Training in progress, step 39200, checkpoint

last-checkpoint/README.md

@@ -1299,6 +1299,10 @@ You can finetune this model on your own dataset.
 | 0.6874 | 38900 | 0.3395        |
 | 0.6883 | 38950 | 0.3296        |
 | 0.6892 | 39000 | 0.349         |
+| 0.6900 | 39050 | 0.2841        |
+| 0.6909 | 39100 | 0.3101        |
+| 0.6918 | 39150 | 0.3094        |
+| 0.6927 | 39200 | 0.2485        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ce327cffaa12e6c6a5ddcb4a6d40429edafacde9dfb54d675b913bfba08975
+oid sha256:c7d6820907915018672901efc19cbb352c179cad3ee4118d2b29f0808a0ba1d9
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20234fcfe1aeda353bad872052502098141b92c7a49294548fc32efb7c40e203
+oid sha256:7813cbc30aeb0e33d540e2c0598083ef1f841767e7b1e8f1969f8a6919b6ff34
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bd0776e6b0bd55ed184f92817d37c75213ff68505295e3fc1bee2b951ea4bee
+oid sha256:92a02a223a41a639360f4d62d4f98e6515f2dbf1c87dd6aca13b94f6ef7e4783
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e33c3adb678c12b738b4f6b854bebd80c46584381912137221d663740b1248a
+oid sha256:66a1e2a4a3b1321cbec7e7bb5a73635e20233c2ebb1cea8ca1f3f936291d006b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54902ad30aa2955b28423fee094e905e66f30b7e8919420508a8b07f3d3c75a6
+oid sha256:b1e6c3ffd695ace5a45f1a39dea8b91d4823676a2ff025905fd82b1c1cf00906
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6891555194288844,
+  "epoch": 0.6926896502977505,
   "eval_steps": 500,
-  "global_step": 39000,
+  "global_step": 39200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5468,6 +5468,34 @@
       "learning_rate": 1.7284168777365455e-05,
       "loss": 0.349,
       "step": 39000
+    },
+    {
+      "epoch": 0.690039052146101,
+      "grad_norm": 1.6141583919525146,
+      "learning_rate": 1.723508275902692e-05,
+      "loss": 0.2841,
+      "step": 39050
+    },
+    {
+      "epoch": 0.6909225848633175,
+      "grad_norm": 1.3648995161056519,
+      "learning_rate": 1.7185996740688384e-05,
+      "loss": 0.3101,
+      "step": 39100
+    },
+    {
+      "epoch": 0.691806117580534,
+      "grad_norm": 1.897626280784607,
+      "learning_rate": 1.7136910722349846e-05,
+      "loss": 0.3094,
+      "step": 39150
+    },
+    {
+      "epoch": 0.6926896502977505,
+      "grad_norm": 1.4272273778915405,
+      "learning_rate": 1.708782470401131e-05,
+      "loss": 0.2485,
+      "step": 39200
     }
   ],
   "logging_steps": 50,