Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9d077ef5d389aa16311ff1f2795224c939dd080956d121188f50c99ae819df
+oid sha256:9ae6b8ad55d852b1e9e20b5184e07c63dcd9dc1f1567b9a7af1a68236ae09f61
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fddaec9223c2cd539163a4982107ecd8225db3118b235405349bf4ebe957d6
+oid sha256:591c8cebf39fdc9aaed4a0aafba82fe0ad60ae51ea804e711205139001dfc6d1
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a4f0069edb1e06dc358b4ff190f10113fb1ddd26ae17efb126b43600cdb989c
+oid sha256:6ed361f2d63bb82818e33c366fb6b15db6cde149e93fdff111aa1f4ea8e127b1
 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": 0.003256513026052104,
+  "epoch": 0.006513026052104208,
   "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": 57.903,
       "eval_steps_per_second": 28.969,
       "step": 10
+    },
+    {
+      "epoch": 0.00375751503006012,
+      "grad_norm": 1.0935112237930298,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.6685,
+      "step": 15
+    },
+    {
+      "epoch": 0.00501002004008016,
+      "grad_norm": 1.1594758033752441,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.4933,
+      "step": 20
+    },
+    {
+      "epoch": 0.00501002004008016,
+      "eval_loss": 3.4188053607940674,
+      "eval_runtime": 29.0052,
+      "eval_samples_per_second": 57.955,
+      "eval_steps_per_second": 28.995,
+      "step": 20
+    },
+    {
+      "epoch": 0.006262525050100201,
+      "grad_norm": 1.1321828365325928,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.2123,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 44580445618176.0,
+  "total_flos": 89160891236352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null