Training in progress, step 55400, checkpoint

last-checkpoint/README.md

@@ -1261,6 +1261,10 @@ You can finetune this model on your own dataset.
 | 0.9737 | 55100 | 0.2965        |
 | 0.9745 | 55150 | 0.2382        |
 | 0.9754 | 55200 | 0.3863        |
+| 0.9763 | 55250 | 0.2909        |
+| 0.9772 | 55300 | 0.3787        |
+| 0.9781 | 55350 | 0.3196        |
+| 0.9790 | 55400 | 0.3738        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84dfa838d5d08ff2f7ba730d306c0960dd6da737376547d2bfca93e1966bc1dd
+oid sha256:e7e0a1455740180aedb80f8bb0aec516cb7153da241701244132cb399617a794
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014ea2c017260d23539bf2018a3aeecb9f09815bf6c03db5f9a232664f2814fd
+oid sha256:f3a83cdaa07d04d231b900b829ca00bf94bbd812391baa3af8be0f339dc5c09a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c101267c3a81601197ccbb38d2e72ad72f0ccd27fd0e0454beeffecf5ebfa6
+oid sha256:7c32e0fe828ffd94931d917ede7d98af8f116069bcef2571793c504c5a05f607
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0369b7df9f4f6057f54d12203a572c70823bfca8ac268e71fe1a019e47a330
+oid sha256:380ffdc8abce86595967f2c6febf85c303c1ae3d84e66897af982ed22c990884
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a98fbd51768bffd64a896f3250670354d9f2cc8cf54c04f0d410e34f028552
+oid sha256:67d3a94240ec5e377beed092b82635ec739c5c48243fbb51753d92a8d8f55ac7
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9754201198070365,
+  "epoch": 0.9789542506759026,
   "eval_steps": 500,
-  "global_step": 55200,
+  "global_step": 55400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7736,6 +7736,34 @@
       "learning_rate": 1.388152598613811e-06,
       "loss": 0.3863,
       "step": 55200
+    },
+    {
+      "epoch": 0.976303652524253,
+      "grad_norm": 1.0731230974197388,
+      "learning_rate": 1.3390665802752744e-06,
+      "loss": 0.2909,
+      "step": 55250
+    },
+    {
+      "epoch": 0.9771871852414695,
+      "grad_norm": 1.6253186464309692,
+      "learning_rate": 1.289980561936738e-06,
+      "loss": 0.3787,
+      "step": 55300
+    },
+    {
+      "epoch": 0.978070717958686,
+      "grad_norm": 1.9667285680770874,
+      "learning_rate": 1.2408945435982016e-06,
+      "loss": 0.3196,
+      "step": 55350
+    },
+    {
+      "epoch": 0.9789542506759026,
+      "grad_norm": 1.1798194646835327,
+      "learning_rate": 1.191808525259665e-06,
+      "loss": 0.3738,
+      "step": 55400
     }
   ],
   "logging_steps": 50,