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:cb52e2245fd22436ef42639406fa91c9fd1ca16ed25e5bad81a097ef7d4a3a14
+oid sha256:67b87b7d42a1dbaec4c3ab0fe8bf07efcf3ef16e4684bfc26a76b004616560ca
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f4986268b99a0654f17c66cc8fe5f50c2150f2a027f132d5707d57aa6687fa9
+oid sha256:e20c6739b1cfabaad0f2466186c77d5104fdee2469f9979a2531c5783c9d949c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e9e7b978e914c84d386479aa37cc1d7c932c264297fa6273686f760143c92a
+oid sha256:477b8bdb96ef0a719a9f207ca69a3d5d20ccc9cc1f6ae115b891fb65634fc1ad
 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": 0.11076923076923077,
+  "epoch": 0.12923076923076923,
   "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": 10.945,
       "eval_steps_per_second": 1.371,
       "step": 54
+    },
+    {
+      "epoch": 0.11692307692307692,
+      "grad_norm": 19.14990234375,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 3.5648,
+      "step": 57
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "grad_norm": 15.191015243530273,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 3.2272,
+      "step": 60
+    },
+    {
+      "epoch": 0.12923076923076923,
+      "grad_norm": 16.499048233032227,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 3.1709,
+      "step": 63
+    },
+    {
+      "epoch": 0.12923076923076923,
+      "eval_loss": 0.8416498303413391,
+      "eval_runtime": 75.1294,
+      "eval_samples_per_second": 10.941,
+      "eval_steps_per_second": 1.371,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.593798585758515e+16,
+  "total_flos": 8.859431683384934e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null