Training in progress, step 14000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e850270b5aa16a087f2ed7bfa63681dceca1195815b909f64ab1cf952f1d36
+oid sha256:c182a1e51857476464622cf47410813ba3759f4f1110016c31bfd5e31d8c394a
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d80443b06a6c12911f010a5102842a6b449c2c4d84eccce4684c05a191a2fef5
+oid sha256:d8533ebd3395cfec590d9d050066e8a5caf4d0920004d2fb0da0c268cd2b25a1
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d78a57832ad3a62d561461213246d0e5485177f398b4ea4f4bb31c91c7f18f2
+oid sha256:c5cd28a278d563bc1af8b7135b1c700a0d4e82e3dce295749a03ce595ed88ea9
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b44bd9c64de4d93ae129aeb4daad40847d4d504a7f4f16e6041b0da96102d3
+oid sha256:09b60145c2911f9262f801c6e42caed6d6222327f4fe92d08c259522a71afbde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 27.795656928604906,
+  "epoch": 27.995625683486956,
   "eval_steps": 500,
-  "global_step": 13900,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1196,6 +1196,21 @@
       "learning_rate": 7.333333333333334e-06,
       "loss": 1.2157,
       "step": 13900
+    },
+    {
+      "epoch": 27.995625683486956,
+      "grad_norm": 0.2475418895483017,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.2175,
+      "step": 14000
+    },
+    {
+      "epoch": 27.995625683486956,
+      "eval_loss": 1.0951762199401855,
+      "eval_runtime": 781.5447,
+      "eval_samples_per_second": 19.861,
+      "eval_steps_per_second": 2.484,
+      "step": 14000
     }
   ],
   "logging_steps": 100,
@@ -1215,7 +1230,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.169417375965774e+19,
+  "total_flos": 2.1850248730845905e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null