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:d2f7d8d596710d73bbb42893485ec4fbd6f852dcad0604c6254205957ab762bf
+oid sha256:0f55a0c1beed4339bd5b16d5fa9b59b387099700fc903db09a84216f27e1738b
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8654aee24ddaa52af4d2badc2fc8ac5f433fd1682f1ae0d1ecaa22a347843883
+oid sha256:1f68ada2af2757d900d5db8b040ff86dc120a17a795910db83d8e88cf4874c97
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89dcf652ef0b14eb3dea9c6d6bedbf9faa98ce2ec21e0b801b03a4485802b288
+oid sha256:9c3e2c18aa2ae28cac6de0a936cf187d80fe9ba4af7aaaf836168b5d337949c1
 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": 0.006435643564356435,
+  "epoch": 0.01287128712871287,
   "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": 30.676,
       "eval_steps_per_second": 15.356,
       "step": 10
+    },
+    {
+      "epoch": 0.007425742574257425,
+      "grad_norm": 0.8921784162521362,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.6192,
+      "step": 15
+    },
+    {
+      "epoch": 0.009900990099009901,
+      "grad_norm": 0.547026515007019,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.5644,
+      "step": 20
+    },
+    {
+      "epoch": 0.009900990099009901,
+      "eval_loss": 2.4996721744537354,
+      "eval_runtime": 27.6222,
+      "eval_samples_per_second": 30.809,
+      "eval_steps_per_second": 15.422,
+      "step": 20
+    },
+    {
+      "epoch": 0.012376237623762377,
+      "grad_norm": 0.717430591583252,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.4506,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 422056764112896.0,
+  "total_flos": 812139530944512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null