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:d533d81dbfdcb2309dd5bef91e344e6bed96a99f6860d1eeac103dd73c45fa49
+oid sha256:d1e8360c9205964b7b0ce5f000ba71a1e91fa596be07763a839b5a5c51bb1783
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:886a761dec666be830b95741b2dacd516d90cb6d27f81b7132bc5dc349dc6bfb
+oid sha256:65a050c85e64c44bf5b7db359ccb994dd25a1981b4f88bfce66b3b2bda9a7bc8
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
+oid sha256:4a997aa8bfab00a35d7cfa486126e3d295d226a899068a295415cfc8e8058a7c
 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": 0.04744525547445255,
+  "epoch": 0.0948905109489051,
   "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": 41.408,
       "eval_steps_per_second": 20.704,
       "step": 10
+    },
+    {
+      "epoch": 0.05474452554744526,
+      "grad_norm": 0.4731990098953247,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.4786,
+      "step": 15
+    },
+    {
+      "epoch": 0.072992700729927,
+      "grad_norm": 0.5890198349952698,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.2385,
+      "step": 20
+    },
+    {
+      "epoch": 0.072992700729927,
+      "eval_loss": 2.2581331729888916,
+      "eval_runtime": 2.169,
+      "eval_samples_per_second": 53.48,
+      "eval_steps_per_second": 26.74,
+      "step": 20
+    },
+    {
+      "epoch": 0.09124087591240876,
+      "grad_norm": 0.5110591053962708,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.1577,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 332529571725312.0,
+  "total_flos": 665059143450624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null