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:f34550dfbfa043d10d2cc9343ee43cb13572b946f68c54d3394692d3d96bf30d
+oid sha256:c60d769b044b42370aaa29f0fb3b2ec773fd3515fcc7cc94a48d09d9953f2828
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61dbf198e5a2ae2f437e674f87edffa2177badbf0187417ecf0509fc4bec502c
+oid sha256:08a6c2c8201a4fd21ddadf406a575c998c29642e96cea5bc402f3db863ecb27a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
+oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
 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": 0.01090375340742294,
+  "epoch": 0.02180750681484588,
   "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": 14.786,
       "eval_steps_per_second": 7.393,
       "step": 10
+    },
+    {
+      "epoch": 0.012581253931641853,
+      "grad_norm": 0.8804078698158264,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.0332,
+      "step": 15
+    },
+    {
+      "epoch": 0.01677500524218914,
+      "grad_norm": 0.9397221207618713,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8737,
+      "step": 20
+    },
+    {
+      "epoch": 0.01677500524218914,
+      "eval_loss": 0.8285709619522095,
+      "eval_runtime": 34.0574,
+      "eval_samples_per_second": 14.74,
+      "eval_steps_per_second": 7.37,
+      "step": 20
+    },
+    {
+      "epoch": 0.020968756552736424,
+      "grad_norm": 0.714771032333374,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.8035,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null