Training in progress, epoch 5

README.md

@@ -34,11 +34,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.21.0
-- Transformers: 4.55.2
+- TRL: 0.23.0
+- Transformers: 4.56.1
 - Pytorch: 2.8.0+cu126
 - Datasets: 4.0.0
-- Tokenizers: 0.21.4
+- Tokenizers: 0.22.0
 
 ## Citations
 

config.json

@@ -7,6 +7,7 @@
   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
+  "dtype": "bfloat16",
   "eos_token_id": 1,
   "final_logit_softcapping": null,
   "head_dim": 256,
@@ -46,8 +47,7 @@
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": 512,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.2",
+  "transformers_version": "4.56.1",
   "use_bidirectional_attention": false,
   "use_cache": true,
   "vocab_size": 262144

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b10557428c98c0639986a03e71013efb7cdb38b40983d9048aa485cef784e3c
+oid sha256:e4bb9346b6ba86a992c9184371e5cf7f8892b7aac0575b4b5a64ec163ab2b512
 size 536223056

runs/Sep13_18-14-38_4a0065bcf0ac/events.out.tfevents.1757787357.4a0065bcf0ac.324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771c17c52b076356d1d4fb8c29a282dfe5d6795660b12d0dfb01e517bca9a513
+size 55640

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cbfba858f8fdb41e125dfd85e7adbf836a4ecb0e22d3dadd39e7df956ed4b3c
-size 6225
+oid sha256:3c86b6c8e023edb2bc3179cc2dffd0453684f6b1f1bec783de609f6b0100a5e6
+size 6289