Calvin806 commited on
Commit
5909fdf
·
verified ·
1 Parent(s): 15b78e8

Initial upload: fine-tuned tagger

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
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ - en
5
+ tags:
6
+ - text-generation
7
+ - keyword-extraction
8
+ - tag-generation
9
+ license: other
10
+ ---
11
+
12
+ # Qwen3-0.6B Float:Right Tagger (float-right.app)
13
+
14
+ This repository contains a fine-tuned tag generator based on **Qwen/Qwen3-0.6B**.
15
+
16
+ ## What it does
17
+
18
+ Given a memo/text, it returns **a JSON array of 3–10 tags**:
19
+
20
+ - Prefer coarse tags (not overly detailed)
21
+ - Keeps the same language as input (Korean -> Korean, English -> English)
22
+ - Avoids underscores `_`
23
+
24
+ > In production, parse only the first JSON array `[ ... ]` from the output.
25
+
26
+ ## Quick usage (Transformers)
27
+
28
+ ```python
29
+ import json, re, torch
30
+ from transformers import AutoTokenizer, AutoModelForCausalLM
31
+
32
+ MODEL_DIR = "./" # or your HF repo id
33
+
34
+ tok = AutoTokenizer.from_pretrained(MODEL_DIR, trust_remote_code=True)
35
+ if tok.pad_token is None:
36
+ tok.pad_token = tok.eos_token
37
+
38
+ model = AutoModelForCausalLM.from_pretrained(
39
+ MODEL_DIR, torch_dtype="auto", device_map="cuda", trust_remote_code=True
40
+ )
41
+
42
+ def extract_array(s: str):
43
+ m = re.search(r"\[[\s\S]*?\]", s)
44
+ if not m:
45
+ return None
46
+ return json.loads(m.group(0))
47
+
48
+ text = "오늘 서울에서 AI 컨퍼런스를 다녀왔다."
49
+ messages = [
50
+ {"role": "system", "content": "너는 태그 생성기다. 출력은 JSON 배열 하나만."},
51
+ {"role": "user", "content": f"문장: {text}\n태그 3~10개. 너무 디테일하지 않게. 언더스코어 금지. JSON 배열만."},
52
+ ]
53
+
54
+ prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
55
+ enc = tok(prompt, return_tensors="pt").to("cuda")
56
+
57
+ out = model.generate(**enc, max_new_tokens=64, do_sample=False)
58
+ decoded = tok.decode(out[0], skip_special_tokens=True)
59
+ print(extract_array(decoded))
60
+ ```
61
+
62
+ Notes
63
+ • Some outputs may include extra tokens (e.g., <think>). In production, extract only the first JSON array [ ... ].
64
+ • Training data is intended to avoid sensitive information.
65
+
66
+ Credits
67
+ • Base model: Qwen/Qwen3-0.6B
68
+ • Project: Float-Right
README.md” ADDED
@@ -0,0 +1 @@
 
 
1
+ “README fixed -
chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 %}
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
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
+ ],
45
+ "max_position_embeddings": 40960,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "pad_token_id": null,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 1000000,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.2.0",
60
+ "use_cache": false,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 151936
63
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "5.2.0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73fc41e79b036aca5e0016aabf4c30a61079cb13a234e42acbd654454339ddb1
3
+ size 1503300328
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6ab688fe4ad89b988049d9cd73e64b3c004ff6b8d8e5c8d677ffa847a13086
3
+ size 3006795403
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659b1cdee2219458dd84ce6a632a595465680b8080e5c44bd600ff97eca8d752
3
+ size 15429
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
3
+ size 15429
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
3
+ size 15429
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
3
+ size 15429
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394453d4186b4da42e0d5ca6a98ddc3855f23b1554cd26f3ec369ecb67591b07
3
+ size 1465
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 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- 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>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
