Training in progress, step 11200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2aed91fcfc0dc2a9f74b27c022a9b5fd65685b3f275947d34d0a74bbd85cfc
+oid sha256:0e31966b04574acebf28546b0bdfcf211d097f9558fdc058e43859331b2c8a0e
 size 403743472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133d6a28a19967cbc75f59be9a1b86aad73a559586a5d23b119a300ac0b7c9d7
+oid sha256:94703dc5960a9835da41502a3360a1fc4b5c68c1773ead90c2697d3e089b010d
 size 205367268

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19eb08424c7cabee7faab0ce98c27d52e75cba94f6aa2d3047f7359f99b575fc
+oid sha256:e106b6afecd31058ad10815f78be4cee707158fc80f75204745e2308e0ccd58d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b2e5d4fc14847d6bfc229f02a4301c760077da2f2d2fa659adaf9fa26c3231b
+oid sha256:b4279e65dc3787fa233c9c49d990863d412fbffdcade9a4bb64aae1614446032
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b564d51e82d445615267852b32843a95a33e723f3d9219c08e2a6d04877189e
+oid sha256:c8d95b84a432ec8962c0ed23a78396eefce6c3d2e0549b24d1e22987f63a16bd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10d21992b1aea28ddf312e346050c6694576a83d817dc70a2b4095d24aa2491
+oid sha256:1378cf09938f0a7f6053316e1af27b9cf888013355a16b03120b96ef23862e63
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3af2a61f3ca2f5a9482fbc3d5606aa4cdb13d821f89c73efbbdd2d1cb65a918a
+oid sha256:94b228fd0c4d52812cee1023eef1bb6b7306de63bb45594524f8c51f4a8a5b06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.269326683291771,
+  "epoch": 9.30257689110557,
   "eval_steps": 1120,
-  "global_step": 11160,
+  "global_step": 11200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7899,6 +7899,42 @@
       "learning_rate": 3.487156452258722e-09,
       "loss": 0.8617,
       "step": 11160
+    },
+    {
+      "epoch": 9.27763923524522,
+      "grad_norm": 0.9801519513130188,
+      "learning_rate": 1.9615354797664075e-09,
+      "loss": 0.8576,
+      "step": 11170
+    },
+    {
+      "epoch": 9.28595178719867,
+      "grad_norm": 0.9950971007347107,
+      "learning_rate": 8.717967133586858e-10,
+      "loss": 0.8547,
+      "step": 11180
+    },
+    {
+      "epoch": 9.29426433915212,
+      "grad_norm": 0.9402633905410767,
+      "learning_rate": 2.1794965335830696e-10,
+      "loss": 0.8521,
+      "step": 11190
+    },
+    {
+      "epoch": 9.30257689110557,
+      "grad_norm": 0.9429795742034912,
+      "learning_rate": 0.0,
+      "loss": 0.8479,
+      "step": 11200
+    },
+    {
+      "epoch": 9.30257689110557,
+      "eval_loss": 2.0490636825561523,
+      "eval_runtime": 27.9107,
+      "eval_samples_per_second": 117.052,
+      "eval_steps_per_second": 5.876,
+      "step": 11200
     }
   ],
   "logging_steps": 10,
@@ -7913,12 +7949,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.1141445027223306e+18,
+  "total_flos": 3.1253063109758157e+18,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null