Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af95ccf557f13a06778dd7d2589ae2d031534e23c548935268db09a6a5ea18f5
+oid sha256:3187d116652c8d7112e3788618a043dfed8174399e30c54bfcfe0acf4dd04e02
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:800e380777c7a27bfdfd6e1094fda5c77b978d1fc79ccd68cdb13335953aad16
+oid sha256:8c666a903c8232d113a1637ff02c446c72a45509076ae7d9daef4e24084c0c67
 size 452984596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89ec0b3464ec81ffe0d2e0c854af74e40aa80a3e3c07ab295b4748b49a1ed383
+oid sha256:3a696f4f4ef874185a5e7579567a0af28c595c2c53f9530c5b0b9f0b7ce590e6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0022137974928743394,
+  "epoch": 0.002767246866092924,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 6.646,
       "eval_steps_per_second": 0.831,
       "step": 20
+    },
+    {
+      "epoch": 0.0023244873675180564,
+      "grad_norm": 5.235165119171143,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.4472,
+      "step": 21
+    },
+    {
+      "epoch": 0.002656556991449207,
+      "grad_norm": 10.688201904296875,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.467,
+      "step": 24
+    },
+    {
+      "epoch": 0.002767246866092924,
+      "eval_loss": 0.4081224501132965,
+      "eval_runtime": 2288.0412,
+      "eval_samples_per_second": 6.65,
+      "eval_steps_per_second": 0.831,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.5124529512448e+16,
+  "total_flos": 6.890566189056e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null