Training in progress, step 3740, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13d441278584800305f9e26da4273dad6d7875090921b28e26b45c6774d333c
+oid sha256:70fc65989648f7dc64734e8244e0e6879cfab6125b857d5586fade7a4f45ce0c
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649594190d4a72c9cfb02a6d63322d7c898194d9e59c41bc49d7da475d2a0c87
+oid sha256:c5f3e74dabdaf3ee4c5231da9311a563abc6cfd59391a593a38304bcd6053332
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91443f3ba02f1daf1ad9b67315df20b52be0e5bd1e6256f5526e1158a26ea37
+oid sha256:98c6a86fe7a3ce61d0893ea3b91307b0a6fe853d64a359a291f505b9ac01cb7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccbe4cbbe78988717a93eeb711aa1df5c2d1ab7d6064c8a0774ed1c855a9c67d
+oid sha256:4c2710cfbdebccda3472bd5dbf8574523b547a65e026efc1ddfdf0be454ac800
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2976,
+  "epoch": 0.2992,
   "eval_steps": 500,
-  "global_step": 3720,
+  "global_step": 3740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1309,6 +1309,13 @@
       "learning_rate": 2.812583271253125e-05,
       "loss": 3.6265,
       "step": 3720
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 25.85703468322754,
+      "learning_rate": 2.8102249451758162e-05,
+      "loss": 3.5619,
+      "step": 3740
     }
   ],
   "logging_steps": 20,
@@ -1316,7 +1323,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8783028556234752.0,
+  "total_flos": 8827316538212352.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null