Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31301ffb862f6d794ce7d936de376d5ef398a8fb4ee6a971090e8e0397ea6b98
+oid sha256:9ae4ebaa0e5914bda660a71adf27e2f79eed304c9c273d4c3dbc247dae62e10a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e87676e85bd2a7df1779a61f413877c7225407262cd0e5bc474ef875bd621f
+oid sha256:0f0146b25aa55360a4f3825b12d1d91d394a3861513e3384a7a4e5ce3420f39d
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31dc448056b0201d2932926c138d87704bc12e9e193df4ea53b253699278ba3e
+oid sha256:b0fbb0d8372c773303ed8b57a701ed3dbe0540d90170abf552bdce6ec3e3a2fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002784150962852208,
+  "epoch": 0.003712201283802944,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 14.029,
       "eval_steps_per_second": 1.754,
       "step": 27
+    },
+    {
+      "epoch": 0.0030935010698357867,
+      "grad_norm": 8.591585159301758,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 6.1041,
+      "step": 30
+    },
+    {
+      "epoch": 0.0034028511768193653,
+      "grad_norm": 8.520772933959961,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 6.4861,
+      "step": 33
+    },
+    {
+      "epoch": 0.003712201283802944,
+      "grad_norm": 7.190521717071533,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 5.586,
+      "step": 36
+    },
+    {
+      "epoch": 0.003712201283802944,
+      "eval_loss": 1.4635615348815918,
+      "eval_runtime": 1164.1403,
+      "eval_samples_per_second": 14.031,
+      "eval_steps_per_second": 1.754,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.972681667549594e+16,
+  "total_flos": 5.27347124011008e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null