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:af80dc3dbc67a8f412ea1776a309e27a01c6ff26da8b1e4388b2990f78c33cd3
+oid sha256:f81c62a3a69f5556635af507c0d9f9a5428adf1842706d7e1fb9db57023e6eb6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eef19dfe87c50999f5459a60b7137435252e9f25d85f89edbf657d86628e45e5
+oid sha256:500596855378d314cbd1c807f6e51deaabd6088719a786e69b7423dc2d9a4716
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88471f2b3b1e4c205d9505ad6de006cb23590a0562a633e21bbcb4ef69f0d7ee
+oid sha256:7b0e1e671455c353fa99a1d12b6e48bbd12137e1c5f529ac1c3f24d8e1df3f99
 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": 0.004986149584487534,
+  "epoch": 0.00554016620498615,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 18.022,
       "eval_steps_per_second": 9.011,
       "step": 9
+    },
+    {
+      "epoch": 0.00554016620498615,
+      "grad_norm": 0.8381862044334412,
+      "learning_rate": 0.0002,
+      "loss": 1.418,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "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