Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d1f11420eef4e1702523cfa6fbbe137d106956b8427bf18df7267d800ebffe
+oid sha256:c887dd28edd96f9ca04c8b173fe1eb10db190187cbf349d55a98d1fb0ea56037
 size 1195453784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2fa6820a41b355bf9b1b99e8009efce4db5456958c8156f60b30521b0ab91cc
+oid sha256:673e1dfc6bba723f70791c7d41ce126c8a2c042b4e7790ef0a16be35e91448e2
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e302694d1910cf7df19983c4bd66c962bff5d81f4ec13c0d68663746769145fe
+oid sha256:f5b1672cbd5ab01c0808cb3fd580c189cbe93d707de7375817aea47011002ed9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07729468599033816,
+  "epoch": 0.08695652173913043,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 7.473,
       "eval_steps_per_second": 0.934,
       "step": 40
+    },
+    {
+      "epoch": 0.08115942028985507,
+      "grad_norm": 0.373145192861557,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1072,
+      "step": 42
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.3523075580596924,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1039,
+      "step": 45
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "eval_loss": 0.09994707256555557,
+      "eval_runtime": 116.7859,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 0.933,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0338966433274266e+17,
+  "total_flos": 1.166264033649623e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null