Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7112d09444dfb155cc0928035841032e71cbb909b0b09e65bf99fc2bf34269fe
+oid sha256:90a2a726e05ae20a90cf9c53772c366b07862323166b9102d0b4ee5708bf7017
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a9e9dc7c88d849dc0da1b108ef642dff5216a0b0148b39dc5fb2156b7f40d8
+oid sha256:3b7b217c592fd9476ea79ce5cb57ffdda20be7520b1b2f919d3a2c1d81b2506c
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8532b81b442a52e7641152d52819f99f24bb427b98bc8d1a82e25a081ba985ff
+oid sha256:295f0a621346f38e97a347d06bb9927816fe04926f6efca6f6b2fe56f30407d9
 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": 0.1171303074670571,
+  "epoch": 0.14641288433382138,
   "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": 15.595,
       "eval_steps_per_second": 1.949,
       "step": 20
+    },
+    {
+      "epoch": 0.12298682284040996,
+      "grad_norm": 11.218101501464844,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.945,
+      "step": 21
+    },
+    {
+      "epoch": 0.14055636896046853,
+      "grad_norm": 13.951614379882812,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.5484,
+      "step": 24
+    },
+    {
+      "epoch": 0.14641288433382138,
+      "eval_loss": 0.6135609149932861,
+      "eval_runtime": 18.4602,
+      "eval_samples_per_second": 15.601,
+      "eval_steps_per_second": 1.95,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.661017318326272e+16,
+  "total_flos": 3.32627164790784e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null