Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab28ecb94b7a818a5a7fd1c75030bb7191001272b6094d37a909690e2363f392
+oid sha256:7a744c13deb25911b66983e31562327d3465c179b21146bc88ec434370beb4e3
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f96d7c8ef3b30034ac3cc33cc9b776b72fa413fbfee63fe75839a96f5fc8817
+oid sha256:253d6301b450c522622839b71d9e12bac5f9cc03981cb65be544bfdf36d7d4b7
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d57fdcf5f9a2ba7a66cb157a536592aea4bc319138ee95de3e9ae0ff3c98c0
+oid sha256:848d4d9f2c4a26bc5101c133c47fd9e2a8a04e37c4bc27e88dacfd4314e7b448
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8aa76edc747fa1f55c383a900f2044d0133f29781c0dba0a687e1604db66b1
+oid sha256:2d2aca196cd5d7049ddd26164789577fde10cf1d311b04f47bbbf913861b9e3d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0416,
+  "epoch": 0.0512,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -98,6 +98,27 @@
       "learning_rate": 4.89608e-05,
       "loss": 0.4939,
       "step": 6500
+    },
+    {
+      "epoch": 0.0448,
+      "grad_norm": 0.9770995378494263,
+      "learning_rate": 4.88808e-05,
+      "loss": 0.4824,
+      "step": 7000
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.981966495513916,
+      "learning_rate": 4.88008e-05,
+      "loss": 0.4875,
+      "step": 7500
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 1.0177415609359741,
+      "learning_rate": 4.87208e-05,
+      "loss": 0.4785,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -117,7 +138,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.166581030912e+16,
+  "total_flos": 3.897330499584e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null