Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56fe9e16ce543ec2ee21fff0edf3e23534143f2801fe47505021787c43080e2d
+oid sha256:0da8be5a21c744688ad028bcc1d6a3d8a87ae6f022e3ce9099aef869272c50ca
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711ca8b0270b9138942d1fe52408af6ccb63824b2690cb0fb2df8fbcc3b3306c
+oid sha256:945c3cdcd7dc4e0f23cee3d2b71a21268616c5e584d268e07a162efdca9fc95b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1157b2d97ca0af7992441b60506a469b898620f5289367d9f77c1782514f2265
+oid sha256:9249b47b1506265e614e53df0780acf62cb0efcbba316cfd15cb2d89c6c382fa
 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": 0.00033457404541842664,
+  "epoch": 0.00041821755677303336,
   "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": 43.703,
       "eval_steps_per_second": 21.851,
       "step": 4
+    },
+    {
+      "epoch": 0.00041821755677303336,
+      "grad_norm": 45.948394775390625,
+      "learning_rate": 5e-05,
+      "loss": 19.244,
+      "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": 2979538636111872.0,
+  "total_flos": 3680606550491136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null