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:eaeb580db24bcbcc92f2848a6377dbe5c287a9edb83ca53b3b354aabbab412e3
+oid sha256:d04b042abaa11a8c4bad43203f5f8438c8b69ed81ef629be0628867c1ee111c5
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1bf4b40a2365aab18468664145b82a4ad72f217d6463faf8071356d09547b6
+oid sha256:1b7cef1593230b9ea1b65cf8d894e86c676e09d94b365081e68716d1f2f91945
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1049aaaabf553e9cc168bd42213749c184f17199a7b92bdba0b18db5a3ebcaec
+oid sha256:c331a15520bfc24518ccec677c3cfcca781a599d881d790a973f017b8b46bf89
 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": 0.03444976076555024,
+  "epoch": 0.03827751196172249,
   "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": 7.431,
       "eval_steps_per_second": 3.716,
       "step": 9
+    },
+    {
+      "epoch": 0.03827751196172249,
+      "grad_norm": 0.4690059721469879,
+      "learning_rate": 0.0002,
+      "loss": 1.3134,
+      "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": 5699169775779840.0,
+  "total_flos": 6332410861977600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null