Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519fd91a95038db41cf0aa0be385b38305ae8c47b7050bb526018769f3b052e8
+oid sha256:eb42c94ecabf7e354e053eee6bb307fcc8bab45c693122ad13a1942114fc5a49
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f016159e7e510d854403029f81b075cce1be4e9360688f56fe2aae0125b7f4
+oid sha256:83c44efd529ec01eeb1857021a4f4d196399fad4a412f9c8dab00c0a0b0fe894
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519f25b43551ebd208fc8e91efe3efb9ed6b1ef480ba8fcb9b6b0c22698c9e5b
+oid sha256:c720c8defd275139cbdc90e31a2e72e4ff1d728eb6df0b7336db7184727078ea
 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": 0.0004480565546940147,
+  "epoch": 0.000497840616326683,
   "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": 78.331,
       "eval_steps_per_second": 39.166,
       "step": 9
+    },
+    {
+      "epoch": 0.000497840616326683,
+      "grad_norm": 6.827943801879883,
+      "learning_rate": 0.0002,
+      "loss": 11.6631,
+      "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": 71316170342400.0,
+  "total_flos": 80699876966400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null