trainer_state.json ADDED
@@ -0,0 +1,1434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.3107520198881293,
6
+ "eval_steps": 500,
7
+ "global_step": 4000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0015537600994406464,
14
+ "grad_norm": 1.6171875,
15
+ "learning_rate": 9.952500000000001e-05,
16
+ "loss": 1.8667953491210938,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.003107520198881293,
21
+ "grad_norm": 1.46875,
22
+ "learning_rate": 9.9025e-05,
23
+ "loss": 1.4211945533752441,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.0046612802983219395,
28
+ "grad_norm": 1.46875,
29
+ "learning_rate": 9.8525e-05,
30
+ "loss": 1.3616345405578614,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.006215040397762586,
35
+ "grad_norm": 1.375,
36
+ "learning_rate": 9.8025e-05,
37
+ "loss": 1.3699079513549806,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.007768800497203232,
42
+ "grad_norm": 1.265625,
43
+ "learning_rate": 9.7525e-05,
44
+ "loss": 1.326680564880371,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.009322560596643879,
49
+ "grad_norm": 1.2421875,
50
+ "learning_rate": 9.7025e-05,
51
+ "loss": 1.3107091903686523,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.010876320696084525,
56
+ "grad_norm": 1.2421875,
57
+ "learning_rate": 9.652500000000002e-05,
58
+ "loss": 1.3247576713562013,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.012430080795525171,
63
+ "grad_norm": 1.234375,
64
+ "learning_rate": 9.6025e-05,
65
+ "loss": 1.306673526763916,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.013983840894965818,
70
+ "grad_norm": 1.2265625,
71
+ "learning_rate": 9.5525e-05,
72
+ "loss": 1.2789793014526367,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.015537600994406464,
77
+ "grad_norm": 1.1796875,
78
+ "learning_rate": 9.5025e-05,
79
+ "loss": 1.2699722290039062,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.01709136109384711,
84
+ "grad_norm": 1.1796875,
85
+ "learning_rate": 9.452500000000001e-05,
86
+ "loss": 1.2735892295837403,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.018645121193287758,
91
+ "grad_norm": 1.15625,
92
+ "learning_rate": 9.402500000000001e-05,
93
+ "loss": 1.255952739715576,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.020198881292728402,
98
+ "grad_norm": 1.0859375,
99
+ "learning_rate": 9.352500000000001e-05,
100
+ "loss": 1.2663206100463866,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.02175264139216905,
105
+ "grad_norm": 1.09375,
106
+ "learning_rate": 9.302500000000001e-05,
107
+ "loss": 1.2674468994140624,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.023306401491609695,
112
+ "grad_norm": 1.0703125,
113
+ "learning_rate": 9.252500000000001e-05,
114
+ "loss": 1.2581491470336914,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.024860161591050343,
119
+ "grad_norm": 1.15625,
120
+ "learning_rate": 9.2025e-05,
121
+ "loss": 1.2293106079101563,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 0.026413921690490987,
126
+ "grad_norm": 1.0703125,
127
+ "learning_rate": 9.1525e-05,
128
+ "loss": 1.2330900192260743,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 0.027967681789931635,
133
+ "grad_norm": 1.0859375,
134
+ "learning_rate": 9.1025e-05,
135
+ "loss": 1.2186731338500976,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.02952144188937228,
140
+ "grad_norm": 1.078125,
141
+ "learning_rate": 9.0525e-05,
142
+ "loss": 1.2420782089233398,
143
+ "step": 380
144
+ },
145
+ {
146
+ "epoch": 0.031075201988812928,
147
+ "grad_norm": 0.984375,
148
+ "learning_rate": 9.0025e-05,
149
+ "loss": 1.2236801147460938,
150
+ "step": 400
151
+ },
152
+ {
153
+ "epoch": 0.032628962088253576,
154
+ "grad_norm": 1.0390625,
155
+ "learning_rate": 8.952500000000001e-05,
156
+ "loss": 1.2241475105285644,
