Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f80570171eb4128ea94897b7fb339be1b8faaae7e455f6c482787a6bc8737ba
+oid sha256:b762063a0a9b6608b0d8641af49144086ae1fd65c181aa9a0a43e0578a5402f1
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f49291774a46c7e4128f9f7f944b39ff8d38785b0d73805d223775fc7d27f41d
+oid sha256:3d1c4fefa78e23324a45960e7950003dc9f282d9b8738d87934157b573f05a6d
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ff583cbed74ae345b2c71bfc9205b2dc7ab182aa8a1dc1b15179eaff92fb8a
+oid sha256:fddb71a9a3d250332f98e562706fe25ec1ff4e66f7c9c4eb0af41236fd2dde1a
 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": 0.0007105086968997226,
+  "epoch": 0.0014210173937994452,
   "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": 11.114,
       "eval_steps_per_second": 5.557,
       "step": 10
+    },
+    {
+      "epoch": 0.0008198177271919876,
+      "grad_norm": 4.444485664367676,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 10.9946,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010930903029226502,
+      "grad_norm": 6.395273685455322,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 9.5317,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010930903029226502,
+      "eval_loss": 2.2416298389434814,
+      "eval_runtime": 695.2564,
+      "eval_samples_per_second": 11.081,
+      "eval_steps_per_second": 5.54,
+      "step": 20
+    },
+    {
+      "epoch": 0.0013663628786533127,
+      "grad_norm": 7.272201061248779,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 8.8218,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 776288159662080.0,
+  "total_flos": 1552576319324160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null