Training in progress, step 11600, checkpoint

last-checkpoint/README.md

@@ -1253,6 +1253,10 @@ You can finetune this model on your own dataset.
 | 0.1997 | 11300 | 0.3883        |
 | 0.2006 | 11350 | 0.3312        |
 | 0.2014 | 11400 | 0.4888        |
+| 0.2023 | 11450 | 0.5102        |
+| 0.2032 | 11500 | 0.4133        |
+| 0.2041 | 11550 | 0.4255        |
+| 0.2050 | 11600 | 0.3766        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0251d55d19012022b3471da785a65a2bc6f56faf0f41cb8aec5fee968199572e
+oid sha256:3ffbfcafcc9fe0626ad95a757161650ebd608dc792a3be66dc280648638250c0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:528621d7ef01154800460a8cccb1fb80bff45f808fc6990cc94b2503052d3ae3
+oid sha256:54acb4c4ed26eb791b88eae901790e10103feef91580aec05ddfaf448cbfd85f
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ccafbbd3f23088187d3f39081089feeb9cb03fb0fae7e1ed1996a1e0cdc7f7
+oid sha256:30da9f4d62258aeaf62aeb9ec9e5016819eb36a85d257e4973896ca659746a7b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a99e201ecedb03053afb6fbd1f38ffbe8b22238d6484e117d413c9c1ea3a69
+oid sha256:af444b90e8c6af59e605b8e6c36eed3028670ac5414ccb3c62069b581f1e100f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18eafe3970ca850979514a20be184f0f34883513f106b08256d4a503712c8ab0
+oid sha256:106144745ca94d3699bc51480a1ded383a9cde9abbc3f32cdef1f9281aa6d035
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20144545952536622,
+  "epoch": 0.2049795903942323,
   "eval_steps": 500,
-  "global_step": 11400,
+  "global_step": 11600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1604,6 +1604,34 @@
       "learning_rate": 4.436688853546956e-05,
       "loss": 0.4888,
       "step": 11400
+    },
+    {
+      "epoch": 0.20232899224258274,
+      "grad_norm": 2.010566473007202,
+      "learning_rate": 4.4317802517131026e-05,
+      "loss": 0.5102,
+      "step": 11450
+    },
+    {
+      "epoch": 0.20321252495979927,
+      "grad_norm": 2.093271493911743,
+      "learning_rate": 4.4268716498792484e-05,
+      "loss": 0.4133,
+      "step": 11500
+    },
+    {
+      "epoch": 0.20409605767701577,
+      "grad_norm": 1.9231561422348022,
+      "learning_rate": 4.421963048045395e-05,
+      "loss": 0.4255,
+      "step": 11550
+    },
+    {
+      "epoch": 0.2049795903942323,
+      "grad_norm": 1.561781644821167,
+      "learning_rate": 4.417054446211541e-05,
+      "loss": 0.3766,
+      "step": 11600
     }
   ],
   "logging_steps": 50,