IoakeimE commited on
Commit
ec386f7
·
verified ·
1 Parent(s): 1db07d1

Training in progress, epoch 1

Browse files
README.md CHANGED
@@ -4,8 +4,8 @@ library_name: transformers
4
  model_name: sft_best_simplification
5
  tags:
6
  - generated_from_trainer
7
- - trl
8
  - unsloth
 
9
  - sft
10
  licence: license
11
  ---
@@ -28,16 +28,16 @@ print(output["generated_text"])
28
 
29
  ## Training procedure
30
 
31
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/sft_best_simplification/runs/kc6lw27s)
32
 
33
 
34
  This model was trained with SFT.
35
 
36
  ### Framework versions
37
 
38
- - TRL: 0.23.0
39
- - Transformers: 4.57.1
40
- - Pytorch: 2.8.0
41
  - Datasets: 4.3.0
42
  - Tokenizers: 0.22.1
43
 
 
4
  model_name: sft_best_simplification
5
  tags:
6
  - generated_from_trainer
 
7
  - unsloth
8
+ - trl
9
  - sft
10
  licence: license
11
  ---
 
28
 
29
  ## Training procedure
30
 
31
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/sft_best_simplification/runs/155qq06u)
32
 
33
 
34
  This model was trained with SFT.
35
 
36
  ### Framework versions
37
 
38
+ - TRL: 0.24.0
39
+ - Transformers: 4.57.2
40
+ - Pytorch: 2.9.0
41
  - Datasets: 4.3.0
42
  - Tokenizers: 0.22.1
43
 
adapter_config.json CHANGED
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
 
36
  "up_proj",
37
  "q_proj",
38
- "down_proj",
39
- "v_proj",
40
- "k_proj",
41
  "gate_proj",
42
- "o_proj"
 
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
+ "down_proj",
37
  "up_proj",
38
  "q_proj",
 
 
 
39
  "gate_proj",
40
+ "o_proj",
41
+ "v_proj",
42
+ "k_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c191500666a73afc7b36b3ae7277329f9cf35396f5c021a71ed8f7acd8aa3ba
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72eb424fcda49e1c6989872f6e1285cabdc01a8b195a05e340a9c235ec65bdf9
3
  size 167832240
tokenizer_config.json CHANGED
@@ -6179,7 +6179,7 @@
6179
  "legacy": false,
6180
  "model_max_length": 32768,
6181
  "pad_token": "[control_768]",
6182
- "padding_side": "left",
6183
  "sp_model_kwargs": {},
6184
  "spaces_between_special_tokens": false,
6185
  "tokenizer_class": "LlamaTokenizer",
 
6179
  "legacy": false,
6180
  "model_max_length": 32768,
6181
  "pad_token": "[control_768]",
6182
+ "padding_side": "right",
6183
  "sp_model_kwargs": {},
6184
  "spaces_between_special_tokens": false,
6185
  "tokenizer_class": "LlamaTokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c40cf0f3fb04a0ff90a766e83b9ee7fcc9800df8b0bf374934d3bf32257ed7ff
3
  size 6353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd370958f23b8bcdae63fbf60cf67ea84485eb6f42a2ac31c8d63a9d834dac5
3
  size 6353