Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71211827399d795a506461d5f56e97cb4e8d4dbf81297788382b1854335029b2
+oid sha256:fdcb24de1af5f355fc6f397e4fa176ccce4da7d84ca6236d312fba7b37713538
 size 608249904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0079e84d78ef19eff2a9f985d42262b580d662cd21fe81193589800dbc2f6b2e
+oid sha256:8ccb04434d6a3e161cb9878b4b3f57d668a8fa7cba2c332a3987cff25c456169
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05fe95363144ef3cc38bcd7440fb89fde10bc93ca8cbfa57af8f7736ec5802e
+oid sha256:45d933a07aade8a49bb8dc8d3bcb7da3273871b976473408cd44c3a5c6bcd640
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0addd62454d87d49bfedc26e0b85659f0aaed290a84e144284ca9b72f10d6fc8
+oid sha256:27ca192899ed606f0971eef111fc1026e18024acb472ba59e8b2804c88f803cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5294117647058824,
+  "epoch": 0.7941176470588235,
   "eval_steps": 7,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,6 +38,21 @@
       "eval_samples_per_second": 18.82,
       "eval_steps_per_second": 2.373,
       "step": 14
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.011018212884664536,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0005,
+      "step": 20
+    },
+    {
+      "epoch": 0.6176470588235294,
+      "eval_loss": 3.617151014623232e-05,
+      "eval_runtime": 12.2504,
+      "eval_samples_per_second": 18.775,
+      "eval_steps_per_second": 2.367,
+      "step": 21
     }
   ],
   "logging_steps": 10,
@@ -57,7 +72,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.047691882633626e+16,
+  "total_flos": 7.571537823950438e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null