Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1967693c07100a438639df88eb53656c00dbba558ea2c42ffa73fba1446eee
+oid sha256:cc4a41d5d22b7d0d85455aa32db9e7c97b9166ea007173ae0f8b60ba7996b322
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d45889a4c17db0d906d24c6227c6bbf1fdbb6d34fea3d26203a12f9f0683abd
+oid sha256:37a60897eab1d7588d260a33b2f1fa0c1b58f193663e391249437e08e9459931
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0148258d1b2661f822e58a2e46026292898ff3e4839b6f90a538404d4b5f2622
+oid sha256:e9ab3296562ebe49bf8535f9527f415326e1c9c49a2be5613326da9318c84575
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0462e85c2b1ec59cd7a49bd120323355f5e0e393ea43eb4f442fb4759b197602
+oid sha256:b87b8c463789ee95efb85f337d13d204d6d893266f8733a46591a2aa7fddc131
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0464,
+  "epoch": 0.048,
   "eval_steps": 500,
-  "global_step": 580,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -210,6 +210,13 @@
       "learning_rate": 2.9e-05,
       "loss": 3.7538,
       "step": 580
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 22.339618682861328,
+      "learning_rate": 3e-05,
+      "loss": 3.726,
+      "step": 600
     }
   ],
   "logging_steps": 20,
@@ -217,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1390577022271488.0,
+  "total_flos": 1434832198336512.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null