Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0449ef28d5ce1ae2f02b4aab520a2e7720275b7419165e3ff0df63c5056c1607
+oid sha256:a0d213d8ae0aea6f4cdfa77d22c89adfcbd9c58933233799b7e3f09510a46750
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08a1f72caa44de4c9aec860d23ed9c2faef5f0234fc55dcda7d32908c27fbbfd
+oid sha256:ec64c232bd230a8b7a9122cbf487b1eb9fdb9dd599f309fa53baa9e0e16560ee
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a73e21189a4195a376996e0cdf789430bf6c3938dd06e270a134b6faf6d3f863
+oid sha256:425c36d2edac2adad60398a311dbff6f62f10a36b16242ecec13588ec6e6ad76
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
+oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016377952755905513,
+  "epoch": 0.032755905511811026,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 54.082,
       "eval_steps_per_second": 27.121,
       "step": 13
+    },
+    {
+      "epoch": 0.025196850393700787,
+      "grad_norm": 0.6350086331367493,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.1128,
+      "step": 20
+    },
+    {
+      "epoch": 0.032755905511811026,
+      "eval_loss": 3.009904623031616,
+      "eval_runtime": 6.1583,
+      "eval_samples_per_second": 54.398,
+      "eval_steps_per_second": 27.28,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 99740943384576.0,
+  "total_flos": 199481886769152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null