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:df3dec194597d2557c392468c3488c45db32c8281ba7401a58975476a6bf00d5
+oid sha256:bd5a1596c86ab389bca675a7d654eaf33a8bd5f39cdbe065a001862b220e2f63
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ffcadb7aad7efd24c634b594f3fd738c2419b4e41dd0df1a14da7dc1a0b1d3
+oid sha256:170f0f5b77e001848eb7478aa4aba5a07896f485e307119b8c5540f94401b078
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1062f79177d2635d7d8b560b420014391b57cb1f30c0a2cf7f9ac503015703de
+oid sha256:a31c36714655102fa4f4337685c2b42f88149f7418eced50fa29426793cb348a
 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": 0.0012721381860104554,
+  "epoch": 0.0015901727325130692,
   "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": 8.499,
       "eval_steps_per_second": 4.25,
       "step": 4
+    },
+    {
+      "epoch": 0.0015901727325130692,
+      "grad_norm": 1.681339979171753,
+      "learning_rate": 5e-05,
+      "loss": 10.7575,
+      "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": 8663286782361600.0,
+  "total_flos": 1.07866413858816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null