Training in progress, step 6460, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3af3f46a335a87c6b76ec18533625ed12e8e29961e53f6dc3be542d5a74f0002
+oid sha256:4edb15d0e1b52d3bdcfb17044d4d5c2d1bc11a9b89494c965b286c71d0b836fb
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c80eed6c07efd228bfcfa1507ab4ac22f1a23cb4bd220bc59f5df3f7c3bd75
+oid sha256:72ef6fc0399c4259225d888ed2a17fdb3c50a5cc0882ff3768013ef0d4c4d8dd
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da2f1477dc9c167a98fe2511d7dffc41edd20cb35e5912c6fa279b7d20bc16e
+oid sha256:3530b4cc0dc079d6d7d3f5eab27538955528f7a1c8ce95515130807a04042a5c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a55377ec1b6b36e53a1240f266f3f10f121118011b220f4ef8031aa5ff90f9
+oid sha256:b967ab9913addda1efeba2ec99f16fcff83f1b776c306d39cf95d5b4425c3f06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.512,
+  "epoch": 0.5168,
   "eval_steps": 500,
-  "global_step": 6400,
+  "global_step": 6460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2247,6 +2247,27 @@
       "learning_rate": 2.385603559508884e-05,
       "loss": 3.5718,
       "step": 6400
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 30.199399948120117,
+      "learning_rate": 2.3816778784387097e-05,
+      "loss": 3.4446,
+      "step": 6420
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 53.968971252441406,
+      "learning_rate": 2.3777429489847935e-05,
+      "loss": 3.5161,
+      "step": 6440
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 34.33303451538086,
+      "learning_rate": 2.3737988124226834e-05,
+      "loss": 3.422,
+      "step": 6460
     }
   ],
   "logging_steps": 20,
@@ -2254,7 +2275,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.511155153944576e+16,
+  "total_flos": 1.5247728882548736e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null