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:fc254380db18ef9e03a89daf645a5586631a157d1d06c72267e43f64086c0e5f
+oid sha256:584c91f92dfd46b64e3f789784521837cd22bf2cb243b1060fdc8f5b717619e5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57f93acc85887a6284b34117ba37170f6f7939807e26d955b8842ed8d01d0bb4
+oid sha256:b987a1f8fd00ef98a3de03fa34eb81cfc7d522e4933c76f8c80affdfb8ca7c13
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c400d8725348b2cb960736157adb45bbbed9a27fd149b460f4c6a8ef61fcfc7c
+oid sha256:2dc8cef09f79bbc389e1e25c86a79b3b1677939aa39a0c694228bfacccf9be77
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
+oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.049672300793377026,
+  "epoch": 0.062090375991721285,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 7.142,
       "eval_steps_per_second": 0.895,
       "step": 36
+    },
+    {
+      "epoch": 0.053811659192825115,
+      "grad_norm": 2.966871738433838,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 0.8124,
+      "step": 39
+    },
+    {
+      "epoch": 0.057951017592273196,
+      "grad_norm": 2.5523316860198975,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.7702,
+      "step": 42
+    },
+    {
+      "epoch": 0.062090375991721285,
+      "grad_norm": 2.8729777336120605,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.7699,
+      "step": 45
+    },
+    {
+      "epoch": 0.062090375991721285,
+      "eval_loss": 0.18150073289871216,
+      "eval_runtime": 171.1339,
+      "eval_samples_per_second": 7.135,
+      "eval_steps_per_second": 0.894,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0125064781011354e+17,
+  "total_flos": 1.2656330976264192e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null