Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4529dca6b71cea56b3148d04825f54df33cd68658f14e016db9e861e240616
+oid sha256:4605344d9da58de3bca7dc05241c8c7710554407f33652f7bc94bba41822a8ed
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dffa3c6f2823ae22d3aa07828d8a683c85be2795ddff5f4112725c8711f50319
+oid sha256:bb51e7e31a04f95d811fb3375744e35b821950af981ea67764cdbd143a64770c
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a8ea6f872ad69b36a140052965078e0a1e019eff596980afdef00155896881
+oid sha256:d208fc8ffc06a5de0e78a66250af5e4040febbcf16cdc254af2f5493300ac1c9
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac99ee8e22746ac5d76a305ad5b41f5db35e50e5bf8e6923c976375c5dd9c11
+oid sha256:171729bc4986a9839636ee98592d71f8b00583a8eaabd1d63cf9d7610cef9d8e
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee7bc09cc5a34a5399c7ac2031fe648cc8f7c7c45cfe9a6a5f195d546cb4e07
+oid sha256:e28a9e95efff5f4fdbdab6994e651e446586624a0f8b61ff953351f9ace2fd28
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5bc4d5b483cd0139d1dd6497c17adfd72199395dd9fb59760db4eeefb18d90d
+oid sha256:a87f5e3936866d69d87c5ebfdc7bf0d96d0c6bd727c3a6dbd5f5cb4c98ccb1ee
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f146764400aee269ace30336f52d5b91a0e05b6413450f2da5ab7e40cccbfc22
+oid sha256:99817fbab47484f57146aab5db5d1d20950343ead7ff360b6f6af4b55cb9d971
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b5709b9458937bdf0beba73ee9c1b24aa748fbe41f4e89256fabae5db1ea04
+oid sha256:dd6d7b5374da01deb55707ef3ca400e859d43ff9196f00ccd1413b068442c0ac
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14d62a3d1654c081e8c665b79a207d9450a999239c270cf50a0ffae1c57648b9
+oid sha256:7c436452d7af3913a771cc03d673e6c05ed368a9b1cf6d0e23e1bfe1832a5e7c
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901aa808fd1c4548a3a0d072638a38f2fb141a4a2dbe1b2636bc961acd923b85
+oid sha256:7f09039d225663348fb992c94c210c08e9332bf92c2e8818ce5057bb9610639d
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:f193dee591957702c791ef1b0861987f5cc59c358aa6dd7c5c0054f6dbca1910
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6153846153846154,
+  "epoch": 0.9230769230769231,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 88.807,
       "eval_steps_per_second": 5.677,
       "step": 10
+    },
+    {
+      "epoch": 0.676923076923077,
+      "grad_norm": 17.112119674682617,
+      "learning_rate": 9.504844339512095e-05,
+      "loss": 2.943,
+      "step": 11
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 13.983518600463867,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 2.4841,
+      "step": 12
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 21.6774959564209,
+      "learning_rate": 6.112604669781572e-05,
+      "loss": 2.3941,
+      "step": 13
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "grad_norm": 19.613525390625,
+      "learning_rate": 3.887395330218429e-05,
+      "loss": 1.867,
+      "step": 14
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 9.981058120727539,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 1.6661,
+      "step": 15
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "eval_loss": 1.7354800701141357,
+      "eval_runtime": 2.4723,
+      "eval_samples_per_second": 88.58,
+      "eval_steps_per_second": 5.663,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.587960141021184e+16,
+  "total_flos": 9.881940211531776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null