Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edb455920aa95cf9ada95ab94d78e0b6940976a5262e1f27d468e9d2ce187ddc
+oid sha256:a9e99e59bad3936a53b55c549edee9c54e5ef217806171186930b2376024b82a
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f479c4315b5ddbf149138fc6ec05fc8a86a44a6cbc038a90a7aefa3ebbfc7fb3
+oid sha256:ac8286fb2b82ebe608c12d6303458dca5fc5c8311d32ecaa4907f21dd6efdd32
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd424b40558ff64379aeb46692c348d6b618b41d4236dc9fd2e104bf0cbad808
+oid sha256:dc5bcd07c7980be2bcc780ec62347040974b973719b0561b7d2425edc8426ebd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e916177211118fc8a152e53676009788e79374ee54f188f77aebc8c03e2bf7b9
+oid sha256:814b79b47e12bde76b22a1ac4fd2f1e7ddf84c332d0b19c3538a1fad1c6cc96e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10309278350515463,
+  "epoch": 0.12886597938144329,
   "eval_steps": 97,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -155,6 +155,41 @@
       "learning_rate": 4e-05,
       "loss": 1.1069,
       "step": 20
+    },
+    {
+      "epoch": 0.10824742268041238,
+      "grad_norm": 0.3861861526966095,
+      "learning_rate": 4.2e-05,
+      "loss": 0.864,
+      "step": 21
+    },
+    {
+      "epoch": 0.1134020618556701,
+      "grad_norm": 0.5285366773605347,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.8627,
+      "step": 22
+    },
+    {
+      "epoch": 0.11855670103092783,
+      "grad_norm": 0.39096203446388245,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.8984,
+      "step": 23
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 0.39784133434295654,
+      "learning_rate": 4.8e-05,
+      "loss": 0.9631,
+      "step": 24
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "grad_norm": 0.37275853753089905,
+      "learning_rate": 5e-05,
+      "loss": 0.831,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -174,7 +209,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7741780556513280.0,
+  "total_flos": 9677225695641600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null