Training in progress, step 3800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4223f69fa5c4d343cdb0daf20def262d26468340b68b3012ba5b5bf860add746
+oid sha256:36ac2a87ab309a324156770cff23fbcfbbf432e170a53864d6322a1b4b0f07fa
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07336ce007d26d9a03fa7d6fb0fb6a9b44ea05300d930f065fe4546aa4d1e107
+oid sha256:f4e71a65761b91f23557705c80c31bf4dc741e188e8b8dd3cb91d9e1d04d0829
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b38fda0416b95acf561519c239d9553c03304b18c4ad47455ccbf998847d400
+oid sha256:ae7fdc9e832b9048f8d780c7ee755c1b7ac708ee22fb1d6c77d7ce7699702566
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eab6ea1f9b7df74951725865c85704c6f9d44947e8a6d8f259ab0d7413d273be
+oid sha256:a0e3d8cec0e23166a3a5218cd6c00728334e53ee9906c6ef1df2da53651ea7a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3024,
+  "epoch": 0.304,
   "eval_steps": 500,
-  "global_step": 3780,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1330,6 +1330,13 @@
       "learning_rate": 2.805467086984027e-05,
       "loss": 3.4905,
       "step": 3780
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 41.776817321777344,
+      "learning_rate": 2.803067604777227e-05,
+      "loss": 3.5289,
+      "step": 3800
     }
   ],
   "logging_steps": 20,
@@ -1337,7 +1344,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8928030689820672.0,
+  "total_flos": 8969070886453248.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null