157
+ "step": 420
158
+ },
159
+ {
160
+ "epoch": 0.03418272218769422,
161
+ "grad_norm": 0.98828125,
162
+ "learning_rate": 8.902500000000001e-05,
163
+ "loss": 1.2227598190307618,
164
+ "step": 440
165
+ },
166
+ {
167
+ "epoch": 0.035736482287134864,
168
+ "grad_norm": 1.0390625,
169
+ "learning_rate": 8.8525e-05,
170
+ "loss": 1.2154598236083984,
171
+ "step": 460
172
+ },
173
+ {
174
+ "epoch": 0.037290242386575516,
175
+ "grad_norm": 1.0859375,
176
+ "learning_rate": 8.8025e-05,
177
+ "loss": 1.20736665725708,
178
+ "step": 480
179
+ },
180
+ {
181
+ "epoch": 0.03884400248601616,
182
+ "grad_norm": 1.0546875,
183
+ "learning_rate": 8.7525e-05,
184
+ "loss": 1.1936758041381836,
185
+ "step": 500
186
+ },
187
+ {
188
+ "epoch": 0.040397762585456805,
189
+ "grad_norm": 1.09375,
190
+ "learning_rate": 8.7025e-05,
191
+ "loss": 1.1817484855651856,
192
+ "step": 520
193
+ },
194
+ {
195
+ "epoch": 0.04195152268489745,
196
+ "grad_norm": 1.0703125,
197
+ "learning_rate": 8.6525e-05,
198
+ "loss": 1.2060453414916992,
199
+ "step": 540
200
+ },
201
+ {
202
+ "epoch": 0.0435052827843381,
203
+ "grad_norm": 0.99609375,
204
+ "learning_rate": 8.6025e-05,
205
+ "loss": 1.2340307235717773,
206
+ "step": 560
207
+ },
208
+ {
209
+ "epoch": 0.045059042883778745,
210
+ "grad_norm": 1.0,
211
+ "learning_rate": 8.5525e-05,
212
+ "loss": 1.2149415969848634,
213
+ "step": 580
214
+ },
215
+ {
216
+ "epoch": 0.04661280298321939,
217
+ "grad_norm": 0.97265625,
218
+ "learning_rate": 8.502499999999999e-05,
219
+ "loss": 1.2079537391662598,
220
+ "step": 600
221
+ },
222
+ {
223
+ "epoch": 0.048166563082660034,
224
+ "grad_norm": 1.015625,
225
+ "learning_rate": 8.4525e-05,
226
+ "loss": 1.1671560287475586,
227
+ "step": 620
228
+ },
229
+ {
230
+ "epoch": 0.049720323182100686,
231
+ "grad_norm": 1.0,
232
+ "learning_rate": 8.402500000000001e-05,
233
+ "loss": 1.1967806816101074,
234
+ "step": 640
235
+ },
236
+ {
237
+ "epoch": 0.05127408328154133,
238
+ "grad_norm": 1.0234375,
239
+ "learning_rate": 8.352500000000001e-05,
240
+ "loss": 1.178822135925293,
241
+ "step": 660
242
+ },
243
+ {
244
+ "epoch": 0.052827843380981974,
245
+ "grad_norm": 1.0625,
246
+ "learning_rate": 8.302500000000001e-05,
247
+ "loss": 1.1784405708312988,
248
+ "step": 680
249
+ },
250
+ {
251
+ "epoch": 0.054381603480422626,
252
+ "grad_norm": 0.9765625,
253
+ "learning_rate": 8.252500000000001e-05,
254
+ "loss": 1.1611870765686034,
255
+ "step": 700
256
+ },
257
+ {
258
+ "epoch": 0.05593536357986327,
259
+ "grad_norm": 1.0078125,
260
+ "learning_rate": 8.2025e-05,
261
+ "loss": 1.1876888275146484,
262
+ "step": 720
263
+ },
264
+ {
265
+ "epoch": 0.057489123679303915,
266
+ "grad_norm": 0.94921875,
267
+ "learning_rate": 8.1525e-05,
268
+ "loss": 1.18981876373291,
269
+ "step": 740
270
+ },
271
+ {
272
+ "epoch": 0.05904288377874456,
273
+ "grad_norm": 0.93359375,
274
+ "learning_rate": 8.1025e-05,
275
+ "loss": 1.1651229858398438,
276
+ "step": 760
277
+ },
278
+ {
279
+ "epoch": 0.06059664387818521,
280
+ "grad_norm": 0.953125,
281
+ "learning_rate": 8.0525e-05,
282
+ "loss": 1.1725165367126464,
283
+ "step": 780
284
+ },
285
+ {
286
+ "epoch": 0.062150403977625855,
287
+ "grad_norm": 0.94921875,
288
+ "learning_rate": 8.002500000000001e-05,
289
+ "loss": 1.1620153427124023,
290
+ "step": 800
291
+ },
292
+ {
293
+ "epoch": 0.0637041640770665,
294
+ "grad_norm": 0.94921875,
295
+ "learning_rate": 7.952500000000001e-05,
296
+ "loss": 1.180180549621582,
297
+ "step": 820
298
+ },
299
+ {
300
+ "epoch": 0.06525792417650715,
301
+ "grad_norm": 0.953125,
302
+ "learning_rate": 7.902500000000001e-05,
303
+ "loss": 1.169425106048584,
304
+ "step": 840
305
+ },
306
+ {
307
+ "epoch": 0.06681168427594779,
308
+ "grad_norm": 0.96875,
309
+ "learning_rate": 7.8525e-05,
310
+ "loss": 1.1701436996459962,
