Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c03b40d520d2f20ca7f8fe14d233f188908f6f0e132f49120bbf902cbb3a65
+oid sha256:d5893767cdcaab2cad943c901cf1003e8d8eddf579c309e766c044dc9afe412d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b10d385d17816b4355bce575402b5f8e7861f8f46b30b5b87877d787b9eb49a
+oid sha256:c5311c5224542bac0c7ff303187e099a8bdb7a62fd5e652263e7d4ed87e0902f
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6c1736fef1dd6f59b0e0436ac03f5bf52fc685c6304e2891f3922fbeca4f35
+oid sha256:5bcc9dec470456049b85d58761d8b1cb7c00e042c845ac37d7d42f59480fe0bd
 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": 0.024226110363391656,
+  "epoch": 0.026917900403768506,
   "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": 12.954,
       "eval_steps_per_second": 12.954,
       "step": 9
+    },
+    {
+      "epoch": 0.026917900403768506,
+      "grad_norm": 1.2041003704071045,
+      "learning_rate": 0.0002,
+      "loss": 0.4258,
+      "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": 2080759779164160.0,
+  "total_flos": 2358194416386048.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null