Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e13f2a6a244743510288bcd7a39dcdd9ddfacaf4b8e5fca21ef5e13914ac180
+oid sha256:c8fdab2749ab700cdcbd215765631960a327e512cd01b5f04b030e416e065972
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e14b017fb8c7ed092c4b8f4f6af845f4354e61fd078b318f035bd01d68917afb
+oid sha256:5ccc9927edd24a80b113f328d7e28b70cd0fb609083e99505be64422e8b327f6
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f540bc4d39210732d06fe60e3fb05a18215eb5bdf32c0697391e60e2105ca433
+oid sha256:5937b2d23ad85f37009cf032d023af240d8787d5d33f30bae27a2bd090137a04
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff994fffd2fb6fe21545e6fbc55baa2a1474438a89b2d40605678f7de701427c
+oid sha256:06c69db2db6de56f38ba12b474a491d20087e27dc2893a95d6ac7716476ca645
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14105793450881612,
+  "epoch": 0.16120906801007556,
   "eval_steps": 4,
-  "global_step": 28,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,42 @@
       "eval_samples_per_second": 127.78,
       "eval_steps_per_second": 63.89,
       "step": 28
+    },
+    {
+      "epoch": 0.14609571788413098,
+      "grad_norm": 0.13849467039108276,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 11.7754,
+      "step": 29
+    },
+    {
+      "epoch": 0.15113350125944586,
+      "grad_norm": 0.24436236917972565,
+      "learning_rate": 0.0001,
+      "loss": 11.777,
+      "step": 30
+    },
+    {
+      "epoch": 0.1561712846347607,
+      "grad_norm": 0.12146396189928055,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 11.7583,
+      "step": 31
+    },
+    {
+      "epoch": 0.16120906801007556,
+      "grad_norm": 0.13603943586349487,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 11.7767,
+      "step": 32
+    },
+    {
+      "epoch": 0.16120906801007556,
+      "eval_loss": 11.76652717590332,
+      "eval_runtime": 0.6557,
+      "eval_samples_per_second": 128.109,
+      "eval_steps_per_second": 64.054,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -286,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5703601225728.0,
+  "total_flos": 6518401400832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null