Training in progress, step 2660, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c37478ba6579cff2d0646434ea7d1892cb48a4219f90126afbdf7bde329abb
+oid sha256:e9d5da627a83cc018d4bf0bfc59c1098cf129633a1abc41bd7d51fb13114c0b1
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b0e5872ff2188ce6710b4b1015cc3fcaf69768dd90c4fa6ab9ac4aecfb9a52a
+oid sha256:682f21df5b619b8fc7a877dafd3f697aa66e4f2b393f8b846f0e3646f7ba1e83
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27177ac056c4d9dbf19f5cb10b2bae9ee9392da9370d73a04aa8b3b9bc1e770d
+oid sha256:cfdb4aa20ae8b96f35fdee422b168c0d1ffe465638f08b59f076576138bbe18e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea196c4dba55ede2883451624fdfc54856529c0e1f9c30be6a7f36bcba4e1179
+oid sha256:d6164b3c850dce9a36a31f30919cac3506bfad9cadb5f9ef73ee2c76d96b38ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2112,
+  "epoch": 0.2128,
   "eval_steps": 500,
-  "global_step": 2640,
+  "global_step": 2660,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -931,6 +931,13 @@
       "learning_rate": 2.918891825699857e-05,
       "loss": 3.6067,
       "step": 2640
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 40.04263687133789,
+      "learning_rate": 2.9173085201008144e-05,
+      "loss": 3.5365,
+      "step": 2660
     }
   ],
   "logging_steps": 20,
@@ -938,7 +945,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6257137317445632.0,
+  "total_flos": 6299096079630336.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null