311
+ "step": 860
312
+ },
313
+ {
314
+ "epoch": 0.06836544437538844,
315
+ "grad_norm": 0.98828125,
316
+ "learning_rate": 7.8025e-05,
317
+ "loss": 1.1514653205871581,
318
+ "step": 880
319
+ },
320
+ {
321
+ "epoch": 0.06991920447482909,
322
+ "grad_norm": 0.9453125,
323
+ "learning_rate": 7.7525e-05,
324
+ "loss": 1.166794776916504,
325
+ "step": 900
326
+ },
327
+ {
328
+ "epoch": 0.07147296457426973,
329
+ "grad_norm": 0.98828125,
330
+ "learning_rate": 7.7025e-05,
331
+ "loss": 1.1640316009521485,
332
+ "step": 920
333
+ },
334
+ {
335
+ "epoch": 0.07302672467371038,
336
+ "grad_norm": 1.0,
337
+ "learning_rate": 7.6525e-05,
338
+ "loss": 1.1756441116333007,
339
+ "step": 940
340
+ },
341
+ {
342
+ "epoch": 0.07458048477315103,
343
+ "grad_norm": 0.921875,
344
+ "learning_rate": 7.6025e-05,
345
+ "loss": 1.1775863647460938,
346
+ "step": 960
347
+ },
348
+ {
349
+ "epoch": 0.07613424487259167,
350
+ "grad_norm": 0.94140625,
351
+ "learning_rate": 7.5525e-05,
352
+ "loss": 1.1620708465576173,
353
+ "step": 980
354
+ },
355
+ {
356
+ "epoch": 0.07768800497203232,
357
+ "grad_norm": 0.93359375,
358
+ "learning_rate": 7.502500000000001e-05,
359
+ "loss": 1.1424921989440917,
360
+ "step": 1000
361
+ },
362
+ {
363
+ "epoch": 0.07924176507147296,
364
+ "grad_norm": 0.94140625,
365
+ "learning_rate": 7.4525e-05,
366
+ "loss": 1.1636884689331055,
367
+ "step": 1020
368
+ },
369
+ {
370
+ "epoch": 0.08079552517091361,
371
+ "grad_norm": 0.96875,
372
+ "learning_rate": 7.4025e-05,
373
+ "loss": 1.1640792846679688,
374
+ "step": 1040
375
+ },
376
+ {
377
+ "epoch": 0.08234928527035426,
378
+ "grad_norm": 0.96875,
379
+ "learning_rate": 7.3525e-05,
380
+ "loss": 1.1577949523925781,
381
+ "step": 1060
382
+ },
383
+ {
384
+ "epoch": 0.0839030453697949,
385
+ "grad_norm": 0.9375,
386
+ "learning_rate": 7.3025e-05,
387
+ "loss": 1.1563040733337402,
388
+ "step": 1080
389
+ },
390
+ {
391
+ "epoch": 0.08545680546923555,
392
+ "grad_norm": 0.9296875,
393
+ "learning_rate": 7.2525e-05,
394
+ "loss": 1.1314552307128907,
395
+ "step": 1100
396
+ },
397
+ {
398
+ "epoch": 0.0870105655686762,
399
+ "grad_norm": 0.953125,
400
+ "learning_rate": 7.2025e-05,
401
+ "loss": 1.1430686950683593,
402
+ "step": 1120
403
+ },
404
+ {
405
+ "epoch": 0.08856432566811684,
406
+ "grad_norm": 0.921875,
407
+ "learning_rate": 7.1525e-05,
408
+ "loss": 1.1624882698059082,
409
+ "step": 1140
410
+ },
411
+ {
412
+ "epoch": 0.09011808576755749,
413
+ "grad_norm": 0.9375,
414
+ "learning_rate": 7.1025e-05,
415
+ "loss": 1.1404618263244628,
416
+ "step": 1160
417
+ },
418
+ {
419
+ "epoch": 0.09167184586699814,
420
+ "grad_norm": 0.94921875,
421
+ "learning_rate": 7.0525e-05,
422
+ "loss": 1.142820453643799,
423
+ "step": 1180
424
+ },
425
+ {
426
+ "epoch": 0.09322560596643878,
427
+ "grad_norm": 0.9296875,
428
+ "learning_rate": 7.002500000000001e-05,
429
+ "loss": 1.1361354827880858,
430
+ "step": 1200
431
+ },
432
+ {
433
+ "epoch": 0.09477936606587943,
434
+ "grad_norm": 0.91796875,
435
+ "learning_rate": 6.952500000000001e-05,
436
+ "loss": 1.141007137298584,
437
+ "step": 1220
438
+ },
439
+ {
440
+ "epoch": 0.09633312616532007,
441
+ "grad_norm": 0.93359375,
442
+ "learning_rate": 6.902500000000001e-05,
443
+ "loss": 1.140983772277832,
444
+ "step": 1240
445
+ },
446
+ {
447
+ "epoch": 0.09788688626476072,
448
+ "grad_norm": 0.94921875,
449
+ "learning_rate": 6.852500000000001e-05,
450
+ "loss": 1.1491514205932618,
451
+ "step": 1260
452
+ },
453
+ {
454
+ "epoch": 0.09944064636420137,
455
+ "grad_norm": 0.953125,
456
+ "learning_rate": 6.8025e-05,
457
+ "loss": 1.1248952865600585,
458
+ "step": 1280
459
+ },
460
+ {
461
+ "epoch": 0.10099440646364201,
462
+ "grad_norm": 0.9296875,
463
+ "learning_rate": 6.7525e-05,
464
+ "loss": 1.1090205192565918,
465
