Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2dd652f0e85af20c6349682564e76c998738ecd18c1e7216d303cc9bbaa23ea
+oid sha256:66acfd41a6bd5d397dd2912f3889b5b20dfbd8328418f869888b343f8046e748
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe20e9dc61002034468a4e14d7939b3fa42f91f1d1bbf03d5586d3bc9854a571
+oid sha256:7e00b41a03700faa246fd1f1b8279886a9d0880ef636e3b248e8ed84181deffd
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8af4596fe237dbd9e82b409cdc62eb03990ab4f2816bfa06519cfc946ade541
+oid sha256:088c088af7cf27b9140215093eff25bfd4aea5cba83c9d1e10989ec38ee693b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02617637893424743,
+  "epoch": 0.02991586163913992,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 23.376,
       "eval_steps_per_second": 2.923,
       "step": 63
+    },
+    {
+      "epoch": 0.027422873169211593,
+      "grad_norm": 0.7362277507781982,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 1.2666,
+      "step": 66
+    },
+    {
+      "epoch": 0.028669367404175757,
+      "grad_norm": 0.7522065043449402,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 1.2857,
+      "step": 69
+    },
+    {
+      "epoch": 0.02991586163913992,
+      "grad_norm": 0.7410892844200134,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 1.1732,
+      "step": 72
+    },
+    {
+      "epoch": 0.02991586163913992,
+      "eval_loss": 1.250916600227356,
+      "eval_runtime": 173.421,
+      "eval_samples_per_second": 23.377,
+      "eval_steps_per_second": 2.924,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.533351692120883e+16,
+  "total_flos": 2.895259076709581e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null