Hugging Face's logo

YujieZhao
/
PRO-V-R1-8B

Safetensors
Model card Files
xet
 Community
1
Snyhlxde commited on
Commit
282a5fa
·
1 Parent(s): a3eb30d

rm optimizer

Browse files
Files changed (12) hide show
  1. .gitattributes +18 -0
  2. added_tokens.json +3 -28
  3. chat_template.jinja +3 -89
  4. config.json +3 -68
  5. generation_config.json +3 -13
  6. merges.txt +0 -0
  7. model.safetensors.index.json +3 -407
  8. optimizer.pt +0 -3
  9. special_tokens_map.json +3 -31
  10. tokenizer_config.json +3 -240
  11. trainer_state.json +3 -538
  12. vocab.json +0 -0
.gitattributes CHANGED
@@ -34,3 +34,21 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
39
+ model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
40
+ trainer_state.json filter=lfs diff=lfs merge=lfs -text
41
+ added_tokens.json filter=lfs diff=lfs merge=lfs -text
42
+ chat_template.jinja filter=lfs diff=lfs merge=lfs -text
43
+ model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
44
+ model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
45
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
46
+ generation_config.json filter=lfs diff=lfs merge=lfs -text
47
+ optimizer.pt filter=lfs diff=lfs merge=lfs -text
48
+ rng_state.pth filter=lfs diff=lfs merge=lfs -text
49
+ scheduler.pt filter=lfs diff=lfs merge=lfs -text
50
+ tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
51
+ vocab.json filter=lfs diff=lfs merge=lfs -text
52
+ special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
53
+ config.json filter=lfs diff=lfs merge=lfs -text
54
+ merges.txt filter=lfs diff=lfs merge=lfs -text
added_tokens.json CHANGED
@@ -1,28 +1,3 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
3
+ size 707
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
chat_template.jinja CHANGED
@@ -1,89 +1,3 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0].role == 'system' %}
4
- {{- messages[0].content + '\n\n' }}
5
- {%- endif %}
6
- {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
- {%- for tool in tools %}
8
- {{- "\n" }}
9
- {{- tool | tojson }}
10
- {%- endfor %}
11
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
- {%- else %}
13
- {%- if messages[0].role == 'system' %}
14
- {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
- {%- endif %}
16
- {%- endif %}
17
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
- {%- for message in messages[::-1] %}
19
- {%- set index = (messages|length - 1) - loop.index0 %}
20
- {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
- {%- set ns.multi_step_tool = false %}
22
- {%- set ns.last_query_index = index %}
23
- {%- endif %}
24
- {%- endfor %}
25
- {%- for message in messages %}
26
- {%- if message.content is string %}
27
- {%- set content = message.content %}
28
- {%- else %}
29
- {%- set content = '' %}
30
- {%- endif %}
31
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
- {%- elif message.role == "assistant" %}
34
- {%- set reasoning_content = '' %}
35
- {%- if message.reasoning_content is string %}
36
- {%- set reasoning_content = message.reasoning_content %}
37
- {%- else %}
38
- {%- if '</think>' in content %}
39
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
- {%- endif %}
42
- {%- endif %}
43
- {%- if loop.index0 > ns.last_query_index %}
44
- {%- if loop.last or (not loop.last and reasoning_content) %}
45
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
- {%- else %}
47
- {{- '<|im_start|>' + message.role + '\n' + content }}
48
- {%- endif %}
49
- {%- else %}
50
- {{- '<|im_start|>' + message.role + '\n' + content }}
51
- {%- endif %}
52
- {%- if message.tool_calls %}
53
- {%- for tool_call in message.tool_calls %}
54
- {%- if (loop.first and content) or (not loop.first) %}
55
- {{- '\n' }}
56
- {%- endif %}
57
- {%- if tool_call.function %}
58
- {%- set tool_call = tool_call.function %}
59
- {%- endif %}
60
- {{- '<tool_call>\n{"name": "' }}
61
- {{- tool_call.name }}
62
- {{- '", "arguments": ' }}
63
- {%- if tool_call.arguments is string %}
64
- {{- tool_call.arguments }}
65
- {%- else %}
66
- {{- tool_call.arguments | tojson }}
67
- {%- endif %}
68
- {{- '}\n</tool_call>' }}
69
- {%- endfor %}
70
- {%- endif %}
71
- {{- '<|im_end|>\n' }}
72
- {%- elif message.role == "tool" %}
73
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
- {{- '<|im_start|>user' }}
75
- {%- endif %}
76
- {{- '\n<tool_response>\n' }}
77
- {{- content }}
78
- {{- '\n</tool_response>' }}
79
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
- {{- '<|im_end|>\n' }}
81
- {%- endif %}
82
- {%- endif %}
83
- {%- endfor %}
84
- {%- if add_generation_prompt %}
85
- {{- '<|im_start|>assistant\n' }}
86
- {%- if enable_thinking is defined and enable_thinking is false %}
87
- {{- '<think>\n\n</think>\n\n' }}
88
- {%- endif %}
89
- {%- endif %}
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
3
+ size 4168
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,68 +1,3 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "dtype": "bfloat16",
9
- "eos_token_id": 151645,
10
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 4096,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 12288,
15
- "layer_types": [
16
- "full_attention",
17
- "full_attention",
18
- "full_attention",
19
- "full_attention",
20
- "full_attention",
21
- "full_attention",
22
- "full_attention",
23
- "full_attention",
24
- "full_attention",
25
- "full_attention",
26
- "full_attention",
27
- "full_attention",
28
- "full_attention",
29
- "full_attention",
30
- "full_attention",
31
- "full_attention",
32
- "full_attention",
33
- "full_attention",
34
- "full_attention",
35
- "full_attention",
36
- "full_attention",
37
- "full_attention",
38
- "full_attention",
39
- "full_attention",
40
- "full_attention",
41
- "full_attention",
42
- "full_attention",
43
- "full_attention",
44
- "full_attention",
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention",
51
- "full_attention"
52
- ],
53
- "max_position_embeddings": 40960,
54
- "max_window_layers": 36,
55
- "model_type": "qwen3",
56
- "num_attention_heads": 32,
57
- "num_hidden_layers": 36,
58
- "num_key_value_heads": 8,
59
- "rms_norm_eps": 1e-06,
60
- "rope_scaling": null,
61
- "rope_theta": 1000000,
