Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381f88e72ab8faa50d04d2967ce84087f35a4e07a5783e7377b6f00449ed46e0
+oid sha256:a9638ab5a52f88ebd80032bb8f3263d6b4c81329d4fc18b6c09010428f1cb87d
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672b225d1faef3ea5f6520b9dcf2cf61b47f7076eafbcb799a051779d7df75b5
+oid sha256:4adce36d56d6ca4cab7255d215a6ac2722f78872fbc18add544cbd4c9f9f92fb
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55d612405db30be7631ef4ed93147098ce2f77f32dbf1625edcdff1fe641de56
+oid sha256:2bf42e7f87caba383b22782e2b7179fde7a6de33b2b24b2c9d2794c015512971
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
+oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012490458677399209,
+  "epoch": 0.01498855041287905,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 9.194,
       "eval_steps_per_second": 1.15,
       "step": 45
+    },
+    {
+      "epoch": 0.013323155922559156,
+      "grad_norm": 0.1587727814912796,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.363,
+      "step": 48
+    },
+    {
+      "epoch": 0.014155853167719104,
+      "grad_norm": 0.19063134491443634,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 0.3633,
+      "step": 51
+    },
+    {
+      "epoch": 0.01498855041287905,
+      "grad_norm": 0.16761146485805511,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.3519,
+      "step": 54
+    },
+    {
+      "epoch": 0.01498855041287905,
+      "eval_loss": 0.3595520257949829,
+      "eval_runtime": 660.1365,
+      "eval_samples_per_second": 9.192,
+      "eval_steps_per_second": 1.15,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.646733967910502e+16,
+  "total_flos": 1.1673946178558362e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null