Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11a545004aff1139236a1a901c250a4312bf7048511bef94d95b4a19f9360cb4
+oid sha256:47cb74eaa3f3e9416d6bba83d46d9bbce0dda0b60c298114867aa85bed7c7be1
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8afa6537c01a22f18638ba7242ffc9fff167f28dec2e8f1a1ee1e37094255886
+oid sha256:377f4a7c12ec6aed8c816b86fe8b486d5a6d6ecae7bdb4b6faefe81e31611ba1
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acaabd0241bdb4b71e1d0732da71569e99114da61db10e89ea929a99ec596161
+oid sha256:7b0bee0f47e046288a8ab410015fc2b2510b7d505ae807cb056407e3f2c1143e
 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": 0.12949640287769784,
+  "epoch": 0.14388489208633093,
   "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": 54.96,
       "eval_steps_per_second": 27.48,
       "step": 9
+    },
+    {
+      "epoch": 0.14388489208633093,
+      "grad_norm": 2.875525712966919,
+      "learning_rate": 0.0002,
+      "loss": 2.8397,
+      "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": 69051422343168.0,
+  "total_flos": 76723802603520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null