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:c8fdab2749ab700cdcbd215765631960a327e512cd01b5f04b030e416e065972
+oid sha256:fcd7ffcb3e4a9f4bfc4ad8648cfbb675bd6afe0bd814d648853e775947350c0f
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ccc9927edd24a80b113f328d7e28b70cd0fb609083e99505be64422e8b327f6
+oid sha256:4928a4ea058d36d00d5fa931f38e737bf9e77813884c198e504dd55291d5efaf
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5937b2d23ad85f37009cf032d023af240d8787d5d33f30bae27a2bd090137a04
+oid sha256:3a6d12bbdf31e66e64bbfd314e06ec60bdc4d273af3264013c74689308316443
 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": 0.16120906801007556,
+  "epoch": 0.181360201511335,
   "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": 128.109,
       "eval_steps_per_second": 64.054,
       "step": 32
+    },
+    {
+      "epoch": 0.16624685138539042,
+      "grad_norm": 0.1841493397951126,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 11.7572,
+      "step": 33
+    },
+    {
+      "epoch": 0.1712846347607053,
+      "grad_norm": 0.1587410420179367,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 11.7721,
+      "step": 34
+    },
+    {
+      "epoch": 0.17632241813602015,
+      "grad_norm": 0.1748318076133728,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 11.7697,
+      "step": 35
+    },
+    {
+      "epoch": 0.181360201511335,
+      "grad_norm": 0.15539947152137756,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 11.7722,
+      "step": 36
+    },
+    {
+      "epoch": 0.181360201511335,
+      "eval_loss": 11.765742301940918,
+      "eval_runtime": 0.6575,
+      "eval_samples_per_second": 127.75,
+      "eval_steps_per_second": 63.875,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -322,7 +358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6518401400832.0,
+  "total_flos": 7333201575936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null