Training in progress, step 640, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92ea041d259fd0f1f97d3d99cc8dcb4a35f0729c4f9cfe1e03af37c28316782
+oid sha256:7b35ddd4427844661dfab289de8478e50dd50f1beeb81b60b938f6decab96be8
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a98df909e786b9af2ba1de67522448ec74261759633c6997092bdf4beaab7f
+oid sha256:213ebcbe3bb1067adfedc8d41c2d0ccdc1e057c3d9dd18c30ed17bdbd4df6c1f
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c65cd55e2fff96c97e67ca068ed8c714e7c66984dea1333f2e03593c396075d
+oid sha256:001288f4eaf188f446d2ca5cd5f672ec468ff9152761daa8c936edbc48ef4642
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ce72457ecdb61a4ff660064d82592f9b16269351060cb691068fea59fdedc2
+oid sha256:71b63c6d0a28783ef8450676a810d5195abcf4c2886ef29e04e2c6964bcd124c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0496,
+  "epoch": 0.0512,
   "eval_steps": 500,
-  "global_step": 620,
+  "global_step": 640,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -224,6 +224,13 @@
       "learning_rate": 2.999992132854894e-05,
       "loss": 3.8692,
       "step": 620
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 45.1494026184082,
+      "learning_rate": 2.999968531502098e-05,
+      "loss": 3.7374,
+      "step": 640
     }
   ],
   "logging_steps": 20,
@@ -231,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1478300032499712.0,
+  "total_flos": 1526262276685824.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null