Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82eae30cad5b29368e050d7444c6bfd96fc319cdcfe12aa85434f9d323a111e8
+oid sha256:51581e48ee166ee26ee4f2ecca213c29ca9e5b2efde2af16556162219fe359a2
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b320bdff87bb8823ee9465f66629e25f23795394634c196167930d877c317f02
+oid sha256:56a5ed99eaa8960d202147b7983e4604d295b3693ec6fa2ff7be3e60c83ea551
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311ebeed04d0f61c03df33f8b12e2b83d96fcfcaa46ade7e86d87e96b5020def
+oid sha256:ea9b7c11e7b99a178580a46667e4e41b4aae3b906e765f175b969edf030ede0a
 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": 0.0033218346748434906,
+  "epoch": 0.006643669349686981,
   "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": 9.755,
       "eval_steps_per_second": 4.878,
       "step": 10
+    },
+    {
+      "epoch": 0.0038328861632809506,
+      "grad_norm": 0.6246739029884338,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.2917,
+      "step": 15
+    },
+    {
+      "epoch": 0.0051105148843746005,
+      "grad_norm": 0.3205125331878662,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.2045,
+      "step": 20
+    },
+    {
+      "epoch": 0.0051105148843746005,
+      "eval_loss": 0.18292254209518433,
+      "eval_runtime": 213.9892,
+      "eval_samples_per_second": 7.701,
+      "eval_steps_per_second": 3.851,
+      "step": 20
+    },
+    {
+      "epoch": 0.006388143605468251,
+      "grad_norm": 0.29717549681663513,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1541,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 607377426481152.0,
+  "total_flos": 1154618474102784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null