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:df7f56e2543984d2cfd48e15af93db3d274508ebeba028290b8b8857927fe8d7
+oid sha256:e451082732b220335e8d15479b4e3cf6486e38de5af5e0e8f483376a18e6e95b
 size 1195453784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1b332a5c0ad454bd31619ce08dfcb9703883011895912ea16f530e750af660
+oid sha256:cdf9832d998f3decad68663aca7fda2b7f88f06ae29893be47a0d2203fbcba3f
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74b05f2720b311440022765a28fc8006a7374957aaca6aca1b5e6bc5db4cbaa
+oid sha256:9468f12fd263659cd15b6e12650b1ad5cf41f0942309f8a6a6622fdf7c268a27
 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": 0.03864734299516908,
+  "epoch": 0.04830917874396135,
   "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": 7.471,
       "eval_steps_per_second": 0.934,
       "step": 20
+    },
+    {
+      "epoch": 0.04057971014492753,
+      "grad_norm": 0.47375577688217163,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.1083,
+      "step": 21
+    },
+    {
+      "epoch": 0.0463768115942029,
+      "grad_norm": 0.4400457441806793,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.1057,
+      "step": 24
+    },
+    {
+      "epoch": 0.04830917874396135,
+      "eval_loss": 0.10784460604190826,
+      "eval_runtime": 116.7599,
+      "eval_samples_per_second": 7.468,
+      "eval_steps_per_second": 0.934,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.151595731458458e+16,
+  "total_flos": 6.403719693965722e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null