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:e7de09bfdafd876609ac0bc3c71ab00882e1bc8e1a4cea5b4738b7f68d94c339
+oid sha256:12fba7876854fbb78ac5e65af42728cd39979bb341c851c3863872dade26cf43
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebcd242452bfc654bc56e9a65e9d1d143de4499f001e4ee6bfa43ef06a4b7a55
+oid sha256:e2ae8abc8ff92b054e56fb4f9238a57df46bcef7073b869636c9a3b14dc3b0da
 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": 0.019857275829972074,
+  "epoch": 0.024821594787465096,
   "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": 13.548,
       "eval_steps_per_second": 6.774,
       "step": 4
+    },
+    {
+      "epoch": 0.024821594787465096,
+      "grad_norm": 51.19380569458008,
+      "learning_rate": 5e-05,
+      "loss": 16.9652,
+      "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