Training in progress, step 23500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be1cf4c3d10cfbf74e0b37f9cbc786fae12e5bbc6e3706973bfac0175c00ecce
+oid sha256:f8780b961dcbf09881cce6a4ec4f3ce77d0ac1ee0f91af800fa2edc12b4f6187
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bca9f5a43e8c43cfe44e64364c4d417027de463f09d30955f0ca8d99d5517c8a
+oid sha256:ef9bac5420d614e9bac93f0dd5fea2e0183354a0f7d5a23ad1f55f6681e9e683
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29008ac370065a7f89ca5e36ad7037a88abffeace17ded8b029713d8007c00c5
+oid sha256:243e2ec3e6c9bc99b16b0183c86988f987cd95808c30f0890be20ce20d1d5d66
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f8453b710c139b3558b89069d0f1dbb29ca8e0859ba342fa8818ead3f6d844
+oid sha256:06c57df543e7b3168b7bf3184803db11f7fb923e889cb830127c49143334357b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5333333333333332,
+  "epoch": 1.5666666666666667,
   "eval_steps": 500,
-  "global_step": 23000,
+  "global_step": 23500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1625,6 +1625,41 @@
       "learning_rate": 9.78088888888889e-06,
       "loss": 0.0545,
       "step": 23000
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.11006025224924088,
+      "learning_rate": 9.736444444444444e-06,
+      "loss": 0.0612,
+      "step": 23100
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 0.14539223909378052,
+      "learning_rate": 9.692e-06,
+      "loss": 0.0582,
+      "step": 23200
+    },
+    {
+      "epoch": 1.5533333333333332,
+      "grad_norm": 0.23037117719650269,
+      "learning_rate": 9.647555555555557e-06,
+      "loss": 0.0599,
+      "step": 23300
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.2668769657611847,
+      "learning_rate": 9.603111111111112e-06,
+      "loss": 0.0545,
+      "step": 23400
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.3005671501159668,
+      "learning_rate": 9.558666666666667e-06,
+      "loss": 0.0621,
+      "step": 23500
     }
   ],
   "logging_steps": 100,
@@ -1644,7 +1679,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.602412593152e+16,
+  "total_flos": 5.724204171264e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null