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: 0.22.2
+- Transformers: 4.56.0
 - 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": "4.56.0",
   "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 sha256:9c0e67da1e88572625fbf9688a538a116ad6ed8ded53a821d1afdb707a731b9f
+oid sha256:89768c2d0f105cadecb667e828250feb827b8aa83001bf9dc641a2bb7a9109fa
 size 536223056

runs/Sep08_11-54-48_5f34c200f541/events.out.tfevents.1757332505.5f34c200f541.1106.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1322a82e2ab02ef0ee6cc7b337773f19fc67dbb1487b39971753f219a059004
+size 5743601

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de315fbe2e1d76177f34e52ca96f9f1782e278c76da02bbcff123ee3a8ba491
+oid sha256:4b10d1081a95bf5f129916c9627dbc00bfc27d252b4fb401de2e4310f36f9012
 size 6225