Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b736ae7a9e8b7d666739556b9d6bf5ea2955250af69c59d19bd5b527ae0f39
+oid sha256:06361a5f37694860d45455bd36f05948f7004a758571d256ed658aec99554747
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:853f7c31f307d3c64a7de01d9081ae67aabf9de6b21ce393ebdb5b1f4f411392
+oid sha256:601694bd5b1fcd38726af40fbb4daebe99740a0ddb3b8faace887549213e4d6d
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd93ad71d1e4da2e65f4e2c9390e9d7b7bc2ea6079b0f1bd60a10893bb8881fb
+oid sha256:ab22ddf51bfbb0e52394ea82ce6def3703300cb6b77357d2a920d3ed8bca3047
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07155635062611806,
+  "epoch": 0.1073345259391771,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 11.063,
       "eval_steps_per_second": 1.406,
       "step": 10
+    },
+    {
+      "epoch": 0.08586762075134168,
+      "grad_norm": 12.302176475524902,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 5.5122,
+      "step": 12
+    },
+    {
+      "epoch": 0.1073345259391771,
+      "grad_norm": 7.404484272003174,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.4541,
+      "step": 15
+    },
+    {
+      "epoch": 0.1073345259391771,
+      "eval_loss": 0.1575503647327423,
+      "eval_runtime": 21.3407,
+      "eval_samples_per_second": 11.059,
+      "eval_steps_per_second": 1.406,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.330508659163136e+16,
+  "total_flos": 1.995762988744704e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null