Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e95b60871b50e0ec52fc2d731195bb0ef69eefc156c352d1c2aa00de4649c21
+oid sha256:5f8092d25c74fb1c7d31f5e23d9f70d762f2337b84dcf563daacfdfcc81675b8
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8efacc201472f5a33ea2db6f676e7e3a9e0772b4ec5797aec86d367529d9a0
+oid sha256:49a691c3fa38b80f6becace3ec748ce4c42b052a1416e1377a39b99784753b15
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a51f7b3ad4f6a583e4c2b2258318f92176c7adc85cde5c856bbabd7b4231af1
+oid sha256:8a8943f40817df1d296cf5ab4d9c0c953ce4b5123cc54152f56d79f4818f6e5c
 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": 0.00029143897996357013,
+  "epoch": 0.00032382108884841123,
   "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": 34.408,
       "eval_steps_per_second": 17.205,
       "step": 9
+    },
+    {
+      "epoch": 0.00032382108884841123,
+      "grad_norm": 1.7546979188919067,
+      "learning_rate": 0.0002,
+      "loss": 0.7048,
+      "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": 550107063779328.0,
+  "total_flos": 612619230117888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null