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:c3b2dfcc940e66bafd7e4c91a84c4b4e75684d8905cebae420274093c32b4d60
+oid sha256:851a949f52a55eb2e7cde5dac90fe07a27e93dadc2402481887bc25e8f28a6f1
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d949f878988588b279a6bf4caf97838072ec99c1249eea9297d3c20febbf56f5
+oid sha256:9af8b3885021d714e2d461c428c78e84902a1943b1787c161a6f8edd04211159
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cda0ba450d27bbf2281f6a3a6a9d6b8e9a27248312721aa88724608eaf3ee7a
+oid sha256:0508585c9fe24f58afe76f4785f10d81474c66e1c4c5763458f7a0c3f7b88ae7
 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": 0.0024091547881951417,
+  "epoch": 0.002676838653550157,
   "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": 131.217,
       "eval_steps_per_second": 65.65,
       "step": 9
+    },
+    {
+      "epoch": 0.002676838653550157,
+      "grad_norm": 5.6722798347473145,
+      "learning_rate": 0.0002,
+      "loss": 10.1299,
+      "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": 19106560475136.0,
+  "total_flos": 21229511639040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null