Training in progress, step 560, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7042f9ed08ad702b4807e2082f62b7c77edad4356283c5cfef4c2ac8b3b06034
+oid sha256:796907df6dad182b13ce60cc0ccb07c112a82034aaa5441dd30b61e18d46838c
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea2f7979011099fe7dff43f9cdaa7c8c71ecebd10fcfa3e69aea88e5fe4630df
+oid sha256:d4690d06bae8821a7b6f9abbbdeddc59340b43f3b519fcd1343c54658a8e61c5
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cad5804f88e56590ede594cde634ed7edf004b94b62834acab77d105f3c4294b
+oid sha256:5c6995b24c4f5e8f78c1ffb24f2e17f0e7ac641fd12550a93bad04b92d9a530b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8954cfae79acdcb584a4c2168efc0e60ef154434502bd57627e490c360dd8a90
+oid sha256:fa82337c72273104e0d7cc27c48a05e78f4a8c0defe4d7528f9fd4baa01b222e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0432,
+  "epoch": 0.0448,
   "eval_steps": 500,
-  "global_step": 540,
+  "global_step": 560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -196,6 +196,13 @@
       "learning_rate": 2.7000000000000002e-05,
       "loss": 3.9166,
       "step": 540
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 23.113840103149414,
+      "learning_rate": 2.8e-05,
+      "loss": 3.8248,
+      "step": 560
     }
   ],
   "logging_steps": 20,
@@ -203,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1299081332097024.0,
+  "total_flos": 1347371635408896.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null