Training in progress, step 6600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c448acb197cac2ff41883b95dd2638d4520107e6fabdd779c26a2104c239dbec
+oid sha256:ae6463dbdc2d91e9b1322891346f3833afe4775061c6f0d3b48157d6dc75931b
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bea9366110eb126918d6bd54a6076b009e1e42b45b792b4257de387cca7a230
+oid sha256:15999c7ecd152d668237b91758fdf2cc3d249213db421bac4f67f330f90f0aed
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3f270725a091664f0e5136926832fa25bc9d5c6fd1757199539906c68a4edf
+oid sha256:c054359dfd0c186601f9d93f0acef8011e2b1aa8a1492ec2b57ae90a1bc5794b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47fd382c1759e8992bf827fcae1a0f8564edc018afc6fd46493c07694bb97f98
+oid sha256:9cc67bbe12a73a6303ede190a9fcdf4c085df79ad7d2b182ce6b8dfd5dcdfecd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5264,
+  "epoch": 0.528,
   "eval_steps": 500,
-  "global_step": 6580,
+  "global_step": 6600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2310,6 +2310,13 @@
       "learning_rate": 2.3499429673227224e-05,
       "loss": 3.4745,
       "step": 6580
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 39.59190368652344,
+      "learning_rate": 2.3459355447763596e-05,
+      "loss": 3.4875,
+      "step": 6600
     }
   ],
   "logging_steps": 20,
@@ -2317,7 +2324,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.553491184123904e+16,
+  "total_flos": 1.5577756363063296e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null