Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96740feaba8523e9c3b53692397b2fb119e0196f18943d61b2332dbd549a912c
+oid sha256:ad818c83ecada0ac38ac9925d364fe72c911bbfa7d0d92d3ba36f6a3ad0c67f7
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ba2c727a9c424e9b844c344ea4a60963ca2aa5b5a23dc8af002e8f7c036554
+oid sha256:302b8df31ea93fc8a26d7ae1c8ef10adf3233e1a216cdd840ba6ce88d7c18b73
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52518ace7820dede4a68d1f859bf12f32d7d01add7448650df33b1db9fec6153
+oid sha256:96e7f674eb8e0d7b06038546beef4656bebd11a28fbd56de62105d83f601544a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04724940938238272,
+  "epoch": 0.0539993250084374,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 4.335,
       "eval_steps_per_second": 0.542,
       "step": 35
+    },
+    {
+      "epoch": 0.04859939250759365,
+      "grad_norm": 4.739097595214844,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 3.6449,
+      "step": 36
+    },
+    {
+      "epoch": 0.05264934188322646,
+      "grad_norm": 5.869235038757324,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 3.446,
+      "step": 39
+    },
+    {
+      "epoch": 0.0539993250084374,
+      "eval_loss": 0.9727193117141724,
+      "eval_runtime": 287.775,
+      "eval_samples_per_second": 4.337,
+      "eval_steps_per_second": 0.542,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.113984315267482e+16,
+  "total_flos": 1.0444492974430618e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null