Training in progress, epoch 1

README.md

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

config.json

@@ -47,7 +47,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": 512,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.2",
+  "transformers_version": "4.55.1",
   "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:aaf308efb7c79b1413c2a4c9504a85e77f69945fc306d89af654964339ca4075
+oid sha256:7b2a0723314cc530439b6789d029c1b8e332e820b3aee125ffebe45381a51748
 size 536223056

runs/Aug18_16-22-25_91af6bbf27c2/events.out.tfevents.1755534172.91af6bbf27c2.423.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a0f8abac5daef3374a00ac18f30577429001080c9b6c4d19d8df7a9159801c
+size 8969

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db2796c329d3bd563bc5fbcf623bb690a19562cbbbfc863e3f42d0c48b25588
-size 5816
+oid sha256:3d163c8b8913815a22e930347f58fbfebc36b53013bee35d203afecb1839751b
+size 5880