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:c5b622a279289e3a15cd81401ae5c8683d3d1c8fccb600a52e3d8a9f3596e468
+oid sha256:718d2f7a2f1c30c6ed13ca91e6b694d984882534bd27e2983baa42641ce77013
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc717097de3a7118fb6627b13f626793cff4ff2482c223483e6b374ef8db26a7
+oid sha256:ab307f875b834173c6e362283b79d84d9b98c4dcc08be3c08c506b18a8bf1c23
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59870425f15b9c5b2c89fce32a5e0487ab127e9451b5309669abcf6644851b81
+oid sha256:e57f9552f8359753dd8755b0f26ee46ce1eecb1abf0af76b7586afd0f50093da
 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": 0.0009338279162667636,
+  "epoch": 0.0010375865736297373,
   "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": 49.699,
       "eval_steps_per_second": 24.849,
       "step": 9
+    },
+    {
+      "epoch": 0.0010375865736297373,
+      "grad_norm": 0.955893337726593,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "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": 109071750660096.0,
+  "total_flos": 126879383420928.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null