Hugging Face's logo

mdagost
/
SmolLM2-FT-DPO

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
smol-course
module_1
trl
dpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
mdagost commited on
Commit
19e1659
•
1 Parent(s): b764f92

End of training

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. model.safetensors +2 -2
  3. runs/Dec11_23-20-53_ff43bde1d962/events.out.tfevents.1733959265.ff43bde1d962.5122.1 +3 -0
  4. training_args.bin +1 -1
config.json CHANGED
@@ -26,7 +26,7 @@
26
  "rope_scaling": null,
27
  "rope_theta": 100000,
28
  "tie_word_embeddings": true,
29
- "torch_dtype": "float16",
30
  "transformers.js_config": {
31
  "kv_cache_dtype": {
32
  "fp16": "float16",
 
26
  "rope_scaling": null,
27
  "rope_theta": 100000,
28
  "tie_word_embeddings": true,
29
+ "torch_dtype": "float32",
30
  "transformers.js_config": {
31
  "kv_cache_dtype": {
32
  "fp16": "float16",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4172da91230a15e51f6075ae3c36dc385dc1fd19feffdd55acd8944466aad173
3
- size 269060280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9666f32c346c3e685ee4abe09aa74918d3d2e96783ee70b159823238d1ed8e8
3
+ size 538090408
runs/Dec11_23-20-53_ff43bde1d962/events.out.tfevents.1733959265.ff43bde1d962.5122.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2986eae0a7b8f8a55221eb64980ccbb1beb153dc33c05cb7fafddf572aea2221
3
+ size 146271
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5821c050006249a972c7858643549f3fd2ad4002261c8ccaa83c7ba7d4ea1979
3
  size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ce91e730c51150b850a178dbc43ce6aaa480e3571422e41a8eeeb0b416cb8d
3
  size 6136