Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ce9763b927742ad7890cc95a7434695d73a8f0d7d03cd81200c1f49c6fa795
+oid sha256:20863b62d25bc43d36965fb88e0c8c737d5f03e908f7ff6e6ca2e1da2c9c7448
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870910708e1a62cf24639c601fa5ea3c54b0d1b6305dd07c7bae628ca16a790a
+oid sha256:db6de2d0c600353c34d4d86c78f18f77b4682926d3cee0a0ac65c7a79776253e
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
+oid sha256:4a997aa8bfab00a35d7cfa486126e3d295d226a899068a295415cfc8e8058a7c
 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": 0.03537414965986395,
+  "epoch": 0.0707482993197279,
   "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": 32.012,
       "eval_steps_per_second": 16.109,
       "step": 10
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 8.878782272338867,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 4.9712,
+      "step": 15
+    },
+    {
+      "epoch": 0.05442176870748299,
+      "grad_norm": 6.79744815826416,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.2754,
+      "step": 20
+    },
+    {
+      "epoch": 0.05442176870748299,
+      "eval_loss": 2.7712717056274414,
+      "eval_runtime": 4.9098,
+      "eval_samples_per_second": 31.57,
+      "eval_steps_per_second": 15.887,
+      "step": 20
+    },
+    {
+      "epoch": 0.06802721088435375,
+      "grad_norm": 11.151188850402832,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.6417,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 332529571725312.0,
+  "total_flos": 665059143450624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null