Training in progress, step 28, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd856d4b5279e7d10774d470ff7bac9dfaf43ddd58c9a3d24478acedc82edd9
+oid sha256:7f3374b8575b528d547c2a07e71dce5df416a89c6ea9c6c5802c76870cdc6ff0
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dea331b78a0088850af38aae3caf2a969275f094f678e0bfc657194711ae15c
+oid sha256:ca634fd616985bfc8f4635b55110dcb16241bc4cc729a0f10d5216d0863d329a
 size 328468404

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff79fe953d04826b99fecfe7e010fe07129025452d919884191f130eb42747c
+oid sha256:83ad3df394b5c1740144f63f879f830a1b591a452277192b95163ec0b6aaef4f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:045b85bc34af39145c81016bdd7a5ad641dcaf58ffb672ec2ccc21781da3fac6
+oid sha256:aa24382b61af9f090dfff2dabddbb2717e3143ca7ce014da302e91d850e78a66
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915d76157a5cbef9e1abdf860e14d4497c54f8707e539c6d6a75cf5e840a42eb
+oid sha256:e14bba59ee88608d23505dd811c8b74f2aa22814f32bf17efc7ac75dc9d20eba
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ef3913b9b2ad955bc286b3dc480ecd0223a8025a0332846a26073b62d442cc9
+oid sha256:13e2928b6b58c8077cb9f7a6e9e608874da88eeea809c730ebeb6907aca27f57
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e11730ab4a3a7ded716d3fd9997c2ef9af71a212e12a9490d14cbc3f60a6cced
+oid sha256:d968513c39068becb287a22a50f8e35eb3e6705f8e36951d8beb043b32eb1ab1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8316831683168316,
+  "epoch": 1.108910891089109,
   "eval_steps": 7,
-  "global_step": 21,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,28 @@
       "eval_samples_per_second": 65.997,
       "eval_steps_per_second": 4.659,
       "step": 21
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 0.7568883299827576,
+      "learning_rate": 8.930265473713938e-05,
+      "loss": 1.5255,
+      "step": 24
+    },
+    {
+      "epoch": 1.0693069306930694,
+      "grad_norm": 0.6296226978302002,
+      "learning_rate": 8.450395057410561e-05,
+      "loss": 1.6128,
+      "step": 27
+    },
+    {
+      "epoch": 1.108910891089109,
+      "eval_loss": 1.4710044860839844,
+      "eval_runtime": 1.2852,
+      "eval_samples_per_second": 66.136,
+      "eval_steps_per_second": 4.668,
+      "step": 28
     }
   ],
   "logging_steps": 3,
@@ -107,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.97193233751081e+16,
+  "total_flos": 7.962576450014413e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null