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:fb125c7942e13fce5cc509b0ad3776d36e8c0d4f50c4966df47651ea5ff3db0f
+oid sha256:f2858c949221d333516b4376dc6c6d051a44ad5a16b802a62bed50e5b4dae4f5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f6838f4c50571efc3067e25a1b8fce7ac398b17a28333d781213a7f1bfa73bd
+oid sha256:9e077f0d939953dd87c683a45c8ea9c25291c4fdee0621f9f262f315765edfe5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
+oid sha256:deed864d9094dd276975b1a0b401102b49095b3b4735cef2dfce0c737a2bfd46
 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": 0.006153846153846154,
+  "epoch": 0.006837606837606838,
   "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": 17.557,
       "eval_steps_per_second": 8.779,
       "step": 9
+    },
+    {
+      "epoch": 0.006837606837606838,
+      "grad_norm": 1.270402431488037,
+      "learning_rate": 0.0002,
+      "loss": 2.3454,
+      "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": 3329215646662656.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null