Training in progress, step 43500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:341cf52e44aee26bac163dde1d46d0da21ad4c56269b433dfffb30a288535511
+oid sha256:36cf0603c7daac3e8ed590090bcf677f50dccc7cd1d396cc2534c536d8ef5ab1
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa19a4f5dbef468935d63a1f85e3cfae44ec707144d148f1de907a8b462aaae
+oid sha256:c019e8b6aa64d4ba31d0d7d4b1bb427ab8e78e240572d25da85d969eb311e683
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be41eee8b8a0220527e2dacace3c21226f82da4d47c62f24e447c03fa2152a0
+oid sha256:3c7f4e1eca9309d1d98afa1140a219e6354390e4eff786b2f5b9b5e736195e76
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8cafd6acaa1b671acd46943cc34e18e4d792ad12b254ee219f6cb062b3f2459
+oid sha256:ee89a7efb22e08ab90c8b6a16d6b67293611a17a0121ecbac30fb8a1fc489b33
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2688,
+  "epoch": 0.2784,
   "eval_steps": 500,
-  "global_step": 42000,
+  "global_step": 43500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -595,6 +595,27 @@
       "learning_rate": 4.328256e-05,
       "loss": 0.3516,
       "step": 42000
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.756515622138977,
+      "learning_rate": 4.320256e-05,
+      "loss": 0.3461,
+      "step": 42500
+    },
+    {
+      "epoch": 0.2752,
+      "grad_norm": 0.7201528549194336,
+      "learning_rate": 4.3122560000000003e-05,
+      "loss": 0.3497,
+      "step": 43000
+    },
+    {
+      "epoch": 0.2784,
+      "grad_norm": 0.7436856031417847,
+      "learning_rate": 4.3042560000000004e-05,
+      "loss": 0.3505,
+      "step": 43500
     }
   ],
   "logging_steps": 500,
@@ -614,7 +635,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0460985122816e+17,
+  "total_flos": 2.1191734591488e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null