Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1ec4423671a6f225577326f04fd9d64b6e0928ca423d82d1739f5a61d39c9b
+oid sha256:8a4986982f1721b0d7826540a1e0b19de579da5982717b08a1786d66861ca6c9
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5678a642de0f846174b19dcdcb3798db37d89f29a029963f4eadec103d7ac7a9
+oid sha256:7c43f52e944734165137cfe1749d4d4f1ca2f53a2a9aab6602a28897ea2ae869
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232b35a26bef178eec09e66c24898c4e539aa83018f1fe5fb9337bcbf7093c76
+oid sha256:38b203c487a223bbc58ff68bdb5abcc1dc73df8232401ff6f5ebb4ec48efbf8d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01403755044744692,
+  "epoch": 0.01754693805930865,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 457.498,
       "eval_steps_per_second": 57.187,
       "step": 20
+    },
+    {
+      "epoch": 0.014739427969819266,
+      "grad_norm": 0.10688723623752594,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 10.3719,
+      "step": 21
+    },
+    {
+      "epoch": 0.016845060536936303,
+      "grad_norm": 0.12940353155136108,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 10.3709,
+      "step": 24
+    },
+    {
+      "epoch": 0.01754693805930865,
+      "eval_loss": 10.36774730682373,
+      "eval_runtime": 5.2455,
+      "eval_samples_per_second": 457.536,
+      "eval_steps_per_second": 57.192,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2286788542464.0,
+  "total_flos": 2844541845504.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null