Training in progress, step 615, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32edca6079f3b9484783f232ac0ccb1d340292cb18066f64fd7821f34d446723
+oid sha256:27a7402608e3d69d7ce2d2204b47870c570eef8eb66dc46b4245b80a26fba6e5
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd94789a924990bbe5fdd71e1ae4a4ed24b474b41e969e7e388565234d65aee6
+oid sha256:f7f616c4ab3733f01573f5a4639cf3c0ef5c1986b5eaa57d7c93f315f4084899
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609743375850d853d6f9c3893828fefdf1e7c4e4f00a29e837453857db0e6e70
+oid sha256:7899d12248de67f6668e94b559c6ecc0d5fb53b6914bce371d9ea4bfc9af1fcd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f797c771cc3ef7f2bb02c5a7bc50a7c409a56da80db274d374a4aaeeeecf121
+oid sha256:07d99be8288b9bf599312a370a348e25f4abff486d9b14aebde6c262d55e60e9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7893885473956649,
+  "epoch": 0.7958589453251375,
   "eval_steps": 386,
-  "global_step": 610,
+  "global_step": 615,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4293,6 +4293,41 @@
       "learning_rate": 9.476356825510612e-05,
       "loss": 0.9179,
       "step": 610
+    },
+    {
+      "epoch": 0.7906826269815593,
+      "grad_norm": 0.7338031530380249,
+      "learning_rate": 9.474518497821409e-05,
+      "loss": 0.9518,
+      "step": 611
+    },
+    {
+      "epoch": 0.7919767065674539,
+      "grad_norm": 0.8368909358978271,
+      "learning_rate": 9.472677127873958e-05,
+      "loss": 0.875,
+      "step": 612
+    },
+    {
+      "epoch": 0.7932707861533485,
+      "grad_norm": 0.7648499011993408,
+      "learning_rate": 9.47083271692022e-05,
+      "loss": 1.0374,
+      "step": 613
+    },
+    {
+      "epoch": 0.794564865739243,
+      "grad_norm": 0.767672598361969,
+      "learning_rate": 9.468985266214223e-05,
+      "loss": 0.8341,
+      "step": 614
+    },
+    {
+      "epoch": 0.7958589453251375,
+      "grad_norm": 0.9221040606498718,
+      "learning_rate": 9.467134777012063e-05,
+      "loss": 1.0149,
+      "step": 615
     }
   ],
   "logging_steps": 1,
@@ -4312,7 +4347,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.819416747330765e+17,
+  "total_flos": 6.875313605915443e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null