Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aee6814908f60d28f3e5fcc332554daab1d81bbd0d9381a2818cf428f91a055
+oid sha256:5b0a9ddfee0836ce999045e37984c53e1fd5db5723d2c234bb526f71266b9a3a
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23cd49c0107bd85eef33672afcfbfae97e1304bb32ad1839126632c6ab5c754
+oid sha256:f3dedfad9b182a8043dfff409080c3e2610386a02849bc00bdf2b07c11fabec5
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5fa5a15dacc246c77ef90ba7e7896379953025d6077daf340f31bc19decacb1
+oid sha256:e270735a79923e0c6166ab5b689b246abcdff7e078e01068f6374acfd7f47f1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
+oid sha256:5b52924c88c1c80163d374a6650253dd74b8b46052a3da6fc5e4076e57b5effa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032303654350898446,
+  "epoch": 0.004307153913453126,
   "eval_steps": 4,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,42 @@
       "eval_samples_per_second": 8.376,
       "eval_steps_per_second": 4.191,
       "step": 12
+    },
+    {
+      "epoch": 0.003499562554680665,
+      "grad_norm": 3.562119483947754,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 4.4314,
+      "step": 13
+    },
+    {
+      "epoch": 0.0037687596742714854,
+      "grad_norm": 3.721893548965454,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 4.4538,
+      "step": 14
+    },
+    {
+      "epoch": 0.004037956793862305,
+      "grad_norm": 2.8506362438201904,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 4.2002,
+      "step": 15
+    },
+    {
+      "epoch": 0.004307153913453126,
+      "grad_norm": 2.9634995460510254,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 4.3413,
+      "step": 16
+    },
+    {
+      "epoch": 0.004307153913453126,
+      "eval_loss": 4.165503978729248,
+      "eval_runtime": 187.0045,
+      "eval_samples_per_second": 8.369,
+      "eval_steps_per_second": 4.187,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -142,7 +178,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9202732338511872.0,
+  "total_flos": 1.2270309784682496e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null