Training in progress, step 6860, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:518c66ebd8ad215b6e10e1e9f964e45894e80619dac9fca6659b4f3ddeb3b3fd
+oid sha256:59e4deb0fd7483db8ad6ecbc4b685edbd17935d1da824196ba4fc901973119e0
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06d2f34d5afc5a2972610b94f622e8929acb7496b3920789e233305f50c0f6f
+oid sha256:2d0a5a0084d24afc11f74c50b817d93674fb054ada62fbbef9c92566dd4897ab
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b522addaf0562d6804ca14f05b7612546f36db18c9447cb63a2360b49b82fb
+oid sha256:379130258049e0cbeef66efed7dd213cfd228d8c04c387dcbb54754f2a453a5a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b9e247c644d88c6b75288b062ce133bd318a7b3c27e9c864410974153f4cd6
+oid sha256:7e4378be4b8a985777dc1876169a11bcb383075ed65c6a773225043d0598af8d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5472,
+  "epoch": 0.5488,
   "eval_steps": 500,
-  "global_step": 6840,
+  "global_step": 6860,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2401,6 +2401,13 @@
       "learning_rate": 2.2971664586314055e-05,
       "loss": 3.531,
       "step": 6840
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 29.17162322998047,
+      "learning_rate": 2.293046993300198e-05,
+      "loss": 3.567,
+      "step": 6860
     }
   ],
   "logging_steps": 20,
@@ -2408,7 +2415,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.6145823545229312e+16,
+  "total_flos": 1.6194507519492096e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null