Training in progress, step 21, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db9d4c81f5c870d5091ce1248df2321c3627377437eb1fd3a02dd2b09cc6d84d
+oid sha256:8dd856d4b5279e7d10774d470ff7bac9dfaf43ddd58c9a3d24478acedc82edd9
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f00519a1280a9ba1ae5ff258ebfbecfd3d048156dc03b5da31fc62e86da27a
+oid sha256:8dea331b78a0088850af38aae3caf2a969275f094f678e0bfc657194711ae15c
 size 328468404

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bc6a98341976d14774c9db5fc9e42d35e0df44221b751477e2174edc7ac28df
+oid sha256:7ff79fe953d04826b99fecfe7e010fe07129025452d919884191f130eb42747c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4575ea3777bfc5a1c4772e7aa158bf61093c0ee16bcbfb398eb4b1ad9f500f0e
+oid sha256:045b85bc34af39145c81016bdd7a5ad641dcaf58ffb672ec2ccc21781da3fac6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fafa18e0be672f8fc31e8d231a7a8babae560a95bb0e01aefaa36a7ac352fe61
+oid sha256:915d76157a5cbef9e1abdf860e14d4497c54f8707e539c6d6a75cf5e840a42eb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5307b323e04b0aa5281216bce5c3f1719f8a0b241a803e1b840f8fb7bac651ff
+oid sha256:1ef3913b9b2ad955bc286b3dc480ecd0223a8025a0332846a26073b62d442cc9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e879686ec70e90a34bf505630c03eb25089480b81e2ef9381471251f2ea6ef8
+oid sha256:e11730ab4a3a7ded716d3fd9997c2ef9af71a212e12a9490d14cbc3f60a6cced
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5544554455445545,
+  "epoch": 0.8316831683168316,
   "eval_steps": 7,
-  "global_step": 14,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,35 @@
       "eval_samples_per_second": 66.133,
       "eval_steps_per_second": 4.668,
       "step": 14
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 0.7464063763618469,
+      "learning_rate": 9.859057841617709e-05,
+      "loss": 1.8413,
+      "step": 15
+    },
+    {
+      "epoch": 0.7128712871287128,
+      "grad_norm": 0.7601683139801025,
+      "learning_rate": 9.641839665080363e-05,
+      "loss": 1.6764,
+      "step": 18
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "grad_norm": 0.8399017453193665,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.6186,
+      "step": 21
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "eval_loss": 1.5880630016326904,
+      "eval_runtime": 1.2879,
+      "eval_samples_per_second": 65.997,
+      "eval_steps_per_second": 4.659,
+      "step": 21
     }
   ],
   "logging_steps": 3,
@@ -78,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.981288225007206e+16,
+  "total_flos": 5.97193233751081e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null