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:cd4d5f1c4e16fd37993ec057ce9d13a4f5908f28556ce1be4f94a4d93d0f2a88
+oid sha256:0a8b84805ce10b8a286e60f8d45ef85fae3794cfce814dba81aaffb4561ec595
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20bff29b5b796daff7724929331939ca217210a8d053ca927c9d6f9b2991c02
+oid sha256:459c7d490af6a8e4997db8ad2dcdf7f267b64ccc118a93da00d4ae5c9dc3a8b0
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:635c47772ce41ed550f0ac7920b2ba0a1cd09a12c8aab2bbc6149708a1dac331
+oid sha256:3db62b9e3564a9abcfe2f4c185ea6ef35dca6f84f5f3e8fc8815147a04d9f3d7
 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": 0.0224019912881145,
+  "epoch": 0.024891101431238332,
   "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": 78.521,
       "eval_steps_per_second": 39.26,
       "step": 9
+    },
+    {
+      "epoch": 0.024891101431238332,
+      "grad_norm": 2.5304298400878906,
+      "learning_rate": 0.0002,
+      "loss": 8.087,
+      "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": 22290987220992.0,
+  "total_flos": 24944676175872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null