v-stone commited on
Commit
bd6a901
·
verified ·
1 Parent(s): c06669c

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip 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
 
 
33
  *.zip 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
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
chat_template.jinja ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# 5D7QyM5hag4mNBKL8Hz1mFdcT2YFMcCvjuTbPmkH2zGr8ouu #}{%- 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
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "layer_types": [
15
+ "full_attention",
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
+ ],
52
+ "max_position_embeddings": 262144,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "pad_token_id": 151643,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 5000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": true,
64
+ "transformers_version": "4.56.1",
65
+ "use_cache": false,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936
68
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "temperature": 0.6,
9
+ "top_k": 20,
10
+ "top_p": 0.95,
11
+ "transformers_version": "4.56.1"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c707505860f2cb54f04322a325c38c54d24818b98049168a93e0b5d3de7ddc08
3
+ size 4967215360
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5cfc5172dd5af21330400c6e6e795297bc082089c21a2c948ff400b201488ed
3
+ size 3077766632
model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4022468096,
4
+ "total_size": 8044936192
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
344
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
351
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
358
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
366
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.norm.weight": "model-00002-of-00002.safetensors"
405
+ }
406
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 262144,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
trainer_state.json ADDED
@@ -0,0 +1,1594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 200,
3
+ "best_metric": 0.0016466762172058225,
4
+ "best_model_checkpoint": "unified_sft_output/checkpoint-200",
5
+ "epoch": 50.0,
6
+ "eval_steps": 10,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.27586206896551724,
14
+ "grad_norm": 11.375,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.2371,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.5517241379310345,
21
+ "grad_norm": 10.75,
22
+ "learning_rate": 5.000000000000001e-07,
23
+ "loss": 1.249,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.8275862068965517,
28
+ "grad_norm": 12.375,
29
+ "learning_rate": 1.0000000000000002e-06,
30
+ "loss": 1.4344,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "grad_norm": 12.25,
36
+ "learning_rate": 1.5e-06,
37
+ "loss": 1.2445,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 1.2758620689655173,
42
+ "grad_norm": 10.1875,
43
+ "learning_rate": 2.0000000000000003e-06,
44
+ "loss": 1.1814,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 1.5517241379310345,
49
+ "grad_norm": 13.25,
50
+ "learning_rate": 2.5e-06,
51
+ "loss": 1.2665,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 1.8275862068965516,
56
+ "grad_norm": 21.375,
57
+ "learning_rate": 3e-06,
58
+ "loss": 1.3003,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 2.0,
63
+ "grad_norm": 12.0625,
64
+ "learning_rate": 3.5e-06,
65
+ "loss": 1.4292,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 2.2758620689655173,
70
+ "grad_norm": 10.8125,
71
+ "learning_rate": 4.000000000000001e-06,
72
+ "loss": 1.1558,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 2.5517241379310347,
77
+ "grad_norm": 8.375,
78
+ "learning_rate": 4.5e-06,
79
+ "loss": 1.2145,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 2.5517241379310347,
84
+ "eval_loss": 1.21233069896698,
85
+ "eval_runtime": 1.7228,
86
+ "eval_samples_per_second": 1.741,
87
+ "eval_steps_per_second": 1.741,
88
+ "step": 10
89
+ },
90
+ {
91
+ "epoch": 2.8275862068965516,
92
+ "grad_norm": 8.8125,
93
+ "learning_rate": 5e-06,
94
+ "loss": 1.2393,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 3.0,
99
+ "grad_norm": 6.875,
100
+ "learning_rate": 5.500000000000001e-06,
101
+ "loss": 1.1221,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 3.2758620689655173,
106
+ "grad_norm": 5.5625,
107
+ "learning_rate": 6e-06,
108
+ "loss": 1.0858,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 3.5517241379310347,
113
+ "grad_norm": 5.59375,
114
+ "learning_rate": 6.5000000000000004e-06,
115
+ "loss": 1.1747,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 3.8275862068965516,
120
+ "grad_norm": 3.625,
121
+ "learning_rate": 7e-06,
122
+ "loss": 0.9076,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 4.0,
127
+ "grad_norm": 4.53125,
128
+ "learning_rate": 7.500000000000001e-06,
129
+ "loss": 1.1572,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 4.275862068965517,
134
+ "grad_norm": 3.453125,
135
+ "learning_rate": 8.000000000000001e-06,
136
