Training in progress, step 284, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8cf8057910d23a062865985ba852f2938eae817046dfaf5681661132eaf58de
+oid sha256:426a166c05ce6a9c2a3792ab7d5ae7d338239f2ba38be047201caa54ba30a791
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3538e3394b23b3adf8ac36f79431127cf553e2ff2786b3ddb23d8b296f28eeaa
+oid sha256:5f0ddfa6ca4416d999191fb8e260b82136a5552597c0f780e612c9c54f372809
 size 37431220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0786adcac2c7889cfa58c3afdb23ea4f83c558cdd0755806988521c514ef08d
+oid sha256:1f5d774857468bd6c5b471d495c3b4439bbde7fd03bb61dbdcc2120a4b2a557c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7626886145404664,
+  "epoch": 0.7791495198902606,
   "eval_steps": 500,
-  "global_step": 278,
+  "global_step": 284,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1953,6 +1953,48 @@
       "learning_rate": 6.515151515151516e-05,
       "loss": 1.1607,
       "step": 278
+    },
+    {
+      "epoch": 0.7654320987654321,
+      "grad_norm": 0.164581760764122,
+      "learning_rate": 6.439393939393939e-05,
+      "loss": 1.2018,
+      "step": 279
+    },
+    {
+      "epoch": 0.7681755829903978,
+      "grad_norm": 0.1688939481973648,
+      "learning_rate": 6.363636363636364e-05,
+      "loss": 1.1698,
+      "step": 280
+    },
+    {
+      "epoch": 0.7709190672153635,
+      "grad_norm": 0.1699894666671753,
+      "learning_rate": 6.287878787878788e-05,
+      "loss": 1.2385,
+      "step": 281
+    },
+    {
+      "epoch": 0.7736625514403292,
+      "grad_norm": 0.16270920634269714,
+      "learning_rate": 6.212121212121213e-05,
+      "loss": 1.2186,
+      "step": 282
+    },
+    {
+      "epoch": 0.7764060356652949,
+      "grad_norm": 0.1695300042629242,
+      "learning_rate": 6.136363636363636e-05,
+      "loss": 1.1761,
+      "step": 283
+    },
+    {
+      "epoch": 0.7791495198902606,
+      "grad_norm": 0.15952111780643463,
+      "learning_rate": 6.060606060606061e-05,
+      "loss": 1.1664,
+      "step": 284
     }
   ],
   "logging_steps": 1,
@@ -1972,7 +2014,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.438408126791516e+17,
+  "total_flos": 3.5131733923058074e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null