Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c8eb8325ee56887bcac39c7154198c4c29da0906f5c3ea537f9c33b12522a7
+oid sha256:0a1753c72ccb1a9e11a6df65bbb400bf263999aa26bfd6fcf1f8806d8816b064
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c50dbc656fd8436361ad2967fe1a74152d58ec2100319552b81b9e758a442b69
+oid sha256:a17bdd80252dacd4805f6ca57d077838d307db0512aa91161d298af42030ec86
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7a7ac14760662453a208d3a2065875c8aad63732e589bcd3c513e8d0acfc26
+oid sha256:17eca7e25974cd391c6342b957032cb7907005ec238e47db0663301f0f4322c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c69db2db6de56f38ba12b474a491d20087e27dc2893a95d6ac7716476ca645
+oid sha256:0aa0f75a1f3e346be25756b578158b09a68943f0b9f1cfe29f97939687f864ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008614307826906252,
+  "epoch": 0.009691096305269533,
   "eval_steps": 4,
-  "global_step": 32,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,42 @@
       "eval_samples_per_second": 8.342,
       "eval_steps_per_second": 4.174,
       "step": 32
+    },
+    {
+      "epoch": 0.008883504946497072,
+      "grad_norm": 2.5778937339782715,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 3.8609,
+      "step": 33
+    },
+    {
+      "epoch": 0.009152702066087893,
+      "grad_norm": 2.673618793487549,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.7293,
+      "step": 34
+    },
+    {
+      "epoch": 0.009421899185678713,
+      "grad_norm": 2.699422597885132,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 4.1321,
+      "step": 35
+    },
+    {
+      "epoch": 0.009691096305269533,
+      "grad_norm": 2.799333095550537,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 3.8541,
+      "step": 36
+    },
+    {
+      "epoch": 0.009691096305269533,
+      "eval_loss": 3.8941519260406494,
+      "eval_runtime": 187.6155,
+      "eval_samples_per_second": 8.342,
+      "eval_steps_per_second": 4.173,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -322,7 +358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.454061956936499e+16,
+  "total_flos": 2.7608197015535616e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null