gsmyrnis commited on
Commit
ac7bae4
·
verified ·
1 Parent(s): 95c0fc7

Training in progress, epoch 0

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
@@ -7,23 +7,23 @@
7
  "bos_token_id": 151643,
8
  "eos_token_id": 151645,
9
  "hidden_act": "silu",
10
- "hidden_size": 896,
11
  "initializer_range": 0.02,
12
- "intermediate_size": 4864,
13
  "max_position_embeddings": 32768,
14
- "max_window_layers": 21,
15
  "model_type": "qwen2",
16
- "num_attention_heads": 14,
17
- "num_hidden_layers": 24,
18
- "num_key_value_heads": 2,
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
21
  "rope_theta": 1000000.0,
22
  "sliding_window": null,
23
- "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.46.1",
26
  "use_cache": false,
27
  "use_sliding_window": false,
28
- "vocab_size": 151936
29
  }
 
1
  {
2
+ "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
 
7
  "bos_token_id": 151643,
8
  "eos_token_id": 151645,
9
  "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
  "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
  "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
21
  "rope_theta": 1000000.0,
22
  "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.46.1",
26
  "use_cache": false,
27
  "use_sliding_window": false,
28
+ "vocab_size": 152064
29
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c78053150ae441725154a98408eb4dd32649afbbc3333e477357353fb18b6c4f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76304d214fae0a740bb4fbc3c23abb9300610273f5b3d5ca132dcce44092b64f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0942def3d623fa8d729fa050e9720510354fdf55026696312cbc08b7d6dbb3e
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079bfb3f0ed47587461c74f3be997fcc232d133f9476971ec76d71f7a98e25ea
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e88f7dc7b083614e9fd2add8243c02663566daf84b3d66a898c02b318e16708
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73745049d80771cf6f864bceb36015477879a88a966bc6b47906479f79b34525
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:112b5b8032d441774a18b54e690dbf22bbc613cedc507c742b2c7b724f4dc227
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a8d94aa13d1614a7b4523b345cde3fcce160cd5190a9d5deb809a3a69d7557c
3
  size 1089994880
trainer_log.jsonl CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:348aedf1a416ba77d6d23e13b1cb2ca66309eef1f291b485124f81964c6bcad0
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5f0e0df88dd6b6ab5eff60b853a170062518dc475660ba7b8aa73216d36b48
3
  size 7480