Training in progress, step 680, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be0bca22803c9150df03e6466773cd219b4542d072342c711ec03c97247eb64c
+oid sha256:03e4d7a2e6b882be3d4a0cc7b960dffb4a278acc68bfa17fed5afd5a7ba89cc9
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835a7525c06da7ed873e20c691c9e2e2c793823b899c56c236618edeabdee1e4
+oid sha256:f6f1b2f0c9e7cd6b2c29b7325f99e1c569e645a85e246f18e83ddfd1cc60b9ed
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:084dccba20efd6b3e5dec3fea90abdf37dfbc8e08f2e8403d8ff8352b73dbaf5
+oid sha256:975cd3c0d8ed686eac6636689f78b9ba276d9ea46ea9d8f16d84080c1f677717
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d360c1de8e8e92eec017cc71d37bb9f185d942b9274c99e38578ff0397698ae
+oid sha256:5304725a872898493d436386ca2c07b5b449e34cbdcdf743fbe4d162bd012bf4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0528,
+  "epoch": 0.0544,
   "eval_steps": 500,
-  "global_step": 660,
+  "global_step": 680,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,6 +238,13 @@
       "learning_rate": 2.99992919618918e-05,
       "loss": 3.7735,
       "step": 660
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 39.445220947265625,
+      "learning_rate": 2.999874127328748e-05,
+      "loss": 3.759,
+      "step": 680
     }
   ],
   "logging_steps": 20,
@@ -245,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1566580743241728.0,
+  "total_flos": 1618578114674688.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null