62
- "sliding_window": null,
63
- "tie_word_embeddings": false,
64
- "transformers_version": "4.57.1",
65
- "use_cache": false,
66
- "use_sliding_window": false,
67
- "vocab_size": 151936
68
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef7563ac83d66bd2d0ed70c5e24a7f59166414954d50a12d3ee5b0cbc7e7786
3
+ size 1539
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "temperature": 0.6,
10
- "top_k": 20,
11
- "top_p": 0.95,
12
- "transformers_version": "4.57.1"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e057bbca66b92f33a8bdc6a1301014e0e4ab69b3b3fd2e442d9fe0c69f3431
3
+ size 214
 
 
 
 
 
 
 
 
 
 
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json CHANGED
@@ -1,407 +1,3 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 8190735360,
4
- "total_size": 16381470720
5
- },
6
- "weight_map": {
7
- "lm_head.weight": "model-00004-of-00004.safetensors",
8
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
- "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
15
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
- "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
18
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
- "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
26
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
- "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
29
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
31
- "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
32
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
33
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
34
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
35
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
36
- "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
37
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
38
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
39
- "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
40
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
41
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
42
- "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
43
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
44
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
45
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
46
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
47
- "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
48
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
- "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
51
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
- "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
- "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
59
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
- "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
62
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
63
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
64
- "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
65
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
66
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
67
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
68
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
69
- "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
70
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
71
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
72
- "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
73
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
74
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
75
- "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
76
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
77
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
78
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
79
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
80
- "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
81
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
82
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
83
- "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
84
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
85
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
86
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
87
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
88
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
89
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
90
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
91
- "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
92
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
93
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
94
- "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
95
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
96
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
97
- "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
98
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
99
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
100
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
101
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
102
- "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
103
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
- "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
106
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
- "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
- "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
114
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
115
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
116
- "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
117
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
118
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
119
- "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
120
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
121
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
122
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
123
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
124
- "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
125
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
126
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
