Training in progress, step 684, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47c1e90dbecf9635856d092c6cddea8202536da475af28c5df57f9a15b232128
+oid sha256:0bb3d5a1f2bc1aa0163e2600885712b21040ba69d0674c75e1d94918847b2c42
 size 100198584

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99bb6870709dc61c780604e0ba8b8967af8b3b68a8fe57d1de47cc64ae9e2f69
+oid sha256:7db8f3ea3079591a8d48d7a67e7bbe0855bf2ee0d183b3e3c3acbf5c02c8cbf2
 size 50675604

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9967ef256882f56c127a1407616df2fb585de0b861d9905ab72b987597cec7ec
+oid sha256:4aedc1d040a37f21c3823ca8487bdb8d19041f448765618e91b99e64d27abfb7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.741838134430727,
+  "epoch": 0.7506172839506173,
   "eval_steps": 500,
-  "global_step": 676,
+  "global_step": 684,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4739,6 +4739,62 @@
       "learning_rate": 5.7953144266337855e-06,
       "loss": 1.184,
       "step": 676
+    },
+    {
+      "epoch": 0.7429355281207133,
+      "grad_norm": 0.12598906457424164,
+      "learning_rate": 5.770653514180024e-06,
+      "loss": 1.1155,
+      "step": 677
+    },
+    {
+      "epoch": 0.7440329218106996,
+      "grad_norm": 0.13896718621253967,
+      "learning_rate": 5.745992601726265e-06,
+      "loss": 1.1824,
+      "step": 678
+    },
+    {
+      "epoch": 0.7451303155006859,
+      "grad_norm": 0.13778887689113617,
+      "learning_rate": 5.721331689272504e-06,
+      "loss": 1.1126,
+      "step": 679
+    },
+    {
+      "epoch": 0.7462277091906722,
+      "grad_norm": 0.12722033262252808,
+      "learning_rate": 5.696670776818743e-06,
+      "loss": 1.1672,
+      "step": 680
+    },
+    {
+      "epoch": 0.7473251028806585,
+      "grad_norm": 0.13544504344463348,
+      "learning_rate": 5.6720098643649825e-06,
+      "loss": 1.1423,
+      "step": 681
+    },
+    {
+      "epoch": 0.7484224965706447,
+      "grad_norm": 0.14108151197433472,
+      "learning_rate": 5.6473489519112214e-06,
+      "loss": 1.1087,
+      "step": 682
+    },
+    {
+      "epoch": 0.749519890260631,
+      "grad_norm": 0.15130096673965454,
+      "learning_rate": 5.62268803945746e-06,
+      "loss": 1.0687,
+      "step": 683
+    },
+    {
+      "epoch": 0.7506172839506173,
+      "grad_norm": 0.15002749860286713,
+      "learning_rate": 5.5980271270037e-06,
+      "loss": 1.0799,
+      "step": 684
     }
   ],
   "logging_steps": 1,
@@ -4758,7 +4814,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.010987710203372e+17,
+  "total_flos": 7.092525781016617e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null