Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75994ea16d4069456a370be23886e2292761f4ede8eec27a44af6723ac97e466
+oid sha256:d108cee729de49b3ff488faf87997b682efb399eaa41da2a2dc205281c2d6e8e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ace7c9d158e362dcc481dd0c43b08f3445dda3a95ca8a271a6e1c81bfb3f63
+oid sha256:360a1f4972b3423f54ec206105fb405be437f56b015cc5ae046a01178eeafaf8
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a94b83956618c5f6ad1eb1e148eb701d120c1b0cae59d7acf6b263a4a79491
+oid sha256:7f67aff9f0cdd92218acf4442ad1be927d0f03fbd597b3574918cfb798f32cfe
 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": 0.0014719110311554502,
+  "epoch": 0.0016354567012838335,
   "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": 22.003,
       "eval_steps_per_second": 11.006,
       "step": 9
+    },
+    {
+      "epoch": 0.0016354567012838335,
+      "grad_norm": 2.14523983001709,
+      "learning_rate": 0.0002,
+      "loss": 3.9452,
+      "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": 2849583755427840.0,
+  "total_flos": 3166204172697600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null