Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:490e80fc3303d8ba4985a8e3d6013f86765bd5ee413eac34ae40b592d0e1e682
+oid sha256:c9398ca1f244b98baf693cd2f0b87f6499445218c4ed1c30e34848feb13b22c7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f8d0b52ba78bd4fdd27b425da1511601d02a19a685c2803324a9bc6412b097
+oid sha256:f71c407168f4c2269c0f69d47f80dfc3bf8958b3044b8a43c3de9a9c36f84d66
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aefe369047933c8006be57c15def186ab4b9904527891de282a469d3b182dfdc
+oid sha256:dfeb80672bc82fbc9cf7b55a6f4b05f3057992133a3ddf20f5677f3611342707
 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": 0.022377622377622378,
+  "epoch": 0.027972027972027972,
   "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": 10.042,
       "eval_steps_per_second": 1.256,
       "step": 36
+    },
+    {
+      "epoch": 0.024242424242424242,
+      "grad_norm": 2.687164545059204,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 3.3259,
+      "step": 39
+    },
+    {
+      "epoch": 0.026107226107226107,
+      "grad_norm": 2.353116750717163,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 3.1402,
+      "step": 42
+    },
+    {
+      "epoch": 0.027972027972027972,
+      "grad_norm": 2.298196315765381,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 2.9699,
+      "step": 45
+    },
+    {
+      "epoch": 0.027972027972027972,
+      "eval_loss": 3.1050002574920654,
+      "eval_runtime": 269.7032,
+      "eval_samples_per_second": 10.048,
+      "eval_steps_per_second": 1.257,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.010834829646234e+16,
+  "total_flos": 9.088119223615488e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null