Training in progress, step 47400, checkpoint

last-checkpoint/README.md

@@ -1237,6 +1237,10 @@ You can finetune this model on your own dataset.
 | 0.8323 | 47100 | 0.3721        |
 | 0.8332 | 47150 | 0.3483        |
 | 0.8341 | 47200 | 0.3002        |
+| 0.8349 | 47250 | 0.2333        |
+| 0.8358 | 47300 | 0.3043        |
+| 0.8367 | 47350 | 0.2992        |
+| 0.8376 | 47400 | 0.3367        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf1ef32acc663cef4a7b10084a698b74270f6eb741911cc2c19a40d4c0c9fe9
+oid sha256:9fa899c39466858c1bb72384b17719bcb1b30345e9ce76f3b6b83ef15a3594ea
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b8fd1c7342aa7b1f5feea1cd8fd2a3cbc1f9d6821e77a4dc9f2f20c41b62f35
+oid sha256:2193950b0b0024f572dc11e3f6e5765584be0f18471c5c13d65ef36051f2d86c
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdfd2dd2386f51d8558af20986c5a837b3c2dfc1672baa40ef9d7dad6e51ec01
+oid sha256:8eb8dcdd8e8b75fd491010fd65bc9f4650cdec68128bc3f93969648db6824c7d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424edc0ec5b25fea421881d2bc754b25bc2bf24839236dba41579726e027f84d
+oid sha256:f17b09e37e3cf1eb4e07e5a39443f3088190a89ec52eee73b652e920bd5e3c6d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b9442ef8854cff06718d69b0eacec882112fefdafab14f1f997662b135eaff9
+oid sha256:0328ae42c77686bf92831f9769ee36bd90306f1f061a996a4634ff09f38cc121
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8340548850523934,
+  "epoch": 0.8375890159212596,
   "eval_steps": 500,
-  "global_step": 47200,
+  "global_step": 47400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6616,6 +6616,34 @@
       "learning_rate": 9.237988651312562e-06,
       "loss": 0.3002,
       "step": 47200
+    },
+    {
+      "epoch": 0.83493841776961,
+      "grad_norm": 1.0670841932296753,
+      "learning_rate": 9.188902632974023e-06,
+      "loss": 0.2333,
+      "step": 47250
+    },
+    {
+      "epoch": 0.8358219504868265,
+      "grad_norm": 1.9052667617797852,
+      "learning_rate": 9.139816614635488e-06,
+      "loss": 0.3043,
+      "step": 47300
+    },
+    {
+      "epoch": 0.836705483204043,
+      "grad_norm": 2.9311811923980713,
+      "learning_rate": 9.09073059629695e-06,
+      "loss": 0.2992,
+      "step": 47350
+    },
+    {
+      "epoch": 0.8375890159212596,
+      "grad_norm": 1.2520331144332886,
+      "learning_rate": 9.041644577958415e-06,
+      "loss": 0.3367,
+      "step": 47400
     }
   ],
   "logging_steps": 50,