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:a941e6b20e406fe49a70015195facd9789aedbea0b44c25f0151a0243cc5c081
+oid sha256:41d0e8ed5341825c2e85323a30b329f97e125d28bae44ffd10b73165b164d12e
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f79d884a885ab34fedef92671dbe1ae2146e22579459757c2ef1373e61639bd
+oid sha256:627447a836d838f6f3a84a23e6bbdd680e77629c359f8e293b06981495477f28
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:816a4601e6f061b3c924af3d54ebe883d86531a89df578e78e9d43e92d995eb2
+oid sha256:4d841e4da3c97756d6b77dd41d54eb76213e71d7eaf4110eeb297aee8677a586
 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": 0.049170251997541485,
+  "epoch": 0.05531653349723417,
   "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": 12.703,
       "eval_steps_per_second": 1.594,
       "step": 40
+    },
+    {
+      "epoch": 0.05162876459741856,
+      "grad_norm": 1.4950206279754639,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4697,
+      "step": 42
+    },
+    {
+      "epoch": 0.05531653349723417,
+      "grad_norm": 1.9292529821395874,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.553,
+      "step": 45
+    },
+    {
+      "epoch": 0.05531653349723417,
+      "eval_loss": 0.473427951335907,
+      "eval_runtime": 107.8864,
+      "eval_samples_per_second": 12.708,
+      "eval_steps_per_second": 1.594,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.298044191263949e+16,
+  "total_flos": 7.12772665957417e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null