Training in progress, step 660, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b35ddd4427844661dfab289de8478e50dd50f1beeb81b60b938f6decab96be8
+oid sha256:be0bca22803c9150df03e6466773cd219b4542d072342c711ec03c97247eb64c
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213ebcbe3bb1067adfedc8d41c2d0ccdc1e057c3d9dd18c30ed17bdbd4df6c1f
+oid sha256:835a7525c06da7ed873e20c691c9e2e2c793823b899c56c236618edeabdee1e4
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001288f4eaf188f446d2ca5cd5f672ec468ff9152761daa8c936edbc48ef4642
+oid sha256:084dccba20efd6b3e5dec3fea90abdf37dfbc8e08f2e8403d8ff8352b73dbaf5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b63c6d0a28783ef8450676a810d5195abcf4c2886ef29e04e2c6964bcd124c
+oid sha256:9d360c1de8e8e92eec017cc71d37bb9f185d942b9274c99e38578ff0397698ae
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0512,
+  "epoch": 0.0528,
   "eval_steps": 500,
-  "global_step": 640,
+  "global_step": 660,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,13 @@
       "learning_rate": 2.999968531502098e-05,
       "loss": 3.7374,
       "step": 640
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 72.25853729248047,
+      "learning_rate": 2.99992919618918e-05,
+      "loss": 3.7735,
+      "step": 660
     }
   ],
   "logging_steps": 20,
@@ -238,7 +245,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1526262276685824.0,
+  "total_flos": 1566580743241728.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null