Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e7126bcfcc552d56d9fa7745715d46838b39e7773a28f6d7cd407af502b2c48
+oid sha256:690e10a45319d93e3beda43b9d14b44a87f2557e3df01747b77b4281e353a097
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0802ac09f69974e0d8d696c0cec4c6563080a62407710d7c4d4e2ef9076f8103
+oid sha256:2d1a41c3924d58b254a12b45e549f5eaf738776421574d76d080c47b41325b98
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b148dae93754a9c9183af03d1af07df714063cc5db251501ea3ac1e44fb9557c
+oid sha256:34814341da005ffb046cecfb1e7d59a902f8b0155a2b2f4933cc4b87a95a54db
 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": 0.0007196257945868149,
+  "epoch": 0.000799584216207572,
   "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": 108.253,
       "eval_steps_per_second": 54.126,
       "step": 9
+    },
+    {
+      "epoch": 0.000799584216207572,
+      "grad_norm": 0.6814618110656738,
+      "learning_rate": 0.0002,
+      "loss": 1.7769,
+      "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": 24936692318208.0,
+  "total_flos": 28120099848192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null