Training in progress, step 6560, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30cf0270ab7eb3471153a28d31eec5ab87afc18c35880c0689d7b33e9ccec01
+oid sha256:af05e0a6c9ba308c4aa54b622a45d3520ca159d9d263a4a9c8055c1826a20938
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15270cb1bec565741ee825e92d321439b45a02901ba1581ae9722a89f84ea419
+oid sha256:90d032f3a40082b9d9daff6363158374b72c5065b002445b695a99ca47398242
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3334f41707da2f1f3b6ff0afd38e2f3ea20e604b3409a23e240e2d1711a472d3
+oid sha256:723ef5e592813da00df6025c04119524c1f1ef85c5f1fe9c93dc4858a8d9cc57
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d3da2849decc3d12a1c67a143710f26acee85daa0e821364144220b5cf57d3c
+oid sha256:8119438268b977f27b827c8867c2f6dee7675b5e1267fc478a5f6ac6f0b45e53
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5232,
+  "epoch": 0.5248,
   "eval_steps": 500,
-  "global_step": 6540,
+  "global_step": 6560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2296,6 +2296,13 @@
       "learning_rate": 2.3579310239743776e-05,
       "loss": 3.5194,
       "step": 6540
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 26.61548614501953,
+      "learning_rate": 2.353941474369544e-05,
+      "loss": 3.4933,
+      "step": 6560
     }
   ],
   "logging_steps": 20,
@@ -2303,7 +2310,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5443350539239424e+16,
+  "total_flos": 1.5485571748724736e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null