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:c74aa95c0d6843bb56eb659da6307a783209dfb61ef7e5218cff57095e6becbc
+oid sha256:e4600cd174efa3ff8a9058ca256119fe312810869e303a1f213de94fc80244a5
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:406d48535f66fbac919f1619c655e2d522b80b8697f9b1ddd13211efa53533d6
+oid sha256:01255b4251364d582ed9216576c633a888418f684b069582f4cc0ea89c5a7ba3
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfc5f880a99221c3c2668670b0468ffc28d7a3abf27d797b7a28920c8da464c4
+oid sha256:016c55e82eccfcbb8148b8b86c4e028c9b46d0568f2e785086aa10cc78ee6493
 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": 0.003222208452100632,
+  "epoch": 0.006444416904201264,
   "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": 56.334,
       "eval_steps_per_second": 28.183,
       "step": 10
+    },
+    {
+      "epoch": 0.003717932829346883,
+      "grad_norm": 0.8132537603378296,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.2522,
+      "step": 15
+    },
+    {
+      "epoch": 0.004957243772462511,
+      "grad_norm": 0.7359092831611633,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.0345,
+      "step": 20
+    },
+    {
+      "epoch": 0.004957243772462511,
+      "eval_loss": 3.0423290729522705,
+      "eval_runtime": 30.1065,
+      "eval_samples_per_second": 56.433,
+      "eval_steps_per_second": 28.233,
+      "step": 20
+    },
+    {
+      "epoch": 0.006196554715578138,
+      "grad_norm": 0.7544383406639099,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.8972,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 47152394403840.0,
+  "total_flos": 93447472545792.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null