Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa1f55ca17910d96c748348fa6a7720b94fda253b2fdbb715737bc2e7f018317
+oid sha256:939c51cc2293246b64bb1959811fc88d589257a53aa1f711a77986a7a4bb5e68
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fb19e46616d9ce5e455efd53c8f3614df6ba1b32361816708e3035b29b769c
+oid sha256:6d87a9dc6ac0f9d1f605c68b17c6f864ca9882717c9116882dad41bbccf95fab
 size 61926

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d13877ed3f59aa7198c8574c3fa03073b1b0fe0c1150b102e7c126b147c06058
+oid sha256:328fe9968df7bf20cce6c816bd538e730876deaee486e22d46258667abf17afc
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6267e78b9753bf43c76319d17432b962781d32df9e944e6f3cc798be019cdac9
+oid sha256:eba43fdf56448fad0ffc4b3800ab3289204a7137e290f6a13302e4d4c52a37fd
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.41167738743196436,
+  "epoch": 0.6175160811479465,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 121.662,
       "eval_steps_per_second": 30.558,
       "step": 26
+    },
+    {
+      "epoch": 0.42751113310242456,
+      "grad_norm": 0.00884031318128109,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.931,
+      "step": 27
+    },
+    {
+      "epoch": 0.4433448787728847,
+      "grad_norm": 0.007135901600122452,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.931,
+      "step": 28
+    },
+    {
+      "epoch": 0.4591786244433449,
+      "grad_norm": 0.007375482469797134,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9303,
+      "step": 29
+    },
+    {
+      "epoch": 0.47501237011380504,
+      "grad_norm": 0.019206728786230087,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9285,
+      "step": 30
+    },
+    {
+      "epoch": 0.49084611578426524,
+      "grad_norm": 0.00676517840474844,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9313,
+      "step": 31
+    },
+    {
+      "epoch": 0.5066798614547254,
+      "grad_norm": 0.0074449400417506695,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9308,
+      "step": 32
+    },
+    {
+      "epoch": 0.5225136071251856,
+      "grad_norm": 0.006442636717110872,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.931,
+      "step": 33
+    },
+    {
+      "epoch": 0.5383473527956457,
+      "grad_norm": 0.0078086163848638535,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9313,
+      "step": 34
+    },
+    {
+      "epoch": 0.5541810984661059,
+      "grad_norm": 0.007814242504537106,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9313,
+      "step": 35
+    },
+    {
+      "epoch": 0.570014844136566,
+      "grad_norm": 0.008247659541666508,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9309,
+      "step": 36
+    },
+    {
+      "epoch": 0.5858485898070263,
+      "grad_norm": 0.006319059990346432,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9309,
+      "step": 37
+    },
+    {
+      "epoch": 0.6016823354774864,
+      "grad_norm": 0.0059829698875546455,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9316,
+      "step": 38
+    },
+    {
+      "epoch": 0.6175160811479465,
+      "grad_norm": 0.006849578581750393,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9299,
+      "step": 39
+    },
+    {
+      "epoch": 0.6175160811479465,
+      "eval_loss": 11.931235313415527,
+      "eval_runtime": 3.5072,
+      "eval_samples_per_second": 121.464,
+      "eval_steps_per_second": 30.509,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 629179809792.0,
+  "total_flos": 942458142720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null