Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28bef07b8c33a1adad24bfb8fc1b1451e70da549fd034b32c1d72f51d992d2cf
+oid sha256:ea8296502262505e846d860d2323039070852f38b610bf76235b52cad43c4657
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98cfc0f1fc3e4b629d331db2d37c40d7e6b9a255d1417ca89477741021ec7a13
+oid sha256:fd15d34e39d649fd0d3b0777707166420d3ae2eea0b7fc3d19f5f2c0397ed2ac
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d485098d9e658f97ab7f44865088d931e9723cd939cde2757d2a7485dc14c1f
+oid sha256:390edf6a33ff1f595e7f87de892b284ec2bccd3a3e2701a66d5055a476d66450
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098701d87daa8176da669f731787f8326702510e8abb54b18e920ededa301ec5
+oid sha256:4ef0e768220ab06b0b8ca60bf0cb82c3ba1ffa61503120e1cf6e3622be29cf83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08705114254624592,
+  "epoch": 0.1305767138193689,
   "eval_steps": 10,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 3.48,
       "eval_steps_per_second": 1.745,
       "step": 20
+    },
+    {
+      "epoch": 0.1305767138193689,
+      "grad_norm": 2.7661397457122803,
+      "learning_rate": 1e-05,
+      "loss": 4.2368,
+      "step": 30
+    },
+    {
+      "epoch": 0.1305767138193689,
+      "eval_loss": 0.22000382840633392,
+      "eval_runtime": 111.0485,
+      "eval_samples_per_second": 3.485,
+      "eval_steps_per_second": 1.747,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.686011971928064e+16,
+  "total_flos": 6.997355714838528e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null