Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9fb72c818d636ef98bcfe85fc5da2cb6b31e7441cce90cb70ecc8705d120bd
+oid sha256:1d6e806b48bfa14269984e70c5b652348421b5366f88a4f8f36fcc8e71115eb3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64cbf58fef940612c0b00b5c7b75dc1570e87a28aa6a758b9f6edf234dda59ad
+oid sha256:3d052357be06b2a19acac200dcd4f270a27886f89103f0b491d9f5fd74cb7659
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894ae9e2dd56efcd745c69d81e84d269bfa54a0f8cbcf8e14a4428f929aae407
+oid sha256:629575ee7c6b92853a352888f0843a4c6538c991a998ec627f12a96885306e87
 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": 0.00041520096880226054,
+  "epoch": 0.0004613344097802895,
   "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": 26.119,
       "eval_steps_per_second": 13.061,
       "step": 9
+    },
+    {
+      "epoch": 0.0004613344097802895,
+      "grad_norm": 0.6119644641876221,
+      "learning_rate": 0.0002,
+      "loss": 0.6808,
+      "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": 2034556106440704.0,
+  "total_flos": 2311995575500800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null