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:b678e7bf1677a175fea27faa499ac73a4e67f832f5c64cc70c6298cb317c662f
+oid sha256:536a2db40947885db5bf9939f158205f8c46a50508b2bdd36f1ed245f8262c50
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf5c627eb9fcfb39d7b5b726231fa2ff79edd928bbee3315aa5477f2b033a6d
+oid sha256:a82134c5cbbbc13a2981ee8253f5766698b00b94248832958a6460cd2a2703bb
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e8229120dce69fa1081c29f9ca7f12647fb8db9c60a1f8dce12e8d0bda6beb
+oid sha256:ea402b9b27c3cc250416823d1fd916c155c6766d61390bd38b5912be5e16fc65
 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": 0.004319295622560013,
+  "epoch": 0.008638591245120026,
   "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": 18.262,
       "eval_steps_per_second": 9.131,
       "step": 10
+    },
+    {
+      "epoch": 0.0049838026414154,
+      "grad_norm": 1.071433424949646,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.0207,
+      "step": 15
+    },
+    {
+      "epoch": 0.006645070188553866,
+      "grad_norm": 1.2155852317810059,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.873,
+      "step": 20
+    },
+    {
+      "epoch": 0.006645070188553866,
+      "eval_loss": 0.8100319504737854,
+      "eval_runtime": 70.2598,
+      "eval_samples_per_second": 18.047,
+      "eval_steps_per_second": 9.024,
+      "step": 20
+    },
+    {
+      "epoch": 0.008306337735692334,
+      "grad_norm": 1.0802018642425537,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.8331,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 650126529921024.0,
+  "total_flos": 1300253059842048.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null