Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b87b7d42a1dbaec4c3ab0fe8bf07efcf3ef16e4684bfc26a76b004616560ca
+oid sha256:8e17d71748b14e6a0ba7eb39db38cb86e9e3c3371c660866d372a0c97360a6d2
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20c6739b1cfabaad0f2466186c77d5104fdee2469f9979a2531c5783c9d949c
+oid sha256:7c76d8714b5a748a3d8ac9480c0bf0031ba79b519b06f9c6bc996b53a59dc97d
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477b8bdb96ef0a719a9f207ca69a3d5d20ccc9cc1f6ae115b891fb65634fc1ad
+oid sha256:4dc1adf60f6339233314012883dccb2c7751dd3329abcbd3ebf96c8f47dafc91
 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": 0.12923076923076923,
+  "epoch": 0.1476923076923077,
   "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": 10.941,
       "eval_steps_per_second": 1.371,
       "step": 63
+    },
+    {
+      "epoch": 0.13538461538461538,
+      "grad_norm": 16.03173828125,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 3.1598,
+      "step": 66
+    },
+    {
+      "epoch": 0.14153846153846153,
+      "grad_norm": 15.822704315185547,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 3.1743,
+      "step": 69
+    },
+    {
+      "epoch": 0.1476923076923077,
+      "grad_norm": 22.87495994567871,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 3.7806,
+      "step": 72
+    },
+    {
+      "epoch": 0.1476923076923077,
+      "eval_loss": 0.8304129838943481,
+      "eval_runtime": 75.1064,
+      "eval_samples_per_second": 10.944,
+      "eval_steps_per_second": 1.371,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.859431683384934e+16,
+  "total_flos": 1.0125064781011354e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null