Training in progress, step 55000, checkpoint

last-checkpoint/README.md

@@ -1253,6 +1253,10 @@ You can finetune this model on your own dataset.
 | 0.9666 | 54700 | 0.2484        |
 | 0.9675 | 54750 | 0.3228        |
 | 0.9684 | 54800 | 0.2935        |
+| 0.9692 | 54850 | 0.3085        |
+| 0.9701 | 54900 | 0.3112        |
+| 0.9710 | 54950 | 0.2889        |
+| 0.9719 | 55000 | 0.2746        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4660d5cc04b8230e366c2507b6edc6eb9740e5655f078f06d7fa8b708868348d
+oid sha256:b7de782f93f57348bf850bc04f35cc7f6059cfdc1487661cd5cf4f11ce0e636f
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7ddc79258480305b86c7de987bf66efad05525fb132f3c4537096562844858a
+oid sha256:8dc1a5e4533471281ab4208b72f4dd16330451bdcbc3512cd1466d1a94c0279b
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe80331ddc64a10f3922d2d2aa6e1345a324e582ebfcde4acd33dd3c01a97f23
+oid sha256:035838ab30ab4d07fb2aaaa81eb5cd5230f5b5f92e211ace87a3143ca1c3c17c
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a394d9ef4969559c2e748a44250c8baede91e41491cb79bd3a87fcd799d229f
+oid sha256:0d88e34fed71326e402519391fc702de0ba4ca1011f3b15e76161c4e72df1f1c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175e278f8a42116e02058ec0c5ec6fdf92f24c652abe7967b071b8b6350190f1
+oid sha256:73e5c254a90680845431aa779809105481c9b9fb095d05b8d7eb9127bf1f4c4d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9683518580693043,
+  "epoch": 0.9718859889381704,
   "eval_steps": 500,
-  "global_step": 54800,
+  "global_step": 55000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7680,6 +7680,34 @@
       "learning_rate": 1.779859024955332e-06,
       "loss": 0.2935,
       "step": 54800
+    },
+    {
+      "epoch": 0.9692353907865209,
+      "grad_norm": 1.5993742942810059,
+      "learning_rate": 1.7307730066167953e-06,
+      "loss": 0.3085,
+      "step": 54850
+    },
+    {
+      "epoch": 0.9701189235037373,
+      "grad_norm": 4.223308086395264,
+      "learning_rate": 1.681686988278259e-06,
+      "loss": 0.3112,
+      "step": 54900
+    },
+    {
+      "epoch": 0.9710024562209538,
+      "grad_norm": 1.7939913272857666,
+      "learning_rate": 1.6326009699397223e-06,
+      "loss": 0.2889,
+      "step": 54950
+    },
+    {
+      "epoch": 0.9718859889381704,
+      "grad_norm": 1.1405465602874756,
+      "learning_rate": 1.583514951601186e-06,
+      "loss": 0.2746,
+      "step": 55000
     }
   ],
   "logging_steps": 50,