127
- "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
128
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
129
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
130
- "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
131
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
132
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
133
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
134
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
135
- "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
136
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
137
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
138
- "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
139
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
140
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
142
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
143
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
144
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
145
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
146
- "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
147
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
148
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
149
- "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
150
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
151
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
152
- "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
153
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
154
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
155
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
156
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
157
- "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
158
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
159
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
160
- "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
161
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
162
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
163
- "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
164
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
165
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
166
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
167
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
168
- "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
169
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
170
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
171
- "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
172
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
173
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
174
- "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
175
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
176
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
177
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
178
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
179
- "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
180
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
181
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
182
- "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
183
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
184
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
185
- "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
186
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
187
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
188
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
189
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
190
- "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
191
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
192
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
193
- "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
194
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
195
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
196
- "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
198
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
199
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
200
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
201
- "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
202
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
- "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
205
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
- "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
- "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
213
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
214
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
215
- "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
216
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
217
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
218
- "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
219
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
220
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
221
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
222
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
223
- "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
224
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
225
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
226
- "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
227
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
228
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
229
- "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
230
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
231
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
232
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
233
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
234
- "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
235
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
236
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
237
- "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
238
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
239
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
240
- "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
241
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
242
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
243
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
244
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
245
- "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
246
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
247
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
248
- "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
249
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
250
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
251
- "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
252
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
253
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
254
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
255
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
256
- "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
257
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
258
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
259
- "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
260
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
261
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
262
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
263
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
264
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
265
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
266
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
267
- "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
268
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
269
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
270
- "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
271
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
272
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
- "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
274
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
275
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
276
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
277
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
278
- "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
279
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
280
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
281
- "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
282
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
283
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
284
- "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
285
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
286
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
287
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
288
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
289
- "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
290
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
291
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
292
- "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
293
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
294
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
295
- "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
296
- "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
297
- "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
298
- "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
299
- "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
300
- "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
301
- "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
302
- "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
303
- "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
304
- "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
305
- "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
306
- "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
307
- "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
308
- "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
309
- "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
310
- "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
311
- "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
312
- "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
313
- "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
314
- "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
315
- "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
316
- "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
317
- "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
318
- "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
319
- "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
320
- "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
321
- "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
322
- "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
323
- "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
324
- "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
325
- "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
326
- "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
327
- "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
328
- "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
329
- "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
330
- "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
331
- "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
332
- "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
333
- "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
334
- "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
335
- "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
336
- "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
337
- "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
338
- "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
339
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
340
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
341
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
342
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
343
