Training in progress, step 690, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a662f46feddbe2497f49933107c98ff00f401806533aaf98017b0ee6565b00be
+oid sha256:4a3b487bcd9f0f8a52ebb009ad90b8ecda6c53af66c9e15949f86cd4ee4c5493
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d00e266f5b1f45df60e8c44f7e3943273cb57caebf20915b93c9a2bb87831d7
+oid sha256:963768aacc28d56da4770e8791826eb46d62fef62323535d71a32db43b751e99
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad79945a21a826c0f45869cc500d5d990f1fd3dd860f10e0654ca0015c8252fb
+oid sha256:679bf09455ce8b50952b872f5ea495d76ca0e5689b5a5b2ac13810d836dad521
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6df9925b4c7f085a8aa1642bfcd531b37d20682fc6e02418e3381af28e29b06
+oid sha256:eb6690e503326fa9d439d70768c7431f28556349fb205663edc4009a63fe4c77
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8864445163377548,
+  "epoch": 0.8929149142672275,
   "eval_steps": 386,
-  "global_step": 685,
+  "global_step": 690,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4818,6 +4818,41 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 0.7166,
       "step": 685
+    },
+    {
+      "epoch": 0.8877385959236493,
+      "grad_norm": 0.8031767010688782,
+      "learning_rate": 9.328064134610727e-05,
+      "loss": 0.9718,
+      "step": 686
+    },
+    {
+      "epoch": 0.8890326755095438,
+      "grad_norm": 0.7503944635391235,
+      "learning_rate": 9.325998307616417e-05,
+      "loss": 0.9732,
+      "step": 687
+    },
+    {
+      "epoch": 0.8903267550954383,
+      "grad_norm": 0.8711128234863281,
+      "learning_rate": 9.323929539343837e-05,
+      "loss": 1.05,
+      "step": 688
+    },
+    {
+      "epoch": 0.8916208346813329,
+      "grad_norm": 0.7816237211227417,
+      "learning_rate": 9.321857831199554e-05,
+      "loss": 0.9514,
+      "step": 689
+    },
+    {
+      "epoch": 0.8929149142672275,
+      "grad_norm": 0.8090843558311462,
+      "learning_rate": 9.319783184592142e-05,
+      "loss": 0.9691,
+      "step": 690
     }
   ],
   "logging_steps": 1,
@@ -4837,7 +4872,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.657869626100941e+17,
+  "total_flos": 7.713766484685619e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null