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:d7d0416ac724832d55b0e97a8f45f9746203e28c7b195acb216c2ebda9a6c9e4
+oid sha256:0c9a3d886ac532585ebb7af13091a19768a562624d4f99daf36e82b46c03e450
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f942e01878dba063cda5ac527caeed83474f8089255656ccd78385a2c5d6ae
+oid sha256:4acb0f392e4e76e3b4336497484525c09281cf6ed984d0875d6169eb07ebb6e0
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc527ae92339ea167c2945496cfde8562215165c21050204ee36547f80f22391
+oid sha256:eab0aa09bbb2059eef409050846e568360b5b777e22dcbcc22066ef429c07f97
 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": 0.03829787234042553,
+  "epoch": 0.0425531914893617,
   "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": 32.466,
       "eval_steps_per_second": 16.397,
       "step": 9
+    },
+    {
+      "epoch": 0.0425531914893617,
+      "grad_norm": 1.6802290678024292,
+      "learning_rate": 0.0002,
+      "loss": 1.4407,
+      "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": 450087597637632.0,
+  "total_flos": 500097330708480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null