+ "loss": 1.0446,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 4.551724137931035,
141
+ "grad_norm": 3.078125,
142
+ "learning_rate": 8.5e-06,
143
+ "loss": 1.011,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 4.827586206896552,
148
+ "grad_norm": 2.375,
149
+ "learning_rate": 9e-06,
150
+ "loss": 0.9294,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 5.0,
155
+ "grad_norm": 1.9453125,
156
+ "learning_rate": 9.5e-06,
157
+ "loss": 0.7185,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 5.0,
162
+ "eval_loss": 0.8018922209739685,
163
+ "eval_runtime": 1.7241,
164
+ "eval_samples_per_second": 1.74,
165
+ "eval_steps_per_second": 1.74,
166
+ "step": 20
167
+ },
168
+ {
169
+ "epoch": 5.275862068965517,
170
+ "grad_norm": 2.453125,
171
+ "learning_rate": 1e-05,
172
+ "loss": 0.8795,
173
+ "step": 21
174
+ },
175
+ {
176
+ "epoch": 5.551724137931035,
177
+ "grad_norm": 1.90625,
178
+ "learning_rate": 1.0500000000000001e-05,
179
+ "loss": 0.8248,
180
+ "step": 22
181
+ },
182
+ {
183
+ "epoch": 5.827586206896552,
184
+ "grad_norm": 1.7421875,
185
+ "learning_rate": 1.1000000000000001e-05,
186
+ "loss": 0.6881,
187
+ "step": 23
188
+ },
189
+ {
190
+ "epoch": 6.0,
191
+ "grad_norm": 1.671875,
192
+ "learning_rate": 1.15e-05,
193
+ "loss": 0.7153,
194
+ "step": 24
195
+ },
196
+ {
197
+ "epoch": 6.275862068965517,
198
+ "grad_norm": 3.125,
199
+ "learning_rate": 1.2e-05,
200
+ "loss": 0.6096,
201
+ "step": 25
202
+ },
203
+ {
204
+ "epoch": 6.551724137931035,
205
+ "grad_norm": 1.5234375,
206
+ "learning_rate": 1.25e-05,
207
+ "loss": 0.6779,
208
+ "step": 26
209
+ },
210
+ {
211
+ "epoch": 6.827586206896552,
212
+ "grad_norm": 2.15625,
213
+ "learning_rate": 1.3000000000000001e-05,
214
+ "loss": 0.6229,
215
+ "step": 27
216
+ },
217
+ {
218
+ "epoch": 7.0,
219
+ "grad_norm": 1.2265625,
220
+ "learning_rate": 1.3500000000000001e-05,
221
+ "loss": 0.5901,
222
+ "step": 28
223
+ },
224
+ {
225
+ "epoch": 7.275862068965517,
226
+ "grad_norm": 1.203125,
227
+ "learning_rate": 1.4e-05,
228
+ "loss": 0.593,
229
+ "step": 29
230
+ },
231
+ {
232
+ "epoch": 7.551724137931035,
233
+ "grad_norm": 1.4296875,
234
+ "learning_rate": 1.45e-05,
235
+ "loss": 0.5158,
236
+ "step": 30
237
+ },
238
+ {
239
+ "epoch": 7.551724137931035,
240
+ "eval_loss": 0.4224577248096466,
241
+ "eval_runtime": 1.7416,
242
+ "eval_samples_per_second": 1.723,
243
+ "eval_steps_per_second": 1.723,
244
+ "step": 30
245
+ },
246
+ {
247
+ "epoch": 7.827586206896552,
248
+ "grad_norm": 1.0625,
249
+ "learning_rate": 1.5000000000000002e-05,
250
+ "loss": 0.4175,
251
+ "step": 31
252
+ },
253
+ {
254
+ "epoch": 8.0,
255
+ "grad_norm": 0.96484375,
256
+ "learning_rate": 1.55e-05,
257
+ "loss": 0.478,
258
+ "step": 32
259
+ },
260
+ {
261
+ "epoch": 8.275862068965518,
262
+ "grad_norm": 0.79296875,
263
+ "learning_rate": 1.6000000000000003e-05,
264
+ "loss": 0.4238,
265
+ "step": 33
266
+ },
267
+ {
268
+ "epoch": 8.551724137931034,
269
+ "grad_norm": 1.0703125,
270
+ "learning_rate": 1.65e-05,
271
+ "loss": 0.4365,
272
+ "step": 34
273
+ },
274
+ {
275
+ "epoch": 8.827586206896552,
276
+ "grad_norm": 0.9453125,
277
+ "learning_rate": 1.7e-05,
278
+ "loss": 0.3686,
279
+ "step": 35
280
+ },
281
+ {
282
+ "epoch": 9.0,
283
+ "grad_norm": 2.328125,
284
+ "learning_rate": 1.7500000000000002e-05,
285
+ "loss": 0.4172,
286
+ "step": 36
287
+ },
288
+ {
289
+ "epoch": 9.275862068965518,
290
+ "grad_norm": 0.73046875,
291
+ "learning_rate": 1.8e-05,
292
+ "loss": 0.3731,
293
+ "step": 37
294
+ },
295
+ {
296
+ "epoch": 9.551724137931034,
297
+ "grad_norm": 0.953125,
298
+ "learning_rate": 1.8500000000000002e-05,
299
+ "loss": 0.3885,
300
+ "step": 38
301
+ },
302
+ {
303
+ "epoch": 9.827586206896552,
304
+ "grad_norm": 0.79296875,
305
+ "learning_rate": 1.9e-05,
306
+ "loss": 0.3008,
307
+ "step": 39
308
+ },
309
+ {
310
+ "epoch": 10.0,
311
+ "grad_norm": 1.265625,
312
+ "learning_rate": 1.95e-05,
313
+ "loss": 0.2395,
314
+ "step": 40
315
+ },
316
+ {
317
+ "epoch": 10.0,
318
+ "eval_loss": 0.21218304336071014,
319
+ "eval_runtime": 1.7107,
320
+ "eval_samples_per_second": 1.754,
321
+ "eval_steps_per_second": 1.754,
322
+ "step": 40
323
+ },
324
+ {
325
+ "epoch": 10.275862068965518,
326
+ "grad_norm": 0.91796875,
327
+ "learning_rate": 2e-05,
328
+ "loss": 0.2379,
329
+ "step": 41
330
+ },
331
+ {
332
+ "epoch": 10.551724137931034,
333
+ "grad_norm": 0.859375,
334
+ "learning_rate": 1.9999619230641714e-05,
335
+ "loss": 0.267,
336
+ "step": 42
337
+ },
338
+ {
339
+ "epoch": 10.827586206896552,
340
+ "grad_norm": 0.953125,
341
+ "learning_rate": 1.9998476951563914e-05,
342
+ "loss": 0.2913,
343
+ "step": 43
344
+ },
345
+ {
346
+ "epoch": 11.0,
347
+ "grad_norm": 1.2578125,
348
+ "learning_rate": 1.9996573249755573e-05,
349
+ "loss": 0.2742,
350
+ "step": 44
351
+ },
352
+ {
353
+ "epoch": 11.275862068965518,
354
+ "grad_norm": 0.875,
355
+ "learning_rate": 1.999390827019096e-05,
356
+ "loss": 0.1832,
357
+ "step": 45
358
+ },
359
+ {
360
+ "epoch": 11.551724137931034,
361
+ "grad_norm": 0.87890625,
362
+ "learning_rate": 1.999048221581858e-05,
363
+ "loss": 0.2744,
