Training in progress, step 39000, checkpoint

last-checkpoint/README.md

@@ -1295,6 +1295,10 @@ You can finetune this model on your own dataset.
 | 0.6839 | 38700 | 0.3456        |
 | 0.6847 | 38750 | 0.2554        |
 | 0.6856 | 38800 | 0.2289        |
+| 0.6865 | 38850 | 0.2409        |
+| 0.6874 | 38900 | 0.3395        |
+| 0.6883 | 38950 | 0.3296        |
+| 0.6892 | 39000 | 0.349         |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee25825aff4959fe5e0a2781134b9e96da88058dbf8690e35445a67610af73c
+oid sha256:e6ce327cffaa12e6c6a5ddcb4a6d40429edafacde9dfb54d675b913bfba08975
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d050884a4252ba97d0bb88532a3164adec318594e47284644fd45a2c9c9a7cc4
+oid sha256:20234fcfe1aeda353bad872052502098141b92c7a49294548fc32efb7c40e203
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8540dc3b35a3094fd45d5158b8f89bcbd7079e7ed16edbb02c263246cd8ebc
+oid sha256:6bd0776e6b0bd55ed184f92817d37c75213ff68505295e3fc1bee2b951ea4bee
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64aa6796f2a5b524134346b6756db7d56f573132ef410dc4c37c3f8db2fcd06d
+oid sha256:4e33c3adb678c12b738b4f6b854bebd80c46584381912137221d663740b1248a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6c315739e8675a2e6e8b7f539ac0cd78a1153ea0c4434aeaf8094027721b1e
+oid sha256:54902ad30aa2955b28423fee094e905e66f30b7e8919420508a8b07f3d3c75a6
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6856213885600184,
+  "epoch": 0.6891555194288844,
   "eval_steps": 500,
-  "global_step": 38800,
+  "global_step": 39000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5440,6 +5440,34 @@
       "learning_rate": 1.7480512850719603e-05,
       "loss": 0.2289,
       "step": 38800
+    },
+    {
+      "epoch": 0.686504921277235,
+      "grad_norm": 1.4531927108764648,
+      "learning_rate": 1.7431426832381064e-05,
+      "loss": 0.2409,
+      "step": 38850
+    },
+    {
+      "epoch": 0.6873884539944514,
+      "grad_norm": 3.168332576751709,
+      "learning_rate": 1.738234081404253e-05,
+      "loss": 0.3395,
+      "step": 38900
+    },
+    {
+      "epoch": 0.6882719867116679,
+      "grad_norm": 1.5215202569961548,
+      "learning_rate": 1.7333254795703994e-05,
+      "loss": 0.3296,
+      "step": 38950
+    },
+    {
+      "epoch": 0.6891555194288844,
+      "grad_norm": 1.9889358282089233,
+      "learning_rate": 1.7284168777365455e-05,
+      "loss": 0.349,
+      "step": 39000
     }
   ],
   "logging_steps": 50,