Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46277b724be0a2ccc39293ba11a647315d6f0dd7024940b45dba50a6cb96911d
+oid sha256:0d050eac9f8fb9ea580cee6928fa7005258421f2dd9bf958bcd77a6489c6f94c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40553dd62707e6ac72ba8ab73d4daac9e8edb315217654d6c1ef881386bf9e25
+oid sha256:d86953ca84e4e0a0c15e29384e03ebdf4f7538f1762dab1f63760c53916062a5
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4015cf50661106d4c867455d8fcb77ddec867e70f0f882bba91a3ca1ad588408
+oid sha256:18bf5eedb9307c1a22691567263f1584f03ded28702243a8ec493eae3c50d20a
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49fc59e53e240b3838dadf2af67159484079789c12a330a205e27c230ccee1c9
+oid sha256:04666bd159da863b41bc1923e9f56c84b7f24ebf6dbbd0cfa898061b81fecbce
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11722b6394ecb3833f200e9d6276276d305ce41580dceb70733998603948c9fc
+oid sha256:45d8cc4a19a1ea830e01a7bd15340e304d5c7ec1e77a47b36a02704cc3fbb3a0
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd64b1aeac101aad3ba6d07f9650b71a9fb5556ba4d6b15ea569bef72eb6f8a8
+oid sha256:b64531a461f6463a92bc4459ce0611534817c4988b807c722240c9b1e45a5853
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5ac429c02100c8ea139dc1bcd52228cac30b904cf2277e02640b844afb2bf8
+oid sha256:4f0ab952d5b1bf7e3df002cc404ba0d23aff6354996a49bb920eb681ad4ec844
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0e4c1cc21bbb8ce749c794ec6e7606eb777967d6020afb33f90761e165cff8
+oid sha256:05130ae4624a0f5381e9e9d85091accc7a18a1319a44593fb3f36167022af878
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5c2dab0c365a1d31bee5cff9b44deecc376511a9331204b441812b880c65e5
+oid sha256:d280577e17675dfc2d1780f43621051fba52dca5de4d6d3b113e0a4564d60383
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9cad6b44df5f70ced5eafddb1c84bd1a3ffb87a9e3b79a3b70e4204f0ed6e8a
+oid sha256:d9cda439d83b1b78c12925915bfa11a29f289b7d4ee9707f93389cd060f3a0ea
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021352313167259787,
+  "epoch": 0.03202846975088968,
   "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": 33.783,
       "eval_steps_per_second": 4.276,
       "step": 6
+    },
+    {
+      "epoch": 0.02491103202846975,
+      "grad_norm": NaN,
+      "learning_rate": 2e-05,
+      "loss": 9.3528,
+      "step": 7
+    },
+    {
+      "epoch": 0.028469750889679714,
+      "grad_norm": 16.465744018554688,
+      "learning_rate": 4e-05,
+      "loss": 10.3572,
+      "step": 8
+    },
+    {
+      "epoch": 0.03202846975088968,
+      "grad_norm": 12.530702590942383,
+      "learning_rate": 6e-05,
+      "loss": 9.0991,
+      "step": 9
+    },
+    {
+      "epoch": 0.03202846975088968,
+      "eval_loss": 9.917542457580566,
+      "eval_runtime": 14.0571,
+      "eval_samples_per_second": 33.72,
+      "eval_steps_per_second": 4.268,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.5610589610901504e+16,
+  "total_flos": 5.341588441635226e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null