Training in progress, step 64, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eb161f828d10a50e45a015a2784664029f2476c18e36c62373032812c1be221
+oid sha256:a932cc6ddedf990950279865803e7116f761bd6fab492b1a26ffa16bea102743
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8037d816176c010f337de14924d2658d16a59fb2ec73a775b9b3984bb233330c
+oid sha256:39fa2d3c51eb98dee0433d6812b7bb79c56876f236d243c3f77f4df232ee531b
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72bb0203fc4f241fbefdff46e3149502a543e3931c4ad5061ac8e4a3a4a9a8ee
+oid sha256:26ea915120766314e2bacd5006186d9012cb095e8e05a1dafbc048035142676f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bcf905f092c501de6d33df5091b8a086f9e7304b56a4c771c8627db9d77566e
+oid sha256:79429063411e5f67f663bb03057ea480ea282e8a7a96044eb033f6b9f55143b5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020224364038552694,
+  "epoch": 0.02311355890120308,
   "eval_steps": 8,
-  "global_step": 56,
+  "global_step": 64,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -197,6 +197,35 @@
       "eval_samples_per_second": 9.361,
       "eval_steps_per_second": 4.681,
       "step": 56
+    },
+    {
+      "epoch": 0.02058551339638399,
+      "grad_norm": 0.27935004234313965,
+      "learning_rate": 9.103606910965666e-05,
+      "loss": 2.0368,
+      "step": 57
+    },
+    {
+      "epoch": 0.021668961469877887,
+      "grad_norm": 0.29219961166381836,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 2.0315,
+      "step": 60
+    },
+    {
+      "epoch": 0.02275240954337178,
+      "grad_norm": 0.2893526554107666,
+      "learning_rate": 6.486251759186572e-05,
+      "loss": 2.0128,
+      "step": 63
+    },
+    {
+      "epoch": 0.02311355890120308,
+      "eval_loss": 2.0402984619140625,
+      "eval_runtime": 995.4422,
+      "eval_samples_per_second": 9.37,
+      "eval_steps_per_second": 4.685,
+      "step": 64
     }
   ],
   "logging_steps": 3,
@@ -216,7 +245,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9793075735822336e+17,
+  "total_flos": 3.4049229412368384e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null