Training in progress, step 2620, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b209e171b2bafde533025af3ea490078abf0bfdeb25b88b922c9d4d854d7b585
+oid sha256:102a934b9c2b16bd152b8fb45fb756ed8a39ee8f7db8b00ff347bd79c86fbef6
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9900e84d62e1d0ceb495e78efd151917fcdd6603f10280c405bee9baf962ad13
+oid sha256:352473e3f8f3dae7afcda846881ada181c756f061e5a3d9beb1d4a3e068eeb5d
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c86c37e77e2165a2cba8e32a777876823669c841174ddad0c6db1d6a6bb511bb
+oid sha256:fcc2667f22c446f99eb24a0261709aeedb26c632fa56415781522ee28f079a36
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4529d17c1dc6d14789563fff0e0673b46a1f72fc77c5c6b3c74935a83d7232d5
+oid sha256:6b7e6b2fa8982dc42ac672b8fc6e736397d0e1ef6af55fabc97bdaa24968e490
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1888,
+  "epoch": 0.2096,
   "eval_steps": 500,
-  "global_step": 2360,
+  "global_step": 2620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -833,6 +833,97 @@
       "learning_rate": 2.9394880643660242e-05,
       "loss": 3.5974,
       "step": 2360
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 43.614994049072266,
+      "learning_rate": 2.938114567894659e-05,
+      "loss": 3.4834,
+      "step": 2380
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 27.587766647338867,
+      "learning_rate": 2.9367259862819805e-05,
+      "loss": 3.6154,
+      "step": 2400
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 30.223772048950195,
+      "learning_rate": 2.9353223340935533e-05,
+      "loss": 3.4871,
+      "step": 2420
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 34.057884216308594,
+      "learning_rate": 2.933903626053024e-05,
+      "loss": 3.605,
+      "step": 2440
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 39.219242095947266,
+      "learning_rate": 2.932469877041969e-05,
+      "loss": 3.6091,
+      "step": 2460
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 33.33955001831055,
+      "learning_rate": 2.931021102099737e-05,
+      "loss": 3.4862,
+      "step": 2480
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 37.07484436035156,
+      "learning_rate": 2.9295573164232913e-05,
+      "loss": 3.5267,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 27.145864486694336,
+      "learning_rate": 2.9280785353670514e-05,
+      "loss": 3.4369,
+      "step": 2520
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 30.31035041809082,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 3.6056,
+      "step": 2540
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 40.823490142822266,
+      "learning_rate": 2.925076049319174e-05,
+      "loss": 3.5916,
+      "step": 2560
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 44.224796295166016,
+      "learning_rate": 2.9235523758221944e-05,
+      "loss": 3.5881,
+      "step": 2580
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 33.34773254394531,
+      "learning_rate": 2.922013769934406e-05,
+      "loss": 3.5315,
+      "step": 2600
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 25.755775451660156,
+      "learning_rate": 2.920460247795056e-05,
+      "loss": 3.621,
+      "step": 2620
     }
   ],
   "logging_steps": 20,
@@ -840,7 +931,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 5591767798579200.0,
+  "total_flos": 6207501971718144.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null