Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46bab68235b5cf79bb8bdbd21dff8168ceb96b2de12f660c1c568912711d374b
+oid sha256:1a8be4e4172d7cb65510f3bb55b5983f687ded0286495693b68edc120e16ffb5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0aaf802f087992b6afe6cd186331187a7a94bbbe39eec0e06dd779b3baf1f47
+oid sha256:c40a178926a860e65cf18ed27d0d17bc6e802de04ff1a5f5e50917a6e6f383db
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0e1e671455c353fa99a1d12b6e48bbd12137e1c5f529ac1c3f24d8e1df3f99
+oid sha256:2832083b4e6c15f4e4a293e39577f239ce48e4a52291017055748ff52251da78
 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": 0.002841806125670982,
+  "epoch": 0.0031575623618566467,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 19.9,
       "eval_steps_per_second": 9.95,
       "step": 9
+    },
+    {
+      "epoch": 0.0031575623618566467,
+      "grad_norm": 9.006460189819336,
+      "learning_rate": 0.0002,
+      "loss": 3.7795,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1752671799214080.0,
+  "total_flos": 1971755774115840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null