Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662ac36374eb95cf6d0ecb8dc7383c2145e3272ede89caa37971de5727f0a3fc
+oid sha256:3ebe9ed55e5cddea53be3fce7da7137d7f7d0205d95cd4fe81940105aa0236b3
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d6d62df0d88f8721c4983a2ed8228845d9793a2cb4dddf86fe8eaa13227e64
+oid sha256:0a6230dcead7d2138cd72966b2bb2331530b3f871aedfe5ea95bdb3ccfb36913
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:224258860bc5cff9f205d97ac5c1dc59aa62cd3755d71e40d0c636a476b22317
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.3595505617977528,
+  "epoch": 0.449438202247191,
   "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": 95.969,
       "eval_steps_per_second": 24.503,
       "step": 20
+    },
+    {
+      "epoch": 0.3775280898876405,
+      "grad_norm": 0.42053401470184326,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 11.9182,
+      "step": 21
+    },
+    {
+      "epoch": 0.4314606741573034,
+      "grad_norm": 0.44844770431518555,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 11.9144,
+      "step": 24
+    },
+    {
+      "epoch": 0.449438202247191,
+      "eval_loss": 11.909857749938965,
+      "eval_runtime": 0.9776,
+      "eval_samples_per_second": 96.152,
+      "eval_steps_per_second": 24.55,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 189820108800.0,
+  "total_flos": 237425786880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null