Training in progress, step 60000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354ba10ebc308001d4962c34661a8b4b0018d23c0c76b41e17787d26889f66e6
+oid sha256:57ccebdd082ea318372ffeb90a683283c04a1d53aa3b54c67fa99060a8ac05eb
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58d3111213f9decf5b467b7a9451ca4618a5ac83c7d6653282bdb4621eb614c
+oid sha256:6147e34482389f722b0f2bd04dd98805d253ab94e45aaad38f239fa78576356a
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b66a547b30bb0f6d0472863be4967b31509f44e757837a03afe57cbd2cdac3
+oid sha256:ba80147f178822473ec973474efa5be9a54273706827c8cc8ddf6b54fd92f4b6
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.779092702169626,
+  "epoch": 23.668639053254438,
   "eval_steps": 20000,
-  "global_step": 40000,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,34 @@
       "learning_rate": 5e-05,
       "loss": 0.001,
       "step": 40000
+    },
+    {
+      "epoch": 17.75147928994083,
+      "grad_norm": 0.02221524901688099,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 45000
+    },
+    {
+      "epoch": 19.723865877712033,
+      "grad_norm": 0.020608918741345406,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 50000
+    },
+    {
+      "epoch": 21.696252465483234,
+      "grad_norm": 0.018035519868135452,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 55000
+    },
+    {
+      "epoch": 23.668639053254438,
+      "grad_norm": 0.033636949956417084,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 60000
     }
   ],
   "logging_steps": 5000,
@@ -82,7 +110,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.454391836863656e+17,
+  "total_flos": 5.1811282772976576e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null