Training in progress, epoch 1

logs/events.out.tfevents.1740248437.2fc0677913f2.828.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f852b6b58f63624151c33de49c8c28c837a44e43c17a7e2411d06a6072de0621
-size 88
+oid sha256:3387ab9691ffb7a10f0ac4ca55e670dc703975a9e9100bf3ff6c08459a54f07a
+size 6488

logs/events.out.tfevents.1740248525.2fc0677913f2.828.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a1e6932d6b4f3a2f3534cece5a5e1d47ccc4f4c9eeb83d1c72e6541bb423d4b
-size 88
+oid sha256:6b1d3f053019d71e98a1dd4fee35e341c732280d2301aa400b8084aadfda2021
+size 7023

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4156abcbdf9d4c9baa861761069d4695f65c342abf358680a148960c112abb33
+oid sha256:3c47937028d365d4da8fdaaac6ef220fa06d42418f54ac878be2bc3f62f5f48d
 size 343098784

trainer_state.json

@@ -9,7 +9,7 @@
   "is_world_process_zero": true,
   "log_history": [],
   "logging_steps": 500,
-  "max_steps": 2500,
+  "max_steps": 1260,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
@@ -26,7 +26,7 @@
     }
   },
   "total_flos": 0,
-  "train_batch_size": 64,
+  "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null
 }