Training in progress, step 783, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0943a41a553462c4d372d11f0db7e7ac74b82191589741e8cc65f7c9bf91ac59
+oid sha256:1d209977df9813fed44fad624e5fb58dc1e5b15c5b51940ed1468e7c3dfe5fd9
 size 100198584

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee780c3dfac7ae5d183bedef0b48a628ef423302dc70107b1ca832ddb1dcaca5
+oid sha256:3a853076cce04170a9efa4aba119013888999f2ac0422fb5d16b39458831a719
 size 50675604

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7deeaf0e67bca4eb52e599acdab6e6d26eff4b93874f78b39bfb4318b5785931
+oid sha256:2ca9fb85c447c86084528e309b6c6989260de379c269ae99f82548ef6b07c4e0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.850480109739369,
+  "epoch": 0.8592592592592593,
   "eval_steps": 500,
-  "global_step": 775,
+  "global_step": 783,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5432,6 +5432,62 @@
       "learning_rate": 3.3538840937114674e-06,
       "loss": 1.1299,
       "step": 775
+    },
+    {
+      "epoch": 0.8515775034293552,
+      "grad_norm": 0.12276988476514816,
+      "learning_rate": 3.3292231812577068e-06,
+      "loss": 1.1005,
+      "step": 776
+    },
+    {
+      "epoch": 0.8526748971193415,
+      "grad_norm": 0.14884981513023376,
+      "learning_rate": 3.3045622688039457e-06,
+      "loss": 1.0838,
+      "step": 777
+    },
+    {
+      "epoch": 0.8537722908093278,
+      "grad_norm": 0.1271783709526062,
+      "learning_rate": 3.2799013563501854e-06,
+      "loss": 1.0585,
+      "step": 778
+    },
+    {
+      "epoch": 0.8548696844993141,
+      "grad_norm": 0.13373488187789917,
+      "learning_rate": 3.2552404438964248e-06,
+      "loss": 1.1283,
+      "step": 779
+    },
+    {
+      "epoch": 0.8559670781893004,
+      "grad_norm": 0.15838205814361572,
+      "learning_rate": 3.2305795314426637e-06,
+      "loss": 1.0838,
+      "step": 780
+    },
+    {
+      "epoch": 0.8570644718792867,
+      "grad_norm": 0.13347558677196503,
+      "learning_rate": 3.205918618988903e-06,
+      "loss": 1.1981,
+      "step": 781
+    },
+    {
+      "epoch": 0.858161865569273,
+      "grad_norm": 0.1298656165599823,
+      "learning_rate": 3.181257706535142e-06,
+      "loss": 1.1628,
+      "step": 782
+    },
+    {
+      "epoch": 0.8592592592592593,
+      "grad_norm": 0.14071859419345856,
+      "learning_rate": 3.1565967940813812e-06,
+      "loss": 1.0938,
+      "step": 783
     }
   ],
   "logging_steps": 1,
@@ -5451,7 +5507,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.037403550740316e+17,
+  "total_flos": 8.117704792212849e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null