Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8adf86e102e6669d7d744eac25012232cacd9e2c2b5577eb27edd8f31747996
+oid sha256:593880cb57f7296249dfb7fd4e4893cea19d4c98de08b77d76321b25dc93b8c3
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591e8884025421ed099e3e74468620c5d3e460172062eb8910a9338a65fd6793
+oid sha256:ab45de1f863a2a240ea88b6522e7fafee3ad5f522cb7872c19df7b6a6d5a4adf
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a518030d53de0f16e895fae2210619017ee14ab7fb9e1626b05ae41a39c13ac2
+oid sha256:bd6b9c7c0b8987c7e0e5d0153c4f1710b900efe6354c3e9b604bb41f90977c0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72ea6df83991d3025ed7e36df9a5c32138772ee24f1af389000a804685c36c9
+oid sha256:289ccbafd4cbc565d30135d7789ffd97a9803f5eaa40921290229dea676c429b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.28595178719867,
+  "epoch": 2.493765586034913,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -100,6 +100,13 @@
       "learning_rate": 1.086118038237739e-05,
       "loss": 0.3526,
       "step": 5500
+    },
+    {
+      "epoch": 2.493765586034913,
+      "grad_norm": 0.7811100482940674,
+      "learning_rate": 1.0029925187032419e-05,
+      "loss": 0.3438,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -119,7 +126,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.339585567653888e+16,
+  "total_flos": 1.461377145765888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null