Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a3729b1d5b7fd9ea071a21b658deedd6dced7e490cdb146317ad1bf99d88d80
+oid sha256:e1b32a121118bc495273d8f072ee0fae76c1db5d5f720f09d189b5da501a562e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b303240b5dd23c4531eaa2f03fc3b99dd0058964f72cddbc09ef98b92a4dc2f3
+oid sha256:c285872efd3f26770f136d5e20057005abde8d8f57b075d76865a55f4db812e1
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
+oid sha256:a3efe221c4a0adf497082884c488f9d91c42d1d873e72d47409fbf104eb83048
 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": 0.0013001552963270613,
+  "epoch": 0.001444616995918957,
   "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": 31.577,
       "eval_steps_per_second": 15.794,
       "step": 9
+    },
+    {
+      "epoch": 0.001444616995918957,
+      "grad_norm": 15.71590805053711,
+      "learning_rate": 0.0002,
+      "loss": 11.5817,
+      "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": 1465874317836288.0,
+  "total_flos": 1628749242040320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null