Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9045b7a38badf4c816d0772df3b73e28f1bc6b7c0ceef97790d1fb85834705
+oid sha256:726a20157b44f0d96c2c60c0951a2823a61527baa692eaf82e9935913f07ea6a
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8202700e2d05e79d5a1f28b478c85851ebf6a33aef61a18d80bd2305d1ced241
+oid sha256:097d3d4e81eec4d98953b162cb43a40cbc96b17503c912959ea1b984edeb744b
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85d17decd2512557bcac0228d4f0a5a08ae80e2de8f8e01345b3e66581287a6
+oid sha256:d61c9d931c3b1a1eab2c53d8ea1998fb67431e2d86c8ae81a25b7370aaa88270
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5555555555555556,
+  "epoch": 1.7777777777777777,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 68.033,
       "eval_steps_per_second": 8.874,
       "step": 63
+    },
+    {
+      "epoch": 1.6296296296296298,
+      "grad_norm": 0.18209777772426605,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 1.8804,
+      "step": 66
+    },
+    {
+      "epoch": 1.7037037037037037,
+      "grad_norm": 0.19758297502994537,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 1.8818,
+      "step": 69
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.19676625728607178,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 2.0798,
+      "step": 72
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "eval_loss": 1.9025213718414307,
+      "eval_runtime": 1.0144,
+      "eval_samples_per_second": 68.024,
+      "eval_steps_per_second": 8.873,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4002737484595200.0,
+  "total_flos": 4574840906711040.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null