Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:263af0d0ecc3dd92bf3572419c7b2b85512ff89dc5bf9cb8283273dea62f255f
+oid sha256:1ee23bcd24b105c2369fe92de75f495194ccd07f80f56518ea785b2f6f0fc826
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580aec9c9570e7496cf594bb0db8a39121196c524ee2fbe796c48ddbb0915c43
+oid sha256:c9a54ffac78717d570e6a1ee8b057d7a76ec595a4d83ab2223ea64e2b290b716
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
+oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
 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": 0.0052435212261772715,
+  "epoch": 0.010487042452354543,
   "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": 12.64,
       "eval_steps_per_second": 6.32,
       "step": 10
+    },
+    {
+      "epoch": 0.006050216799435313,
+      "grad_norm": 26.486326217651367,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.1914,
+      "step": 15
+    },
+    {
+      "epoch": 0.008066955732580417,
+      "grad_norm": 63.64850997924805,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8607,
+      "step": 20
+    },
+    {
+      "epoch": 0.008066955732580417,
+      "eval_loss": 0.11317463964223862,
+      "eval_runtime": 83.5211,
+      "eval_samples_per_second": 12.5,
+      "eval_steps_per_second": 6.25,
+      "step": 20
+    },
+    {
+      "epoch": 0.010083694665725522,
+      "grad_norm": 6.259247779846191,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.5215,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2278473338978304.0,
+  "total_flos": 4556946677956608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null