Training in progress, step 55200, checkpoint

last-checkpoint/README.md

@@ -1257,6 +1257,10 @@ You can finetune this model on your own dataset.
 | 0.9701 | 54900 | 0.3112        |
 | 0.9710 | 54950 | 0.2889        |
 | 0.9719 | 55000 | 0.2746        |
+| 0.9728 | 55050 | 0.2772        |
+| 0.9737 | 55100 | 0.2965        |
+| 0.9745 | 55150 | 0.2382        |
+| 0.9754 | 55200 | 0.3863        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7de782f93f57348bf850bc04f35cc7f6059cfdc1487661cd5cf4f11ce0e636f
+oid sha256:84dfa838d5d08ff2f7ba730d306c0960dd6da737376547d2bfca93e1966bc1dd
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc1a5e4533471281ab4208b72f4dd16330451bdcbc3512cd1466d1a94c0279b
+oid sha256:014ea2c017260d23539bf2018a3aeecb9f09815bf6c03db5f9a232664f2814fd
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:035838ab30ab4d07fb2aaaa81eb5cd5230f5b5f92e211ace87a3143ca1c3c17c
+oid sha256:74c101267c3a81601197ccbb38d2e72ad72f0ccd27fd0e0454beeffecf5ebfa6
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d88e34fed71326e402519391fc702de0ba4ca1011f3b15e76161c4e72df1f1c
+oid sha256:9d0369b7df9f4f6057f54d12203a572c70823bfca8ac268e71fe1a019e47a330
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e5c254a90680845431aa779809105481c9b9fb095d05b8d7eb9127bf1f4c4d
+oid sha256:f7a98fbd51768bffd64a896f3250670354d9f2cc8cf54c04f0d410e34f028552
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9718859889381704,
+  "epoch": 0.9754201198070365,
   "eval_steps": 500,
-  "global_step": 55000,
+  "global_step": 55200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7708,6 +7708,34 @@
       "learning_rate": 1.583514951601186e-06,
       "loss": 0.2746,
       "step": 55000
+    },
+    {
+      "epoch": 0.9727695216553869,
+      "grad_norm": 1.8150931596755981,
+      "learning_rate": 1.5344289332626496e-06,
+      "loss": 0.2772,
+      "step": 55050
+    },
+    {
+      "epoch": 0.9736530543726034,
+      "grad_norm": 1.4807177782058716,
+      "learning_rate": 1.485342914924113e-06,
+      "loss": 0.2965,
+      "step": 55100
+    },
+    {
+      "epoch": 0.9745365870898199,
+      "grad_norm": 1.4012283086776733,
+      "learning_rate": 1.4362568965855766e-06,
+      "loss": 0.2382,
+      "step": 55150
+    },
+    {
+      "epoch": 0.9754201198070365,
+      "grad_norm": 1.435829520225525,
+      "learning_rate": 1.388152598613811e-06,
+      "loss": 0.3863,
+      "step": 55200
     }
   ],
   "logging_steps": 50,