Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:584c91f92dfd46b64e3f789784521837cd22bf2cb243b1060fdc8f5b717619e5
+oid sha256:4e5da7b80a8e4f67ea44fe4ca7c5e90734b8f6babd4122e07ab7ab0ef6091249
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b987a1f8fd00ef98a3de03fa34eb81cfc7d522e4933c76f8c80affdfb8ca7c13
+oid sha256:c4a2618ba96c1c76f87ce4bb59587c7b1bff56663475f050645aba90427ca9e7
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc8cef09f79bbc389e1e25c86a79b3b1677939aa39a0c694228bfacccf9be77
+oid sha256:8d2430a504f31c9b7fd3120e51e379d0900588466ffc423d40adc7cb940aa491
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
+oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.062090375991721285,
+  "epoch": 0.07450845119006554,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 7.135,
       "eval_steps_per_second": 0.894,
       "step": 45
+    },
+    {
+      "epoch": 0.06622973439116937,
+      "grad_norm": 4.041275501251221,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.9123,
+      "step": 48
+    },
+    {
+      "epoch": 0.07036909279061745,
+      "grad_norm": 2.8718698024749756,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 0.6675,
+      "step": 51
+    },
+    {
+      "epoch": 0.07450845119006554,
+      "grad_norm": 2.9034252166748047,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.5178,
+      "step": 54
+    },
+    {
+      "epoch": 0.07450845119006554,
+      "eval_loss": 0.17112058401107788,
+      "eval_runtime": 171.0347,
+      "eval_samples_per_second": 7.139,
+      "eval_steps_per_second": 0.895,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2656330976264192e+17,
+  "total_flos": 1.518759717151703e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null