Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf440db6594c84604740fed8cda28caf0921c07c724d151bcb3cb42c39e9539
+oid sha256:4e226863fb04becfa4bb040389ad11874e2f2582ffebeff56e384c1c64b6958f
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bdb516b4acf1d6b65bd43cebcdad610903fb270a28a57592cef712c010bc3a8
+oid sha256:6a78e0dd545ee65c159e0ee94a9081e3ce9a151a921855e2bf39fac19ffa0d7c
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53cb619a5ccb222884fa3789cef341bb8e4b5441bee4ff9cd1343500f85d9d21
+oid sha256:0befc8c1b5470331de1f06f4866b7f913569491ebf0fa2e81579002c94820b4d
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97d469c2d1ff6d4cb5f670c08e09df4f08fd3742fcd2f7e54012931e0d6d476
+oid sha256:745ac8d66cbe146de7db53c59e64e6360229a39a692a8f7fce8aeecef079d08a
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac9ecbe85481a4e8d86a388fa4c6209a870f702b0d0252aae9f9e31a5e396ad
+oid sha256:e4ea31088ff346d9260a586478ddec6c17a76ba8b8cad39ec03fb38b331316c6
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97c9c12b1cca18b9d68cf758cec45fb2341027dbadb09d49ba12c4f8c2ba9aa
+oid sha256:6e31c14de4f0b09b0949f920ba6edd99601d5ad9d96e91268fd167b28ec61a14
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4f1ab2f108da9a540e579e8eb4fe7879ce1b2d4bc117501313387ab106dde1
+oid sha256:66a3dc4fb38a81c84d46fc2421cb9708f6624ef461485172d9307406501681da
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5e132a7d035d553db132ede574b00cced69641455ad4a6157b0102cdcd0c78
+oid sha256:0321605316161bbd28089a763d175f03af99ada03b47255a37e8b3612627ba68
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:912e872d3c365513889972e6f7039482d5bc50a57eb0c2d3d0c7af303ca21576
+oid sha256:1193cb012cc88b5fe420a65baea2555f9b40d26da5a73c09666a69d4c03d606e
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e55a4c2490cd5fee87293d304c31ce3cec1fb6ea51d17e81369ad67604328c
+oid sha256:d83a6a2d5708ef4004d174211696864bde8c72aab8f0e570199be9d3f3fbada4
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015683199372672025,
+  "epoch": 0.002352479905900804,
   "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": 107.986,
       "eval_steps_per_second": 13.509,
       "step": 6
+    },
+    {
+      "epoch": 0.0018297065934784029,
+      "grad_norm": 0.43685799837112427,
+      "learning_rate": 0.00014,
+      "loss": 0.0965,
+      "step": 7
+    },
+    {
+      "epoch": 0.0020910932496896032,
+      "grad_norm": 0.6890192627906799,
+      "learning_rate": 0.00016,
+      "loss": 0.1035,
+      "step": 8
+    },
+    {
+      "epoch": 0.002352479905900804,
+      "grad_norm": 0.38788190484046936,
+      "learning_rate": 0.00018,
+      "loss": 0.07,
+      "step": 9
+    },
+    {
+      "epoch": 0.002352479905900804,
+      "eval_loss": 0.05562698468565941,
+      "eval_runtime": 59.7185,
+      "eval_samples_per_second": 107.889,
+      "eval_steps_per_second": 13.497,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4645068333907968.0,
+  "total_flos": 6991795581878272.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null