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:ce349377e802b7a114167392046f8df0fda5731465823c873a2f6ca9339ce5ae
+oid sha256:05b2e973c7dd74d301cdab4e697a49ac48628a15047c9f61a17204521869c792
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a0d34dcfd90114ec4613515b75c3431ec73ed64ed4d6c4461c061340342e46
+oid sha256:fef344b6e2b38edb4add7e03e6220402d38a32564f400c16eec1cd40eee81a10
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acdade362df9dd708bf0582f5eb23853e9115d60b97013c2d2b1a9acd29023bc
+oid sha256:b2ac488ce1f441ca1ae6806867cc0d824ea5a04d174d746efdffa5a728cba642
 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": 0.0006502185456778529,
+  "epoch": 0.0007224650507531698,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 12.527,
       "eval_steps_per_second": 6.264,
       "step": 9
+    },
+    {
+      "epoch": 0.0007224650507531698,
+      "grad_norm": 0.09472781419754028,
+      "learning_rate": 0.0002,
+      "loss": 11.9347,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1783472062464.0,
+  "total_flos": 1939916980224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null