364
+ "step": 46
365
+ },
366
+ {
367
+ "epoch": 11.827586206896552,
368
+ "grad_norm": 1.1875,
369
+ "learning_rate": 1.9986295347545738e-05,
370
+ "loss": 0.1503,
371
+ "step": 47
372
+ },
373
+ {
374
+ "epoch": 12.0,
375
+ "grad_norm": 1.3125,
376
+ "learning_rate": 1.998134798421867e-05,
377
+ "loss": 0.1235,
378
+ "step": 48
379
+ },
380
+ {
381
+ "epoch": 12.275862068965518,
382
+ "grad_norm": 0.82421875,
383
+ "learning_rate": 1.9975640502598243e-05,
384
+ "loss": 0.1688,
385
+ "step": 49
386
+ },
387
+ {
388
+ "epoch": 12.551724137931034,
389
+ "grad_norm": 0.8671875,
390
+ "learning_rate": 1.9969173337331283e-05,
391
+ "loss": 0.1676,
392
+ "step": 50
393
+ },
394
+ {
395
+ "epoch": 12.551724137931034,
396
+ "eval_loss": 0.09635955095291138,
397
+ "eval_runtime": 1.7755,
398
+ "eval_samples_per_second": 1.69,
399
+ "eval_steps_per_second": 1.69,
400
+ "step": 50
401
+ },
402
+ {
403
+ "epoch": 12.827586206896552,
404
+ "grad_norm": 1.1953125,
405
+ "learning_rate": 1.9961946980917457e-05,
406
+ "loss": 0.0832,
407
+ "step": 51
408
+ },
409
+ {
410
+ "epoch": 13.0,
411
+ "grad_norm": 1.2734375,
412
+ "learning_rate": 1.9953961983671792e-05,
413
+ "loss": 0.1309,
414
+ "step": 52
415
+ },
416
+ {
417
+ "epoch": 13.275862068965518,
418
+ "grad_norm": 0.78125,
419
+ "learning_rate": 1.9945218953682736e-05,
420
+ "loss": 0.0907,
421
+ "step": 53
422
+ },
423
+ {
424
+ "epoch": 13.551724137931034,
425
+ "grad_norm": 0.796875,
426
+ "learning_rate": 1.9935718556765878e-05,
427
+ "loss": 0.094,
428
+ "step": 54
429
+ },
430
+ {
431
+ "epoch": 13.827586206896552,
432
+ "grad_norm": 1.0703125,
433
+ "learning_rate": 1.9925461516413224e-05,
434
+ "loss": 0.0985,
435
+ "step": 55
436
+ },
437
+ {
438
+ "epoch": 14.0,
439
+ "grad_norm": 1.265625,
440
+ "learning_rate": 1.9914448613738107e-05,
441
+ "loss": 0.1094,
442
+ "step": 56
443
+ },
444
+ {
445
+ "epoch": 14.275862068965518,
446
+ "grad_norm": 0.66015625,
447
+ "learning_rate": 1.9902680687415704e-05,
448
+ "loss": 0.0448,
449
+ "step": 57
450
+ },
451
+ {
452
+ "epoch": 14.551724137931034,
453
+ "grad_norm": 1.0078125,
454
+ "learning_rate": 1.989015863361917e-05,
455
+ "loss": 0.0836,
456
+ "step": 58
457
+ },
458
+ {
459
+ "epoch": 14.827586206896552,
460
+ "grad_norm": 0.8125,
461
+ "learning_rate": 1.9876883405951378e-05,
462
+ "loss": 0.0687,
463
+ "step": 59
464
+ },
465
+ {
466
+ "epoch": 15.0,
467
+ "grad_norm": 0.7890625,
468
+ "learning_rate": 1.9862856015372315e-05,
469
+ "loss": 0.0276,
470
+ "step": 60
471
+ },
472
+ {
473
+ "epoch": 15.0,
474
+ "eval_loss": 0.03497372567653656,
475
+ "eval_runtime": 1.7662,
476
+ "eval_samples_per_second": 1.699,
477
+ "eval_steps_per_second": 1.699,
478
+ "step": 60
479
+ },
480
+ {
481
+ "epoch": 15.275862068965518,
482
+ "grad_norm": 0.7265625,
483
+ "learning_rate": 1.9848077530122083e-05,
484
+ "loss": 0.0395,
485
+ "step": 61
486
+ },
487
+ {
488
+ "epoch": 15.551724137931034,
489
+ "grad_norm": 0.51953125,
490
+ "learning_rate": 1.983254907563955e-05,
491
+ "loss": 0.0248,
492
+ "step": 62
493
+ },
494
+ {
495
+ "epoch": 15.827586206896552,
496
+ "grad_norm": 1.1640625,
497
+ "learning_rate": 1.9816271834476642e-05,
498
+ "loss": 0.0355,
499
+ "step": 63
500
+ },
501
+ {
502
+ "epoch": 16.0,
503
+ "grad_norm": 0.80859375,
504
+ "learning_rate": 1.9799247046208297e-05,
505
+ "loss": 0.035,
506
+ "step": 64
507
+ },
508
+ {
509
+ "epoch": 16.275862068965516,
510
+ "grad_norm": 0.494140625,
511
+ "learning_rate": 1.9781476007338058e-05,
512
+ "loss": 0.0172,
513
+ "step": 65
514
+ },
515
+ {
516
+ "epoch": 16.551724137931036,
517
+ "grad_norm": 0.59765625,
518
+ "learning_rate": 1.9762960071199334e-05,
519
+ "loss": 0.0216,
520
+ "step": 66
521
+ },
522
+ {
523
+ "epoch": 16.82758620689655,
524
+ "grad_norm": 0.984375,
525
+ "learning_rate": 1.9743700647852356e-05,
526
+ "loss": 0.0215,
527
+ "step": 67
528
+ },
529
+ {
530
+ "epoch": 17.0,
531
+ "grad_norm": 0.875,
532
+ "learning_rate": 1.9723699203976768e-05,
533
+ "loss": 0.0206,
534
+ "step": 68
535
+ },
536
+ {
537
+ "epoch": 17.275862068965516,
538
+ "grad_norm": 0.49609375,
539
+ "learning_rate": 1.9702957262759964e-05,
540
+ "loss": 0.0142,
541
+ "step": 69
542
+ },
543
+ {
544
+ "epoch": 17.551724137931036,
545
+ "grad_norm": 0.546875,
546
+ "learning_rate": 1.968147640378108e-05,
547
+ "loss": 0.0107,
548
+ "step": 70
549
+ },
550
+ {
551
+ "epoch": 17.551724137931036,
552
+ "eval_loss": 0.010336539708077908,
553
+ "eval_runtime": 1.7352,
554
+ "eval_samples_per_second": 1.729,
555
+ "eval_steps_per_second": 1.729,
556
+ "step": 70
557
+ },
558
+ {
559
+ "epoch": 17.82758620689655,
560
+ "grad_norm": 0.50390625,
561
+ "learning_rate": 1.9659258262890683e-05,
562
+ "loss": 0.0105,
563
+ "step": 71
564
+ },
565
+ {
566
+ "epoch": 18.0,
567
+ "grad_norm": 0.58203125,
568
+ "learning_rate": 1.963630453208623e-05,
569
+ "loss": 0.012,
570
+ "step": 72
571
+ },
572
+ {
573
+ "epoch": 18.275862068965516,
574
+ "grad_norm": 0.361328125,
575
+ "learning_rate": 1.961261695938319e-05,
576
+ "loss": 0.0079,
577
+ "step": 73
