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:e72f73dfc4300734c8ed35095c7b97ed64373aec4f2048b40ddb819133e97290
+oid sha256:7df34b6417c8610b3aef0b6e00d087b520d8429b0c2a1834c88105a7ef3122ca
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88065eff5f6420a776d19c46d8f6f9c5cad71429c3a3c84678d263ec21177ff
+oid sha256:eaef8506300ee4403ae7a371dd204e0c158986579bc7f3a92c2e6ad93cac8f0a
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
+oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
 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": 0.015157894736842105,
+  "epoch": 0.016842105263157894,
   "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": 97.064,
       "eval_steps_per_second": 48.532,
       "step": 9
+    },
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 35.027122497558594,
+      "learning_rate": 0.0002,
+      "loss": 10.6329,
+      "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": 78955709202432.0,
+  "total_flos": 87728565780480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null