Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dfe3673067135aa8170382cc944b11b622d610403ea10b7b1f4457e077bea3e
+oid sha256:48ae5bd7c4d6fe9409efbc4453b6728e02bc913dc9f4849177d6aeb59bafc70a
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42750a2ed30613b988fecc249d607a70d0f4497950aa1d5a8322305d6975711
+oid sha256:1cd8a1ecd181db264d4e28c8c51d617c76b2405f2046ad21641a769bd3116886
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0a52bb46f51e660abcb041b0b835241189b691ea4109f2665f135f52d27aa2
+oid sha256:b52a51c3b4c01f9b630403ebb6928c43e1ecb011855669002547cf6d66e6c4a9
 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": 0.009379763160980185,
+  "epoch": 0.010552233556102708,
   "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": 6.545,
       "eval_steps_per_second": 0.818,
       "step": 40
+    },
+    {
+      "epoch": 0.009848751319029195,
+      "grad_norm": 1.2443710565567017,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.9659,
+      "step": 42
+    },
+    {
+      "epoch": 0.010552233556102708,
+      "grad_norm": 1.705289363861084,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9469,
+      "step": 45
+    },
+    {
+      "epoch": 0.010552233556102708,
+      "eval_loss": 0.49251818656921387,
+      "eval_runtime": 1097.4638,
+      "eval_samples_per_second": 6.544,
+      "eval_steps_per_second": 0.818,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.030418891538432e+17,
+  "total_flos": 1.159221252980736e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null