+ "step": 1300
466
+ },
467
+ {
468
+ "epoch": 0.10254816656308266,
469
+ "grad_norm": 0.9765625,
470
+ "learning_rate": 6.7025e-05,
471
+ "loss": 1.1208727836608887,
472
+ "step": 1320
473
+ },
474
+ {
475
+ "epoch": 0.10410192666252331,
476
+ "grad_norm": 0.9375,
477
+ "learning_rate": 6.6525e-05,
478
+ "loss": 1.1511701583862304,
479
+ "step": 1340
480
+ },
481
+ {
482
+ "epoch": 0.10565568676196395,
483
+ "grad_norm": 0.8828125,
484
+ "learning_rate": 6.6025e-05,
485
+ "loss": 1.1259963989257813,
486
+ "step": 1360
487
+ },
488
+ {
489
+ "epoch": 0.1072094468614046,
490
+ "grad_norm": 0.921875,
491
+ "learning_rate": 6.552500000000001e-05,
492
+ "loss": 1.1311534881591796,
493
+ "step": 1380
494
+ },
495
+ {
496
+ "epoch": 0.10876320696084525,
497
+ "grad_norm": 0.9375,
498
+ "learning_rate": 6.502500000000001e-05,
499
+ "loss": 1.1099111557006835,
500
+ "step": 1400
501
+ },
502
+ {
503
+ "epoch": 0.11031696706028589,
504
+ "grad_norm": 0.953125,
505
+ "learning_rate": 6.4525e-05,
506
+ "loss": 1.126076602935791,
507
+ "step": 1420
508
+ },
509
+ {
510
+ "epoch": 0.11187072715972654,
511
+ "grad_norm": 0.8984375,
512
+ "learning_rate": 6.4025e-05,
513
+ "loss": 1.1338358879089356,
514
+ "step": 1440
515
+ },
516
+ {
517
+ "epoch": 0.11342448725916718,
518
+ "grad_norm": 0.91796875,
519
+ "learning_rate": 6.3525e-05,
520
+ "loss": 1.1149433135986329,
521
+ "step": 1460
522
+ },
523
+ {
524
+ "epoch": 0.11497824735860783,
525
+ "grad_norm": 0.96484375,
526
+ "learning_rate": 6.3025e-05,
527
+ "loss": 1.1221566200256348,
528
+ "step": 1480
529
+ },
530
+ {
531
+ "epoch": 0.11653200745804848,
532
+ "grad_norm": 0.921875,
533
+ "learning_rate": 6.2525e-05,
534
+ "loss": 1.1223237991333008,
535
+ "step": 1500
536
+ },
537
+ {
538
+ "epoch": 0.11808576755748912,
539
+ "grad_norm": 0.90234375,
540
+ "learning_rate": 6.2025e-05,
541
+ "loss": 1.1033407211303712,
542
+ "step": 1520
543
+ },
544
+ {
545
+ "epoch": 0.11963952765692977,
546
+ "grad_norm": 0.90234375,
547
+ "learning_rate": 6.1525e-05,
548
+ "loss": 1.1114818572998046,
549
+ "step": 1540
550
+ },
551
+ {
552
+ "epoch": 0.12119328775637042,
553
+ "grad_norm": 0.91796875,
554
+ "learning_rate": 6.1025e-05,
555
+ "loss": 1.1105637550354004,
556
+ "step": 1560
557
+ },
558
+ {
559
+ "epoch": 0.12274704785581106,
560
+ "grad_norm": 0.90625,
561
+ "learning_rate": 6.0525e-05,
562
+ "loss": 1.1189040184020995,
563
+ "step": 1580
564
+ },
565
+ {
566
+ "epoch": 0.12430080795525171,
567
+ "grad_norm": 0.921875,
568
+ "learning_rate": 6.0024999999999995e-05,
569
+ "loss": 1.1234063148498534,
570
+ "step": 1600
571
+ },
572
+ {
573
+ "epoch": 0.12585456805469236,
574
+ "grad_norm": 0.953125,
575
+ "learning_rate": 5.9525e-05,
576
+ "loss": 1.1020179748535157,
577
+ "step": 1620
578
+ },
579
+ {
580
+ "epoch": 0.127408328154133,
581
+ "grad_norm": 0.921875,
582
+ "learning_rate": 5.9025000000000005e-05,
583
+ "loss": 1.1260129928588867,
584
+ "step": 1640
585
+ },
586
+ {
587
+ "epoch": 0.12896208825357364,
588
+ "grad_norm": 0.87890625,
589
+ "learning_rate": 5.8525000000000006e-05,
590
+ "loss": 1.1067705154418945,
591
+ "step": 1660
592
+ },
593
+ {
594
+ "epoch": 0.1305158483530143,
595
+ "grad_norm": 0.94140625,
596
+ "learning_rate": 5.802500000000001e-05,
597
+ "loss": 1.115440273284912,
598
+ "step": 1680
599
+ },
600
+ {
601
+ "epoch": 0.13206960845245494,
602
+ "grad_norm": 0.91796875,
603
+ "learning_rate": 5.752500000000001e-05,
604
+ "loss": 1.1169689178466797,
605
+ "step": 1700
606
+ },
607
+ {
608
+ "epoch": 0.13362336855189558,
609
+ "grad_norm": 0.921875,
610
+ "learning_rate": 5.7025000000000004e-05,
611
+ "loss": 1.1162803649902344,
612
+ "step": 1720
613
+ },
614
+ {
615
+ "epoch": 0.13517712865133624,
616
+ "grad_norm": 0.8984375,
617
+ "learning_rate": 5.6525000000000005e-05,
618
