Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:461dbbaeb5f65cb767c069783ec893610397babc197c6d923540b29ec58a6313
+oid sha256:1dc9942994957221327e996823f578b1b78fd131db0b07f29088a2e0d2fca32d
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dee9d08462d4dce024de8abf0503cae23ebca74cbbaa8eaf7e994a72cf5b5fb
+oid sha256:ff6794282b03f8f5db02ee0158a9e872c1ddf7c79d487e89d52ece1697cc7c10
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d3253e1657e0e5e1dce4606e0080d6574b33a3e708581e44bc5526ab5260da9
+oid sha256:46a26cffb30d94dfb85a910a3e3a744db87392e329b9566998aa7724bb44f185
 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": 0.020156774916013438,
+  "epoch": 0.022396416573348264,
   "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": 20.912,
       "eval_steps_per_second": 10.456,
       "step": 9
+    },
+    {
+      "epoch": 0.022396416573348264,
+      "grad_norm": 0.9850199222564697,
+      "learning_rate": 0.0002,
+      "loss": 5.7362,
+      "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": 1847154255593472.0,
+  "total_flos": 2052393617326080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null