Training in progress, step 2440, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038495b3a63af56769edf9078d4b682bf44448bc55b162182ee09bf787a8ba7f
+oid sha256:6a1057e20ef792fc90c9ecff83a00d848ccc0ae3deab4667bd0c2e6bc4d267d1
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fda6e10efb8ac88031ab2158fa3990b6952f450622e390e8dee841e7b170701
+oid sha256:0c5b49a7e6c52ddda0765c314c6cf225b945342c4930ac0976dccb277d23d504
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c71bb30ffe2cbf6cb6a4c5307d148d41457f0a5c28c71e1d46deb37de729c943
+oid sha256:977734e5fe7bc11e4d6ed6aad6cba91a2133b09eb5e2150e6fe83ae79e2649ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb1f1f4b2148e4dce7f39dd646c931ea5ab2e6010ac296b1045418cc3290fa37
+oid sha256:2a738aa1757ae6fa7df683e4fddbcc331434574a0f55ddc368da19ecd66c122e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8658318425760286,
+  "epoch": 0.8729874776386404,
   "eval_steps": 500,
-  "global_step": 2420,
+  "global_step": 2440,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1943,14 +1943,30 @@
       "loss": 0.3816,
       "num_input_tokens_seen": 1643015,
       "step": 2420
+    },
+    {
+      "epoch": 0.8694096601073346,
+      "grad_norm": 0.33169665932655334,
+      "learning_rate": 2.6118067978533094e-05,
+      "loss": 0.3707,
+      "num_input_tokens_seen": 1648061,
+      "step": 2430
+    },
+    {
+      "epoch": 0.8729874776386404,
+      "grad_norm": 0.37958571314811707,
+      "learning_rate": 2.5402504472271914e-05,
+      "loss": 0.3905,
+      "num_input_tokens_seen": 1655672,
+      "step": 2440
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1643015,
+  "num_input_tokens_seen": 1655672,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.694560521997312e+16,
+  "total_flos": 3.723021645314458e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null