Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44fa72b36bb76c0ece04d174fe30da2cf885c2736d6b52ce166d23f6ad457b6f
+oid sha256:35cbdd7d2c2b118733466af6b07c125b07a95ba4283700751f1a849a9528f13f
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374efcc16212a10250b9021ae231c85652028cbced1cdeac1efd59df8f6cfbc7
+oid sha256:fb3a9c6142b2216994f7ca0cf696e7bbc47e0b8d8c0920e46fedcfd16b77b6fd
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef9f1d4879be0518d6465f2707e78cd83bf4911c48a1ca7e31f99068a69cbca
+oid sha256:bb4f84e3df39bc4065fc2ef04f4d348327ebe5cfd5943e53bd9f635d7b1e00ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003450060376056581,
+  "epoch": 0.006900120752113162,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 0.5964,
       "step": 9
+    },
+    {
+      "epoch": 0.004140072451267897,
+      "grad_norm": 2.3001599311828613,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.3384,
+      "step": 12
+    },
+    {
+      "epoch": 0.005175090564084871,
+      "grad_norm": 1.6452058553695679,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.6674,
+      "step": 15
+    },
+    {
+      "epoch": 0.005520096601690529,
+      "eval_loss": 0.3198825418949127,
+      "eval_runtime": 115.0968,
+      "eval_samples_per_second": 10.608,
+      "eval_steps_per_second": 5.309,
+      "step": 16
+    },
+    {
+      "epoch": 0.006210108676901846,
+      "grad_norm": 1.4537681341171265,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5395,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1697012470775808.0,
+  "total_flos": 3443213708820480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null