Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d213d8ae0aea6f4cdfa77d22c89adfcbd9c58933233799b7e3f09510a46750
+oid sha256:df60136d03e23f4d49bf6eba23440ffaa370b225ab93d45cc24036370a3a5715
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec64c232bd230a8b7a9122cbf487b1eb9fdb9dd599f309fa53baa9e0e16560ee
+oid sha256:f9e2c6bed21db4281a194ccffd66c4b93d0039bfacc5b0d33dc37e017ca37f85
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:425c36d2edac2adad60398a311dbff6f62f10a36b16242ecec13588ec6e6ad76
+oid sha256:75edea52d41d208ca719ebf2156cdc8388477750345a58b2d3c205bcb4108543
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
+oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.032755905511811026,
+  "epoch": 0.04913385826771653,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 54.398,
       "eval_steps_per_second": 27.28,
       "step": 26
+    },
+    {
+      "epoch": 0.03779527559055118,
+      "grad_norm": 0.7571959495544434,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 2.9715,
+      "step": 30
+    },
+    {
+      "epoch": 0.04913385826771653,
+      "eval_loss": 2.9804084300994873,
+      "eval_runtime": 6.0644,
+      "eval_samples_per_second": 55.241,
+      "eval_steps_per_second": 27.703,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 199481886769152.0,
+  "total_flos": 299222830153728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null