Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5595a5e01dcc5449a8fa9076f96e49eec34eb415f3751d77825b3632da3d5487
+oid sha256:7d67e8fb46053ac0fc94be34d4d0e6d12912e2e3556551d04e0b0bc7aee4d2ef
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c8ce8cf368ff79449b20bce29c832bc2c7ae6e1fcb61a39a9a1e13e302ecc2
+oid sha256:2d166806ec9636747186cded1b046355bb68f7b39fc9a0b967930d2161d34582
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16175748798ebd7e55ba83d6c76d4f9b9828c7b45b2602fa6b62af224a20f7b0
+oid sha256:fe7ae5caa9591d6bfc8c8458bfa47028dac7c9716f0f14f4708179c47f9ab8cc
 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": 0.0001746165711125986,
+  "epoch": 0.00019401841234733177,
   "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": 50.761,
       "eval_steps_per_second": 25.38,
       "step": 9
+    },
+    {
+      "epoch": 0.00019401841234733177,
+      "grad_norm": 0.5800514817237854,
+      "learning_rate": 0.0002,
+      "loss": 0.6344,
+      "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": 421881031163904.0,
+  "total_flos": 462446514929664.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null