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:ce143c93cbf3c57b5d24ef72f791c9898746110620dce01296d88f3bbe40c01c
+oid sha256:d3a177976f1593e48621458531ffc23db55d9fcf85c029b85f892f0bd4f57b5d
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be55418bd6e0948225c01ed6b56800621835abfdac90382dc9fd672bda76aeb
+oid sha256:65242a003b0f2aacaec946c84b9c57945b1defd18dbe03efc5ab01540aae1e62
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b18069b57791b3ae2b5099cd170b1de564d9d383b48678ee518b571e7209716
+oid sha256:b3eddb53d43bec72d82b2f8828d9c4c6965d92f3d33f2eae247de40f6d59e18a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03117505995203837,
+  "epoch": 0.06235011990407674,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 629.048,
       "eval_steps_per_second": 78.799,
       "step": 10
+    },
+    {
+      "epoch": 0.047961630695443645,
+      "grad_norm": 0.027547860518097878,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3738,
+      "step": 20
+    },
+    {
+      "epoch": 0.047961630695443645,
+      "eval_loss": 10.37330150604248,
+      "eval_runtime": 4.558,
+      "eval_samples_per_second": 616.503,
+      "eval_steps_per_second": 77.227,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2689628897280.0,
+  "total_flos": 5379257794560.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null