578
+ },
579
+ {
580
+ "epoch": 18.551724137931036,
581
+ "grad_norm": 0.376953125,
582
+ "learning_rate": 1.958819734868193e-05,
583
+ "loss": 0.0083,
584
+ "step": 74
585
+ },
586
+ {
587
+ "epoch": 18.82758620689655,
588
+ "grad_norm": 0.2734375,
589
+ "learning_rate": 1.9563047559630356e-05,
590
+ "loss": 0.0072,
591
+ "step": 75
592
+ },
593
+ {
594
+ "epoch": 19.0,
595
+ "grad_norm": 0.310546875,
596
+ "learning_rate": 1.953716950748227e-05,
597
+ "loss": 0.0072,
598
+ "step": 76
599
+ },
600
+ {
601
+ "epoch": 19.275862068965516,
602
+ "grad_norm": 0.2392578125,
603
+ "learning_rate": 1.9510565162951538e-05,
604
+ "loss": 0.006,
605
+ "step": 77
606
+ },
607
+ {
608
+ "epoch": 19.551724137931036,
609
+ "grad_norm": 0.259765625,
610
+ "learning_rate": 1.9483236552061996e-05,
611
+ "loss": 0.0056,
612
+ "step": 78
613
+ },
614
+ {
615
+ "epoch": 19.82758620689655,
616
+ "grad_norm": 0.28125,
617
+ "learning_rate": 1.945518575599317e-05,
618
+ "loss": 0.005,
619
+ "step": 79
620
+ },
621
+ {
622
+ "epoch": 20.0,
623
+ "grad_norm": 0.439453125,
624
+ "learning_rate": 1.9426414910921785e-05,
625
+ "loss": 0.0061,
626
+ "step": 80
627
+ },
628
+ {
629
+ "epoch": 20.0,
630
+ "eval_loss": 0.005222354084253311,
631
+ "eval_runtime": 1.7373,
632
+ "eval_samples_per_second": 1.727,
633
+ "eval_steps_per_second": 1.727,
634
+ "step": 80
635
+ },
636
+ {
637
+ "epoch": 20.275862068965516,
638
+ "grad_norm": 0.2353515625,
639
+ "learning_rate": 1.9396926207859085e-05,
640
+ "loss": 0.0047,
641
+ "step": 81
642
+ },
643
+ {
644
+ "epoch": 20.551724137931036,
645
+ "grad_norm": 0.16796875,
646
+ "learning_rate": 1.9366721892483976e-05,
647
+ "loss": 0.0034,
648
+ "step": 82
649
+ },
650
+ {
651
+ "epoch": 20.82758620689655,
652
+ "grad_norm": 0.609375,
653
+ "learning_rate": 1.9335804264972018e-05,
654
+ "loss": 0.0056,
655
+ "step": 83
656
+ },
657
+ {
658
+ "epoch": 21.0,
659
+ "grad_norm": 0.1884765625,
660
+ "learning_rate": 1.9304175679820247e-05,
661
+ "loss": 0.0043,
662
+ "step": 84
663
+ },
664
+ {
665
+ "epoch": 21.275862068965516,
666
+ "grad_norm": 0.1630859375,
667
+ "learning_rate": 1.9271838545667876e-05,
668
+ "loss": 0.0031,
669
+ "step": 85
670
+ },
671
+ {
672
+ "epoch": 21.551724137931036,
673
+ "grad_norm": 0.1552734375,
674
+ "learning_rate": 1.9238795325112867e-05,
675
+ "loss": 0.0041,
676
+ "step": 86
677
+ },
678
+ {
679
+ "epoch": 21.82758620689655,
680
+ "grad_norm": 0.189453125,
681
+ "learning_rate": 1.9205048534524405e-05,
682
+ "loss": 0.0034,
683
+ "step": 87
684
+ },
685
+ {
686
+ "epoch": 22.0,
687
+ "grad_norm": 0.36328125,
688
+ "learning_rate": 1.917060074385124e-05,
689
+ "loss": 0.0043,
690
+ "step": 88
691
+ },
692
+ {
693
+ "epoch": 22.275862068965516,
694
+ "grad_norm": 0.1279296875,
695
+ "learning_rate": 1.913545457642601e-05,
696
+ "loss": 0.003,
697
+ "step": 89
698
+ },
699
+ {
700
+ "epoch": 22.551724137931036,
701
+ "grad_norm": 0.1513671875,
702
+ "learning_rate": 1.9099612708765432e-05,
703
+ "loss": 0.0033,
704
+ "step": 90
705
+ },
706
+ {
707
+ "epoch": 22.551724137931036,
708
+ "eval_loss": 0.0038691603112965822,
709
+ "eval_runtime": 1.7266,
710
+ "eval_samples_per_second": 1.738,
711
+ "eval_steps_per_second": 1.738,
712
+ "step": 90
713
+ },
714
+ {
715
+ "epoch": 22.82758620689655,
716
+ "grad_norm": 0.1689453125,
717
+ "learning_rate": 1.9063077870366504e-05,
718
+ "loss": 0.0029,
719
+ "step": 91
720
+ },
721
+ {
722
+ "epoch": 23.0,
723
+ "grad_norm": 0.1435546875,
724
+ "learning_rate": 1.902585284349861e-05,
725
+ "loss": 0.0032,
726
+ "step": 92
727
+ },
728
+ {
729
+ "epoch": 23.275862068965516,
730
+ "grad_norm": 0.1376953125,
731
+ "learning_rate": 1.8987940462991673e-05,
732
+ "loss": 0.003,
733
+ "step": 93
734
+ },
735
+ {
736
+ "epoch": 23.551724137931036,
737
+ "grad_norm": 0.1083984375,
738
+ "learning_rate": 1.894934361602025e-05,
739
+ "loss": 0.0024,
740
+ "step": 94
741
+ },
742
+ {
743
+ "epoch": 23.82758620689655,
744
+ "grad_norm": 0.08203125,
745
+ "learning_rate": 1.891006524188368e-05,
746
+ "loss": 0.0026,
747
+ "step": 95
748
+ },
749
+ {
750
+ "epoch": 24.0,
751
+ "grad_norm": 0.1748046875,
752
+ "learning_rate": 1.887010833178222e-05,
753
+ "loss": 0.0031,
754
+ "step": 96
755
+ },
756
+ {
757
+ "epoch": 24.275862068965516,
758
+ "grad_norm": 0.11474609375,
759
+ "learning_rate": 1.8829475928589272e-05,
760
+ "loss": 0.0026,
761
+ "step": 97
762
+ },
763
+ {
764
+ "epoch": 24.551724137931036,
765
+ "grad_norm": 0.109375,
766
+ "learning_rate": 1.8788171126619653e-05,
767
+ "loss": 0.002,
768
+ "step": 98
769
+ },
770
+ {
771
+ "epoch": 24.82758620689655,
772
+ "grad_norm": 0.1123046875,
773
+ "learning_rate": 1.874619707139396e-05,
774
+ "loss": 0.0026,
775
+ "step": 99
776
+ },
777
+ {
778
+ "epoch": 25.0,
779
+ "grad_norm": 0.09912109375,
780
+ "learning_rate": 1.8703556959398998e-05,
781
+ "loss": 0.0025,
782
+ "step": 100
783
+ },
784
+ {
785
+ "epoch": 25.0,
786
+ "eval_loss": 0.0027635388541966677,
787
+ "eval_runtime": 1.7315,
788
+ "eval_samples_per_second": 1.733,
789
+ "eval_steps_per_second": 1.733,
