Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53afecfd67a91d4a2aad3f5db113c466a27cefef8ad7eed9563ae676d06dfacf
+oid sha256:4098029b7716ff739d06f8220062506fa2eabdb703b31d8d1acd04e4b4ca5612
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ae655c264990c9098a5ec4b548e8af336ad66329e8984acb61f0da136baa1f
+oid sha256:44c60003aac1798e5ad887546706ae113ae861addb5df31abdcd5c8ab16e41e2
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:950c5cceb85e460a2a6d67642a8393ef4a1e5902e2c55873fdcea4b712960518
+oid sha256:9c1536289cb73d62a2875a4749c24fda72b2a21b4512f03dda34aea93e03ca09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05742935278030994,
+  "epoch": 0.06563354603463993,
   "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": 4.522,
       "eval_steps_per_second": 0.565,
       "step": 63
+    },
+    {
+      "epoch": 0.0601640838650866,
+      "grad_norm": 9.282758712768555,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 3.6969,
+      "step": 66
+    },
+    {
+      "epoch": 0.06289881494986327,
+      "grad_norm": 9.940718650817871,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 3.4917,
+      "step": 69
+    },
+    {
+      "epoch": 0.06563354603463993,
+      "grad_norm": 10.431665420532227,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.7412,
+      "step": 72
+    },
+    {
+      "epoch": 0.06563354603463993,
+      "eval_loss": 0.8883235454559326,
+      "eval_runtime": 408.7916,
+      "eval_samples_per_second": 4.521,
+      "eval_steps_per_second": 0.565,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6629012643813786e+17,
+  "total_flos": 1.9019652939330355e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null