Training in progress, epoch 2

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: Philosopher
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
@@ -35,10 +35,10 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.21.0
-- Transformers: 4.55.1
+- Transformers: 4.55.2
 - Pytorch: 2.6.0+cu124
-- Datasets: 4.0.0
-- Tokenizers: 0.21.4
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
 
 ## Citations
 

config.json

@@ -47,7 +47,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": 512,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.1",
+  "transformers_version": "4.55.2",
   "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 sha256:172d2d45d7b981fa4dc056c3216aabb854e9867f13334721b886e6a756bfdba4
+oid sha256:d39a9feb93f4a127963f4ef0f07fd88694fbc79fc3f0d6e92ac8fb9ec2071fb9
 size 536223056

runs/Aug17_11-50-05_be32f6b915f0/events.out.tfevents.1755431423.be32f6b915f0.36.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b475078000367b2e84a2965b4d3a78069acce03b05a9506a299e5d458938a05c
+size 24137

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba90a657f0e405cfb21e2ec1ad24ca9f317c494ba28568dcdf8e59efa6b429ef
+oid sha256:6db2796c329d3bd563bc5fbcf623bb690a19562cbbbfc863e3f42d0c48b25588
 size 5816