Training in progress, step 10000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d243eb39c86985f967eb6f02049efebe487ab967e0d538e211c584ebe29bd66
+oid sha256:8885252f0b860bacd73affa5affb163964fc25ec4387dbc707302f951d22b8a4
 size 5544932128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1b0259667b34bb543e6d855676b8c931dd58b61ff2dc77fde42032ec1b22a36
+oid sha256:90774a7d9ae114bf5996c76da2dd4e2964dd6726c59397719108f740b10a69dd
 size 2779550366

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f0ae4da9f9ac888ff3cd775ec2138daac6234e1b7139debcdbd969549cce21
+oid sha256:c067a130d681f8c9339b5e4f17102ad2106756f3a65f40b34464671d516635c4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3828618926475404,
+  "epoch": 0.4030125185763583,
   "eval_steps": 500,
-  "global_step": 9500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -140,6 +140,13 @@
       "learning_rate": 3.428641798396848e-05,
       "loss": 0.5048,
       "step": 9500
+    },
+    {
+      "epoch": 0.4030125185763583,
+      "grad_norm": 0.5959055423736572,
+      "learning_rate": 3.316689803412297e-05,
+      "loss": 0.5021,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -159,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5174649254725517e+19,
+  "total_flos": 1.5974482040134631e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null