Training in progress, step 21200, checkpoint

last-checkpoint/README.md

@@ -1447,6 +1447,10 @@ You can finetune this model on your own dataset.
 | 0.3693 | 20900 | 0.4061        |
 | 0.3702 | 20950 | 0.3412        |
 | 0.3711 | 21000 | 0.3619        |
+| 0.3720 | 21050 | 0.314         |
+| 0.3729 | 21100 | 0.2912        |
+| 0.3737 | 21150 | 0.3402        |
+| 0.3746 | 21200 | 0.3462        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a3acd9a3207e3da6ba11eed7eb69a0e47965296ed3705edb0291288f4ba6b4
+oid sha256:4eb970c7628ca165b5a062a28ad2708c90ea109132db4b038f4972c1098f4cd3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a2a1c6ca3b664330d252fc223b17bbf693bbca085612f3859c6f296a40edd15
+oid sha256:07ae8bcd2a7dafcb1ceb8e1ef8877981025e7fe727faad70bf73cbc035f46114
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde2d77fb5f8a6059634e011ccb92791a33daebbb2a593b29b9a9f7cf46a0c7a
+oid sha256:741bdb1704d229c73eec48b6812d828a33d2944f4e04e42ed9af5864cb8f4858
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5bb6b386a610284b8662dfd5a6292ebf91e688fce8f9594b479216784ff976a
+oid sha256:eb6b2b89ac841094a59187934ba361ecf73eba3e326ef63976f096359b2648c3
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc1ed1de742b8ceb6a4b045495a5daf14bac6f6cc397bb6df6345b8871c1b3f
+oid sha256:1bb71367724378f66d77db9556efcf84bf028b8330a0ff63dbe88a7a3d8a40e3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3710837412309378,
+  "epoch": 0.37461787209980385,
   "eval_steps": 500,
-  "global_step": 21000,
+  "global_step": 21200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2948,6 +2948,34 @@
       "learning_rate": 3.494728161630441e-05,
       "loss": 0.3619,
       "step": 21000
+    },
+    {
+      "epoch": 0.3719672739481543,
+      "grad_norm": 1.3728086948394775,
+      "learning_rate": 3.4898195597965874e-05,
+      "loss": 0.314,
+      "step": 21050
+    },
+    {
+      "epoch": 0.3728508066653708,
+      "grad_norm": 1.6389710903167725,
+      "learning_rate": 3.4849109579627346e-05,
+      "loss": 0.2912,
+      "step": 21100
+    },
+    {
+      "epoch": 0.3737343393825873,
+      "grad_norm": 3.552582025527954,
+      "learning_rate": 3.4800023561288803e-05,
+      "loss": 0.3402,
+      "step": 21150
+    },
+    {
+      "epoch": 0.37461787209980385,
+      "grad_norm": 1.6479156017303467,
+      "learning_rate": 3.475093754295027e-05,
+      "loss": 0.3462,
+      "step": 21200
     }
   ],
   "logging_steps": 50,