Training in progress, step 440, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c65255ddd80a79d081a462fb0e47c505c70cc4ec1f5c180d5893fc538c0cf46
+oid sha256:1674414802f9fbe588c0e7c80e41a4aee0fa4811a147cf95f3e7209fcf5f367a
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a0b0d2ee83c41e0a6310838f74db01ddc2200d37e671a4de13bb392a19faf7b
+oid sha256:cf3dd7299a79572c367ec3a7034816a83882a521d87f261d46d93c99d9d2ed3e
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466b75100f91cee5a56826b8b389b4e82eaca68c0c9410222ac8faaf583279b1
+oid sha256:9711e3d87545bdf48821f9fd5761e262ef9bd1ddc4068a680e4e83b9dc83ad25
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c8022bf7a9a1164892708673761968b7e2c729d993619227f343f725c5c5ae
+oid sha256:94ba7cf77106ef0a466e3de51efaacf64578702f2e35c780d3a38c5b2f51bb42
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0336,
+  "epoch": 0.0352,
   "eval_steps": 500,
-  "global_step": 420,
+  "global_step": 440,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,6 +154,13 @@
       "learning_rate": 2.1e-05,
       "loss": 4.0119,
       "step": 420
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 26.383380889892578,
+      "learning_rate": 2.2e-05,
+      "loss": 3.9554,
+      "step": 440
     }
   ],
   "logging_steps": 20,
@@ -161,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1006518203744256.0,
+  "total_flos": 1050707767984128.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null