Training in progress, step 35800, checkpoint

last-checkpoint/README.md

@@ -1229,6 +1229,10 @@ You can finetune this model on your own dataset.
 | 0.6273 | 35500 | 0.3418        |
 | 0.6282 | 35550 | 0.3118        |
 | 0.6291 | 35600 | 0.2889        |
+| 0.6300 | 35650 | 0.319         |
+| 0.6308 | 35700 | 0.312         |
+| 0.6317 | 35750 | 0.2776        |
+| 0.6326 | 35800 | 0.2574        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20174b6b2c2d93226ddeb321dbabd4bc1c8af76305e7d7148c8cc355e3d7cd60
+oid sha256:bae377c97d95c091e602ea66921e5e1054c92655fcc87b72a9e144d35f4777b9
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a9d9a1fa3ca8642b4bdf418f1c296a72f8625176479edd5bcdc2533d1bdf26
+oid sha256:53dd7b57f3f8c10ab9b2a35f0933e4ed0758fa2fa30468c3dcc9a374cbfea064
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3288273f695a1df0217fae4938baee576d7a5a6d2a38836aee6bceb6a8de02
+oid sha256:21564110007d55db6f6a52d1c9590217ce427ced36eba0a8dc124d9288a67d6c
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8450c711e1de0810b6e36b835decaee09acd21b4ab25d2432aa749fd8de4d2d4
+oid sha256:2ecaf6e4f08856d634b99dd1969eedbd96a7e22708903309e7e68fda2bacc394
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e3f9784f622226c37c073ce2a64e597153fe7fa7c42f2778e8d0d5f771e26e
+oid sha256:c7083008eae1faaed45dcde0eba354b7d59a06375dff301d884f49f745cc4e30
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6290752946581611,
+  "epoch": 0.6326094255270273,
   "eval_steps": 500,
-  "global_step": 35600,
+  "global_step": 35800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4992,6 +4992,34 @@
       "learning_rate": 2.0620054583652393e-05,
       "loss": 0.2889,
       "step": 35600
+    },
+    {
+      "epoch": 0.6299588273753777,
+      "grad_norm": 1.478084683418274,
+      "learning_rate": 2.0570968565313857e-05,
+      "loss": 0.319,
+      "step": 35650
+    },
+    {
+      "epoch": 0.6308423600925942,
+      "grad_norm": 3.230463743209839,
+      "learning_rate": 2.0521882546975322e-05,
+      "loss": 0.312,
+      "step": 35700
+    },
+    {
+      "epoch": 0.6317258928098107,
+      "grad_norm": 1.2029914855957031,
+      "learning_rate": 2.0472796528636783e-05,
+      "loss": 0.2776,
+      "step": 35750
+    },
+    {
+      "epoch": 0.6326094255270273,
+      "grad_norm": 1.6909867525100708,
+      "learning_rate": 2.0423710510298248e-05,
+      "loss": 0.2574,
+      "step": 35800
     }
   ],
   "logging_steps": 50,