Ba2han commited on
Commit
f20caa6
·
verified ·
1 Parent(s): c8f0472

Training in progress, step 660

Browse files
README.md CHANGED
@@ -3,9 +3,9 @@ library_name: transformers
3
  model_name: outputs
4
  tags:
5
  - generated_from_trainer
6
- - sft
7
  - unsloth
8
  - trl
 
9
  licence: license
10
  ---
11
 
@@ -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/gj7eichr)
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: 4.3.0
41
  - Tokenizers: 0.22.2
42
 
43
  ## Citations
 
3
  model_name: outputs
4
  tags:
5
  - generated_from_trainer
 
6
  - unsloth
7
  - trl
8
+ - sft
9
  licence: license
10
  ---
11
 
 
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/g2ae0u89)
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: 4.7.0
41
  - Tokenizers: 0.22.2
42
 
43
  ## Citations
config.json CHANGED
@@ -6,12 +6,12 @@
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,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 4608,
15
  "layer_types": [
16
  "full_attention",
17
  "full_attention",
@@ -52,15 +52,17 @@
52
  "full_attention",
53
  "full_attention",
54
  "full_attention",
 
 
55
  "full_attention"
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,
63
- "num_key_value_heads": 8,
64
  "pad_token_id": 0,
65
  "rms_norm_eps": 1e-08,
66
  "rope_parameters": {
@@ -73,5 +75,5 @@
73
  "unsloth_version": "2026.7.2",
74
  "use_cache": false,
75
  "use_sliding_window": false,
76
- "vocab_size": 60802
77
  }
 
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": 1664,
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 4160,
15
  "layer_types": [
16
  "full_attention",
17
  "full_attention",
 
52
  "full_attention",
53
  "full_attention",
54
  "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
  "full_attention"
58
  ],
59
+ "max_position_embeddings": 16384,
60
+ "max_window_layers": 42,
61
+ "model_name": "random_model",
62
  "model_type": "qwen3",
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 42,
65
+ "num_key_value_heads": 4,
66
  "pad_token_id": 0,
67
  "rms_norm_eps": 1e-08,
68
  "rope_parameters": {
 
75
  "unsloth_version": "2026.7.2",
76
  "use_cache": false,
77
  "use_sliding_window": false,
78
+ "vocab_size": 60800
79
  }
generation_config.json CHANGED
@@ -2,9 +2,9 @@
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,
 
2
  "_from_model_config": true,
3
  "bos_token_id": 2,
4
  "eos_token_id": [
5
+ 3
6
  ],
7
+ "max_length": 16384,
8
  "output_attentions": false,
9
  "output_hidden_states": false,
10
  "pad_token_id": 0,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:701ca595ad1defd750a25409c943adf74f8781010426bdefa517964d000f7cb5
3
- size 2641039512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3262a5785f33d010201cbf20af3095dd76f00c838583906dabd0d256d03df9b2
3
+ size 2519929824
tokenizer.json CHANGED
@@ -2342,24 +2342,6 @@
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": {
 
2342
  "rstrip": false,
2343
  "normalized": false,
2344
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2345
  }
2346
  ],
2347
  "normalizer": {
tokenizer_config.json CHANGED
@@ -2,10 +2,7 @@
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>",
@@ -2092,22 +2089,6 @@
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
  }
 
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
  "rstrip": false,
2090
  "normalized": false,
2091
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2092
  }
2093
  }
2094
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fca29e5eb79657cbb9063a36f8a75cdba332e03ddfbba7316ce46ef48ffcbe6
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdbedf6b6e90518a8ea0dcc536d736ed32396c3ce9c9df7f146cbcc90f4661f8
3
  size 5777