Training in progress, step 2360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d9bb442ae601cf106b3006a0b171f810e2b1e6f85cad6fe3662e4f7d6b8c2b
+oid sha256:b209e171b2bafde533025af3ea490078abf0bfdeb25b88b922c9d4d854d7b585
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbbb71c873d74aca94c35ba877c8558929a0c5a34e6a9bb657a8086f1f364b5
+oid sha256:9900e84d62e1d0ceb495e78efd151917fcdd6603f10280c405bee9baf962ad13
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:635cb17a2c9fedd045625390ceabdbcf7a1ac3172f61dcbc182e74aaba6c8f68
+oid sha256:c86c37e77e2165a2cba8e32a777876823669c841174ddad0c6db1d6a6bb511bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b2ca6293707bf7061331d560bd97d2236fd7b5ba46591c5449e07ebfb92b17b
+oid sha256:4529d17c1dc6d14789563fff0e0673b46a1f72fc77c5c6b3c74935a83d7232d5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1872,
+  "epoch": 0.1888,
   "eval_steps": 500,
-  "global_step": 2340,
+  "global_step": 2360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -826,6 +826,13 @@
       "learning_rate": 2.9408464612887484e-05,
       "loss": 3.5959,
       "step": 2340
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 31.878395080566406,
+      "learning_rate": 2.9394880643660242e-05,
+      "loss": 3.5974,
+      "step": 2360
     }
   ],
   "logging_steps": 20,
@@ -833,7 +840,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 5545413044109312.0,
+  "total_flos": 5591767798579200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null