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:fb27303750eeb9955d01ad58efe94ad7d710fd0ff322a0747df94615b9ba7eef
+oid sha256:d55bf6da0644cb0d2142e588ebee24edec7c8fbaa1101999298c5f16307d184f
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55826e737172b13c45258f706141fa38f30950c6c0784cd3b1fbe2fafd1d1bd5
+oid sha256:66cc0efe7eada77580833e1b65a2f2bb2bf75cfa8182684aa3f7c47a6bd94512
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e0a74fe9508dbfd827ca0321e6a651e901032790ac8b3d5db071ccf895bbe5
+oid sha256:abee12ff943f61ea027547de22fd9946ae7c7d29fc3926528191d84051846b55
 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": 0.029612756264236904,
+  "epoch": 0.04441913439635535,
   "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": 114.724,
       "eval_steps_per_second": 57.362,
       "step": 26
+    },
+    {
+      "epoch": 0.03416856492027335,
+      "grad_norm": 0.93305504322052,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 3.276,
+      "step": 30
+    },
+    {
+      "epoch": 0.04441913439635535,
+      "eval_loss": 3.166438579559326,
+      "eval_runtime": 3.2453,
+      "eval_samples_per_second": 114.01,
+      "eval_steps_per_second": 57.005,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 173177884901376.0,
+  "total_flos": 259766827352064.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null