Training in progress, step 22200, checkpoint

last-checkpoint/README.md

@@ -1467,6 +1467,10 @@ You can finetune this model on your own dataset.
 | 0.3870 | 21900 | 0.4425        |
 | 0.3879 | 21950 | 0.3249        |
 | 0.3888 | 22000 | 0.3649        |
+| 0.3896 | 22050 | 0.3621        |
+| 0.3905 | 22100 | 0.4232        |
+| 0.3914 | 22150 | 0.266         |
+| 0.3923 | 22200 | 0.3767        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144309d3cb489609a60ee13d31953ea99ace5b0518b61c42e5c654597d5caf99
+oid sha256:03c8968fca47e48633874837fddb47eb63f3f1f5e2be0fe1b553d5aa0a6701f6
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f2da87398c33f85561f0e89151fe0ca6422c5dce26bb436111403b0957fe886
+oid sha256:1f4f75680b753beac3dd7a2a07e701a0454ccd7703bd9a6386af2d91cda8e1a0
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32b079f3c62b4eff480bfaa645f5db8ea9ea2d2c099e347e5a04d42cb1fede9c
+oid sha256:de7c8f475ae53bd43a56e2cee3897dc4f63fdcbe385245382e65191e77948087
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7674cd4fcfc16ec7b80a741a9302e2d8f22435da4fd303c0cbb13aa05c1489df
+oid sha256:96bcea01a349704fb7ccf988b63e7772fe6dbee601549f7bef592655d9ef9498
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a8067d58d30f3f199792d362e10f473ee7d2bf83e6010350a5fd57fb91e3c4
+oid sha256:ecedb650d6c7c528ffb3f5b6952960cedfd2e3e0172bdfac9efd808168f5cb27
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.38875439557526814,
+  "epoch": 0.3922885264441342,
   "eval_steps": 500,
-  "global_step": 22000,
+  "global_step": 22200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3088,6 +3088,34 @@
       "learning_rate": 3.396556124953368e-05,
       "loss": 0.3649,
       "step": 22000
+    },
+    {
+      "epoch": 0.38963792829248467,
+      "grad_norm": 1.6155461072921753,
+      "learning_rate": 3.391647523119515e-05,
+      "loss": 0.3621,
+      "step": 22050
+    },
+    {
+      "epoch": 0.3905214610097012,
+      "grad_norm": 1.7477047443389893,
+      "learning_rate": 3.386738921285661e-05,
+      "loss": 0.4232,
+      "step": 22100
+    },
+    {
+      "epoch": 0.3914049937269177,
+      "grad_norm": 3.0512797832489014,
+      "learning_rate": 3.3818303194518076e-05,
+      "loss": 0.266,
+      "step": 22150
+    },
+    {
+      "epoch": 0.3922885264441342,
+      "grad_norm": 1.4074236154556274,
+      "learning_rate": 3.376921717617954e-05,
+      "loss": 0.3767,
+      "step": 22200
     }
   ],
   "logging_steps": 50,