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:ca43d21084be50bee747efb87c3d0ce96cb035fe3cf5c6baf083200a498470ed
+oid sha256:b4822f4ed84abb200f086eb3d10e774eaba3dc38f8c1b9c318a6246369223f1b
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf5a2fdf94b816554b1ed43267c6a21755fa282233b371a01e4fba5be0620b3
+oid sha256:276ae1e02a63c5f7153d716ec9ed9bbedf5a182f0cf066dffd60b02f9c688ee8
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:763f8e5e1764f8fe266a2cfc69a07a7744dcf177e3e51c837cea1db60fa9ebeb
+oid sha256:aa1c11cc02ca6c0d441d7517efb44d7c4ea980e6fce251e31e8f625c6ac0020e
 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": 0.013729977116704805,
+  "epoch": 0.015255530129672006,
   "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": 5.438,
       "eval_steps_per_second": 2.729,
       "step": 9
+    },
+    {
+      "epoch": 0.015255530129672006,
+      "grad_norm": 15.314831733703613,
+      "learning_rate": 0.0002,
+      "loss": 1.8957,
+      "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": 2006645987082240.0,
+  "total_flos": 2245532414115840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null