Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75eae593436901837c027503accd88a9beb20b130e576a7c7a9ceb8574c354fd
+oid sha256:55f7552d03b04940b9e7d43563acbb72268e0d3bb333ae1528f5ceabc4abdafd
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b7d7d3607aeee19503b4c9332af3525d9168ea700f12855e5eb61bb6655bb9
+oid sha256:4c85b769baa7b1da8d6e41332a634d3610a88824be7dc3bf7a5251eb61536ba6
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32442624db2133a9d6b51e901ac7b682f8491c9bb67fa0e1e7c86275e697d327
+oid sha256:c87ab95555879c3a66d17eb6017af1bce4104a9c10d5831421c0b7ac3bcbe7a8
 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": 0.010584164461632404,
+  "epoch": 0.02116832892326481,
   "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": 9.435,
       "eval_steps_per_second": 4.717,
       "step": 10
+    },
+    {
+      "epoch": 0.012212497455729696,
+      "grad_norm": 0.6268041729927063,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.2516,
+      "step": 15
+    },
+    {
+      "epoch": 0.01628332994097293,
+      "grad_norm": 0.6889188885688782,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.7638,
+      "step": 20
+    },
+    {
+      "epoch": 0.01628332994097293,
+      "eval_loss": 1.7881678342819214,
+      "eval_runtime": 55.6645,
+      "eval_samples_per_second": 9.306,
+      "eval_steps_per_second": 4.653,
+      "step": 20
+    },
+    {
+      "epoch": 0.02035416242621616,
+      "grad_norm": 1.2505710124969482,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.6658,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2657519970287616.0,
+  "total_flos": 5271474039422976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null