Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef039086e6370220f6756f552d58e0cb564302668350534f4abb6bb611b2751
+oid sha256:08e3a27c9447aec6788e8ea3f59e44a52d639d38477a83ea9193a7824dbeca4d
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a7379985a56e77bbc28e9739a2be3d794cafd42b80543e5376d84bfda9fa0a3
+oid sha256:5d3ed6e7fa1b36f65c6531fea59fb94ad545b5e0b1aa9acb7eb40eb0f393f191
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7567ae8a1ec33e28c23869de794452faaab4545ecafbc1b4920ceae179c9547
+oid sha256:f34cad3af4891ba4d35d6fef0d4d3a99903a2b740801a9646aa2f6b99de9be9e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002866926813729394,
+  "epoch": 0.0031854742374771046,
   "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": 16.998,
       "eval_steps_per_second": 16.998,
       "step": 9
+    },
+    {
+      "epoch": 0.0031854742374771046,
+      "grad_norm": 7.70857048034668,
+      "learning_rate": 0.00016,
+      "loss": 1.0961,
+      "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": 324429435371520.0,
+  "total_flos": 360477150412800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null