Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31644b6bca1f4fb6f2bb1ff9fb2bf9dcb7a7832e13796aae00339c4c57c14fc4
+oid sha256:055e5b5ef94c766b6912391e0081f9fcd036e4025c0490aed2fd2cace885170c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:666fd88d2d828e6a2a82843fb94bfa6743b7e3b91fafe1110c150addc149f79d
+oid sha256:5fc8ca7c6d9229a07a6335fd703709165c4ad47e74fafa03affe9695f5813bf0
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f1872ba5383f53de53fb881877731e4ff3e596923a22f878117c3299ae01169
+oid sha256:0faafb2ae711d4fd7df5493691d652c88f534d84da92ff77eb8863dda28af9a0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29508196721311475,
+  "epoch": 0.39344262295081966,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 15.402,
       "eval_steps_per_second": 2.0,
       "step": 27
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 1.1863789558410645,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 7.6305,
+      "step": 30
+    },
+    {
+      "epoch": 0.36065573770491804,
+      "grad_norm": 1.1477130651474,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 7.6748,
+      "step": 33
+    },
+    {
+      "epoch": 0.39344262295081966,
+      "grad_norm": 1.2501188516616821,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 7.5313,
+      "step": 36
+    },
+    {
+      "epoch": 0.39344262295081966,
+      "eval_loss": 1.8740694522857666,
+      "eval_runtime": 10.0026,
+      "eval_samples_per_second": 15.396,
+      "eval_steps_per_second": 1.999,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.594020110467072e+16,
+  "total_flos": 4.770244873892659e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null