790
+ "step": 100
791
+ },
792
+ {
793
+ "epoch": 25.275862068965516,
794
+ "grad_norm": 0.0986328125,
795
+ "learning_rate": 1.866025403784439e-05,
796
+ "loss": 0.0022,
797
+ "step": 101
798
+ },
799
+ {
800
+ "epoch": 25.551724137931036,
801
+ "grad_norm": 0.08837890625,
802
+ "learning_rate": 1.861629160441526e-05,
803
+ "loss": 0.0024,
804
+ "step": 102
805
+ },
806
+ {
807
+ "epoch": 25.82758620689655,
808
+ "grad_norm": 0.09814453125,
809
+ "learning_rate": 1.8571673007021124e-05,
810
+ "loss": 0.002,
811
+ "step": 103
812
+ },
813
+ {
814
+ "epoch": 26.0,
815
+ "grad_norm": 0.103515625,
816
+ "learning_rate": 1.8526401643540924e-05,
817
+ "loss": 0.0023,
818
+ "step": 104
819
+ },
820
+ {
821
+ "epoch": 26.275862068965516,
822
+ "grad_norm": 0.09716796875,
823
+ "learning_rate": 1.848048096156426e-05,
824
+ "loss": 0.0021,
825
+ "step": 105
826
+ },
827
+ {
828
+ "epoch": 26.551724137931036,
829
+ "grad_norm": 0.0830078125,
830
+ "learning_rate": 1.843391445812886e-05,
831
+ "loss": 0.0021,
832
+ "step": 106
833
+ },
834
+ {
835
+ "epoch": 26.82758620689655,
836
+ "grad_norm": 0.06982421875,
837
+ "learning_rate": 1.8386705679454243e-05,
838
+ "loss": 0.0021,
839
+ "step": 107
840
+ },
841
+ {
842
+ "epoch": 27.0,
843
+ "grad_norm": 0.1494140625,
844
+ "learning_rate": 1.8338858220671683e-05,
845
+ "loss": 0.0022,
846
+ "step": 108
847
+ },
848
+ {
849
+ "epoch": 27.275862068965516,
850
+ "grad_norm": 0.09423828125,
851
+ "learning_rate": 1.8290375725550417e-05,
852
+ "loss": 0.0025,
853
+ "step": 109
854
+ },
855
+ {
856
+ "epoch": 27.551724137931036,
857
+ "grad_norm": 0.06982421875,
858
+ "learning_rate": 1.8241261886220155e-05,
859
+ "loss": 0.0019,
860
+ "step": 110
861
+ },
862
+ {
863
+ "epoch": 27.551724137931036,
864
+ "eval_loss": 0.0022178783547133207,
865
+ "eval_runtime": 1.7843,
866
+ "eval_samples_per_second": 1.681,
867
+ "eval_steps_per_second": 1.681,
868
+ "step": 110
869
+ },
870
+ {
871
+ "epoch": 27.82758620689655,
872
+ "grad_norm": 0.14453125,
873
+ "learning_rate": 1.819152044288992e-05,
874
+ "loss": 0.0022,
875
+ "step": 111
876
+ },
877
+ {
878
+ "epoch": 28.0,
879
+ "grad_norm": 0.06689453125,
880
+ "learning_rate": 1.8141155183563195e-05,
881
+ "loss": 0.0016,
882
+ "step": 112
883
+ },
884
+ {
885
+ "epoch": 28.275862068965516,
886
+ "grad_norm": 0.0771484375,
887
+ "learning_rate": 1.8090169943749477e-05,
888
+ "loss": 0.002,
889
+ "step": 113
890
+ },
891
+ {
892
+ "epoch": 28.551724137931036,
893
+ "grad_norm": 0.06298828125,
894
+ "learning_rate": 1.8038568606172172e-05,
895
+ "loss": 0.0018,
896
+ "step": 114
897
+ },
898
+ {
899
+ "epoch": 28.82758620689655,
900
+ "grad_norm": 0.07958984375,
901
+ "learning_rate": 1.798635510047293e-05,
902
+ "loss": 0.0017,
903
+ "step": 115
904
+ },
905
+ {
906
+ "epoch": 29.0,
907
+ "grad_norm": 0.16015625,
908
+ "learning_rate": 1.7933533402912354e-05,
909
+ "loss": 0.0022,
910
+ "step": 116
911
+ },
912
+ {
913
+ "epoch": 29.275862068965516,
914
+ "grad_norm": 0.07373046875,
915
+ "learning_rate": 1.788010753606722e-05,
916
+ "loss": 0.0018,
917
+ "step": 117
918
+ },
919
+ {
920
+ "epoch": 29.551724137931036,
921
+ "grad_norm": 0.07861328125,
922
+ "learning_rate": 1.782608156852414e-05,
923
+ "loss": 0.002,
924
+ "step": 118
925
+ },
926
+ {
927
+ "epoch": 29.82758620689655,
928
+ "grad_norm": 0.0634765625,
929
+ "learning_rate": 1.777145961456971e-05,
930
+ "loss": 0.0017,
931
+ "step": 119
932
+ },
933
+ {
934
+ "epoch": 30.0,
935
+ "grad_norm": 0.14453125,
936
+ "learning_rate": 1.7716245833877202e-05,
937
+ "loss": 0.0019,
938
+ "step": 120
939
+ },
940
+ {
941
+ "epoch": 30.0,
942
+ "eval_loss": 0.001993604702875018,
943
+ "eval_runtime": 1.7303,
944
+ "eval_samples_per_second": 1.734,
945
+ "eval_steps_per_second": 1.734,
946
+ "step": 120
947
+ },
948
+ {
949
+ "epoch": 30.275862068965516,
950
+ "grad_norm": 0.06884765625,
951
+ "learning_rate": 1.766044443118978e-05,
952
+ "loss": 0.0018,
953
+ "step": 121
954
+ },
955
+ {
956
+ "epoch": 30.551724137931036,
957
+ "grad_norm": 0.064453125,
958
+ "learning_rate": 1.7604059656000313e-05,
959
+ "loss": 0.0015,
960
+ "step": 122
961
+ },
962
+ {
963
+ "epoch": 30.82758620689655,
964
+ "grad_norm": 0.119140625,
965
+ "learning_rate": 1.7547095802227723e-05,
966
+ "loss": 0.002,
967
+ "step": 123
968
+ },
969
+ {
970
+ "epoch": 31.0,
971
+ "grad_norm": 0.09814453125,
972
+ "learning_rate": 1.7489557207890025e-05,
973
+ "loss": 0.0021,
974
+ "step": 124
975
+ },
976
+ {
977
+ "epoch": 31.275862068965516,
978
+ "grad_norm": 0.0703125,
979
+ "learning_rate": 1.7431448254773943e-05,
980
+ "loss": 0.0015,
981
+ "step": 125
982
+ },
983
+ {
984
+ "epoch": 31.551724137931036,
985
+ "grad_norm": 0.0810546875,
986
+ "learning_rate": 1.737277336810124e-05,
987
+ "loss": 0.0017,
988
+ "step": 126
989
+ },
990
+ {
991
+ "epoch": 31.82758620689655,
992
+ "grad_norm": 0.0810546875,
993
+ "learning_rate": 1.7313537016191706e-05,
994
+ "loss": 0.0018,
995
+ "step": 127
996
+ },
997
+ {
998
+ "epoch": 32.0,
999
+ "grad_norm": 0.10302734375,
1000
