Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66acfd41a6bd5d397dd2912f3889b5b20dfbd8328418f869888b343f8046e748
+oid sha256:b3f06d5a256218c51477ed27f947cc4ddd92361865cb8aece152711a7808d949
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e00b41a03700faa246fd1f1b8279886a9d0880ef636e3b248e8ed84181deffd
+oid sha256:5af5b1543c2dce0f4a4cff0437e159cd486ffa735a87ccbe8495323aab7239d3
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:088c088af7cf27b9140215093eff25bfd4aea5cba83c9d1e10989ec38ee693b4
+oid sha256:e319105a9624bf44a15e7fef3006b447aaee5aad98a6dbb41ed242bf9f28e8cc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02991586163913992,
+  "epoch": 0.03365534434403241,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 23.377,
       "eval_steps_per_second": 2.924,
       "step": 72
+    },
+    {
+      "epoch": 0.031162355874104083,
+      "grad_norm": 0.8000510334968567,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 1.2934,
+      "step": 75
+    },
+    {
+      "epoch": 0.032408850109068243,
+      "grad_norm": 0.8692224621772766,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 1.37,
+      "step": 78
+    },
+    {
+      "epoch": 0.03365534434403241,
+      "grad_norm": 0.8634310364723206,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 1.2589,
+      "step": 81
+    },
+    {
+      "epoch": 0.03365534434403241,
+      "eval_loss": 1.2482656240463257,
+      "eval_runtime": 173.4527,
+      "eval_samples_per_second": 23.372,
+      "eval_steps_per_second": 2.923,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.895259076709581e+16,
+  "total_flos": 3.2571664612982784e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null