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:d2e963dde9961f57cbf8a0df2a915b8847e83e348c6ff844674169e4076005f4
+oid sha256:276f3ba9ed2bf8356df73ca02bf2f16d5579c2d8940681f88bd784a8745e6095
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc22d34520c1d2f7ca5126a9aaa56b2c2219319fc505a91f80b1d6e35d887f59
+oid sha256:4f9da777910d331cd67f7b8b8afbea2d9a277be783e32c3d6f42b8df78671fc5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7177ecbe52d6aaeee56e537bbfe7e049381013812c79a445b7d7dc2bb7591924
+oid sha256:46b250027aa7f478a085b3fee4a82c9a03a61ed325ad8cf718942d3c12fc0926
 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": 0.017127799736495388,
+  "epoch": 0.034255599472990776,
   "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": 9.214,
       "eval_steps_per_second": 4.607,
       "step": 10
+    },
+    {
+      "epoch": 0.019762845849802372,
+      "grad_norm": 0.7260387539863586,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.5863,
+      "step": 15
+    },
+    {
+      "epoch": 0.026350461133069828,
+      "grad_norm": 0.6288080811500549,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.4501,
+      "step": 20
+    },
+    {
+      "epoch": 0.026350461133069828,
+      "eval_loss": 1.3593571186065674,
+      "eval_runtime": 34.6864,
+      "eval_samples_per_second": 9.226,
+      "eval_steps_per_second": 4.613,
+      "step": 20
+    },
+    {
+      "epoch": 0.03293807641633729,
+      "grad_norm": 0.6772316694259644,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.2137,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4272226987671552.0,
+  "total_flos": 8544453975343104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null