Training in progress, step 6300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4952d07d35404125ac82a69ff1d2b691b555ce36f8f5e2491332621aa761003d
+oid sha256:44d9867527ada8f06b3d5b4a3b1a084c5587bf5d24b8f6abb3243ac9e5ecc1bb
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dfa581ec2b543e12a4d9e7daa6a74d185441160dd1412bf1875fce58548b340
+oid sha256:664614e14cc5551b8f4f79a692c8c7ab8b97cdcef757ae57c283fec6b60fca8b
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c20249241b6c1615d63c46164c68a0aefa907c40365a5dc082bbe417fdd12bf6
+oid sha256:fe631caac525a44feb552772252434ef5806653f82e9cba96375efa0ad983cd3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac175a77f9ab524825431337f25ea7bdd98b98a7ae16ff30a1d8c19f59c4b3f
+oid sha256:5b8ab3807f200a849a139d1332c1073c145c9a442b57cd4342cee505d555158f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5024,
+  "epoch": 0.504,
   "eval_steps": 500,
-  "global_step": 6280,
+  "global_step": 6300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2205,6 +2205,13 @@
       "learning_rate": 2.408961130718405e-05,
       "loss": 3.4637,
       "step": 6280
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 35.380767822265625,
+      "learning_rate": 2.405091801274387e-05,
+      "loss": 3.4403,
+      "step": 6300
     }
   ],
   "logging_steps": 20,
@@ -2212,7 +2219,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.4845134723416064e+16,
+  "total_flos": 1.4891030195109888e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null