Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0a2c4f5804bc833543977a5610b19ecf809ed3e1c030f43ee00839a70ff92f
+oid sha256:27dce25ba5c7e7df33cbe403c90e6ee2dcbd457478dd6ddd2734e913775c0e6f
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a7ca2ef6a2d13030630527be80ee345db1102a3327f9d64c73b1ea3b3437b9
+oid sha256:a030d1feb8e9f6cead6ddba5726d4bf957b67a48ea42e93c520c35e9eb29f1f1
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923c546d72e202dad57c207c925fd1b276eaac8a8b8d2e0e6daee9cfc60c92c9
+oid sha256:351706e9c0dde7029671bf4c1ac36641f73142394ca971499ac6c64d83613271
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7949526813880127,
+  "epoch": 0.9085173501577287,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 59.778,
       "eval_steps_per_second": 7.584,
       "step": 63
+    },
+    {
+      "epoch": 0.832807570977918,
+      "grad_norm": 0.718596875667572,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.5353,
+      "step": 66
+    },
+    {
+      "epoch": 0.8706624605678234,
+      "grad_norm": 0.6250401735305786,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.5808,
+      "step": 69
+    },
+    {
+      "epoch": 0.9085173501577287,
+      "grad_norm": 0.7185081243515015,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.8177,
+      "step": 72
+    },
+    {
+      "epoch": 0.9085173501577287,
+      "eval_loss": 1.6348599195480347,
+      "eval_runtime": 2.2303,
+      "eval_samples_per_second": 60.082,
+      "eval_steps_per_second": 7.622,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4992608533217280.0,
+  "total_flos": 5659491261480960.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null