Training in progress, step 22000, checkpoint

last-checkpoint/README.md

@@ -1463,6 +1463,10 @@ You can finetune this model on your own dataset.
 | 0.3835 | 21700 | 0.3556        |
 | 0.3843 | 21750 | 0.2877        |
 | 0.3852 | 21800 | 0.3203        |
+| 0.3861 | 21850 | 0.2553        |
+| 0.3870 | 21900 | 0.4425        |
+| 0.3879 | 21950 | 0.3249        |
+| 0.3888 | 22000 | 0.3649        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71536271e303b359bc8885941a3b51c93842494cf3d4dd02a6e2f6ca81dff99c
+oid sha256:144309d3cb489609a60ee13d31953ea99ace5b0518b61c42e5c654597d5caf99
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f26a81bbdd86a74215227f787a393193d8868c1c4b4f7123d8f3e9f866ce49
+oid sha256:5f2da87398c33f85561f0e89151fe0ca6422c5dce26bb436111403b0957fe886
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c3344300d9b776b16db056048b915b6ad2ce1e2919d2dcc21729cfbaff84521
+oid sha256:32b079f3c62b4eff480bfaa645f5db8ea9ea2d2c099e347e5a04d42cb1fede9c
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:512e3b81dd92786746b027cf126ada5052ba205d7c4f2693485fe5d762f3208f
+oid sha256:7674cd4fcfc16ec7b80a741a9302e2d8f22435da4fd303c0cbb13aa05c1489df
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c93e9773694165737861e364ae6ffe7000e5f2e5bc790ae63fee35e5d02bb7
+oid sha256:a5a8067d58d30f3f199792d362e10f473ee7d2bf83e6010350a5fd57fb91e3c4
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3852202647064021,
+  "epoch": 0.38875439557526814,
   "eval_steps": 500,
-  "global_step": 21800,
+  "global_step": 22000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3060,6 +3060,34 @@
       "learning_rate": 3.416190532288783e-05,
       "loss": 0.3203,
       "step": 21800
+    },
+    {
+      "epoch": 0.3861037974236186,
+      "grad_norm": 1.1625959873199463,
+      "learning_rate": 3.4112819304549295e-05,
+      "loss": 0.2553,
+      "step": 21850
+    },
+    {
+      "epoch": 0.38698733014083514,
+      "grad_norm": 1.5695985555648804,
+      "learning_rate": 3.406373328621076e-05,
+      "loss": 0.4425,
+      "step": 21900
+    },
+    {
+      "epoch": 0.3878708628580516,
+      "grad_norm": 1.6758594512939453,
+      "learning_rate": 3.401464726787222e-05,
+      "loss": 0.3249,
+      "step": 21950
+    },
+    {
+      "epoch": 0.38875439557526814,
+      "grad_norm": 3.6129748821258545,
+      "learning_rate": 3.396556124953368e-05,
+      "loss": 0.3649,
+      "step": 22000
     }
   ],
   "logging_steps": 50,