Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f53e8ae8971ac669c2c58bba49858e0fdba892ed1e3d78082d5d8bb519c5a2af
+oid sha256:480248b4ea5ea1f17872ce0300d353a0da309a6dc89f8b90c6b671e8d575d264
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d0bf82eb759ac8ae434f2f233626f9cdf6a51b49d0215d60e18833c8a9fb4b
+oid sha256:525094f0f721eb83b5aeb3b1a6bed7b85708a25432ba0cd85775dc0871a711de
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
+oid sha256:648a063f91ae3ab228fd410ffbd4321ad14a00c1e969d3c92bcd911e862ae5e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01073645361516524,
+  "epoch": 0.013420567018956551,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 9.157,
       "eval_steps_per_second": 4.579,
       "step": 4
+    },
+    {
+      "epoch": 0.013420567018956551,
+      "grad_norm": 1.1429316997528076,
+      "learning_rate": 5e-05,
+      "loss": 2.4975,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3057746266030080.0,
+  "total_flos": 3822182832537600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null