Training in progress, step 7, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b22b66defc29b740d6361639a4424ad82a1d7df191d06c8f1a727e736732bb13
+oid sha256:18ee0830f20883212ecd96393ecbb3afe5bb9d4481251c3d3a73c0d69808e562
 size 42002136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0278e79cbc1820dfbc7ecb9b9a1d45e310e55f67c65ccb4aeaf29323c63671f5
+oid sha256:7e48930dd9a549221a3046a56610553133822837a22c722f2d5c49bd4c638781
 size 21822612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29ac0ebf1347f2ea10001dca6dda2df96ef033b162f3a81ba520ade824913065
+oid sha256:fec19c27ad1594bd7124ae126aa2d7f12e0203e8b32777f0b3883e04359817bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010984819589594935,
+  "epoch": 0.012815622854527423,
   "eval_steps": 2,
-  "global_step": 6,
+  "global_step": 7,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,13 @@
       "eval_samples_per_second": 5.4,
       "eval_steps_per_second": 5.4,
       "step": 6
+    },
+    {
+      "epoch": 0.012815622854527423,
+      "grad_norm": 2.0892226696014404,
+      "learning_rate": 0.00014,
+      "loss": 3.1195,
+      "step": 7
     }
   ],
   "logging_steps": 1,
@@ -95,12 +102,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2493476298031104.0,
+  "total_flos": 2885967937536000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null