Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c716644c8f1a8ce110351b2a690c1a9911d46caabb538148e256f7b261c460
+oid sha256:5e18f0bde01cb88e882e0a9e96054f29b09c23a84d1562eac8c685af3b03d7a6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602f44bda3b2a895a7f055e58a1de2d779540bd4cfcee24d1e8e6e47702f742c
+oid sha256:c9c621510328160e80aa80b84d7deb32dd16406a820f826f146497b3331f3c58
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74b05f2720b311440022765a28fc8006a7374957aaca6aca1b5e6bc5db4cbaa
+oid sha256:a15f8b7e107d1944aa714244b7981525070751630348b2f99259785cab9c85cb
 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": 0.003063699417046083,
+  "epoch": 0.0038296242713076038,
   "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": 13.832,
       "eval_steps_per_second": 1.729,
       "step": 36
+    },
+    {
+      "epoch": 0.0033190077017999234,
+      "grad_norm": 2.741870164871216,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 4.6275,
+      "step": 39
+    },
+    {
+      "epoch": 0.003574315986553764,
+      "grad_norm": 2.8776938915252686,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 4.5287,
+      "step": 42
+    },
+    {
+      "epoch": 0.0038296242713076038,
+      "grad_norm": 2.7638866901397705,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 4.4224,
+      "step": 45
+    },
+    {
+      "epoch": 0.0038296242713076038,
+      "eval_loss": 1.1293689012527466,
+      "eval_runtime": 1429.6849,
+      "eval_samples_per_second": 13.843,
+      "eval_steps_per_second": 1.73,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.062538188711526e+16,
+  "total_flos": 6.328172735889408e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null