Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e59777a7cfe1559f0102ac38de438f53c8906418bb638c69622963006726246
+oid sha256:a3b3069c6728edcd9b3d48a6a3bf47cc9dec4b53f905463665a5b98fb92684db
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef36988a855c6f9724204fe3d2ed86883b08121f4790e72a65832823a9a3f09a
+oid sha256:a52edbe6b6e28a87e1d9b4af967c298c180d67201eac8f5b433ddefde5c96579
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
+oid sha256:787ef78ee12881294c4aa83ed64603709fff88fc133de1a040e06eba2a245935
 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": 0.00034053501835105374,
+  "epoch": 0.00037837224261228196,
   "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": 2.141,
       "eval_steps_per_second": 2.141,
       "step": 9
+    },
+    {
+      "epoch": 0.00037837224261228196,
+      "grad_norm": 2.7024037837982178,
+      "learning_rate": 0.0002,
+      "loss": 2.68,
+      "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": 6328165488132096.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null