+ "loss": 1.1266037940979003,
619
+ "step": 1740
620
+ },
621
+ {
622
+ "epoch": 0.13673088875077688,
623
+ "grad_norm": 0.953125,
624
+ "learning_rate": 5.6025000000000007e-05,
625
+ "loss": 1.1090587615966796,
626
+ "step": 1760
627
+ },
628
+ {
629
+ "epoch": 0.13828464885021752,
630
+ "grad_norm": 0.8828125,
631
+ "learning_rate": 5.552500000000001e-05,
632
+ "loss": 1.1141853332519531,
633
+ "step": 1780
634
+ },
635
+ {
636
+ "epoch": 0.13983840894965818,
637
+ "grad_norm": 0.88671875,
638
+ "learning_rate": 5.5025e-05,
639
+ "loss": 1.1379024505615234,
640
+ "step": 1800
641
+ },
642
+ {
643
+ "epoch": 0.14139216904909882,
644
+ "grad_norm": 0.91015625,
645
+ "learning_rate": 5.4525000000000004e-05,
646
+ "loss": 1.110361099243164,
647
+ "step": 1820
648
+ },
649
+ {
650
+ "epoch": 0.14294592914853946,
651
+ "grad_norm": 0.8984375,
652
+ "learning_rate": 5.4025000000000005e-05,
653
+ "loss": 1.1104223251342773,
654
+ "step": 1840
655
+ },
656
+ {
657
+ "epoch": 0.14449968924798012,
658
+ "grad_norm": 0.953125,
659
+ "learning_rate": 5.3525e-05,
660
+ "loss": 1.0993282318115234,
661
+ "step": 1860
662
+ },
663
+ {
664
+ "epoch": 0.14605344934742076,
665
+ "grad_norm": 0.88671875,
666
+ "learning_rate": 5.3025e-05,
667
+ "loss": 1.1151838302612305,
668
+ "step": 1880
669
+ },
670
+ {
671
+ "epoch": 0.1476072094468614,
672
+ "grad_norm": 0.91796875,
673
+ "learning_rate": 5.2525e-05,
674
+ "loss": 1.1184428215026856,
675
+ "step": 1900
676
+ },
677
+ {
678
+ "epoch": 0.14916096954630206,
679
+ "grad_norm": 0.921875,
680
+ "learning_rate": 5.2025000000000004e-05,
681
+ "loss": 1.1321413040161132,
682
+ "step": 1920
683
+ },
684
+ {
685
+ "epoch": 0.1507147296457427,
686
+ "grad_norm": 0.875,
687
+ "learning_rate": 5.1525e-05,
688
+ "loss": 1.1035722732543944,
689
+ "step": 1940
690
+ },
691
+ {
692
+ "epoch": 0.15226848974518334,
693
+ "grad_norm": 0.92578125,
694
+ "learning_rate": 5.1025e-05,
695
+ "loss": 1.0843469619750976,
696
+ "step": 1960
697
+ },
698
+ {
699
+ "epoch": 0.153822249844624,
700
+ "grad_norm": 0.89453125,
701
+ "learning_rate": 5.0525e-05,
702
+ "loss": 1.102191162109375,
703
+ "step": 1980
704
+ },
705
+ {
706
+ "epoch": 0.15537600994406464,
707
+ "grad_norm": 0.93359375,
708
+ "learning_rate": 5.0025e-05,
709
+ "loss": 1.1058999061584474,
710
+ "step": 2000
711
+ },
712
+ {
713
+ "epoch": 0.15692977004350528,
714
+ "grad_norm": 0.8984375,
715
+ "learning_rate": 4.9525000000000004e-05,
716
+ "loss": 1.1077130317687989,
717
+ "step": 2020
718
+ },
719
+ {
720
+ "epoch": 0.15848353014294592,
721
+ "grad_norm": 0.91796875,
722
+ "learning_rate": 4.9025000000000006e-05,
723
+ "loss": 1.0922195434570312,
724
+ "step": 2040
725
+ },
726
+ {
727
+ "epoch": 0.16003729024238658,
728
+ "grad_norm": 0.92578125,
729
+ "learning_rate": 4.8525e-05,
730
+ "loss": 1.130363941192627,
731
+ "step": 2060
732
+ },
733
+ {
734
+ "epoch": 0.16159105034182722,
735
+ "grad_norm": 0.8984375,
736
+ "learning_rate": 4.8025e-05,
737
+ "loss": 1.0666452407836915,
738
+ "step": 2080
739
+ },
740
+ {
741
+ "epoch": 0.16314481044126786,
742
+ "grad_norm": 0.91015625,
743
+ "learning_rate": 4.7525e-05,
744
+ "loss": 1.096773052215576,
745
+ "step": 2100
746
+ },
747
+ {
748
+ "epoch": 0.16469857054070852,
749
+ "grad_norm": 0.9296875,
750
+ "learning_rate": 4.7025000000000005e-05,
751
+ "loss": 1.0890857696533203,
752
+ "step": 2120
753
+ },
754
+ {
755
+ "epoch": 0.16625233064014916,
756
+ "grad_norm": 0.91015625,
757
+ "learning_rate": 4.6525e-05,
758
+ "loss": 1.1071590423583983,
759
+ "step": 2140
760
+ },
761
+ {
762
+ "epoch": 0.1678060907395898,
763
+ "grad_norm": 0.87890625,
764
+ "learning_rate": 4.6025e-05,
765
+ "loss": 1.1148256301879882,
766
+ "step": 2160
767
+ },
768
+ {
769
+ "epoch": 0.16935985083903046,
770
+ "grad_norm": 0.92578125,
