Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c1ef9ebf7c5fb95b771bdc7aad10376427328ae0546a4abfbdf5ea0d254f55
+oid sha256:56a2220281cf6db2e8fb4ba3227b1680ebda56f92856ee0c3aa15f9e8a773c56
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a1acf38457f9b5af05889ec47861cc0ebbf568a8731a123f6682068e40a9b9
+oid sha256:e8a381b9786a960270ee5e6c25559e97461f1a261c1ee1277c44115ee5f40cad
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7957c17c71e66dc963f46e6d3be7b079b5bf99abf8ca68e0a62e46a93d0f813
+oid sha256:f97292ed42f9c01b4b0e8df986ba9ff63c6636f8f25d1de47adaf014800a18f8
 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": 0.0014674112420005707,
+  "epoch": 0.0016304569355561896,
   "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": 54.133,
       "eval_steps_per_second": 27.077,
       "step": 9
+    },
+    {
+      "epoch": 0.0016304569355561896,
+      "grad_norm": 0.1170913353562355,
+      "learning_rate": 0.0002,
+      "loss": 0.7992,
+      "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": 422056764112896.0,
+  "total_flos": 466820360306688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null