Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2581558cdd45fd1c75a8ceb4c1e5c7e0a8f1b0f9b0457c69171d130ef58bb793
+oid sha256:1ea225bc7cd779fac9cc9b41f07d0b86436c10a794dd46fe060e53ed137dd42f
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:169bea183fb2793f040eafc8673013d176e78b9100f9ee1ab19dfcb463df5d3c
+oid sha256:538403e5d6e61d307b9cdb985d05c083984df1049d6057c77fd80e01273caaae
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a15dd2d90d035c0c262c0ed9eed0f9b44afdd185709a1e351ea94afecde3a6
+oid sha256:55bb59e79ad5fd2694553ccebf289da4173c21393a2a030c807225f775413eff
 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": 0.013626834381551363,
+  "epoch": 0.027253668763102725,
   "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": 18.013,
       "eval_steps_per_second": 9.006,
       "step": 10
+    },
+    {
+      "epoch": 0.015723270440251572,
+      "grad_norm": 8.73572063446045,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 8.6493,
+      "step": 15
+    },
+    {
+      "epoch": 0.020964360587002098,
+      "grad_norm": 9.366942405700684,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 6.6943,
+      "step": 20
+    },
+    {
+      "epoch": 0.020964360587002098,
+      "eval_loss": 5.824213981628418,
+      "eval_runtime": 22.3607,
+      "eval_samples_per_second": 17.978,
+      "eval_steps_per_second": 8.989,
+      "step": 20
+    },
+    {
+      "epoch": 0.02620545073375262,
+      "grad_norm": 9.473739624023438,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 5.038,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1339266862940160.0,
+  "total_flos": 2643747573596160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null