771
+ "learning_rate": 4.5525e-05,
772
+ "loss": 1.090849018096924,
773
+ "step": 2180
774
+ },
775
+ {
776
+ "epoch": 0.1709136109384711,
777
+ "grad_norm": 0.921875,
778
+ "learning_rate": 4.5025000000000003e-05,
779
+ "loss": 1.1214483261108399,
780
+ "step": 2200
781
+ },
782
+ {
783
+ "epoch": 0.17246737103791174,
784
+ "grad_norm": 0.89453125,
785
+ "learning_rate": 4.4525e-05,
786
+ "loss": 1.099250030517578,
787
+ "step": 2220
788
+ },
789
+ {
790
+ "epoch": 0.1740211311373524,
791
+ "grad_norm": 0.90234375,
792
+ "learning_rate": 4.4025e-05,
793
+ "loss": 1.0906652450561523,
794
+ "step": 2240
795
+ },
796
+ {
797
+ "epoch": 0.17557489123679304,
798
+ "grad_norm": 0.875,
799
+ "learning_rate": 4.352500000000001e-05,
800
+ "loss": 1.0940235137939454,
801
+ "step": 2260
802
+ },
803
+ {
804
+ "epoch": 0.17712865133623368,
805
+ "grad_norm": 0.875,
806
+ "learning_rate": 4.3025e-05,
807
+ "loss": 1.0771520614624024,
808
+ "step": 2280
809
+ },
810
+ {
811
+ "epoch": 0.17868241143567434,
812
+ "grad_norm": 0.875,
813
+ "learning_rate": 4.2525000000000004e-05,
814
+ "loss": 1.0870559692382813,
815
+ "step": 2300
816
+ },
817
+ {
818
+ "epoch": 0.18023617153511498,
819
+ "grad_norm": 0.90625,
820
+ "learning_rate": 4.2025000000000005e-05,
821
+ "loss": 1.0863205909729003,
822
+ "step": 2320
823
+ },
824
+ {
825
+ "epoch": 0.18178993163455562,
826
+ "grad_norm": 0.9296875,
827
+ "learning_rate": 4.1525e-05,
828
+ "loss": 1.0996931076049805,
829
+ "step": 2340
830
+ },
831
+ {
832
+ "epoch": 0.18334369173399628,
833
+ "grad_norm": 0.875,
834
+ "learning_rate": 4.1025e-05,
835
+ "loss": 1.0987712860107421,
836
+ "step": 2360
837
+ },
838
+ {
839
+ "epoch": 0.18489745183343692,
840
+ "grad_norm": 0.9296875,
841
+ "learning_rate": 4.0525e-05,
842
+ "loss": 1.1171295166015625,
843
+ "step": 2380
844
+ },
845
+ {
846
+ "epoch": 0.18645121193287756,
847
+ "grad_norm": 0.9296875,
848
+ "learning_rate": 4.0025000000000004e-05,
849
+ "loss": 1.103907012939453,
850
+ "step": 2400
851
+ },
852
+ {
853
+ "epoch": 0.18800497203231822,
854
+ "grad_norm": 0.94140625,
855
+ "learning_rate": 3.9525e-05,
856
+ "loss": 1.090281867980957,
857
+ "step": 2420
858
+ },
859
+ {
860
+ "epoch": 0.18955873213175886,
861
+ "grad_norm": 0.9140625,
862
+ "learning_rate": 3.9025e-05,
863
+ "loss": 1.0880367279052734,
864
+ "step": 2440
865
+ },
866
+ {
867
+ "epoch": 0.1911124922311995,
868
+ "grad_norm": 0.90625,
869
+ "learning_rate": 3.8525e-05,
870
+ "loss": 1.0839120864868164,
871
+ "step": 2460
872
+ },
873
+ {
874
+ "epoch": 0.19266625233064014,
875
+ "grad_norm": 0.9375,
876
+ "learning_rate": 3.8025e-05,
877
+ "loss": 1.1069268226623534,
878
+ "step": 2480
879
+ },
880
+ {
881
+ "epoch": 0.1942200124300808,
882
+ "grad_norm": 0.87109375,
883
+ "learning_rate": 3.7525e-05,
884
+ "loss": 1.0701780319213867,
885
+ "step": 2500
886
+ },
887
+ {
888
+ "epoch": 0.19577377252952144,
889
+ "grad_norm": 0.921875,
890
+ "learning_rate": 3.7025000000000005e-05,
891
+ "loss": 1.1017258644104004,
892
+ "step": 2520
893
+ },
894
+ {
895
+ "epoch": 0.19732753262896208,
896
+ "grad_norm": 0.9140625,
897
+ "learning_rate": 3.652500000000001e-05,
898
+ "loss": 1.1134037017822265,
899
+ "step": 2540
900
+ },
901
+ {
902
+ "epoch": 0.19888129272840274,
903
+ "grad_norm": 0.9453125,
904
+ "learning_rate": 3.6025e-05,
905
+ "loss": 1.0741355895996094,
906
+ "step": 2560
907
+ },
908
+ {
909
+ "epoch": 0.20043505282784338,
910
+ "grad_norm": 0.890625,
911
+ "learning_rate": 3.5525e-05,
912
+ "loss": 1.0729135513305663,
913
+ "step": 2580
914
+ },
915
+ {
916
+ "epoch": 0.20198881292728402,
917
+ "grad_norm": 0.921875,
918
+ "learning_rate": 3.5025000000000004e-05,
919
+ "loss": 1.0833280563354493,
920
+ "step": 2600
921
+ },
922
+ {
923
+ "epoch": 0.20354257302672468,
924
+ "grad_norm": 0.8984375,
