Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:077578054ad6e6276507b9cb8cad98e1136052b3d315a16c076758206d2260e1
+oid sha256:1c09ade8764822bc41db9194bb283c98df6df3bee8bc2dac95824e7e5616e63c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ede4e11707fef1df5c23dcacfc284744e471dd98105b0ae6a6719b599c5c51a
+oid sha256:89d1e384c279d8088d599548019eedd20bbb6415ba8a885890f8cfab404d32fc
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a65387ba1ec6c284b308cada9b73ceeb24869d32fa7f81a3120b72b695c1d6
+oid sha256:0fa808660ddbc52908e9ed2eaba07f255839ebe308cc6b503b8b517a081559eb
 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": 0.0002702580964821404,
+  "epoch": 0.00030028677386904494,
   "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": 12.868,
       "eval_steps_per_second": 6.434,
       "step": 9
+    },
+    {
+      "epoch": 0.00030028677386904494,
+      "grad_norm": 0.4653288722038269,
+      "learning_rate": 0.0002,
+      "loss": 0.3119,
+      "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": 4986771571998720.0,
+  "total_flos": 5540857302220800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null