Hugging Face's logo

AngelRaychev
/
0.5B-policy-iteration_7

Text Generation
Transformers
PyTorch
qwen2
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
 Community
1
AngelRaychev commited on
Commit
2266c7e
·
verified ·
1 Parent(s): d00ad67

End of training

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
config.json CHANGED
@@ -11,7 +11,7 @@
11
  "intermediate_size": 4864,
12
  "max_position_embeddings": 32768,
13
  "max_window_layers": 24,
14
- "model_card": "\nFinal Loss: 0.1673\nBatch Size: 256\nLearning Rate: 5e-06\nDataset Size: 12591\n",
15
  "model_type": "qwen2",
16
  "num_attention_heads": 14,
17
  "num_hidden_layers": 24,
 
11
  "intermediate_size": 4864,
12
  "max_position_embeddings": 32768,
13
  "max_window_layers": 24,
14
+ "model_card": "\nFinal Loss: 0.1683\nBatch Size: 512\nLearning Rate: 5e-06\nDataset Size: 12591\n",
15
  "model_type": "qwen2",
16
  "num_attention_heads": 14,
17
  "num_hidden_layers": 24,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3df4b903008bb467bcf7c9fb24cdc8101f1b73e469cafee3fd95af2d7559efc
3
  size 988163026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aeaf1b527ead357df85a12973c6d4a6a15acf31cdeca477b3471820323852f6
3
  size 988163026
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2cee0c878a3284dba884d3cacae6a86ae7b4c078fac42091f7e16d39de570d4
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a29d96aa638a5c5562064d795ce2f91fe93f5a8b7f696ad71e36378cecae230
3
  size 5624