Training in progress, step 16400, checkpoint

last-checkpoint/README.md

@@ -1351,6 +1351,10 @@ You can finetune this model on your own dataset.
 | 0.2845 | 16100 | 0.3489        |
 | 0.2854 | 16150 | 0.4209        |
 | 0.2863 | 16200 | 0.2984        |
+| 0.2871 | 16250 | 0.3877        |
+| 0.2880 | 16300 | 0.3508        |
+| 0.2889 | 16350 | 0.3443        |
+| 0.2898 | 16400 | 0.4346        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d75f43e43417714c9eb673b4140e3bc3180d809cd3703e268b196479d4e674
+oid sha256:72204e50bc6a729a9530dbec2c2b7b58645a458ae9d80bb5e58884f5987fcb41
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5b8a814f3aeefa5d532770d34674995a259b1d0de80bb9f90ec6188099e03c
+oid sha256:deb1ec3cd79155004f27b637dbdf8248d31df7a7e6b9271ef520a45273a071c7
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f7e685ed786d075ed1cbf16f75ee06ff18af8652d59bebd10628b722f2e5f2
+oid sha256:0290ac5f04e55c88614a5fc8876370d93a593987208fcc581fc642918b1da8ba
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70ce39dc0484a07cf26175c01edd45d7187b33cf3b7426ec3e7187e560fe7f9
+oid sha256:5f9ee0ff1940dd91113eeb7613899018df3dbdd59112c1db2a4ee540aa7411d1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:198e9c5abe5151f1b8f98a22fd77ae2770a4aa017bd01877ffccc20b1cae28be
+oid sha256:d25210b544040bb154d351b7b54b39ff9c98281c0d9fc772c1d1b0a64f1f30f6
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.286264600378152,
+  "epoch": 0.2897987312470181,
   "eval_steps": 500,
-  "global_step": 16200,
+  "global_step": 16400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2276,6 +2276,34 @@
       "learning_rate": 3.96565942157036e-05,
       "loss": 0.2984,
       "step": 16200
+    },
+    {
+      "epoch": 0.2871481330953685,
+      "grad_norm": 1.705592155456543,
+      "learning_rate": 3.9607508197365065e-05,
+      "loss": 0.3877,
+      "step": 16250
+    },
+    {
+      "epoch": 0.28803166581258505,
+      "grad_norm": 1.5367944240570068,
+      "learning_rate": 3.955842217902653e-05,
+      "loss": 0.3508,
+      "step": 16300
+    },
+    {
+      "epoch": 0.2889151985298016,
+      "grad_norm": 3.140960693359375,
+      "learning_rate": 3.9509336160687994e-05,
+      "loss": 0.3443,
+      "step": 16350
+    },
+    {
+      "epoch": 0.2897987312470181,
+      "grad_norm": 1.2341272830963135,
+      "learning_rate": 3.946025014234945e-05,
+      "loss": 0.4346,
+      "step": 16400
     }
   ],
   "logging_steps": 50,