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:bea89a0aca0456c8e491b4a20e39f18cd350e019db6151165386ca0cf488fe4e
+oid sha256:381f88e72ab8faa50d04d2967ce84087f35a4e07a5783e7377b6f00449ed46e0
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5442ed4aecff44fa62fe3def53c0666982a82e48f4bcafa7d663c0fbfe95561
+oid sha256:672b225d1faef3ea5f6520b9dcf2cf61b47f7076eafbcb799a051779d7df75b5
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231983afa907659f1652066fc762eed7adaf78a00475ebd1528076c8e4e7731f
+oid sha256:55d612405db30be7631ef4ed93147098ce2f77f32dbf1625edcdff1fe641de56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
+oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009992366941919368,
+  "epoch": 0.012490458677399209,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 9.19,
       "eval_steps_per_second": 1.15,
       "step": 36
+    },
+    {
+      "epoch": 0.010825064187079314,
+      "grad_norm": 0.19286595284938812,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 0.378,
+      "step": 39
+    },
+    {
+      "epoch": 0.011657761432239261,
+      "grad_norm": 0.20762427151203156,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.4039,
+      "step": 42
+    },
+    {
+      "epoch": 0.012490458677399209,
+      "grad_norm": 0.1565249115228653,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.3701,
+      "step": 45
+    },
+    {
+      "epoch": 0.012490458677399209,
+      "eval_loss": 0.36458876729011536,
+      "eval_runtime": 659.9797,
+      "eval_samples_per_second": 9.194,
+      "eval_steps_per_second": 1.15,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.689425626595328e+16,
+  "total_flos": 9.646733967910502e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null