Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8553f34a48f03ade0b1f11454223b916ed0ac27f708c96ce4c0286980d49dbf5
+oid sha256:fd9045b7a38badf4c816d0772df3b73e28f1bc6b7c0ceef97790d1fb85834705
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb58e96d9c12acb44e67dbe35936aa7d2af86d69178ef6cc54cda2a178dcb50
+oid sha256:8202700e2d05e79d5a1f28b478c85851ebf6a33aef61a18d80bd2305d1ced241
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63985bc32cad5482f6eca78a52b8b7156b0f0a5bd5f342c01e7ba08ef3576e32
+oid sha256:a85d17decd2512557bcac0228d4f0a5a08ae80e2de8f8e01345b3e66581287a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3333333333333333,
+  "epoch": 1.5555555555555556,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 68.361,
       "eval_steps_per_second": 8.917,
       "step": 54
+    },
+    {
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.31057700514793396,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 1.9642,
+      "step": 57
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.30521175265312195,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 2.0191,
+      "step": 60
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.1954805850982666,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 2.1129,
+      "step": 63
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "eval_loss": 1.9135476350784302,
+      "eval_runtime": 1.0142,
+      "eval_samples_per_second": 68.033,
+      "eval_steps_per_second": 8.874,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3430634062479360.0,
+  "total_flos": 4002737484595200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null