Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad0d242ef458961225639df7392fa49b43a99c9610c8d8b67e816c4dbcbace5
+oid sha256:675f68dd8664c67b6fc30de3df84cb498d85ec44cd2e9f5a1c118eccd51c0966
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a0870f87e737976f6fa5e14d9c27303aaa61909135871ce5f0088d0f35f488
+oid sha256:fa004bfe7e0a0476129372502d20c89bd9cd47e29ea4b2566dc74bec72333b62
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88861b17d557d63b349882c3778027603bbfce23e2152d04a0a61bc48795d1d0
+oid sha256:3d7ac5b3839a270b94b3a90dedaa2a8f2725b6b6d98c2371ca95c199f2c6eb7e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006326333362621913,
+  "epoch": 0.0007029259291802127,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 26.24,
       "eval_steps_per_second": 13.12,
       "step": 9
+    },
+    {
+      "epoch": 0.0007029259291802127,
+      "grad_norm": 0.6198019981384277,
+      "learning_rate": 0.0002,
+      "loss": 2.9676,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2035916419891200.0,
+  "total_flos": 2198789733482496.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null