Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ecbe66bb90005c2da530c4dedfe8bdc57ea610b8d5d4fa9e160f7700dd1dd3e
+oid sha256:d6e98b48e5fb16b4bcaac32f76d22b8e7ca0b1a9b58f226d75c52f6387c97cf8
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff712cd5f541f1626ae44243d65c7c4c7dd32c66ea21b72930170b2fbad7d59
+oid sha256:21a957ab25183edbd2f2c405eb512c1a98890ee2a94c12852460fb085b36edcd
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48eb1b0095c15f46650a9d2ec96e31c26714b620c5be9cc03b1f8120e84563f7
+oid sha256:e42bca74d060f51af786caed77930fe6005b527e22f05fc65e989d6bd87b0b7a
 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": 0.01748664214835889,
+  "epoch": 0.019984733883838736,
   "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": 9.195,
       "eval_steps_per_second": 1.15,
       "step": 63
+    },
+    {
+      "epoch": 0.01831933939351884,
+      "grad_norm": 0.1783250868320465,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.357,
+      "step": 66
+    },
+    {
+      "epoch": 0.019152036638678788,
+      "grad_norm": 0.1924220472574234,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 0.364,
+      "step": 69
+    },
+    {
+      "epoch": 0.019984733883838736,
+      "grad_norm": 0.1912061870098114,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.3565,
+      "step": 72
+    },
+    {
+      "epoch": 0.019984733883838736,
+      "eval_loss": 0.35400116443634033,
+      "eval_runtime": 660.0962,
+      "eval_samples_per_second": 9.193,
+      "eval_steps_per_second": 1.15,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3771062258538906e+17,
+  "total_flos": 1.5693418665187738e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null