Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f7ec55d0d67152854ebe7902e368f300849fec538a8f021e2f7fd19c849a17f
+oid sha256:32dd43c67f0edd6beb327bf268e0bba624d5e22b7e0389c6e1a868f1ad79b84b
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe70b6dff690678e2ebe12b45bd002e54cbccf629c844c816f1ed09daf3f010
+oid sha256:82bfe3fe3268416258cdaa02544d696a142992b49f3284be27b8007ab72f7236
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b543366cfabdd66b7ed63582e5303f4bff99a84636648762ece313be1d5466ed
+oid sha256:024409963b12e6d11d1a7cb7bfc91b755e58587bf312b0dce1b1b785fdb23734
 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

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004729374671571204,
+  "epoch": 0.005254860746190226,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,13 @@
       "eval_samples_per_second": 39.746,
       "eval_steps_per_second": 19.873,
       "step": 9
+    },
+    {
+      "epoch": 0.005254860746190226,
+      "grad_norm": 0.4398048520088196,
+      "learning_rate": 0.00018,
+      "loss": 0.0441,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -117,12 +124,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 291868432662528.0,
+  "total_flos": 324298258513920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null