Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f30e84edb5b48e5b1148e667840944d0a82c8be9c7c61a8c9fd243dd4d67b73
+oid sha256:14a37bb5badc2877c59ce28330b57d08fc4511fcedcfdf1cf36f7e26bc85e494
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e839fd8a0c0887b941caa2afd4820eab5b8dc8375a2f82132c3f83e4dc0117
+oid sha256:93176e8194a3be1f0dd3574a5a7cf82f1a4bd34b373e4ad0a6cb938aba708f91
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02cbecb1241da1dcf720ca1cdcbc95d2d83980810133627d4fd945fcf4ef3576
+oid sha256:028fffffef78be5fac13f01954828f4eda28508234b9795016e510d99737ce54
 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": 0.00015163960320970494,
+  "epoch": 0.00016848844801078326,
   "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": 49.489,
       "eval_steps_per_second": 24.744,
       "step": 9
+    },
+    {
+      "epoch": 0.00016848844801078326,
+      "grad_norm": 0.4741860032081604,
+      "learning_rate": 0.0002,
+      "loss": 1.3574,
+      "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": 357949797040128.0,
+  "total_flos": 405048454545408.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null