Training in progress, step 3480, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:406424f725b9028141f772e089cad085915f5e7009a4360642947df9e09aef62
+oid sha256:a80adce44bfdb009a8a661904d03bfb6e01ae69c7d2f433075c4792085d1441f
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22136554903baf5dc10cdaf8959e7db746437ffba579d74c15cecb3532f4bd87
+oid sha256:1e55f749d779476c80df8878539c00ad63f52e0da2be54f4abf3572dde9103a9
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9773ea3fb71f0f0969063d9b7bfcc76343c6e53cf42371dca5deed02dc682e43
+oid sha256:1e8b2089beb77f6eeff2596a9850dbdefb1299610dc7c930f243156d19eb2060
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fced894a4b71f5250dfe4d1c7fd9bf448653b2cdd683ed6e3b7c3ba78979133a
+oid sha256:64d404973b811ebcc9b13292a749476771ae070589fa9ceb6e87db812be374d0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2768,
+  "epoch": 0.2784,
   "eval_steps": 500,
-  "global_step": 3460,
+  "global_step": 3480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1218,6 +1218,13 @@
       "learning_rate": 2.841979781287424e-05,
       "loss": 3.5411,
       "step": 3460
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 36.41411209106445,
+      "learning_rate": 2.8398023208335537e-05,
+      "loss": 3.5701,
+      "step": 3480
     }
   ],
   "logging_steps": 20,
@@ -1225,7 +1232,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8203774557880320.0,
+  "total_flos": 8244716336775168.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null