Training in progress, step 5620, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fd06c9f2222239e592302c7e30afefc517d5cb1a680437c4ab7fea503265580
+oid sha256:551f265b0824afe04aca693b6dea37fd5b135be5b8dccb283b485991e4dad3cf
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499ab8ad010c3a6f278b1cd553e39c4fc0711e8fcf3b7a6ccdda457fd792691a
+oid sha256:d57e143f333860daa20b388b6223f6ddf41f78b6f0260df5e7f84606866d22b2
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:118a9b4f162443ffba8ddef62d094103298e7cce32dfd348189ba8ded99c2d30
+oid sha256:346e59e0611ec165950f793dc7bab0e7711af8e5091b452f221d2a71732c2269
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:067ea48f98f205db606896f3d7b13ff5b4456f48e2572b42a96efcfda3855838
+oid sha256:29d2f36af1b7bb2b6336bf3a3f577dcb5c5a5a76d17401f059ff27c28f1ca2cc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.448,
+  "epoch": 0.4496,
   "eval_steps": 500,
-  "global_step": 5600,
+  "global_step": 5620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1967,6 +1967,13 @@
       "learning_rate": 2.5345856659171567e-05,
       "loss": 3.4033,
       "step": 5600
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 34.580299377441406,
+      "learning_rate": 2.5310626050032873e-05,
+      "loss": 3.5598,
+      "step": 5620
     }
   ],
   "logging_steps": 20,
@@ -1974,7 +1981,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3255983512322048e+16,
+  "total_flos": 1.3302567908179968e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null