Ba2han commited on
Commit
545114d
·
verified ·
1 Parent(s): 02d7c5b

Training in progress, step 400

Browse files
README.md CHANGED
@@ -3,8 +3,8 @@ library_name: transformers
3
  model_name: outputs
4
  tags:
5
  - generated_from_trainer
6
- - unsloth
7
  - sft
 
8
  - trl
9
  licence: license
10
  ---
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<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/batuhan409/huggingface/runs/ruf7xvfj)
31
 
32
 
33
  This model was trained with SFT.
@@ -37,7 +37,7 @@ This model was trained with SFT.
37
  - TRL: 0.24.0
38
  - Transformers: 5.5.0
39
  - Pytorch: 2.10.0
40
- - Datasets: 4.6.0
41
  - Tokenizers: 0.22.2
42
 
43
  ## Citations
 
3
  model_name: outputs
4
  tags:
5
  - generated_from_trainer
 
6
  - sft
7
+ - unsloth
8
  - trl
9
  licence: license
10
  ---
 
27
 
28
  ## Training procedure
29
 
30
+ [<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/batuhan409/huggingface/runs/gj7eichr)
31
 
32
 
33
  This model was trained with SFT.
 
37
  - TRL: 0.24.0
38
  - Transformers: 5.5.0
39
  - Pytorch: 2.10.0
40
+ - Datasets: 4.3.0
41
  - Tokenizers: 0.22.2
42
 
43
  ## Citations
config.json CHANGED
@@ -6,7 +6,7 @@
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 2,
8
  "dtype": "bfloat16",
9
- "eos_token_id": 3,
10
  "head_dim": 128,
11
  "hidden_act": "silu",
12
  "hidden_size": 1536,
@@ -56,7 +56,7 @@
56
  ],
57
  "max_position_embeddings": 8192,
58
  "max_window_layers": 40,
59
- "model_name": "random_model",
60
  "model_type": "qwen3",
61
  "num_attention_heads": 16,
62
  "num_hidden_layers": 40,
@@ -70,8 +70,8 @@
70
  "sliding_window": null,
71
  "tie_word_embeddings": true,
72
  "transformers_version": "5.5.0",
73
- "unsloth_version": "2026.7.1",
74
  "use_cache": false,
75
  "use_sliding_window": false,
76
- "vocab_size": 60800
77
  }
 
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 2,
8
  "dtype": "bfloat16",
9
+ "eos_token_id": 60800,
10
  "head_dim": 128,
11
  "hidden_act": "silu",
12
  "hidden_size": 1536,
 
56
  ],
57
  "max_position_embeddings": 8192,
58
  "max_window_layers": 40,
59
+ "model_name": "checkpoint-5722",
60
  "model_type": "qwen3",
61
  "num_attention_heads": 16,
62
  "num_hidden_layers": 40,
 
70
  "sliding_window": null,
71
  "tie_word_embeddings": true,
72
  "transformers_version": "5.5.0",
73
+ "unsloth_version": "2026.7.2",
74
  "use_cache": false,
75
  "use_sliding_window": false,
76
+ "vocab_size": 60802
77
  }
generation_config.json CHANGED
@@ -2,12 +2,12 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 2,
4
  "eos_token_id": [
5
- 3
6
  ],
7
  "max_length": 8192,
8
  "output_attentions": false,
9
  "output_hidden_states": false,
10
  "pad_token_id": 0,
11
  "transformers_version": "5.5.0",
12
- "use_cache": false
13
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 2,
4
  "eos_token_id": [
5
+ 60800
6
  ],
7
  "max_length": 8192,
8
  "output_attentions": false,
9
  "output_hidden_states": false,
10
  "pad_token_id": 0,
11
  "transformers_version": "5.5.0",
12
+ "use_cache": true
13
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e75408b6d7a2bc41dc679158c5a5d46816eee321983c86f99e949a643c81f080
3
- size 2641033368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0df04f618d1d05c113a38828a4c5ef6460336b9fc1d3cd4d44ac1a40916a3bcb
3
+ size 2641039512
tokenizer.json CHANGED
@@ -2342,6 +2342,24 @@
2342
  "rstrip": false,
2343
  "normalized": false,
2344
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2345
  }
2346
  ],
2347
  "normalizer": {
 
2342
  "rstrip": false,
2343
  "normalized": false,
2344
  "special": true
2345
+ },
2346
+ {
2347
+ "id": 60800,
2348
+ "content": "<|im_end|>",
2349
+ "single_word": false,
2350
+ "lstrip": false,
2351
+ "rstrip": false,
2352
+ "normalized": false,
2353
+ "special": true
2354
+ },
2355
+ {
2356
+ "id": 60801,
2357
+ "content": "<|im_start|>",
2358
+ "single_word": false,
2359
+ "lstrip": false,
2360
+ "rstrip": false,
2361
+ "normalized": false,
2362
+ "special": true
2363
  }
2364
  ],
2365
  "normalizer": {
tokenizer_config.json CHANGED
@@ -2,7 +2,10 @@
2
  "backend": "tokenizers",
3
  "bos_token": "<bos>",
4
  "clean_up_tokenization_spaces": false,
5
- "eos_token": "<eos>",
 
 
 
6
  "is_local": true,
7
  "model_max_length": 1000000000000000019884624838656,
8
  "pad_token": "<pad>",
@@ -2089,6 +2092,22 @@
2089
  "rstrip": false,
2090
  "normalized": false,
2091
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2092
  }
2093
  }
2094
  }
 
2
  "backend": "tokenizers",
3
  "bos_token": "<bos>",
4
  "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "extra_special_tokens": [
7
+ "<|im_start|>"
8
+ ],
9
  "is_local": true,
10
  "model_max_length": 1000000000000000019884624838656,
11
  "pad_token": "<pad>",
 
2092
  "rstrip": false,
2093
  "normalized": false,
2094
  "special": true
2095
+ },
2096
+ "60800": {
2097
+ "content": "<|im_end|>",
2098
+ "single_word": false,
2099
+ "lstrip": false,
2100
+ "rstrip": false,
2101
+ "normalized": false,
2102
+ "special": true
2103
+ },
2104
+ "60801": {
2105
+ "content": "<|im_start|>",
2106
+ "single_word": false,
2107
+ "lstrip": false,
2108
+ "rstrip": false,
2109
+ "normalized": false,
2110
+ "special": true
2111
  }
2112
  }
2113
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:458f160901eebe1d9e3da94f528353d929397d2d2dd7c68dcf7a79173cf25a91
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fca29e5eb79657cbb9063a36f8a75cdba332e03ddfbba7316ce46ef48ffcbe6
3
  size 5777