Training in progress, step 34600, checkpoint

last-checkpoint/README.md

@@ -1205,6 +1205,10 @@ You can finetune this model on your own dataset.
 | 0.6061 | 34300 | 0.3466        |
 | 0.6070 | 34350 | 0.2608        |
 | 0.6079 | 34400 | 0.3239        |
+| 0.6088 | 34450 | 0.3557        |
+| 0.6096 | 34500 | 0.4175        |
+| 0.6105 | 34550 | 0.3104        |
+| 0.6114 | 34600 | 0.3305        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5f4ea64897e90b4e4c7c1e0cb94dcb0f1492d916413cce2e66078ccfad6960
+oid sha256:ba077d6325305d731409aa162830a3c5d5397210799b60591392b1d61570f746
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf44dfcc82793c060386978756eab303f1fb8ffef4fb86d6d8a80ed57d60773
+oid sha256:726943ff9dec97794faedec459447bcaa417b775d59a98d695e669bfe25957b1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13dc13fdf2d85fe768a37e80558a7b03bdcb432f2ca4a03fa86e5b8f2373ca60
+oid sha256:0770796c8b6d34fe12dcd97fff6f962f270b4c06153537e6c3ceff010a085b43
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8efb8d95dab64304b8fe44c3687dc59b22acc22bfbc66f29596f118c5967e9a
+oid sha256:548fc86584eafaf1a293dbece88e9fbb1e4a6c458e2f0be88ff6b690236f0848
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c62c2049abe02e0f34d9b4894dabef36b68579cab4efe24bc06e5d79c1d79bfd
+oid sha256:381bbbc1437f4c979ed33526acec9652454aa2f2944f4ad7e6a6f3b151477146
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6078705094449648,
+  "epoch": 0.6114046403138308,
   "eval_steps": 500,
-  "global_step": 34400,
+  "global_step": 34600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4824,6 +4824,34 @@
       "learning_rate": 2.1797137303410498e-05,
       "loss": 0.3239,
       "step": 34400
+    },
+    {
+      "epoch": 0.6087540421621813,
+      "grad_norm": 1.5316294431686401,
+      "learning_rate": 2.174805128507196e-05,
+      "loss": 0.3557,
+      "step": 34450
+    },
+    {
+      "epoch": 0.6096375748793977,
+      "grad_norm": 1.539382815361023,
+      "learning_rate": 2.1698965266733427e-05,
+      "loss": 0.4175,
+      "step": 34500
+    },
+    {
+      "epoch": 0.6105211075966143,
+      "grad_norm": 1.6773380041122437,
+      "learning_rate": 2.164987924839489e-05,
+      "loss": 0.3104,
+      "step": 34550
+    },
+    {
+      "epoch": 0.6114046403138308,
+      "grad_norm": 1.3534982204437256,
+      "learning_rate": 2.1601774950423123e-05,
+      "loss": 0.3305,
+      "step": 34600
     }
   ],
   "logging_steps": 50,