Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90695571950ad67a3e0254b360baf813110dbe8cff63c5e69fefaf0527feb126
+oid sha256:550c2c86bdbbef59546c3f613afae27175d76b355a04a2036efa1a4bba635dbf
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6101dfc2f9cd7097d2109c91905cc43768db224f25dc6ff1eecf2fd5344e4d7c
+oid sha256:a6398283bede0aced7497b9e7fca01590b473bb2a5f3e4e03f22fe7c303b0fc9
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12beed8359fe142c0bd78cf5e499f7058c2c13c901dc109a35a05e5a60f3c080
+oid sha256:1e821233b20919d3c89485c13b08f65a9085ff4f3839c7c72d215170c5adce6b
 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": 0.016265248670628715,
+  "epoch": 0.03253049734125743,
   "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": 15.997,
       "eval_steps_per_second": 8.022,
       "step": 10
+    },
+    {
+      "epoch": 0.01876759461995621,
+      "grad_norm": 3.124346971511841,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.8447,
+      "step": 15
+    },
+    {
+      "epoch": 0.025023459493274947,
+      "grad_norm": 4.356178283691406,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.8011,
+      "step": 20
+    },
+    {
+      "epoch": 0.025023459493274947,
+      "eval_loss": 2.1410269737243652,
+      "eval_runtime": 20.9938,
+      "eval_samples_per_second": 16.052,
+      "eval_steps_per_second": 8.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.03127932436659368,
+      "grad_norm": 3.253753900527954,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.9288,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2265426859917312.0,
+  "total_flos": 4530853719834624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null