Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2b2df6a6b4d29c84454ef59206c6d6efbf0d69cb4cb565151bc14ae4378a11
+oid sha256:011048f9134558f57dc0a880c03ad72cf23152038ce6d92228aa8e20854eacf5
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1837e980bcde92f822e400383197de2d0f88fb16a4a139acdd71410fe9ea930b
+oid sha256:298d0e941a5ccf17e985c219e609a623b537258c8dd070fad3b3ea0d976b60cd
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3231eed61bca66024c3cc6045d9ebe8a23049e0e228243789fa6b15f4c52be
+oid sha256:f024375d7496e4b835d6d595543dfd9295d475bb8a4c7fc4ddf17e04330097e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00458028714877125,
+  "epoch": 0.0091605742975425,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 3.395,
       "eval_steps_per_second": 1.699,
       "step": 10
+    },
+    {
+      "epoch": 0.005284946710120673,
+      "grad_norm": 39.66749954223633,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 5.3819,
+      "step": 15
+    },
+    {
+      "epoch": 0.00704659561349423,
+      "grad_norm": 4.8887529373168945,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.7644,
+      "step": 20
+    },
+    {
+      "epoch": 0.00704659561349423,
+      "eval_loss": 0.3575800955295563,
+      "eval_runtime": 357.0091,
+      "eval_samples_per_second": 3.347,
+      "eval_steps_per_second": 1.675,
+      "step": 20
+    },
+    {
+      "epoch": 0.008808244516867788,
+      "grad_norm": 20.166486740112305,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.3496,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2579973411962880.0,
+  "total_flos": 5255501394739200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null