Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b08baaf4d90c9c182b82bfbe70f98f0588f0612ae46f70faa78d50db4120f1
+oid sha256:5e8af44d25e4403e0410db75087bbe76ea4f8927319fb246b38e44369d3d8502
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dcf282781331e78b59b837475418d86057b3283adae7517bfbe819e0a39fc45
+oid sha256:ff6c7add6d380bbc3dc068128784fbf52d0a610e52c9d69c4e04d246f1309eee
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eccc65cdfe52ae2c3cb149ff919417ca3e0864be3a19f409129562df5f10fda
+oid sha256:75400b2389a630f033d8e61a0b4f394aee67e01ef78d82c0ada4855822939a04
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd33b1054a96501be923bebee4d8cba60c917735915ddc1e0790b4ce34f0ce91
+oid sha256:7f286fedd044d4cc087ef5238577cf6b6ba1c5ebf29e1b250b79c60640a10a92
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08,
+  "epoch": 0.0896,
   "eval_steps": 500,
-  "global_step": 12500,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,27 @@
       "learning_rate": 4.80008e-05,
       "loss": 0.438,
       "step": 12500
+    },
+    {
+      "epoch": 0.0832,
+      "grad_norm": 0.9157513976097107,
+      "learning_rate": 4.7920800000000004e-05,
+      "loss": 0.4323,
+      "step": 13000
+    },
+    {
+      "epoch": 0.0864,
+      "grad_norm": 0.9085854887962341,
+      "learning_rate": 4.7840800000000005e-05,
+      "loss": 0.4303,
+      "step": 13500
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 0.9123984575271606,
+      "learning_rate": 4.77608e-05,
+      "loss": 0.4247,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
@@ -201,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.0895789056e+16,
+  "total_flos": 6.820328374272e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null