Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a059bd0ace39431014e1bac4917c4d905723df42c8e218f9dbb93eefc549d72
+oid sha256:bb93af2f0b14d548d4a67fbbb759262e51c89f72f6e133d21d9876d319721308
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d424efba434bb25e8616897573a75263b477c879ecf39e6801b699a6269b747a
+oid sha256:40c7b0ffbc56d00bb88cf1ef0ae244d11440539b2120498421baaf26acbfc0b1
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1fc0e781ebc953a61596ae4d4eb97a2bca42d09c802a3873596a2892def541
+oid sha256:1f98bc0c3a7e4ea6a8ac7c366cccb4bb7940a8ee426517e92269de9f27e81c9a
 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": 0.00028076743097800656,
+  "epoch": 0.00031196381219778506,
   "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": 46.089,
       "eval_steps_per_second": 23.046,
       "step": 9
+    },
+    {
+      "epoch": 0.00031196381219778506,
+      "grad_norm": 0.22768421471118927,
+      "learning_rate": 0.0002,
+      "loss": 2.8706,
+      "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": 559803675967488.0,
+  "total_flos": 624708449992704.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null