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:a259b2fb107027d1a846834b1771afe83d7ff5fa2e88a4b9045601614b88115c
+oid sha256:a5455c2e2aab74bb343b809322a5185f911ab0a8ded8dea477cc734b4f17d964
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c250e3bf7f738584eda24910cd892f14b672fb4cc50f161b6e0fb43e4383048b
+oid sha256:939d0df290e5d0265d205f0658f24c8b62e05c657109dfba4f79d9eecef5c3f6
 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": 0.00555971346092163,
+  "epoch": 0.01111942692184326,
   "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": 64.136,
       "eval_steps_per_second": 32.1,
       "step": 10
+    },
+    {
+      "epoch": 0.006415053993371111,
+      "grad_norm": 0.6130003333091736,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.4281,
+      "step": 15
+    },
+    {
+      "epoch": 0.008553405324494815,
+      "grad_norm": 0.9023367166519165,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.2662,
+      "step": 20
+    },
+    {
+      "epoch": 0.008553405324494815,
+      "eval_loss": 3.300909996032715,
+      "eval_runtime": 15.3919,
+      "eval_samples_per_second": 63.995,
+      "eval_steps_per_second": 32.03,
+      "step": 20
+    },
+    {
+      "epoch": 0.010691756655618518,
+      "grad_norm": 0.7119651436805725,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.1671,
+      "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