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
344
- "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
345
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
346
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
347
- "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
348
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
349
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
350
- "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
351
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
354
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
355
- "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
356
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
357
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
358
- "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
359
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
360
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
361
- "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
362
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
363
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
364
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
365
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
366
- "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
367
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
368
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
369
- "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
370
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
371
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
372
- "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
373
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
374
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
375
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
376
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
377
- "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
378
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
380
- "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
381
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
382
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
383
- "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
384
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
385
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
386
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
387
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
388
- "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
389
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
390
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
391
- "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
392
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
393
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
394
- "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
395
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
396
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
397
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
398
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
399
- "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
400
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
401
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
402
- "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
403
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
404
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
405
- "model.norm.weight": "model-00004-of-00004.safetensors"
406
- }
407
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e4bdc58d3302c97357f27979b270987dd620cf0cd9b1c130e3a51c9d64df95
3
+ size 32914
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:be9b79b90ee37eff778f741572362ad942b2205379e31c205c3ea87e94c20591
3
- size 32763290952
 
 
 
 
special_tokens_map.json CHANGED
@@ -1,31 +1,3 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
- "eos_token": {
18
- "content": "<|im_end|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "pad_token": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
3
+ size 613
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json CHANGED
@@ -1,240 +1,3 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "151665": {
182
- "content": "<tool_response>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "151666": {
190
- "content": "</tool_response>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "151667": {
198
- "content": "<think>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "151668": {
206
- "content": "</think>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|im_start|>",
216
- "<|im_end|>",
217
- "<|object_ref_start|>",
218
- "<|object_ref_end|>",
219
- "<|box_start|>",
220
- "<|box_end|>",
221
- "<|quad_start|>",
222
- "<|quad_end|>",
223
- "<|vision_start|>",
224
- "<|vision_end|>",
225
- "<|vision_pad|>",
226
- "<|image_pad|>",
227
- "<|video_pad|>"
228
- ],
229
- "bos_token": null,
230
- "clean_up_tokenization_spaces": false,
231
- "eos_token": "<|im_end|>",
232
- "errors": "replace",
233
- "extra_special_tokens": {},
234
- "model_max_length": 131072,
235
- "pad_token": "<|endoftext|>",
236
- "padding_side": "right",
237
- "split_special_tokens": false,
238
- "tokenizer_class": "Qwen2Tokenizer",
239
- "unk_token": null
240
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5c1909da4950a610a9e3a6cb6763cff0381d91c6f0838855db8d5ae83d6c9f
3
+ size 5431
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
trainer_state.json CHANGED
@@ -1,538 +1,3 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 2.0,
6
- "eval_steps": 500,
7
- "global_step": 722,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.027700831024930747,
14
- "grad_norm": 8.875,
15
- "learning_rate": 4.128440366972477e-06,
16
- "loss": 1.1711,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.055401662049861494,
21
- "grad_norm": 3.375,
22
- "learning_rate": 8.71559633027523e-06,
23
- "loss": 0.9173,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.08310249307479224,
28
- "grad_norm": 2.0625,
29
- "learning_rate": 1.3302752293577984e-05,
30
- "loss": 0.579,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.11080332409972299,
35
