Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d31681fbb65185e070b319bf153c06fb726bd1d9648ed712a763e7bb11fd9f
+oid sha256:5d8e9736efc006c9f6333bedd4f2cd6d31e4acfcc3e68bc75c6f33db5442d072
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:179893eee9434a66844765bdd5bca7e42ea9ed872c70113baedca413e3090526
+oid sha256:99f71c66c523575cf877e9256f46e1da9413499eceb6265cf29c21811249692c
 size 148462004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17821d011eb66da494053c17071af437b59664d59a79a1c2eb8546e3c4ec4064
+oid sha256:bf6927877e6551a1f0698893e28b93742cc61a7a885e166664a8829bb2eadfce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b25be7469ad981132f7a2420355104a15844ec15e4ebb6da303200a888ed6db
+oid sha256:1df434ec5d39f570ded65a944db333de3cdd9df7c23996fdc6aaf5d06de18167
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011624211052081914,
+  "epoch": 0.0015498948069442554,
   "eval_steps": 500,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,34 @@
       "learning_rate": 2.307692307692308e-05,
       "loss": 1.8556,
       "step": 12
+    },
+    {
+      "epoch": 0.0012592895306422073,
+      "grad_norm": 0.15152186155319214,
+      "learning_rate": 2.5e-05,
+      "loss": 1.938,
+      "step": 13
+    },
+    {
+      "epoch": 0.0013561579560762234,
+      "grad_norm": 0.19589252769947052,
+      "learning_rate": 2.6923076923076923e-05,
+      "loss": 1.9859,
+      "step": 14
+    },
+    {
+      "epoch": 0.0014530263815102393,
+      "grad_norm": 0.17176692187786102,
+      "learning_rate": 2.8846153846153845e-05,
+      "loss": 1.8812,
+      "step": 15
+    },
+    {
+      "epoch": 0.0015498948069442554,
+      "grad_norm": 0.18412314355373383,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 2.0042,
+      "step": 16
     }
   ],
   "logging_steps": 1.0,
@@ -110,7 +138,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4247328129300480.0,
+  "total_flos": 5538570495590400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null