Training in progress, step 55600, checkpoint

last-checkpoint/README.md

@@ -1265,6 +1265,10 @@ You can finetune this model on your own dataset.
 | 0.9772 | 55300 | 0.3787        |
 | 0.9781 | 55350 | 0.3196        |
 | 0.9790 | 55400 | 0.3738        |
+| 0.9798 | 55450 | 0.3588        |
+| 0.9807 | 55500 | 0.3559        |
+| 0.9816 | 55550 | 0.4382        |
+| 0.9825 | 55600 | 0.2588        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e0a1455740180aedb80f8bb0aec516cb7153da241701244132cb399617a794
+oid sha256:4757af97769f9bf496f79482c67b4ad52305ab54793692a8f0992bfb1b3e1d99
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a83cdaa07d04d231b900b829ca00bf94bbd812391baa3af8be0f339dc5c09a
+oid sha256:bc0ad85e5b5865c2909f3ef475b6781df3d6695ce915b04da508edcabe1e676c
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c32e0fe828ffd94931d917ede7d98af8f116069bcef2571793c504c5a05f607
+oid sha256:53cd51ebdd8de8dece2e081300401e55897bd6527506b231b719e81675496d96
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380ffdc8abce86595967f2c6febf85c303c1ae3d84e66897af982ed22c990884
+oid sha256:9cadf5e13e62099775fee57e6f6e29864a5e8da9a1f19033bf424bca204d48d8
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d3a94240ec5e377beed092b82635ec739c5c48243fbb51753d92a8d8f55ac7
+oid sha256:40c3ccdbd565485480694df123a18cb3bc6089aca7ac0b1c3670702db7f9e007
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9789542506759026,
+  "epoch": 0.9824883815447686,
   "eval_steps": 500,
-  "global_step": 55400,
+  "global_step": 55600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7764,6 +7764,34 @@
       "learning_rate": 1.191808525259665e-06,
       "loss": 0.3738,
       "step": 55400
+    },
+    {
+      "epoch": 0.979837783393119,
+      "grad_norm": 1.5018582344055176,
+      "learning_rate": 1.1427225069211286e-06,
+      "loss": 0.3588,
+      "step": 55450
+    },
+    {
+      "epoch": 0.9807213161103355,
+      "grad_norm": 1.1979721784591675,
+      "learning_rate": 1.0936364885825922e-06,
+      "loss": 0.3559,
+      "step": 55500
+    },
+    {
+      "epoch": 0.9816048488275521,
+      "grad_norm": 3.014507532119751,
+      "learning_rate": 1.0445504702440556e-06,
+      "loss": 0.4382,
+      "step": 55550
+    },
+    {
+      "epoch": 0.9824883815447686,
+      "grad_norm": 1.5364562273025513,
+      "learning_rate": 9.954644519055192e-07,
+      "loss": 0.2588,
+      "step": 55600
     }
   ],
   "logging_steps": 50,