Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6e6e4e0c78085870f137fa0e5ff7d4bec55d1da745a93f8e2efffc408a66a95
+oid sha256:cd60d78ff832ad6ec59c7d3b45984ab86641437a3a6b56146371d7b006f6232f
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546a722907e232b88241287b5e97f1c9798542e1209f200daff0c42ebbb18dce
+oid sha256:62a0fba6379e40c5279a500ae9a4f45f54d63218a5f8070b2a23d3dd39571e10
 size 127788180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c228b076b37c853548d34d0925740557e4fb7ff11d3cd9ec6f7b1f2b73899252
+oid sha256:a87d4da7c7f64682ae1dec8a15e6dce7d60ebc44de3f843d98b9f380b7fdf1b7
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c741a6ed6a336d3663e787f24df3773f55bf618c77403a4fccbb85aedbd11613
+oid sha256:326aee700fb60fbb46a592907a2b8a99c1af83ca40cb5363c762d5a69722ae4e
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a135df0eb732e593f9c74befa41ae4526130d5d5362d161ec6a8094454d314
+oid sha256:946c2ecf8cc694e76dd59fd1512c3017f65fe8966cdde509f24fb12b045e3d96
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18adbf267d2d28fc254cefa2939b1685ca9dc60c07f8e86aa923ec7e6ef08d9e
+oid sha256:62eab200b6e2aa6fa66c59aff6254b93c735bf629489c4bf2bc1cbc8fa900a79
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dace29708dd5b17bc7ddcf8235f57a65322a3712963b4aebf0a2a6497f44fe15
+oid sha256:d4d514fca05d4c250f5ade3e05f2831748efca323d99ffb1243bbd3f62ea98bb
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3608bbbeb9341c3d1d095ea76a13e9264ae99d576979fbe6887ebb174f488043
+oid sha256:367a39d46e2c9b5b56c6b0276d2ddf1c9c83c1fab7d750fc5f7310307c5cbdec
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06798e2ca8b6a26d48bcde8e56566edba28782eaf2442b4a9f40c4baefc6f6ee
+oid sha256:5248f48742af9a7b60d01515e81de943006014943e15dfaa064b8dd18631fe81
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1831c4c1812a87d4aa1f026ba3d190ef16316cad9fbddeadc67b41a9d3e0fd
+oid sha256:8d4aa3892e656c1278ad035aebd4016e18bc788d34249ada3e08d7af6cc56d60
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003931847968545216,
+  "epoch": 0.005897771952817824,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 24.428,
       "eval_steps_per_second": 3.059,
       "step": 6
+    },
+    {
+      "epoch": 0.0045871559633027525,
+      "grad_norm": 0.28356343507766724,
+      "learning_rate": 0.00012,
+      "loss": 0.6242,
+      "step": 7
+    },
+    {
+      "epoch": 0.005242463958060288,
+      "grad_norm": 0.24505580961704254,
+      "learning_rate": 0.00014,
+      "loss": 0.5181,
+      "step": 8
+    },
+    {
+      "epoch": 0.005897771952817824,
+      "grad_norm": 0.32702115178108215,
+      "learning_rate": 0.00016,
+      "loss": 0.4097,
+      "step": 9
+    },
+    {
+      "epoch": 0.005897771952817824,
+      "eval_loss": 0.7492024302482605,
+      "eval_runtime": 105.2948,
+      "eval_samples_per_second": 24.417,
+      "eval_steps_per_second": 3.058,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.107484726598042e+16,
+  "total_flos": 9.161227089897062e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null