Training in progress, step 770, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:560166bd58797be34a5a1006e32be8d9d7bdd6e8139374eec22dd6b030c09335
+oid sha256:3a27ac3e1ec7d35dbea0ec3b749056abc8d7add31611980aa12634912c331b3e
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bcb1129b7246e53076259c323b591293fbe3c9a50fd35601ccc934945096be6
+oid sha256:dc2554f05f98e629fa96b10b8d45a8fd3ca22fb76f1ef5482b6601045564c6b8
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3fad3909fb536f4d0d7737147157c83d6378be43badc6330cb993db1a38d1e
+oid sha256:03dbd3ca99b04175952be4801caaa60aa6bc88d41389058fe0bc17432ac48c89
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117b21438fb9f77af4ac0954437849c611bcc84854c07120ecb52f05f7373ae0
+oid sha256:2014e732464a9f8815060f53131de6c0ff6b56b6305dcffb1856efbb56d78b5c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9899708832093174,
+  "epoch": 0.99644128113879,
   "eval_steps": 386,
-  "global_step": 765,
+  "global_step": 770,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5378,6 +5378,41 @@
       "learning_rate": 9.155915935223121e-05,
       "loss": 0.8196,
       "step": 765
+    },
+    {
+      "epoch": 0.9912649627952119,
+      "grad_norm": 0.6537997722625732,
+      "learning_rate": 9.153622237487127e-05,
+      "loss": 0.6911,
+      "step": 766
+    },
+    {
+      "epoch": 0.9925590423811065,
+      "grad_norm": 0.6952023506164551,
+      "learning_rate": 9.15132571567263e-05,
+      "loss": 0.7354,
+      "step": 767
+    },
+    {
+      "epoch": 0.9938531219670009,
+      "grad_norm": 0.7851712703704834,
+      "learning_rate": 9.149026371341049e-05,
+      "loss": 1.0092,
+      "step": 768
+    },
+    {
+      "epoch": 0.9951472015528955,
+      "grad_norm": 0.8476317524909973,
+      "learning_rate": 9.146724206055725e-05,
+      "loss": 1.0262,
+      "step": 769
+    },
+    {
+      "epoch": 0.99644128113879,
+      "grad_norm": 0.7637205123901367,
+      "learning_rate": 9.144419221381919e-05,
+      "loss": 0.879,
+      "step": 770
     }
   ],
   "logging_steps": 1,
@@ -5397,7 +5432,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.552219363455795e+17,
+  "total_flos": 8.608116222040474e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null