+ "learning_rate": 1.7253743710122877e-05,
1001
+ "loss": 0.0021,
1002
+ "step": 128
1003
+ },
1004
+ {
1005
+ "epoch": 32.275862068965516,
1006
+ "grad_norm": 0.07080078125,
1007
+ "learning_rate": 1.7193398003386514e-05,
1008
+ "loss": 0.0016,
1009
+ "step": 129
1010
+ },
1011
+ {
1012
+ "epoch": 32.55172413793103,
1013
+ "grad_norm": 0.08349609375,
1014
+ "learning_rate": 1.713250449154182e-05,
1015
+ "loss": 0.0019,
1016
+ "step": 130
1017
+ },
1018
+ {
1019
+ "epoch": 32.55172413793103,
1020
+ "eval_loss": 0.0018896261462941766,
1021
+ "eval_runtime": 1.787,
1022
+ "eval_samples_per_second": 1.679,
1023
+ "eval_steps_per_second": 1.679,
1024
+ "step": 130
1025
+ },
1026
+ {
1027
+ "epoch": 32.827586206896555,
1028
+ "grad_norm": 0.0625,
1029
+ "learning_rate": 1.7071067811865477e-05,
1030
+ "loss": 0.0016,
1031
+ "step": 131
1032
+ },
1033
+ {
1034
+ "epoch": 33.0,
1035
+ "grad_norm": 0.11865234375,
1036
+ "learning_rate": 1.700909264299851e-05,
1037
+ "loss": 0.0015,
1038
+ "step": 132
1039
+ },
1040
+ {
1041
+ "epoch": 33.275862068965516,
1042
+ "grad_norm": 0.09326171875,
1043
+ "learning_rate": 1.6946583704589973e-05,
1044
+ "loss": 0.0016,
1045
+ "step": 133
1046
+ },
1047
+ {
1048
+ "epoch": 33.55172413793103,
1049
+ "grad_norm": 0.056396484375,
1050
+ "learning_rate": 1.688354575693754e-05,
1051
+ "loss": 0.0015,
1052
+ "step": 134
1053
+ },
1054
+ {
1055
+ "epoch": 33.827586206896555,
1056
+ "grad_norm": 0.0615234375,
1057
+ "learning_rate": 1.6819983600624986e-05,
1058
+ "loss": 0.0018,
1059
+ "step": 135
1060
+ },
1061
+ {
1062
+ "epoch": 34.0,
1063
+ "grad_norm": 0.1123046875,
1064
+ "learning_rate": 1.6755902076156606e-05,
1065
+ "loss": 0.0015,
1066
+ "step": 136
1067
+ },
1068
+ {
1069
+ "epoch": 34.275862068965516,
1070
+ "grad_norm": 0.0810546875,
1071
+ "learning_rate": 1.6691306063588583e-05,
1072
+ "loss": 0.0015,
1073
+ "step": 137
1074
+ },
1075
+ {
1076
+ "epoch": 34.55172413793103,
1077
+ "grad_norm": 0.06591796875,
1078
+ "learning_rate": 1.6626200482157378e-05,
1079
+ "loss": 0.0017,
1080
+ "step": 138
1081
+ },
1082
+ {
1083
+ "epoch": 34.827586206896555,
1084
+ "grad_norm": 0.0703125,
1085
+ "learning_rate": 1.6560590289905074e-05,
1086
+ "loss": 0.0016,
1087
+ "step": 139
1088
+ },
1089
+ {
1090
+ "epoch": 35.0,
1091
+ "grad_norm": 0.08544921875,
1092
+ "learning_rate": 1.6494480483301836e-05,
1093
+ "loss": 0.0018,
1094
+ "step": 140
1095
+ },
1096
+ {
1097
+ "epoch": 35.0,
1098
+ "eval_loss": 0.0019512426806613803,
1099
+ "eval_runtime": 1.7323,
1100
+ "eval_samples_per_second": 1.732,
1101
+ "eval_steps_per_second": 1.732,
1102
+ "step": 140
1103
+ },
1104
+ {
1105
+ "epoch": 35.275862068965516,
1106
+ "grad_norm": 0.0498046875,
1107
+ "learning_rate": 1.6427876096865394e-05,
1108
+ "loss": 0.0015,
1109
+ "step": 141
1110
+ },
1111
+ {
1112
+ "epoch": 35.55172413793103,
1113
+ "grad_norm": 0.1044921875,
1114
+ "learning_rate": 1.636078220277764e-05,
1115
+ "loss": 0.0017,
1116
+ "step": 142
1117
+ },
1118
+ {
1119
+ "epoch": 35.827586206896555,
1120
+ "grad_norm": 0.0927734375,
1121
+ "learning_rate": 1.6293203910498375e-05,
1122
+ "loss": 0.0019,
1123
+ "step": 143
1124
+ },
1125
+ {
1126
+ "epoch": 36.0,
1127
+ "grad_norm": 0.10595703125,
1128
+ "learning_rate": 1.6225146366376198e-05,
1129
+ "loss": 0.0014,
1130
+ "step": 144
1131
+ },
1132
+ {
1133
+ "epoch": 36.275862068965516,
1134
+ "grad_norm": 0.057373046875,
1135
+ "learning_rate": 1.6156614753256583e-05,
1136
+ "loss": 0.0017,
1137
+ "step": 145
1138
+ },
1139
+ {
1140
+ "epoch": 36.55172413793103,
1141
+ "grad_norm": 0.07470703125,
1142
+ "learning_rate": 1.608761429008721e-05,
1143
+ "loss": 0.0014,
1144
+ "step": 146
1145
+ },
1146
+ {
1147
+ "epoch": 36.827586206896555,
1148
+ "grad_norm": 0.0712890625,
1149
+ "learning_rate": 1.6018150231520486e-05,
1150
+ "loss": 0.0014,
1151
+ "step": 147
1152
+ },
1153
+ {
1154
+ "epoch": 37.0,
1155
+ "grad_norm": 0.11328125,
1156
+ "learning_rate": 1.5948227867513416e-05,
1157
+ "loss": 0.0017,
1158
+ "step": 148
1159
+ },
1160
+ {
1161
+ "epoch": 37.275862068965516,
1162
+ "grad_norm": 0.06103515625,
1163
+ "learning_rate": 1.5877852522924733e-05,
1164
+ "loss": 0.0016,
1165
+ "step": 149
1166
+ },
1167
+ {
1168
+ "epoch": 37.55172413793103,
1169
+ "grad_norm": 0.08056640625,
1170
+ "learning_rate": 1.5807029557109398e-05,
1171
+ "loss": 0.0016,
1172
+ "step": 150
1173
+ },
1174
+ {
1175
+ "epoch": 37.55172413793103,
1176
+ "eval_loss": 0.001894477754831314,
1177
+ "eval_runtime": 1.7336,
1178
+ "eval_samples_per_second": 1.731,
1179
+ "eval_steps_per_second": 1.731,
1180
+ "step": 150
1181
+ },
1182
+ {
1183
+ "epoch": 37.827586206896555,
1184
+ "grad_norm": 0.06982421875,
1185
+ "learning_rate": 1.573576436351046e-05,
1186
+ "loss": 0.0016,
1187
+ "step": 151
1188
+ },
1189
+ {
1190
+ "epoch": 38.0,
1191
+ "grad_norm": 0.091796875,
1192
+ "learning_rate": 1.566406236924833e-05,
1193
+ "loss": 0.0014,
1194
+ "step": 152
1195
+ },
1196
+ {
1197
+ "epoch": 38.275862068965516,
1198
+ "grad_norm": 0.05517578125,
1199
+ "learning_rate": 1.5591929034707468e-05,
1200
