Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06361a5f37694860d45455bd36f05948f7004a758571d256ed658aec99554747
+oid sha256:2b4aefb26bd3197fa8a1f24085c1a32f98df41e5904e44081aab060847a5672a
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601694bd5b1fcd38726af40fbb4daebe99740a0ddb3b8faace887549213e4d6d
+oid sha256:488d85bc60101bc276735d86e3e063ea0b21fa18ad7d4bd09206e203054ba5fa
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab22ddf51bfbb0e52394ea82ce6def3703300cb6b77357d2a920d3ed8bca3047
+oid sha256:8532b81b442a52e7641152d52819f99f24bb427b98bc8d1a82e25a081ba985ff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1073345259391771,
+  "epoch": 0.14311270125223613,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 11.059,
       "eval_steps_per_second": 1.406,
       "step": 15
+    },
+    {
+      "epoch": 0.12880143112701253,
+      "grad_norm": 6.458031177520752,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.5215,
+      "step": 18
+    },
+    {
+      "epoch": 0.14311270125223613,
+      "eval_loss": 0.0960574522614479,
+      "eval_runtime": 21.3479,
+      "eval_samples_per_second": 11.055,
+      "eval_steps_per_second": 1.405,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.995762988744704e+16,
+  "total_flos": 2.661017318326272e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null