Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0791d8b6e7947b89bfd5670178133e4fca64d924734116a9f2a909525996416c
+oid sha256:62684bf0eec044fb0a9a60709738b246e464592f15969ca36cbd206f6a65b9ba
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:900cd421c62a638e41d0df8890ddea4c94dca381a83d14c0313c878911da655a
+oid sha256:1ba68244a466bdf0b5d267bb6e43fc63894926d785d1e87c91c9b950737d9101
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300e898fa5a1070babf54be755e6755373a5c60ddc254902e3f1ebacda147586
+oid sha256:60379b7ec7fc50400ed25c0728f72548d8aacb996c92794cc4fa8f2026f83ce9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005418912002890086,
+  "epoch": 0.006502694403468103,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 7.039,
       "eval_steps_per_second": 0.88,
       "step": 45
+    },
+    {
+      "epoch": 0.005780172803082759,
+      "grad_norm": 13.306793212890625,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 6.0942,
+      "step": 48
+    },
+    {
+      "epoch": 0.006141433603275431,
+      "grad_norm": 13.40745735168457,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 5.8127,
+      "step": 51
+    },
+    {
+      "epoch": 0.006502694403468103,
+      "grad_norm": 13.341890335083008,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 5.6365,
+      "step": 54
+    },
+    {
+      "epoch": 0.006502694403468103,
+      "eval_loss": 1.4377180337905884,
+      "eval_runtime": 1988.1753,
+      "eval_samples_per_second": 7.035,
+      "eval_steps_per_second": 0.88,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2656345471778816e+17,
+  "total_flos": 1.518761456613458e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null