- "grad_norm": 1.4765625,
36
- "learning_rate": 1.7889908256880737e-05,
37
- "loss": 0.3616,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.13850415512465375,
42
- "grad_norm": 1.34375,
43
- "learning_rate": 2.2477064220183487e-05,
44
- "loss": 0.287,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.16620498614958448,
49
- "grad_norm": 1.078125,
50
- "learning_rate": 2.7064220183486238e-05,
51
- "loss": 0.2611,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.19390581717451524,
56
- "grad_norm": 0.85546875,
57
- "learning_rate": 3.1651376146788995e-05,
58
- "loss": 0.2728,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.22160664819944598,
63
- "grad_norm": 0.93359375,
64
- "learning_rate": 3.623853211009174e-05,
65
- "loss": 0.2687,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.24930747922437674,
70
- "grad_norm": 1.1171875,
71
- "learning_rate": 4.0825688073394495e-05,
72
- "loss": 0.2722,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.2770083102493075,
77
- "grad_norm": 1.09375,
78
- "learning_rate": 4.541284403669725e-05,
79
- "loss": 0.2492,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.3047091412742382,
84
- "grad_norm": 0.91015625,
85
- "learning_rate": 5e-05,
86
- "loss": 0.2447,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 0.33240997229916897,
91
- "grad_norm": 0.88671875,
92
- "learning_rate": 4.99869966817273e-05,
93
- "loss": 0.2648,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 0.3601108033240997,
98
- "grad_norm": 0.828125,
99
- "learning_rate": 4.994800025381211e-05,
100
- "loss": 0.2581,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 0.3878116343490305,
105
- "grad_norm": 0.8125,
106
- "learning_rate": 4.9883051282891504e-05,
107
- "loss": 0.2444,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 0.4155124653739612,
112
- "grad_norm": 0.8515625,
113
- "learning_rate": 4.9792217333136724e-05,
114
- "loss": 0.2408,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 0.44321329639889195,
119
- "grad_norm": 0.77734375,
120
- "learning_rate": 4.967559289596846e-05,
121
- "loss": 0.247,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 0.4709141274238227,
126
- "grad_norm": 0.81640625,
127
- "learning_rate": 4.9533299291760695e-05,
128
- "loss": 0.2142,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 0.4986149584487535,
133
- "grad_norm": 0.85546875,
134
- "learning_rate": 4.9365484543635324e-05,
135
- "loss": 0.2322,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 0.5263157894736842,
140
- "grad_norm": 0.73046875,
141
- "learning_rate": 4.917232322347881e-05,
142
- "loss": 0.2333,
143
- "step": 190
144
- },
145
- {
146
- "epoch": 0.554016620498615,
147
- "grad_norm": 0.73046875,
148
- "learning_rate": 4.8954016270341065e-05,
149
- "loss": 0.2303,
150
- "step": 200
151
- },
152
- {
153
- "epoch": 0.5817174515235457,
154
- "grad_norm": 0.7734375,
155
- "learning_rate": 4.871079078140551e-05,
156
- "loss": 0.2366,
157
- "step": 210
158
- },
159
- {
160
- "epoch": 0.6094182825484764,
161
- "grad_norm": 0.703125,
162
- "learning_rate": 4.844289977574773e-05,
163
- "loss": 0.2191,
164
- "step": 220
165
- },
166
- {
167
- "epoch": 0.6371191135734072,
168
- "grad_norm": 0.74609375,
169
- "learning_rate": 4.815062193112844e-05,
170
- "loss": 0.2365,
171
- "step": 230
172
- },
173
- {
174
- "epoch": 0.6648199445983379,
175
- "grad_norm": 0.84765625,
176
- "learning_rate": 4.783426129409465e-05,
177
- "loss": 0.237,
178
- "step": 240
179
- },
180
- {
181
- "epoch": 0.6925207756232687,
182
- "grad_norm": 0.64453125,
183
- "learning_rate": 4.7494146963690535e-05,
184
- "loss": 0.2281,
185
- "step": 250
186
- },
187
- {
188
- "epoch": 0.7202216066481995,
189
- "grad_norm": 0.734375,
190
- "learning_rate": 4.713063274910708e-05,
191
- "loss": 0.2239,
192
- "step": 260
193
- },
194
- {
195
- "epoch": 0.7479224376731302,
196
- "grad_norm": 0.65625,
197
- "learning_rate": 4.6744096801626615e-05,
198
- "loss": 0.2097,
199
- "step": 270
200
- },
201
- {
202
- "epoch": 0.775623268698061,
203
- "grad_norm": 0.72265625,
204
- "learning_rate": 4.633494122124504e-05,
205
- "loss": 0.2279,
206
- "step": 280
207
- },
208
- {
209
- "epoch": 0.8033240997229917,
210
- "grad_norm": 0.7734375,
211
- "learning_rate": 4.590359163838114e-05,
212
- "loss": 0.2188,
213
- "step": 290
214
- },
215
- {
216
- "epoch": 0.8310249307479224,
217
- "grad_norm": 0.79296875,
218
- "learning_rate": 4.545049677110793e-05,
219
- "loss": 0.2319,
220
- "step": 300
221
- },
222
- {
223
- "epoch": 0.8587257617728532,
224
- "grad_norm": 0.8046875,
225
- "learning_rate": 4.497612795836677e-05,
226
- "loss": 0.2292,
227
- "step": 310
228
- },
229
- {
230
- "epoch": 0.8864265927977839,
231
- "grad_norm": 0.58984375,
232
- "learning_rate": 4.4480978669649716e-05,
233
- "loss": 0.2443,
234
- "step": 320
235
- },
236
- {
237
- "epoch": 0.9141274238227147,
238
- "grad_norm": 0.86328125,
239
- "learning_rate": 4.3965563991660255e-05,
240
- "loss": 0.2481,
241
- "step": 330
242
- },
243
- {
244
- "epoch": 0.9418282548476454,
245
- "grad_norm": 0.78515625,
246
- "learning_rate": 4.3430420092486414e-05,
247
- "loss": 0.2171,
248
- "step": 340
249
- },
250
- {
251
- "epoch": 0.9695290858725761,
252
- "grad_norm": 0.72265625,
253
- "learning_rate": 4.2876103663843616e-05,
254
- "loss": 0.236,
255
- "step": 350
256
- },
257
- {
258
- "epoch": 0.997229916897507,
259
- "grad_norm": 0.875,
260
- "learning_rate": 4.2303191341967476e-05,
261
- "loss": 0.2289,
262
- "step": 360
263
- },
264
- {
265
- "epoch": 1.0249307479224377,
266
- "grad_norm": 0.83203125,
267
- "learning_rate": 4.1712279107759104e-05,
268
- "loss": 0.1618,
269
- "step": 370
270
- },
271
- {
272
- "epoch": 1.0526315789473684,
273
- "grad_norm": 0.76953125,
274
- "learning_rate": 4.110398166680671e-05,
275
- "loss": 0.163,
276
- "step": 380
277
- },
278
- {
279
- "epoch": 1.080332409972299,
280
- "grad_norm": 0.67578125,
281
- "learning_rate": 4.0478931809928636e-05,
282
- "loss": 0.1457,
283
- "step": 390
284
- },
285
- {
286
- "epoch": 1.10803324099723,
287
- "grad_norm": 0.703125,
288
- "learning_rate": 3.983777975490288e-05,
289
- "loss": 0.1575,
290
- "step": 400
291
- },
292
- {
293
