Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e87e440bf2e1846b30f0d4a6cbbc9312c6b661166524c7e788b4d7f64b7bb7e
+oid sha256:4ed0466fca68da94dfa3d3d8865ddf941cf2083f32d067ee62f18d6a428dbe72
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b665f2f1d3260fc134690ee3cfdbc8cdb282b1a34ba3a82aee53429c8fe2db
+oid sha256:fd9b6804656660c8134448e216e28ee63734fb97c5194956390c535ab7bea1a1
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e537cc525318fa48a97713b6f30825cf7ad8337947272a02e54c5724bee9a3c8
+oid sha256:96aa2f6932796a349a4e1bc725d9730f67302650fffb525e3d0acc18afed398e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008670259204624138,
+  "epoch": 0.009754041605202156,
   "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": 7.04,
       "eval_steps_per_second": 0.88,
       "step": 72
+    },
+    {
+      "epoch": 0.009031520004816811,
+      "grad_norm": 12.658801078796387,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 5.9402,
+      "step": 75
+    },
+    {
+      "epoch": 0.009392780805009483,
+      "grad_norm": 15.684614181518555,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 5.6994,
+      "step": 78
+    },
+    {
+      "epoch": 0.009754041605202156,
+      "grad_norm": 11.472796440124512,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 5.8439,
+      "step": 81
+    },
+    {
+      "epoch": 0.009754041605202156,
+      "eval_loss": 1.4167842864990234,
+      "eval_runtime": 1987.061,
+      "eval_samples_per_second": 7.039,
+      "eval_steps_per_second": 0.88,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0250152754846106e+17,
+  "total_flos": 2.278142184920187e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null