Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b280c727e5ee5e7534e19832eadbef15dafd122763276af4f77d1124b554b1
+oid sha256:3e9ed0cfef618f69e7b2d05eae64f66f0dd266bf47127096b06f364bb5f049d6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:226b8828b9dcdf1de0c3a1814add629b14c5b081db6564f144048001a828139f
+oid sha256:efb8c708ffb144e1285f43dae51b8c16ad6a8696dd318896f4e6e9bbe710e5f6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7170a2d9b24ecc77552af509fa5ca848d0a66f21c29b073517cc02fd19368fe3
+oid sha256:d8b308b5e594ea75d70a9db0c7e4c8ae8b3c774396b79358868a60b3a58dba9e
 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": 0.03299725022914757,
+  "epoch": 0.03666361136571952,
   "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": 9.423,
       "eval_steps_per_second": 4.752,
       "step": 9
+    },
+    {
+      "epoch": 0.03666361136571952,
+      "grad_norm": 13.798932075500488,
+      "learning_rate": 0.0002,
+      "loss": 2.7228,
+      "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": 1664607823331328.0,
+  "total_flos": 1849564248145920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null