Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b919383e2b12ae4b752cdd91644e11318a7a02d10023c438223d4ede3f53326a
+oid sha256:6bbf978b2ed5f6174270566e06766afd464bcc550712af8281772197b1235806
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f5d6ff616254e327717faa7b2be2a379665ca94835ef7f51efab02a97e7636
+oid sha256:afa9ee2778de892a05f41cc7a34cfb288fd871640f919cbb9c3161256f81bedd
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42e4d0276ac2fb70e5c0593f417f2d935273357ff980559b410f61ea4ea09832
+oid sha256:29843bac3ae7f15549b97859e26d118657b48715b2439ab9d58c3760f6e8b44c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3382663847780127,
+  "epoch": 0.38054968287526425,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 12.92,
       "eval_steps_per_second": 1.623,
       "step": 40
+    },
+    {
+      "epoch": 0.35517970401691334,
+      "grad_norm": 1.0083894729614258,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1557,
+      "step": 42
+    },
+    {
+      "epoch": 0.38054968287526425,
+      "grad_norm": 0.3310617506504059,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1498,
+      "step": 45
+    },
+    {
+      "epoch": 0.38054968287526425,
+      "eval_loss": 0.15380239486694336,
+      "eval_runtime": 15.4088,
+      "eval_samples_per_second": 12.915,
+      "eval_steps_per_second": 1.622,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.034054314983424e+16,
+  "total_flos": 6.788311104356352e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null