Training in progress, step 21000, checkpoint

last-checkpoint/README.md

@@ -1443,6 +1443,10 @@ You can finetune this model on your own dataset.
 | 0.3658 | 20700 | 0.35          |
 | 0.3667 | 20750 | 0.3241        |
 | 0.3675 | 20800 | 0.37          |
+| 0.3684 | 20850 | 0.2689        |
+| 0.3693 | 20900 | 0.4061        |
+| 0.3702 | 20950 | 0.3412        |
+| 0.3711 | 21000 | 0.3619        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d579b6d5d93397921c89359b1645f6d237af8feaabf2808aa442f559f31fb4c0
+oid sha256:60a3acd9a3207e3da6ba11eed7eb69a0e47965296ed3705edb0291288f4ba6b4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674bd0a4229124de80961bd58f8a6981f214653c5975a0453bb6e383c35d6ff5
+oid sha256:5a2a1c6ca3b664330d252fc223b17bbf693bbca085612f3859c6f296a40edd15
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ea8f06d7607dd2ef63e1d5df423f0e12babf973592667a187334f294342238
+oid sha256:dde2d77fb5f8a6059634e011ccb92791a33daebbb2a593b29b9a9f7cf46a0c7a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95c7d02cae67a959a1e26802dda7eb773b84117a34d7a400f3d47ccf620db34
+oid sha256:b5bb6b386a610284b8662dfd5a6292ebf91e688fce8f9594b479216784ff976a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d533c21f945b003e7696031dabbdd090fa025b8305d207ee0a2aeeea78458b1
+oid sha256:8bc1ed1de742b8ceb6a4b045495a5daf14bac6f6cc397bb6df6345b8871c1b3f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36754961036207173,
+  "epoch": 0.3710837412309378,
   "eval_steps": 500,
-  "global_step": 20800,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2920,6 +2920,34 @@
       "learning_rate": 3.514264396929179e-05,
       "loss": 0.37,
       "step": 20800
+    },
+    {
+      "epoch": 0.3684331430792882,
+      "grad_norm": 1.5556259155273438,
+      "learning_rate": 3.509355795095325e-05,
+      "loss": 0.2689,
+      "step": 20850
+    },
+    {
+      "epoch": 0.36931667579650473,
+      "grad_norm": 1.6530933380126953,
+      "learning_rate": 3.504447193261472e-05,
+      "loss": 0.4061,
+      "step": 20900
+    },
+    {
+      "epoch": 0.37020020851372126,
+      "grad_norm": 1.250317931175232,
+      "learning_rate": 3.499538591427618e-05,
+      "loss": 0.3412,
+      "step": 20950
+    },
+    {
+      "epoch": 0.3710837412309378,
+      "grad_norm": 1.9599151611328125,
+      "learning_rate": 3.494728161630441e-05,
+      "loss": 0.3619,
+      "step": 21000
     }
   ],
   "logging_steps": 50,