Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e893bb321fb1b9e430fc425d532c0befdbbebb7e1b0543fddf2892f1c2f08d
+oid sha256:f76a89dbc920c09c000ecfb9712362cb280073f5d9e9f543240078bdc78e89ab
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ac4de0ac0d167405b66ec67fa98c7c51577aade0e0f32ee77f0d84505f23a0
+oid sha256:8d4ecaa06528bff6cd607e9680c2643425e53f3d101ad6236539d4bdcd3287a9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
+oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
 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": 0.0011335659505127614,
+  "epoch": 0.0014169574381409518,
   "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": 32.132,
       "eval_steps_per_second": 16.066,
       "step": 4
+    },
+    {
+      "epoch": 0.0014169574381409518,
+      "grad_norm": 6.726502895355225,
+      "learning_rate": 5e-05,
+      "loss": 7.2062,
+      "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": 3837845814902784.0,
+  "total_flos": 4716388832772096.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null