Training in progress, step 8500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d87811e78f2411bb51f67277ec4ff3e7128aeba1a8f60f6083ffcf5e499137c
+oid sha256:521e4efd5377e853a24b9e89c6aab6af4b9c4cd2d9e34944c2b8bf1d605ab7da
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72baa3d9ed25be64c5f61bc4dcd4ad23809cf47c521105da8c0a4a00395ac985
+oid sha256:872aeb7b9e23ef004bd52b7a5f63d3f3a2758ed6247fde9119589cd936404441
 size 3497859804

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc2d65074a2fcc8399dba6d3c0a62d0568496e8b5831e17319a7dcd95d56dc4
+oid sha256:56ada7a9076e894e38e63b2e547d8bfe564d09412403a53a9fd4f37e79358b8d
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833d77c31bdb2ba7eb60d0271717ab3310ed32ad11e10d8490b2d98bed4a9687
+oid sha256:6266f19ec12f14bd9a4d4ed0cba0ac52c21e3e395901947dc6348d59d7ad7dc1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.81770460510618,
+  "epoch": 4.056311142925316,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,6 +567,41 @@
       "learning_rate": 1.6065010321302785e-05,
       "loss": 0.2601,
       "step": 8000
+    },
+    {
+      "epoch": 3.8654259126700072,
+      "grad_norm": 1.5045113563537598,
+      "learning_rate": 1.486034111767885e-05,
+      "loss": 0.2628,
+      "step": 8100
+    },
+    {
+      "epoch": 3.913147220233834,
+      "grad_norm": 1.5543336868286133,
+      "learning_rate": 1.3694693963836646e-05,
+      "loss": 0.2626,
+      "step": 8200
+    },
+    {
+      "epoch": 3.9608685277976616,
+      "grad_norm": 1.1248536109924316,
+      "learning_rate": 1.2569363292981106e-05,
+      "loss": 0.257,
+      "step": 8300
+    },
+    {
+      "epoch": 4.008589835361489,
+      "grad_norm": 0.8004603981971741,
+      "learning_rate": 1.1485598767483852e-05,
+      "loss": 0.2457,
+      "step": 8400
+    },
+    {
+      "epoch": 4.056311142925316,
+      "grad_norm": 0.8413916826248169,
+      "learning_rate": 1.0444603891152616e-05,
+      "loss": 0.1514,
+      "step": 8500
     }
   ],
   "logging_steps": 100,
@@ -586,7 +621,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.096777803147854e+18,
+  "total_flos": 4.3528844255689605e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null