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:d630d522eb7f6e0fed3ead32f56912299c23df8c14a2ad0aceb58502720648e9
+oid sha256:4931c1265410706d44d2d29d6de39e34c5a5158995e9b7f3ff347e963acad089
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bde7e0330f5555349b7bd30a65514d33da915b8384b26cfbfa0ec51085c2277
+oid sha256:9c135060693620f5d0373d16f06a74afad264257fba1bdd621e080ae616ad3b5
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd48a3c93e2f7e60386703e2c4ddc69073e08d6bee605002a3ba55b45289b42
+oid sha256:40babcca9503a67245c4140d11c732c6470361298c591cd784e98d424e5d2837
 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": 0.0001895774529215992,
+  "epoch": 0.00021064161435733244,
   "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": 16.513,
       "eval_steps_per_second": 8.257,
       "step": 9
+    },
+    {
+      "epoch": 0.00021064161435733244,
+      "grad_norm": 25.13823699951172,
+      "learning_rate": 0.0002,
+      "loss": 27.1915,
+      "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": 3397367365632000.0,
+  "total_flos": 3737104102195200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null