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:a841841b200b8c26e36e19e6cf16cd09f95d64eca403f154a16591045e4d8a87
+oid sha256:0f97056afcfda377927af1952cac1d2a96e4b498bcd1a7009f543c2d91656ed6
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ca88ecbe3b8e2bccabf86b0f8acca271ae3b0a07515ce2124870f9a70d81b0
+oid sha256:fb4c024f0b982634d800e653a42da1875fb7cdd549c8db83ba5e5bd306921c16
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
+oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
 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": 0.00033691849164182975,
+  "epoch": 0.0006738369832836595,
   "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": 80.618,
       "eval_steps_per_second": 40.311,
       "step": 10
+    },
+    {
+      "epoch": 0.0003887521057405728,
+      "grad_norm": 5.224070072174072,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.571,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005183361409874304,
+      "grad_norm": 5.187327861785889,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.3059,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005183361409874304,
+      "eval_loss": 11.109954833984375,
+      "eval_runtime": 202.249,
+      "eval_samples_per_second": 80.332,
+      "eval_steps_per_second": 40.168,
+      "step": 20
+    },
+    {
+      "epoch": 0.000647920176234288,
+      "grad_norm": 5.364950656890869,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 11.008,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 868650713088.0,
+  "total_flos": 1737301426176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null