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:a755e1d0f1557988bd0880ff24428bb3a31be51f774e6ccb3e0d7a668a6e3c04
+oid sha256:cfe72aa756e69b8763890050a56df7185c0bdead9cfd01910147054c1be7506a
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721d5eeecd9ca8691fe3713444d1af10d2b3ced4b3adc2b6e8a62f56ca184bed
+oid sha256:509df2936d00578529648e82dc8ebefdb867b4a42d13e70dc75570edcce9f396
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:badd5b37bc59ed340e5cf0ea08f8cb665ed44eee63ba2c43b29ca2ff05a28c64
+oid sha256:53e2dc83e18bda6fddd0ebfc34483e2d1ff844f2307551220db6ecf1af93c478
 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": 0.0017723848801935989,
+  "epoch": 0.0035447697603871978,
   "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": 29.016,
       "eval_steps_per_second": 14.513,
       "step": 10
+    },
+    {
+      "epoch": 0.0020450594771464605,
+      "grad_norm": 0.9104695320129395,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.8042,
+      "step": 15
+    },
+    {
+      "epoch": 0.0027267459695286137,
+      "grad_norm": 0.7825496792793274,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.8319,
+      "step": 20
+    },
+    {
+      "epoch": 0.0027267459695286137,
+      "eval_loss": 1.8885176181793213,
+      "eval_runtime": 106.6603,
+      "eval_samples_per_second": 28.961,
+      "eval_steps_per_second": 14.485,
+      "step": 20
+    },
+    {
+      "epoch": 0.0034084324619107673,
+      "grad_norm": 1.0567548274993896,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.879,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 547241047621632.0,
+  "total_flos": 1052386630041600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null