Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789abd8b6f3e70008ae66ee75a44717ffd07aabad67372292f19406394e56aab
+oid sha256:71c946de8338ff3783943d06d00cbde6394811994ca20db16bc4c6b398b41da6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:273da983aa9a21c729800cb295486e04247ab8246e31ba40ec5d776dc1934e51
+oid sha256:3e41f4ef652a3fcd114689a1565015889ce696f234256822486df87ca5a32ca4
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8b607c048205bc297b604bd021fe4032f014595c5fa46da254a15590c9ff753
+oid sha256:b72f53c3dec353379dbfa92ed5d2f7d41a871fb3d3a1378473c07060fb503188
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01618523097673373,
+  "epoch": 0.020231538720917163,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 10.134,
       "eval_steps_per_second": 1.268,
       "step": 36
+    },
+    {
+      "epoch": 0.017534000224794875,
+      "grad_norm": 2.9369146823883057,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 7.1185,
+      "step": 39
+    },
+    {
+      "epoch": 0.01888276947285602,
+      "grad_norm": 3.4298548698425293,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 7.395,
+      "step": 42
+    },
+    {
+      "epoch": 0.020231538720917163,
+      "grad_norm": 3.0947425365448,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 6.9911,
+      "step": 45
+    },
+    {
+      "epoch": 0.020231538720917163,
+      "eval_loss": 1.794851541519165,
+      "eval_runtime": 369.7107,
+      "eval_samples_per_second": 10.135,
+      "eval_steps_per_second": 1.269,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.453176954145997e+16,
+  "total_flos": 9.351627687749222e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null