+ "loss": 0.0014,
1201
+ "step": 153
1202
+ },
1203
+ {
1204
+ "epoch": 38.55172413793103,
1205
+ "grad_norm": 0.0732421875,
1206
+ "learning_rate": 1.5519369853120584e-05,
1207
+ "loss": 0.0018,
1208
+ "step": 154
1209
+ },
1210
+ {
1211
+ "epoch": 38.827586206896555,
1212
+ "grad_norm": 0.08154296875,
1213
+ "learning_rate": 1.5446390350150272e-05,
1214
+ "loss": 0.0015,
1215
+ "step": 155
1216
+ },
1217
+ {
1218
+ "epoch": 39.0,
1219
+ "grad_norm": 0.1083984375,
1220
+ "learning_rate": 1.5372996083468242e-05,
1221
+ "loss": 0.0015,
1222
+ "step": 156
1223
+ },
1224
+ {
1225
+ "epoch": 39.275862068965516,
1226
+ "grad_norm": 0.06884765625,
1227
+ "learning_rate": 1.529919264233205e-05,
1228
+ "loss": 0.0017,
1229
+ "step": 157
1230
+ },
1231
+ {
1232
+ "epoch": 39.55172413793103,
1233
+ "grad_norm": 0.052978515625,
1234
+ "learning_rate": 1.5224985647159489e-05,
1235
+ "loss": 0.0014,
1236
+ "step": 158
1237
+ },
1238
+ {
1239
+ "epoch": 39.827586206896555,
1240
+ "grad_norm": 0.0712890625,
1241
+ "learning_rate": 1.5150380749100545e-05,
1242
+ "loss": 0.0015,
1243
+ "step": 159
1244
+ },
1245
+ {
1246
+ "epoch": 40.0,
1247
+ "grad_norm": 0.10888671875,
1248
+ "learning_rate": 1.5075383629607043e-05,
1249
+ "loss": 0.0016,
1250
+ "step": 160
1251
+ },
1252
+ {
1253
+ "epoch": 40.0,
1254
+ "eval_loss": 0.0018837498500943184,
1255
+ "eval_runtime": 1.7505,
1256
+ "eval_samples_per_second": 1.714,
1257
+ "eval_steps_per_second": 1.714,
1258
+ "step": 160
1259
+ },
1260
+ {
1261
+ "epoch": 40.275862068965516,
1262
+ "grad_norm": 0.07373046875,
1263
+ "learning_rate": 1.5000000000000002e-05,
1264
+ "loss": 0.0015,
1265
+ "step": 161
1266
+ },
1267
+ {
1268
+ "epoch": 40.55172413793103,
1269
+ "grad_norm": 0.078125,
1270
+ "learning_rate": 1.4924235601034673e-05,
1271
+ "loss": 0.0018,
1272
+ "step": 162
1273
+ },
1274
+ {
1275
+ "epoch": 40.827586206896555,
1276
+ "grad_norm": 0.06884765625,
1277
+ "learning_rate": 1.4848096202463373e-05,
1278
+ "loss": 0.0015,
1279
+ "step": 163
1280
+ },
1281
+ {
1282
+ "epoch": 41.0,
1283
+ "grad_norm": 0.058837890625,
1284
+ "learning_rate": 1.4771587602596085e-05,
1285
+ "loss": 0.0013,
1286
+ "step": 164
1287
+ },
1288
+ {
1289
+ "epoch": 41.275862068965516,
1290
+ "grad_norm": 0.05859375,
1291
+ "learning_rate": 1.469471562785891e-05,
1292
+ "loss": 0.0017,
1293
+ "step": 165
1294
+ },
1295
+ {
1296
+ "epoch": 41.55172413793103,
1297
+ "grad_norm": 0.06494140625,
1298
+ "learning_rate": 1.4617486132350343e-05,
1299
+ "loss": 0.0014,
1300
+ "step": 166
1301
+ },
1302
+ {
1303
+ "epoch": 41.827586206896555,
1304
+ "grad_norm": 0.05908203125,
1305
+ "learning_rate": 1.4539904997395468e-05,
1306
+ "loss": 0.0013,
1307
+ "step": 167
1308
+ },
1309
+ {
1310
+ "epoch": 42.0,
1311
+ "grad_norm": 0.201171875,
1312
+ "learning_rate": 1.4461978131098089e-05,
1313
+ "loss": 0.0021,
1314
+ "step": 168
1315
+ },
1316
+ {
1317
+ "epoch": 42.275862068965516,
1318
+ "grad_norm": 0.055908203125,
1319
+ "learning_rate": 1.4383711467890776e-05,
1320
+ "loss": 0.0014,
1321
+ "step": 169
1322
+ },
1323
+ {
1324
+ "epoch": 42.55172413793103,
1325
+ "grad_norm": 0.07470703125,
1326
+ "learning_rate": 1.4305110968082953e-05,
1327
+ "loss": 0.0014,
1328
+ "step": 170
1329
+ },
1330
+ {
1331
+ "epoch": 42.55172413793103,
1332
+ "eval_loss": 0.0018982401816174388,
1333
+ "eval_runtime": 1.7258,
1334
+ "eval_samples_per_second": 1.738,
1335
+ "eval_steps_per_second": 1.738,
1336
+ "step": 170
1337
+ },
1338
+ {
1339
+ "epoch": 42.827586206896555,
1340
+ "grad_norm": 0.05322265625,
1341
+ "learning_rate": 1.4226182617406996e-05,
1342
+ "loss": 0.0014,
1343
+ "step": 171
1344
+ },
1345
+ {
1346
+ "epoch": 43.0,
1347
+ "grad_norm": 0.16015625,
1348
+ "learning_rate": 1.4146932426562391e-05,
1349
+ "loss": 0.0021,
1350
+ "step": 172
1351
+ },
1352
+ {
1353
+ "epoch": 43.275862068965516,
1354
+ "grad_norm": 0.068359375,
1355
+ "learning_rate": 1.4067366430758004e-05,
1356
+ "loss": 0.0016,
1357
+ "step": 173
1358
+ },
1359
+ {
1360
+ "epoch": 43.55172413793103,
1361
+ "grad_norm": 0.0693359375,
1362
+ "learning_rate": 1.3987490689252463e-05,
1363
+ "loss": 0.0014,
1364
+ "step": 174
1365
+ },
1366
+ {
1367
+ "epoch": 43.827586206896555,
1368
+ "grad_norm": 0.07177734375,
1369
+ "learning_rate": 1.3907311284892737e-05,
1370
+ "loss": 0.0016,
1371
+ "step": 175
1372
+ },
1373
+ {
1374
+ "epoch": 44.0,
1375
+ "grad_norm": 0.07568359375,
1376
+ "learning_rate": 1.3826834323650899e-05,
1377
+ "loss": 0.0013,
1378
+ "step": 176
1379
+ },
1380
+ {
1381
+ "epoch": 44.275862068965516,
1382
+ "grad_norm": 0.07177734375,
1383
+ "learning_rate": 1.3746065934159123e-05,
1384
+ "loss": 0.0013,
1385
+ "step": 177
1386
+ },
1387
+ {
1388
+ "epoch": 44.55172413793103,
1389
+ "grad_norm": 0.0595703125,
1390
+ "learning_rate": 1.3665012267242974e-05,
1391
+ "loss": 0.0015,
1392
+ "step": 178
1393
+ },
1394
+ {
1395
+ "epoch": 44.827586206896555,
1396
+ "grad_norm": 0.0771484375,
1397
+ "learning_rate": 1.3583679495453e-05,
1398
+ "loss": 0.0016,
1399
+ "step": 179
1400
+ },
1401
+ {
1402
+ "epoch": 45.0,
