Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce941deca9c36666bb0f1c546678ed47082c29ea526da8cb064f10003d7bb50
+oid sha256:c2dd652f0e85af20c6349682564e76c998738ecd18c1e7216d303cc9bbaa23ea
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d021a6d6a24125bf6c22d5c861593129874913ab65244f50dc3ca529679471fb
+oid sha256:fe20e9dc61002034468a4e14d7939b3fa42f91f1d1bbf03d5586d3bc9854a571
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f6c38a2ef2447f68ed1ff203f4ba061cc240709cc4b0d15a640d65adf96104
+oid sha256:e8af4596fe237dbd9e82b409cdc62eb03990ab4f2816bfa06519cfc946ade541
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02243689622935494,
+  "epoch": 0.02617637893424743,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 23.364,
       "eval_steps_per_second": 2.922,
       "step": 54
+    },
+    {
+      "epoch": 0.023683390464319103,
+      "grad_norm": 0.6685330271720886,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 1.1958,
+      "step": 57
+    },
+    {
+      "epoch": 0.024929884699283266,
+      "grad_norm": 0.7554190158843994,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 1.1446,
+      "step": 60
+    },
+    {
+      "epoch": 0.02617637893424743,
+      "grad_norm": 0.7289713025093079,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 1.2659,
+      "step": 63
+    },
+    {
+      "epoch": 0.02617637893424743,
+      "eval_loss": 1.2556233406066895,
+      "eval_runtime": 173.4263,
+      "eval_samples_per_second": 23.376,
+      "eval_steps_per_second": 2.923,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1714443075321856e+16,
+  "total_flos": 2.533351692120883e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null