Training in progress, step 3460, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88bd2b571093acbc27fcd8536450a3527fc0193315a3c3ce86c40e2966b6388d
+oid sha256:406424f725b9028141f772e089cad085915f5e7009a4360642947df9e09aef62
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e87e2cffd6499ab28af59d0b4ee7a16fdb3892b678d0ef0cb0afe39a44a7524
+oid sha256:22136554903baf5dc10cdaf8959e7db746437ffba579d74c15cecb3532f4bd87
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee292670562564a7bb33c2459a592a62918de5efa5b5e8582d3b7a88297d572c
+oid sha256:9773ea3fb71f0f0969063d9b7bfcc76343c6e53cf42371dca5deed02dc682e43
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c459e5a971be0d13a40d59c3e5859b24b3694b53687b127d583761b575636ed7
+oid sha256:fced894a4b71f5250dfe4d1c7fd9bf448653b2cdd683ed6e3b7c3ba78979133a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2752,
+  "epoch": 0.2768,
   "eval_steps": 500,
-  "global_step": 3440,
+  "global_step": 3460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1211,6 +1211,13 @@
       "learning_rate": 2.8441431650084018e-05,
       "loss": 3.4839,
       "step": 3440
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 46.23302459716797,
+      "learning_rate": 2.841979781287424e-05,
+      "loss": 3.5411,
+      "step": 3460
     }
   ],
   "logging_steps": 20,
@@ -1218,7 +1225,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8161651766132736.0,
+  "total_flos": 8203774557880320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null