0a64f1f30f6
+oid sha256:4750d7049889a8742682de7ab1e907cdb0b4e5ab032bf6b9deca530e9913b39d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2897987312470181,
+  "epoch": 0.29333286211588416,
   "eval_steps": 500,
-  "global_step": 16400,
+  "global_step": 16600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2304,6 +2304,34 @@
       "learning_rate": 3.946025014234945e-05,
       "loss": 0.4346,
       "step": 16400
+    },
+    {
+      "epoch": 0.2906822639642346,
+      "grad_norm": 1.9500783681869507,
+      "learning_rate": 3.941116412401092e-05,
+      "loss": 0.4262,
+      "step": 16450
+    },
+    {
+      "epoch": 0.2915657966814511,
+      "grad_norm": 1.344519853591919,
+      "learning_rate": 3.936207810567238e-05,
+      "loss": 0.3065,
+      "step": 16500
+    },
+    {
+      "epoch": 0.29244932939866763,
+      "grad_norm": 1.4747456312179565,
+      "learning_rate": 3.9312992087333846e-05,
+      "loss": 0.4003,
+      "step": 16550
+    },
+    {
+      "epoch": 0.29333286211588416,
+      "grad_norm": 1.5639158487319946,
+      "learning_rate": 3.926390606899531e-05,
+      "loss": 0.5295,
+      "step": 16600
     }
   ],
   "logging_steps": 50,