Training in progress, step 147, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e861928e1b2ca38a4a6746866d7d8f7b7ca001e137c5b880cdc7ca389cae56a0
+oid sha256:6151dcd4134499202adb9f850a26aa2c5af6fa3bec8e91e35b43aa56a097fe2c
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d926fce7eee99bf36a4de34f618c75332ae83e4fbcc18a94351c99ca4b7722e1
+oid sha256:9ed8312b126cb5e54ec81601cd004752b3b5deebd4565b60b914c76669a94370
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5043a9d527c42b332561475083f4469c87b7663281bbf8ae1e7c09b5adbc61a
+oid sha256:ed026b8d344c5d0a011031e05610698192a36ffdb63930c6e505b4062d507b67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9350fe25e75c3aec8e0f08fabcc3ea69e0fa51f62eea810c9a733906e4363f8
+oid sha256:e3a17ab167da966fed3c0386891062c971357d34456fa7825f3daecc1ee9f578
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.525679758308157,
+  "epoch": 1.7794561933534743,
   "eval_steps": 21,
-  "global_step": 126,
+  "global_step": 147,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,6 +357,63 @@
       "eval_samples_per_second": 527.718,
       "eval_steps_per_second": 67.849,
       "step": 126
+    },
+    {
+      "epoch": 1.5619335347432024,
+      "grad_norm": 0.2541723847389221,
+      "learning_rate": 5.032861611257783e-05,
+      "loss": 10.2813,
+      "step": 129
+    },
+    {
+      "epoch": 1.5981873111782479,
+      "grad_norm": 0.18722322583198547,
+      "learning_rate": 4.835720332151907e-05,
+      "loss": 10.0301,
+      "step": 132
+    },
+    {
+      "epoch": 1.634441087613293,
+      "grad_norm": 0.2005719244480133,
+      "learning_rate": 4.6388344842726264e-05,
+      "loss": 9.9704,
+      "step": 135
+    },
+    {
+      "epoch": 1.6706948640483383,
+      "grad_norm": 0.22246921062469482,
+      "learning_rate": 4.4425101967610674e-05,
+      "loss": 10.3317,
+      "step": 138
+    },
+    {
+      "epoch": 1.7069486404833838,
+      "grad_norm": 0.16641516983509064,
+      "learning_rate": 4.247052725612852e-05,
+      "loss": 10.1891,
+      "step": 141
+    },
+    {
+      "epoch": 1.743202416918429,
+      "grad_norm": 0.19296815991401672,
+      "learning_rate": 4.052765979048986e-05,
+      "loss": 10.3081,
+      "step": 144
+    },
+    {
+      "epoch": 1.7794561933534743,
+      "grad_norm": 0.30453190207481384,
+      "learning_rate": 3.859952044982329e-05,
+      "loss": 10.2634,
+      "step": 147
+    },
+    {
+      "epoch": 1.7794561933534743,
+      "eval_loss": 10.188948631286621,
+      "eval_runtime": 0.2641,
+      "eval_samples_per_second": 530.026,
+      "eval_steps_per_second": 68.146,
+      "step": 147
     }
   ],
   "logging_steps": 3,
@@ -376,7 +433,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 14055383236608.0,
+  "total_flos": 16397947109376.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null