Training in progress, step 56, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3b36a05bafde111143961c99b5b2b5b3efe5b71cd941101c0e1fc0a43c6d92
+oid sha256:9eb161f828d10a50e45a015a2784664029f2476c18e36c62373032812c1be221
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d485eadb9203fdc2f245d2bbdd5f97b3a1ce3e0baf7c33c90542c2311ebf16e
+oid sha256:8037d816176c010f337de14924d2658d16a59fb2ec73a775b9b3984bb233330c
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc9dbb623e3f171e33d9832b06d94b67f7dfbbcfe98e23137b132240f34a4be
+oid sha256:72bb0203fc4f241fbefdff46e3149502a543e3931c4ad5061ac8e4a3a4a9a8ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cec5e5f4f3cb8de86741361ea071d377a7169e2898cbb10708e17cdfc15a7dc
+oid sha256:8bcf905f092c501de6d33df5091b8a086f9e7304b56a4c771c8627db9d77566e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017335169175902308,
+  "epoch": 0.020224364038552694,
   "eval_steps": 8,
-  "global_step": 48,
+  "global_step": 56,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,28 @@
       "eval_samples_per_second": 9.363,
       "eval_steps_per_second": 4.682,
       "step": 48
+    },
+    {
+      "epoch": 0.018418617249396203,
+      "grad_norm": 0.2522198557853699,
+      "learning_rate": 0.00011785568947986367,
+      "loss": 2.0516,
+      "step": 51
+    },
+    {
+      "epoch": 0.0195020653228901,
+      "grad_norm": 0.2991744875907898,
+      "learning_rate": 0.00010448648303505151,
+      "loss": 2.0324,
+      "step": 54
+    },
+    {
+      "epoch": 0.020224364038552694,
+      "eval_loss": 2.0532875061035156,
+      "eval_runtime": 996.415,
+      "eval_samples_per_second": 9.361,
+      "eval_steps_per_second": 4.681,
+      "step": 56
     }
   ],
   "logging_steps": 3,
@@ -194,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5536922059276288e+17,
+  "total_flos": 2.9793075735822336e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null