Training in progress, step 10400, checkpoint

last-checkpoint/README.md

@@ -1229,6 +1229,10 @@ You can finetune this model on your own dataset.
 | 0.1785 | 10100 | 0.4422        |
 | 0.1794 | 10150 | 0.3747        |
 | 0.1802 | 10200 | 0.3989        |
+| 0.1811 | 10250 | 0.5315        |
+| 0.1820 | 10300 | 0.3565        |
+| 0.1829 | 10350 | 0.4409        |
+| 0.1838 | 10400 | 0.3762        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1113f1dc63b4ef74f5c024aa4257a74f5c601162a5392123b472bd440c772d
+oid sha256:e173a418a6557a53411f35be06de499d8fc58209e23cd022b66875c6fc5b0ae3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372cd21ba6640c7fb2d1ef5b71e6d5270fa8bff460e3c646226db5c68492b951
+oid sha256:35f9ee877e3fc6c79f0984700034054c52886bebbe530aecf764a3bd0fec0227
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11b6cb074bbe2129c4a92512f6b7604d9e93435cd6ffac4a406363aba2e66f67
+oid sha256:f7e3c346ce1d7e857e6a391133332aa5169f5fc12741629168a0c8fad4aa8ade
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8373615cf09b792af1b9fd441a341b87607a411c0918e8ae083ffab9de6dcc10
+oid sha256:8dcdfe9f3f1d3b35aba345a67f9e5702ec3b3998d6ddccfa8925c3c66df7986e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c8231fde4f806f412947f64ac786f123198ace358add629069cb5de99c1e42
+oid sha256:1ba07f8b635a7f5cbd77a454bf0384278026397ef33c00d176608de8376e15fc
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18024067431216978,
+  "epoch": 0.18377480518103587,
   "eval_steps": 500,
-  "global_step": 10200,
+  "global_step": 10400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1436,6 +1436,34 @@
       "learning_rate": 4.5543971255227666e-05,
       "loss": 0.3989,
       "step": 10200
+    },
+    {
+      "epoch": 0.1811242070293863,
+      "grad_norm": 1.464385747909546,
+      "learning_rate": 4.549488523688913e-05,
+      "loss": 0.5315,
+      "step": 10250
+    },
+    {
+      "epoch": 0.1820077397466028,
+      "grad_norm": 1.2073971033096313,
+      "learning_rate": 4.544579921855059e-05,
+      "loss": 0.3565,
+      "step": 10300
+    },
+    {
+      "epoch": 0.18289127246381934,
+      "grad_norm": 1.1773017644882202,
+      "learning_rate": 4.5396713200212054e-05,
+      "loss": 0.4409,
+      "step": 10350
+    },
+    {
+      "epoch": 0.18377480518103587,
+      "grad_norm": 2.4389290809631348,
+      "learning_rate": 4.534762718187352e-05,
+      "loss": 0.3762,
+      "step": 10400
     }
   ],
   "logging_steps": 50,