Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27be97ad38bccfc3c1c90899bbd627f07aa27c1c17f59f9d17d885cef5d9ad04
+oid sha256:25932dbde6bfe2ec4527a99acc0757ae2c8033f39b15a52b243519694426389b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e71de9499edbe539145b76aeaff2b682047bf181588093490c589f2587a6da1
+oid sha256:7e22a29ec86bfca5060dd8ce6879ca70359f54216a657584c958e3af23282a38
 size 168149074

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b152a61d413a27ac560ef449e0ba4034b9ec676ad5323f8e6ac4390200263c
+oid sha256:b09e77debe54ed0e3e4482bd0e6e1d757a4a5b27096f812f8cf629a673ed391f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff891dd44cce64a4a4a6b872ff33b5b845128facd0c88c74496790e54904054c
+oid sha256:ac5fb5062edf1855b8d9be02f6986a07a0529b035f0d48034efc1ef444987518
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85cdfac05f17007eb007264fb938a1e74aee7da83cddc9e86f8bf1f9c8ca2233
+oid sha256:a433385393047d371c26741d9674791aa65aecc2269f3f2d48bea00a51637d29
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:076dc3d47f7fbb6e798c0995e7816f39237c9af238a21717b9be3bd529542c2e
+oid sha256:187df2910c01235fd48fd5c5bbc6b388a5dc210b37f49130a1e5df843be1843f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be43866b7a112efbf8125d7bbc11610819a4fb8c7f205bdfffb33dc32734ab8
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007104059674101263,
+  "epoch": 0.0007400062160522148,
   "eval_steps": 3,
-  "global_step": 24,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,13 @@
       "eval_samples_per_second": 33.067,
       "eval_steps_per_second": 8.267,
       "step": 24
+    },
+    {
+      "epoch": 0.0007400062160522148,
+      "grad_norm": 5.948877811431885,
+      "learning_rate": 0.0,
+      "loss": 0.8171,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -261,12 +268,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.5511633564401664e+16,
+  "total_flos": 3.69912849629184e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null