Training in progress, step 6500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bf6d8c3c7201435b59c86f75284044ae7ca9dd0b83b93d9783cce36eaab3dc
+oid sha256:d0409bd80ccd14ddbeb3024bd062d30e291a180d2ca604903df91238170e4c73
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ff7e3c74491b65303a1d660290aa57aaee8ff25bd74e82739919626ea6a896
+oid sha256:68644ea0237312a6dc011ff6674091c2fc2c55988ee98e26d3612f0699d73a35
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4de3b0ad4cac852dd3da2926f015bb27ffccac6cb7d06eabf2b5f451190bbde
+oid sha256:1d723e76d2cab5754253ee0fd79d89a89aad0f0baf1b96ff814454ee845a638e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.312172232956114,
+  "epoch": 3.5881865857024566,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,41 @@
       "learning_rate": 3.085024690529227e-05,
       "loss": 0.1086,
       "step": 6000
+    },
+    {
+      "epoch": 3.367375103505382,
+      "grad_norm": 0.5468078851699829,
+      "learning_rate": 2.908430113629592e-05,
+      "loss": 0.1083,
+      "step": 6100
+    },
+    {
+      "epoch": 3.4225779740546507,
+      "grad_norm": 0.49241673946380615,
+      "learning_rate": 2.734943742056943e-05,
+      "loss": 0.107,
+      "step": 6200
+    },
+    {
+      "epoch": 3.4777808446039193,
+      "grad_norm": 0.4840191900730133,
+      "learning_rate": 2.5648233875477157e-05,
+      "loss": 0.1081,
+      "step": 6300
+    },
+    {
+      "epoch": 3.532983715153188,
+      "grad_norm": 0.43311458826065063,
+      "learning_rate": 2.398321859723792e-05,
+      "loss": 0.1089,
+      "step": 6400
+    },
+    {
+      "epoch": 3.5881865857024566,
+      "grad_norm": 0.506381094455719,
+      "learning_rate": 2.2356865904013918e-05,
+      "loss": 0.1097,
+      "step": 6500
     }
   ],
   "logging_steps": 100,
@@ -446,7 +481,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.182453705049637e+18,
+  "total_flos": 3.4474544992722616e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null