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:c71b1c3b027742b044b2abd8db6aa277ac349ae21ab92bab96fdd899933f01fe
+oid sha256:06d042b42d6caac87ab6182f9e763c87f8ec19beab9b387c8e3558d5ecf17156
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146a08a886ee9aa5e4dce2817ab008e6370ae4b9930e5f397f3beea090d4f025
+oid sha256:1cb67d68e71875bab600ccfb36fe9c311fc35753c8bf356e3edf2c642090f06b
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b8dbc95226369ce8d50542a4f2958de0c5011de7538e300ac07fb3e667e6c2
+oid sha256:6fe10eafe4187cb1c36e1b7a8856fc84fdfcc71bca3eadc1a108b8f0d4b6c555
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e3b504f4b478d50a181eaa2ef317405b60ed8d97be9beec3f1a5226df2330f
+oid sha256:6b28ee0addfe1fdb5c9554035d0aace280dc61b8aded9640b8ddc91a063558e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025974025974025976,
+  "epoch": 0.02886002886002886,
   "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": 4.999,
       "eval_steps_per_second": 2.5,
       "step": 9
+    },
+    {
+      "epoch": 0.02886002886002886,
+      "grad_norm": 6.57053279876709,
+      "learning_rate": 0.0003,
+      "loss": 5.9022,
+      "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": 1.2582696479883264e+16,
+  "total_flos": 1.398077386653696e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null