Training in progress, step 735, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:627d9b383438039f34abd33800dae002df999132f89cab89ba62dfe1f1426e0a
+oid sha256:efcf0f8f8c2a154e8044f63cdd8e5d1c3f55ca898dd06599f98d5229041bb6c2
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6343af573504b84a3ef47b8bf3ff835b275e67f12e7cfd7551834d448fab77e
+oid sha256:5aba5594c129ca10274fbbcfcc539c09ac0d2ca221f45c5b94c3ca82d22eedfd
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:739536522f1b34f69aa7e5b387ca278212f27483830b111e16647531fa067e63
+oid sha256:2e2d178f20d9841bf93e03060e75a6e60c5ef312c54606c20e4889f2a923bd17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db26a6fc12b0a4e7560698816d6216991118c99b7c0d3e7b40bc0039633de232
+oid sha256:3e4ae50991c958c4eeb4c90286c2129eba88495e624f1ed62c9f2a87ed3c7b15
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9446780977030087,
+  "epoch": 0.9511484956324814,
   "eval_steps": 386,
-  "global_step": 730,
+  "global_step": 735,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5133,6 +5133,41 @@
       "learning_rate": 9.23440419653574e-05,
       "loss": 0.9403,
       "step": 730
+    },
+    {
+      "epoch": 0.9459721772889033,
+      "grad_norm": 0.8904352784156799,
+      "learning_rate": 9.232210310254685e-05,
+      "loss": 0.8514,
+      "step": 731
+    },
+    {
+      "epoch": 0.9472662568747978,
+      "grad_norm": 1.004438877105713,
+      "learning_rate": 9.230013546462512e-05,
+      "loss": 0.9824,
+      "step": 732
+    },
+    {
+      "epoch": 0.9485603364606924,
+      "grad_norm": 0.7370134592056274,
+      "learning_rate": 9.227813906652818e-05,
+      "loss": 0.9869,
+      "step": 733
+    },
+    {
+      "epoch": 0.9498544160465868,
+      "grad_norm": 0.8597853183746338,
+      "learning_rate": 9.225611392321153e-05,
+      "loss": 0.8758,
+      "step": 734
+    },
+    {
+      "epoch": 0.9511484956324814,
+      "grad_norm": 0.7227449417114258,
+      "learning_rate": 9.223406004965023e-05,
+      "loss": 0.8208,
+      "step": 735
     }
   ],
   "logging_steps": 1,
@@ -5152,7 +5187,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.160941353363046e+17,
+  "total_flos": 8.216838211947725e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null