Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e893fbcaa465e354925e7e4397533bb422fbe9cfaa8a149d52928eebc1c82888
+oid sha256:b685e06650274a43b6ab9959b69c0d72728a6036f86c34263d33ecb59b724648
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f798d1c92bcb9150b4f7784419a16b48e9c4b6622f024e39325890b4d3c5628
+oid sha256:aff9bc1530d64b951f812208b7c2736f337ea2acfac6a362bec33b02b5f15af7
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54299c1b253851c243ba145833bfe72e30e9ff59fc9e8be66f87cb9a23394a88
+oid sha256:861730abe8cc65d5d27a22c1c77fda2c515e52a10959f74e74710d0c55ace38f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13745704467353953,
+  "epoch": 0.15463917525773196,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 13.854,
       "eval_steps_per_second": 1.753,
       "step": 40
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 39.78969192504883,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.7115,
+      "step": 42
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 43.422847747802734,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.8553,
+      "step": 45
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "eval_loss": 0.6664606928825378,
+      "eval_runtime": 35.3657,
+      "eval_samples_per_second": 13.855,
+      "eval_steps_per_second": 1.753,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.723995257176064e+16,
+  "total_flos": 6.439494664323072e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null