- "epoch": 1.1357340720221607,
294
- "grad_norm": 0.8359375,
295
- "learning_rate": 3.918119247006807e-05,
296
- "loss": 0.1617,
297
- "step": 410
298
- },
299
- {
300
- "epoch": 1.1634349030470914,
301
- "grad_norm": 0.74609375,
302
- "learning_rate": 3.8509852980499296e-05,
303
- "loss": 0.1603,
304
- "step": 420
305
- },
306
- {
307
- "epoch": 1.1911357340720221,
308
- "grad_norm": 0.75,
309
- "learning_rate": 3.782445965748071e-05,
310
- "loss": 0.1516,
311
- "step": 430
312
- },
313
- {
314
- "epoch": 1.2188365650969528,
315
- "grad_norm": 0.6015625,
316
- "learning_rate": 3.7125725492013986e-05,
317
- "loss": 0.1578,
318
- "step": 440
319
- },
320
- {
321
- "epoch": 1.2465373961218837,
322
- "grad_norm": 0.80078125,
323
- "learning_rate": 3.6414377353118466e-05,
324
- "loss": 0.1544,
325
- "step": 450
326
- },
327
- {
328
- "epoch": 1.2742382271468145,
329
- "grad_norm": 0.84765625,
330
- "learning_rate": 3.5691155231694375e-05,
331
- "loss": 0.1585,
332
- "step": 460
333
- },
334
- {
335
- "epoch": 1.3019390581717452,
336
- "grad_norm": 0.66015625,
337
- "learning_rate": 3.495681147073584e-05,
338
- "loss": 0.1395,
339
- "step": 470
340
- },
341
- {
342
- "epoch": 1.3296398891966759,
343
- "grad_norm": 0.65625,
344
- "learning_rate": 3.421210998269447e-05,
345
- "loss": 0.1602,
346
- "step": 480
347
- },
348
- {
349
- "epoch": 1.3573407202216066,
350
- "grad_norm": 0.76171875,
351
- "learning_rate": 3.345782545480768e-05,
352
- "loss": 0.1556,
353
- "step": 490
354
- },
355
- {
356
- "epoch": 1.3850415512465375,
357
- "grad_norm": 0.796875,
358
- "learning_rate": 3.269474254321818e-05,
359
- "loss": 0.1711,
360
- "step": 500
361
- },
362
- {
363
- "epoch": 1.4127423822714682,
364
- "grad_norm": 0.703125,
365
- "learning_rate": 3.192365505672341e-05,
366
- "loss": 0.1624,
367
- "step": 510
368
- },
369
- {
370
- "epoch": 1.440443213296399,
371
- "grad_norm": 0.796875,
372
- "learning_rate": 3.1145365131003606e-05,
373
- "loss": 0.1583,
374
- "step": 520
375
- },
376
- {
377
- "epoch": 1.4681440443213296,
378
- "grad_norm": 0.5625,
379
- "learning_rate": 3.036068239418777e-05,
380
- "loss": 0.1499,
381
- "step": 530
382
- },
383
- {
384
- "epoch": 1.4958448753462603,
385
- "grad_norm": 0.7578125,
386
- "learning_rate": 2.9570423124625503e-05,
387
- "loss": 0.154,
388
- "step": 540
389
- },
390
- {
391
- "epoch": 1.5235457063711912,
392
- "grad_norm": 0.6328125,
393
- "learning_rate": 2.87754094017408e-05,
394
- "loss": 0.174,
395
- "step": 550
396
- },
397
- {
398
- "epoch": 1.5512465373961217,
399
- "grad_norm": 0.70703125,
400
- "learning_rate": 2.797646825085125e-05,
401
- "loss": 0.161,
402
- "step": 560
403
- },
404
- {
405
- "epoch": 1.5789473684210527,
406
- "grad_norm": 0.7578125,
407
- "learning_rate": 2.7174430782842152e-05,
408
- "loss": 0.162,
409
- "step": 570
410
- },
411
- {
412
- "epoch": 1.6066481994459834,
413
- "grad_norm": 0.78125,
414
- "learning_rate": 2.6370131329590557e-05,
415
- "loss": 0.1579,
416
- "step": 580
417
- },
418
- {
419
- "epoch": 1.634349030470914,
420
- "grad_norm": 0.76953125,
421
- "learning_rate": 2.5564406576038642e-05,
422
- "loss": 0.1573,
423
- "step": 590
424
- },
425
- {
426
- "epoch": 1.662049861495845,
427
- "grad_norm": 0.68359375,
428
- "learning_rate": 2.4758094689819244e-05,
429
- "loss": 0.1474,
430
- "step": 600
431
- },
432
- {
433
- "epoch": 1.6897506925207755,
434
- "grad_norm": 0.703125,
435
- "learning_rate": 2.395203444933906e-05,
436
- "loss": 0.1428,
437
- "step": 610
438
- },
439
- {
440
- "epoch": 1.7174515235457064,
441
- "grad_norm": 0.6953125,
442
- "learning_rate": 2.3147064371226394e-05,
443
- "loss": 0.1432,
444
- "step": 620
445
- },
446
- {
447
- "epoch": 1.745152354570637,
448
- "grad_norm": 0.6796875,
449
- "learning_rate": 2.2344021838051317e-05,
450
- "loss": 0.1443,
451
- "step": 630
452
- },
453
- {
454
- "epoch": 1.7728531855955678,
455
- "grad_norm": 0.66015625,
456
- "learning_rate": 2.1543742227225448e-05,
457
- "loss": 0.1454,
458
- "step": 640
459
- },
460
- {
461
- "epoch": 1.8005540166204987,
462
- "grad_norm": 0.61328125,
463
- "learning_rate": 2.0747058041987733e-05,
464
- "loss": 0.1394,
465
- "step": 650
466
- },
467
- {
468
- "epoch": 1.8282548476454292,
469
- "grad_norm": 0.73046875,
470
- "learning_rate": 1.995479804538004e-05,
471
- "loss": 0.1524,
472
- "step": 660
473
- },
474
- {
475
- "epoch": 1.8559556786703602,
476
- "grad_norm": 0.60546875,
477
- "learning_rate": 1.9167786398113628e-05,
478
- "loss": 0.1672,
479
- "step": 670
480
- },
481
- {
482
- "epoch": 1.8836565096952909,
483
- "grad_norm": 0.62109375,
484
- "learning_rate": 1.8386841801223183e-05,
485
- "loss": 0.1614,
486
- "step": 680
487
- },
488
- {
489
- "epoch": 1.9113573407202216,
490
- "grad_norm": 0.65625,
491
- "learning_rate": 1.7612776644400446e-05,
492
- "loss": 0.1386,
493
- "step": 690
494
- },
495
- {
496
- "epoch": 1.9390581717451525,
497
- "grad_norm": 0.87890625,
498
- "learning_rate": 1.6846396160893262e-05,
499
- "loss": 0.151,
500
- "step": 700
501
- },
502
- {
503
- "epoch": 1.966759002770083,
504
- "grad_norm": 0.765625,
505
- "learning_rate": 1.6088497589849227e-05,
506
- "loss": 0.1549,
507
- "step": 710
508
- },
509
- {
510
- "epoch": 1.994459833795014,
511
- "grad_norm": 0.7109375,
512
- "learning_rate": 1.533986934697536e-05,
513
- "loss": 0.1505,
514
- "step": 720
515
- }
516
- ],
517
- "logging_steps": 10,
518
- "max_steps": 1083,
519
- "num_input_tokens_seen": 0,
520
- "num_train_epochs": 3,
521
- "save_steps": 500,
522
- "stateful_callbacks": {
523
- "TrainerControl": {
524
- "args": {
525
- "should_epoch_stop": false,
526
- "should_evaluate": false,
527
- "should_log": false,
528
- "should_save": true,
529
- "should_training_stop": false
530
- },
531
- "attributes": {}
532
- }
533
- },
534
- "total_flos": 4.898526946086175e+17,
535
- "train_batch_size": 4,
536
- "trial_name": null,
537
- "trial_params": null
538
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f1794567235518d1f2eb89f215e13d8a931d22da52ed06827d82a0a00dada4
3
+ size 12570
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vocab.json CHANGED
The diff for this file is too large to render. See raw diff