Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:937b8c07c668dba4eb2a4fd290a2e788e20ba645e69def3ff99506176a32d1c1
+oid sha256:d7ccf814be933d0123d8e5fb53a91082309dd6cc99d24476159ec0e6d3a4d3d1
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c589467701be8f412a25a877d4cc7e25d3c8b7e60dc6ae757816ef5ed66695
+oid sha256:4ef0353b94ede9930f1bfd7eae3bddb8cf2b65fa2b5229da2a39274a92295389
 size 1656058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fd9a273afce6245b47c12202ac7b282edb77ae2a41fe12118524eef3d6863ae
+oid sha256:f2c0440944cedee5c8bcd4e2460ca401866b61f985a2c5bc78c69d722a2bc1c0
 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": 0.0001334930305513633,
+  "epoch": 0.00014832558950151478,
   "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": 14.817,
       "eval_steps_per_second": 7.409,
       "step": 9
+    },
+    {
+      "epoch": 0.00014832558950151478,
+      "grad_norm": 1681.9525146484375,
+      "learning_rate": 0.0002,
+      "loss": 95.5572,
+      "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": 80435610648576.0,
+  "total_flos": 89372900720640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null