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:c2e1b990778a120ccda2f5d235054acea331ec703a816f3cd7476519676e1f78
+oid sha256:fc5d734fd21c4ffdd7c639e91c6060f654075be2d83bd4ab28331ca09d6d4f6b
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b730240c3478a38621f5fdffc0cc37a719fc56ea5b3f4fdd8b990527174ec8
+oid sha256:060f68c906acb544160e1c34fcf1ebd64e3c9115231fc8b2ca3bd9df6673f6bb
 size 111142

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": 0.24122934183821398,
+  "epoch": 0.361844012757321,
   "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": 366.719,
       "eval_steps_per_second": 91.806,
       "step": 26
+    },
+    {
+      "epoch": 0.25050739344737605,
+      "grad_norm": 0.2082686722278595,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3691,
+      "step": 27
+    },
+    {
+      "epoch": 0.2597854450565381,
+      "grad_norm": 0.22001177072525024,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3636,
+      "step": 28
+    },
+    {
+      "epoch": 0.26906349666570023,
+      "grad_norm": 0.23329807817935944,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3666,
+      "step": 29
+    },
+    {
+      "epoch": 0.2783415482748623,
+      "grad_norm": 0.2456667423248291,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3611,
+      "step": 30
+    },
+    {
+      "epoch": 0.28761959988402436,
+      "grad_norm": 0.27157169580459595,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3665,
+      "step": 31
+    },
+    {
+      "epoch": 0.2968976514931864,
+      "grad_norm": 0.2414681762456894,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.37,
+      "step": 32
+    },
+    {
+      "epoch": 0.3061757031023485,
+      "grad_norm": 0.22449567914009094,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3723,
+      "step": 33
+    },
+    {
+      "epoch": 0.3154537547115106,
+      "grad_norm": 0.23689420521259308,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3668,
+      "step": 34
+    },
+    {
+      "epoch": 0.32473180632067267,
+      "grad_norm": 0.24381740391254425,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3639,
+      "step": 35
+    },
+    {
+      "epoch": 0.33400985792983473,
+      "grad_norm": 0.24260398745536804,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3677,
+      "step": 36
+    },
+    {
+      "epoch": 0.3432879095389968,
+      "grad_norm": 0.23076368868350983,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.36,
+      "step": 37
+    },
+    {
+      "epoch": 0.3525659611481589,
+      "grad_norm": 0.2268386036157608,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3564,
+      "step": 38
+    },
+    {
+      "epoch": 0.361844012757321,
+      "grad_norm": 0.20787151157855988,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3652,
+      "step": 39
+    },
+    {
+      "epoch": 0.361844012757321,
+      "eval_loss": 10.361462593078613,
+      "eval_runtime": 1.9924,
+      "eval_samples_per_second": 364.89,
+      "eval_steps_per_second": 91.348,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 43515635564544.0,
+  "total_flos": 65273453346816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null