Training in progress, step 2420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e732afce22ec32ca479327823c15da79bda2c036818cf68dffa6504bebbe039
+oid sha256:038495b3a63af56769edf9078d4b682bf44448bc55b162182ee09bf787a8ba7f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c49916fc2c8819ea4e88ac71d5999800563cede87d1fbe681c0226feb18c1
+oid sha256:1fda6e10efb8ac88031ab2158fa3990b6952f450622e390e8dee841e7b170701
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3717310ed22609eb472cb933e8ce12dc75189c5307a2dd757612d0dafbdd44fd
+oid sha256:c71bb30ffe2cbf6cb6a4c5307d148d41457f0a5c28c71e1d46deb37de729c943
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:655cb150e23a910120ef43d10145c8ad974ea933a71e70934e13f61b696b9b7e
+oid sha256:eb1f1f4b2148e4dce7f39dd646c931ea5ab2e6010ac296b1045418cc3290fa37
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8586762075134168,
+  "epoch": 0.8658318425760286,
   "eval_steps": 500,
-  "global_step": 2400,
+  "global_step": 2420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1927,14 +1927,30 @@
       "loss": 0.3994,
       "num_input_tokens_seen": 1628983,
       "step": 2400
+    },
+    {
+      "epoch": 0.8622540250447227,
+      "grad_norm": 0.4629397988319397,
+      "learning_rate": 2.7549194991055454e-05,
+      "loss": 0.3868,
+      "num_input_tokens_seen": 1635950,
+      "step": 2410
+    },
+    {
+      "epoch": 0.8658318425760286,
+      "grad_norm": 0.4515867829322815,
+      "learning_rate": 2.6833631484794274e-05,
+      "loss": 0.3816,
+      "num_input_tokens_seen": 1643015,
+      "step": 2420
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1628983,
+  "num_input_tokens_seen": 1643015,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.663007509246566e+16,
+  "total_flos": 3.694560521997312e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null