1403
+ "grad_norm": 0.11083984375,
1404
+ "learning_rate": 1.3502073812594677e-05,
1405
+ "loss": 0.0016,
1406
+ "step": 180
1407
+ },
1408
+ {
1409
+ "epoch": 45.0,
1410
+ "eval_loss": 0.0018364647403359413,
1411
+ "eval_runtime": 1.7371,
1412
+ "eval_samples_per_second": 1.727,
1413
+ "eval_steps_per_second": 1.727,
1414
+ "step": 180
1415
+ },
1416
+ {
1417
+ "epoch": 45.275862068965516,
1418
+ "grad_norm": 0.046142578125,
1419
+ "learning_rate": 1.342020143325669e-05,
1420
+ "loss": 0.0014,
1421
+ "step": 181
1422
+ },
1423
+ {
1424
+ "epoch": 45.55172413793103,
1425
+ "grad_norm": 0.08251953125,
1426
+ "learning_rate": 1.333806859233771e-05,
1427
+ "loss": 0.0015,
1428
+ "step": 182
1429
+ },
1430
+ {
1431
+ "epoch": 45.827586206896555,
1432
+ "grad_norm": 0.09912109375,
1433
+ "learning_rate": 1.3255681544571568e-05,
1434
+ "loss": 0.0015,
1435
+ "step": 183
1436
+ },
1437
+ {
1438
+ "epoch": 46.0,
1439
+ "grad_norm": 0.0986328125,
1440
+ "learning_rate": 1.3173046564050923e-05,
1441
+ "loss": 0.0013,
1442
+ "step": 184
1443
+ },
1444
+ {
1445
+ "epoch": 46.275862068965516,
1446
+ "grad_norm": 0.07275390625,
1447
+ "learning_rate": 1.3090169943749475e-05,
1448
+ "loss": 0.0013,
1449
+ "step": 185
1450
+ },
1451
+ {
1452
+ "epoch": 46.55172413793103,
1453
+ "grad_norm": 0.05859375,
1454
+ "learning_rate": 1.300705799504273e-05,
1455
+ "loss": 0.0015,
1456
+ "step": 186
1457
+ },
1458
+ {
1459
+ "epoch": 46.827586206896555,
1460
+ "grad_norm": 0.06396484375,
1461
+ "learning_rate": 1.2923717047227368e-05,
1462
+ "loss": 0.0014,
1463
+ "step": 187
1464
+ },
1465
+ {
1466
+ "epoch": 47.0,
1467
+ "grad_norm": 0.09033203125,
1468
+ "learning_rate": 1.284015344703923e-05,
1469
+ "loss": 0.0016,
1470
+ "step": 188
1471
+ },
1472
+ {
1473
+ "epoch": 47.275862068965516,
1474
+ "grad_norm": 0.09423828125,
1475
+ "learning_rate": 1.2756373558169992e-05,
1476
+ "loss": 0.0015,
1477
+ "step": 189
1478
+ },
1479
+ {
1480
+ "epoch": 47.55172413793103,
1481
+ "grad_norm": 0.044189453125,
1482
+ "learning_rate": 1.267238376078257e-05,
1483
+ "loss": 0.0013,
1484
+ "step": 190
1485
+ },
1486
+ {
1487
+ "epoch": 47.55172413793103,
1488
+ "eval_loss": 0.0017142044380307198,
1489
+ "eval_runtime": 1.7594,
1490
+ "eval_samples_per_second": 1.705,
1491
+ "eval_steps_per_second": 1.705,
1492
+ "step": 190
1493
+ },
1494
+ {
1495
+ "epoch": 47.827586206896555,
1496
+ "grad_norm": 0.263671875,
1497
+ "learning_rate": 1.2588190451025209e-05,
1498
+ "loss": 0.0024,
1499
+ "step": 191
1500
+ },
1501
+ {
1502
+ "epoch": 48.0,
1503
+ "grad_norm": 0.0712890625,
1504
+ "learning_rate": 1.2503800040544417e-05,
1505
+ "loss": 0.0014,
1506
+ "step": 192
1507
+ },
1508
+ {
1509
+ "epoch": 48.275862068965516,
1510
+ "grad_norm": 0.08154296875,
1511
+ "learning_rate": 1.2419218955996677e-05,
1512
+ "loss": 0.0017,
1513
+ "step": 193
1514
+ },
1515
+ {
1516
+ "epoch": 48.55172413793103,
1517
+ "grad_norm": 0.0595703125,
1518
+ "learning_rate": 1.2334453638559057e-05,
1519
+ "loss": 0.0013,
1520
+ "step": 194
1521
+ },
1522
+ {
1523
+ "epoch": 48.827586206896555,
1524
+ "grad_norm": 0.055419921875,
1525
+ "learning_rate": 1.2249510543438652e-05,
1526
+ "loss": 0.0013,
1527
+ "step": 195
1528
+ },
1529
+ {
1530
+ "epoch": 49.0,
1531
+ "grad_norm": 0.142578125,
1532
+ "learning_rate": 1.2164396139381029e-05,
1533
+ "loss": 0.0016,
1534
+ "step": 196
1535
+ },
1536
+ {
1537
+ "epoch": 49.275862068965516,
1538
+ "grad_norm": 0.07177734375,
1539
+ "learning_rate": 1.2079116908177592e-05,
1540
+ "loss": 0.0015,
1541
+ "step": 197
1542
+ },
1543
+ {
1544
+ "epoch": 49.55172413793103,
1545
+ "grad_norm": 0.059814453125,
1546
+ "learning_rate": 1.1993679344171973e-05,
1547
+ "loss": 0.0014,
1548
+ "step": 198
1549
+ },
1550
+ {
1551
+ "epoch": 49.827586206896555,
1552
+ "grad_norm": 0.1376953125,
1553
+ "learning_rate": 1.190808995376545e-05,
1554
+ "loss": 0.0018,
1555
+ "step": 199
1556
+ },
1557
+ {
1558
+ "epoch": 50.0,
1559
+ "grad_norm": 0.0654296875,
1560
+ "learning_rate": 1.1822355254921478e-05,
1561
+ "loss": 0.0012,
1562
+ "step": 200
1563
+ },
1564
+ {
1565
+ "epoch": 50.0,
1566
+ "eval_loss": 0.0016466762172058225,
1567
+ "eval_runtime": 1.723,
1568
+ "eval_samples_per_second": 1.741,
1569
+ "eval_steps_per_second": 1.741,
1570
+ "step": 200
1571
+ }
1572
+ ],
1573
+ "logging_steps": 1,
1574
+ "max_steps": 400,
1575
+ "num_input_tokens_seen": 0,
1576
+ "num_train_epochs": 100,
1577
+ "save_steps": 40,
1578
+ "stateful_callbacks": {
1579
+ "TrainerControl": {
1580
+ "args": {
1581
+ "should_epoch_stop": false,
1582
+ "should_evaluate": false,
1583
+ "should_log": false,
1584
+ "should_save": true,
1585
+ "should_training_stop": false
1586
+ },
1587
+ "attributes": {}
1588
+ }
1589
+ },
1590
+ "total_flos": 2.072322663530496e+17,
1591
+ "train_batch_size": 1,
1592
+ "trial_name": null,
1593
+ "trial_params": null
1594
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052f01a6f071dce3b570e0317c7bb6872a930f3b21110ad6a65e04f4f7c2e16b
3
+ size 5777
vocab.json ADDED
The diff for this file is too large to render. See raw diff