Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782128a9e0f95cf64610eb61559c38652d06e9e314e40df2a96c9122f4ba4f1b
+oid sha256:517403d960fc46232c92ec410586ce0d63bf9f7003fdb663f48e51bb848d3b5d
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060f614a93fee3509aa3325802b25163a8cede3f7bbce49b48b6c3e7bbe18262
+oid sha256:786db1aa9649115767cd2ff191e8828d021f5fca053535dc3e09a3bddbc20ad9
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
+oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
 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": 0.003789473684210526,
+  "epoch": 0.004210526315789474,
   "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": 361.882,
       "eval_steps_per_second": 180.941,
       "step": 9
+    },
+    {
+      "epoch": 0.004210526315789474,
+      "grad_norm": 0.3295745551586151,
+      "learning_rate": 0.0002,
+      "loss": 10.8424,
+      "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": 738266185728.0,
+  "total_flos": 820295761920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null