Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbaf1ed57b17e15838d7ba427275c71e5239abd01fce75f2b8831fac26d5aba5
+oid sha256:0e784acdeea8251a6336500366d312e683bd14e3b97f10fae082fa3d6941ae7c
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33281a030601722e6e5833c52b1e422fe1559d066595f17c423831e4db7eafe0
+oid sha256:ec526be729fc00766aa465a00eb2bf0692f28ce23edb3bf18d27f8d70b8a5d6c
 size 328468404

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d1e322d844019667efd77005c343afd5a843933d60a6d377f0cac5bb77cb19
+oid sha256:4021ac42541c732a9edf05da0035fae77d4a41abb574781ede4fe889417988ba
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db846ff2ee419b9368c374e099a2c577a7103459c8f15233032b76636eccd21
+oid sha256:41670b12d55b8b5e00e1702187eaf19a951a106909295e3bdb88a154dad660d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346c719b46ba2add08db3614f24dfa501356aff6bef89984c3850b171d54a423
+oid sha256:357fa8adc33d4c6287c5a582578b54604c4e2ff77e822b43c331fe6a4113b76a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6abe539c42e12e554dbb33ca0979eacce661411ac7da2a82a07086d592ab60
+oid sha256:1523cad77aebbc5c93094a08e19a912cbf5e034a61c053725fea450338236ccb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:882cbcdafabe936edc086ed06911378377212c19ac6648379eaecef2ba03d21c
+oid sha256:1e56d433c056f847cd62894fdc7d2cfac435f2db58e37ae7dede3f4334c0f5d0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.217821782178218,
+  "epoch": 2.495049504950495,
   "eval_steps": 7,
-  "global_step": 56,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -205,6 +205,35 @@
       "eval_samples_per_second": 66.094,
       "eval_steps_per_second": 4.665,
       "step": 56
+    },
+    {
+      "epoch": 2.2574257425742577,
+      "grad_norm": 0.8602892160415649,
+      "learning_rate": 1.9092050688969738e-05,
+      "loss": 1.0049,
+      "step": 57
+    },
+    {
+      "epoch": 2.376237623762376,
+      "grad_norm": 0.8723423480987549,
+      "learning_rate": 1.3813298094746491e-05,
+      "loss": 1.0431,
+      "step": 60
+    },
+    {
+      "epoch": 2.495049504950495,
+      "grad_norm": 0.8783928155899048,
+      "learning_rate": 9.271202397483215e-06,
+      "loss": 0.9437,
+      "step": 63
+    },
+    {
+      "epoch": 2.495049504950495,
+      "eval_loss": 1.3786593675613403,
+      "eval_runtime": 1.3013,
+      "eval_samples_per_second": 65.322,
+      "eval_steps_per_second": 4.611,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -224,7 +253,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5925152900028826e+17,
+  "total_flos": 1.791579701253243e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null