Training in progress, step 35400, checkpoint

last-checkpoint/README.md

@@ -1221,6 +1221,10 @@ You can finetune this model on your own dataset.
 | 0.6202 | 35100 | 0.2965        |
 | 0.6211 | 35150 | 0.3557        |
 | 0.6220 | 35200 | 0.3535        |
+| 0.6229 | 35250 | 0.4183        |
+| 0.6238 | 35300 | 0.3355        |
+| 0.6247 | 35350 | 0.3626        |
+| 0.6255 | 35400 | 0.2542        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a73726096d96dbbbaa9a481dfff6e52b1ea1d694b55f2edc2f1405af8895110b
+oid sha256:49e95dbcbd79f97ce1ba67a803455e357f6c9c9ea644273cb7511cae3c831b9d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b3f57d97ffd57e518f40f15d12ad037a0066d481b15f01ac0c5cd7db8dcb47
+oid sha256:29767797f5949aa103f2386e6b46cf5006f18f6853e49108146824052452a81a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca63325ac742a792a3bcdc1dc21baa9c1c96f6a59934e63bc8a87c6b8f66e093
+oid sha256:eea4a8e4afcda31bb844cc13d2627fa89d98644359cf49b2f2f2f5fdbb6dbb81
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6bf385710f1d1a6f64e5b03c0c6f98497de21222ff381a7961ac0b45b93ddc
+oid sha256:e8c2fca16cf2e15838c5424c974921bcfa3346a7bf4c2458c8ecc9892726ed4c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f345579e836e5dec04f17da3b053acb614c611f3b7c11559a8cdc45e09194e58
+oid sha256:ab93b747e0fc75060bb6e7ff7bdc607ad6b06fa8d1c145ad4ab8d80aeeb37b40
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.622007032920429,
+  "epoch": 0.6255411637892951,
   "eval_steps": 500,
-  "global_step": 35200,
+  "global_step": 35400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4936,6 +4936,34 @@
       "learning_rate": 2.1012742730360685e-05,
       "loss": 0.3535,
       "step": 35200
+    },
+    {
+      "epoch": 0.6228905656376456,
+      "grad_norm": 1.9256399869918823,
+      "learning_rate": 2.0963656712022147e-05,
+      "loss": 0.4183,
+      "step": 35250
+    },
+    {
+      "epoch": 0.6237740983548621,
+      "grad_norm": 1.4346308708190918,
+      "learning_rate": 2.0914570693683615e-05,
+      "loss": 0.3355,
+      "step": 35300
+    },
+    {
+      "epoch": 0.6246576310720786,
+      "grad_norm": 1.3797852993011475,
+      "learning_rate": 2.0865484675345076e-05,
+      "loss": 0.3626,
+      "step": 35350
+    },
+    {
+      "epoch": 0.6255411637892951,
+      "grad_norm": 3.1976869106292725,
+      "learning_rate": 2.0816398657006537e-05,
+      "loss": 0.2542,
+      "step": 35400
     }
   ],
   "logging_steps": 50,