Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74939770c5f4de6c54954b66d8697524ed067843d0c95c76c7d913998ec9ba71
+oid sha256:f4cc3ba2204376f37714954e064c4871046555a0d895a8e540a8e0c3c092c763
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69acaf30f6b4a693b7c92bea7bf6b09ab80971083780d77ef435884e19dd5f4a
+oid sha256:3292a8ff107e2b1b311801b4c85ee327fb33d937f265442b81235edb24e98f44
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd5c3a48a3559ff7695d92e037ac134c01ff7aac9031f8f4de3ac26834c34fd
+oid sha256:df283a1b70870abcfda2d24962f264de609052438e9054e2b705f7c0beddc66f
 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": 0.00401920285809981,
+  "epoch": 0.004465780953444233,
   "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": 22.441,
       "eval_steps_per_second": 11.233,
       "step": 9
+    },
+    {
+      "epoch": 0.004465780953444233,
+      "grad_norm": 2.7356202602386475,
+      "learning_rate": 0.0002,
+      "loss": 10.3248,
+      "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": 1750905435193344.0,
+  "total_flos": 1995217821499392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null