Training in progress, step 35600, checkpoint

last-checkpoint/README.md

@@ -1225,6 +1225,10 @@ You can finetune this model on your own dataset.
 | 0.6238 | 35300 | 0.3355        |
 | 0.6247 | 35350 | 0.3626        |
 | 0.6255 | 35400 | 0.2542        |
+| 0.6264 | 35450 | 0.2555        |
+| 0.6273 | 35500 | 0.3418        |
+| 0.6282 | 35550 | 0.3118        |
+| 0.6291 | 35600 | 0.2889        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49e95dbcbd79f97ce1ba67a803455e357f6c9c9ea644273cb7511cae3c831b9d
+oid sha256:20174b6b2c2d93226ddeb321dbabd4bc1c8af76305e7d7148c8cc355e3d7cd60
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29767797f5949aa103f2386e6b46cf5006f18f6853e49108146824052452a81a
+oid sha256:c5a9d9a1fa3ca8642b4bdf418f1c296a72f8625176479edd5bcdc2533d1bdf26
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea4a8e4afcda31bb844cc13d2627fa89d98644359cf49b2f2f2f5fdbb6dbb81
+oid sha256:6f3288273f695a1df0217fae4938baee576d7a5a6d2a38836aee6bceb6a8de02
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c2fca16cf2e15838c5424c974921bcfa3346a7bf4c2458c8ecc9892726ed4c
+oid sha256:8450c711e1de0810b6e36b835decaee09acd21b4ab25d2432aa749fd8de4d2d4
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab93b747e0fc75060bb6e7ff7bdc607ad6b06fa8d1c145ad4ab8d80aeeb37b40
+oid sha256:41e3f9784f622226c37c073ce2a64e597153fe7fa7c42f2778e8d0d5f771e26e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6255411637892951,
+  "epoch": 0.6290752946581611,
   "eval_steps": 500,
-  "global_step": 35400,
+  "global_step": 35600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4964,6 +4964,34 @@
       "learning_rate": 2.0816398657006537e-05,
       "loss": 0.2542,
       "step": 35400
+    },
+    {
+      "epoch": 0.6264246965065117,
+      "grad_norm": 1.4315252304077148,
+      "learning_rate": 2.0767312638668002e-05,
+      "loss": 0.2555,
+      "step": 35450
+    },
+    {
+      "epoch": 0.6273082292237282,
+      "grad_norm": 2.861154079437256,
+      "learning_rate": 2.0718226620329467e-05,
+      "loss": 0.3418,
+      "step": 35500
+    },
+    {
+      "epoch": 0.6281917619409447,
+      "grad_norm": 1.378416895866394,
+      "learning_rate": 2.066914060199093e-05,
+      "loss": 0.3118,
+      "step": 35550
+    },
+    {
+      "epoch": 0.6290752946581611,
+      "grad_norm": 4.129642486572266,
+      "learning_rate": 2.0620054583652393e-05,
+      "loss": 0.2889,
+      "step": 35600
     }
   ],
   "logging_steps": 50,