Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cbf0864f0aa8de4d896fd13b3aa842d71ac879b706ad3a0d8a4fd6b9efde96f
+oid sha256:c20a29a4f350b194f65453ed5e5b1765311278bd7ac338ca2362bed6cd86a020
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9b928c6c37d809e31fb873483ca130fb387f1a0cf751bf4de8f08fbcc44d70
+oid sha256:7359c1838a8974b52757aa5b29a375ab6505e73d980f35626132b315999e14ce
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5059cf0c71c51f02ee969590c9c397dea8c41610c914bdf8477692d8344aa4
+oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
 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": 0.013634426927993182,
+  "epoch": 0.017043033659991477,
   "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": 227.31,
       "eval_steps_per_second": 113.885,
       "step": 4
+    },
+    {
+      "epoch": 0.017043033659991477,
+      "grad_norm": 5.32535457611084,
+      "learning_rate": 5e-05,
+      "loss": 176.9375,
+      "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": 11953766400.0,
+  "total_flos": 14942208000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null