Training in progress, step 2980, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38f3ea2e710f0123cd317966daf5b272ed615e4c14e337828c2d49a95e7b8e06
+oid sha256:724b47d9c8653ca30a08e92b5b2db184a6a2691e07d099d47dd64cd6bfb9234f
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17331faf06503e7a590d855b1e16fe6253841ce13f64d11a95d99f09a89b197b
+oid sha256:5994e3d2d91a83a07b98e2df8057e08df7ce8afe7d5f64a27b2e29b2d9e5760a
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea602ef2e312790e8849d1db4637c3556e36e10604ffe460922bf490e4a189ad
+oid sha256:2bfa72d45322c7889cd0cba044899a675204ad96fd40b4c5e36e86d061721ae8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1976d584552c3d9a749942a954e8edac0eb73a5bcb3e8631cd101d6b353e1f8
+oid sha256:e76d1b9e419841ba38c332935be27d6f7d5387bf715355d0d0b0da74e6ad60ee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2368,
+  "epoch": 0.2384,
   "eval_steps": 500,
-  "global_step": 2960,
+  "global_step": 2980,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1043,6 +1043,13 @@
       "learning_rate": 2.8917845792248085e-05,
       "loss": 3.5737,
       "step": 2960
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 47.12533187866211,
+      "learning_rate": 2.8899655018846297e-05,
+      "loss": 3.5125,
+      "step": 2980
     }
   ],
   "logging_steps": 20,
@@ -1050,7 +1057,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6996976257859584.0,
+  "total_flos": 7043134176854016.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null