925
+ "learning_rate": 3.4525e-05,
926
+ "loss": 1.1003621101379395,
927
+ "step": 2620
928
+ },
929
+ {
930
+ "epoch": 0.20509633312616532,
931
+ "grad_norm": 0.8984375,
932
+ "learning_rate": 3.4025e-05,
933
+ "loss": 1.0958992004394532,
934
+ "step": 2640
935
+ },
936
+ {
937
+ "epoch": 0.20665009322560596,
938
+ "grad_norm": 0.90625,
939
+ "learning_rate": 3.3525e-05,
940
+ "loss": 1.098832893371582,
941
+ "step": 2660
942
+ },
943
+ {
944
+ "epoch": 0.20820385332504662,
945
+ "grad_norm": 0.89453125,
946
+ "learning_rate": 3.3025e-05,
947
+ "loss": 1.0823541641235352,
948
+ "step": 2680
949
+ },
950
+ {
951
+ "epoch": 0.20975761342448726,
952
+ "grad_norm": 0.91015625,
953
+ "learning_rate": 3.2525e-05,
954
+ "loss": 1.0849027633666992,
955
+ "step": 2700
956
+ },
957
+ {
958
+ "epoch": 0.2113113735239279,
959
+ "grad_norm": 0.890625,
960
+ "learning_rate": 3.2025e-05,
961
+ "loss": 1.0959321975708007,
962
+ "step": 2720
963
+ },
964
+ {
965
+ "epoch": 0.21286513362336856,
966
+ "grad_norm": 0.88671875,
967
+ "learning_rate": 3.1525e-05,
968
+ "loss": 1.083869743347168,
969
+ "step": 2740
970
+ },
971
+ {
972
+ "epoch": 0.2144188937228092,
973
+ "grad_norm": 0.8984375,
974
+ "learning_rate": 3.1025e-05,
975
+ "loss": 1.0912399291992188,
976
+ "step": 2760
977
+ },
978
+ {
979
+ "epoch": 0.21597265382224984,
980
+ "grad_norm": 0.9140625,
981
+ "learning_rate": 3.0525e-05,
982
+ "loss": 1.088266944885254,
983
+ "step": 2780
984
+ },
985
+ {
986
+ "epoch": 0.2175264139216905,
987
+ "grad_norm": 0.86328125,
988
+ "learning_rate": 3.0025000000000005e-05,
989
+ "loss": 1.0917407035827638,
990
+ "step": 2800
991
+ },
992
+ {
993
+ "epoch": 0.21908017402113114,
994
+ "grad_norm": 0.88671875,
995
+ "learning_rate": 2.9525000000000003e-05,
996
+ "loss": 1.088615608215332,
997
+ "step": 2820
998
+ },
999
+ {
1000
+ "epoch": 0.22063393412057178,
1001
+ "grad_norm": 0.89453125,
1002
+ "learning_rate": 2.9025e-05,
1003
+ "loss": 1.0885720252990723,
1004
+ "step": 2840
1005
+ },
1006
+ {
1007
+ "epoch": 0.22218769422001244,
1008
+ "grad_norm": 0.8828125,
1009
+ "learning_rate": 2.8525000000000002e-05,
1010
+ "loss": 1.072688388824463,
1011
+ "step": 2860
1012
+ },
1013
+ {
1014
+ "epoch": 0.22374145431945308,
1015
+ "grad_norm": 0.89453125,
1016
+ "learning_rate": 2.8025e-05,
1017
+ "loss": 1.0892706871032716,
1018
+ "step": 2880
1019
+ },
1020
+ {
1021
+ "epoch": 0.22529521441889372,
1022
+ "grad_norm": 0.93359375,
1023
+ "learning_rate": 2.7525e-05,
1024
+ "loss": 1.083917236328125,
1025
+ "step": 2900
1026
+ },
1027
+ {
1028
+ "epoch": 0.22684897451833436,
1029
+ "grad_norm": 0.921875,
1030
+ "learning_rate": 2.7025e-05,
1031
+ "loss": 1.1079219818115233,
1032
+ "step": 2920
1033
+ },
1034
+ {
1035
+ "epoch": 0.22840273461777502,
1036
+ "grad_norm": 0.91796875,
1037
+ "learning_rate": 2.6525e-05,
1038
+ "loss": 1.0851898193359375,
1039
+ "step": 2940
1040
+ },
1041
+ {
1042
+ "epoch": 0.22995649471721566,
1043
+ "grad_norm": 0.91015625,
1044
+ "learning_rate": 2.6025e-05,
1045
+ "loss": 1.0698064804077148,
1046
+ "step": 2960
1047
+ },
1048
+ {
1049
+ "epoch": 0.2315102548166563,
1050
+ "grad_norm": 0.8828125,
1051
+ "learning_rate": 2.5525e-05,
1052
+ "loss": 1.0661302566528321,
1053
+ "step": 2980
1054
+ },
1055
+ {
1056
+ "epoch": 0.23306401491609696,
1057
+ "grad_norm": 0.9140625,
1058
+ "learning_rate": 2.5025e-05,
1059
+ "loss": 1.0647387504577637,
1060
+ "step": 3000
1061
+ },
1062
+ {
1063
+ "epoch": 0.2346177750155376,
1064
+ "grad_norm": 0.8984375,
1065
+ "learning_rate": 2.4525e-05,
1066
+ "loss": 1.074313259124756,
1067
+ "step": 3020
1068
+ },
1069
+ {
1070
+ "epoch": 0.23617153511497824,
1071
+ "grad_norm": 0.9140625,
1072
+ "learning_rate": 2.4025e-05,
1073
+ "loss": 1.0964820861816407,
1074
+ "step": 3040
1075
+ },
1076
+ {
1077
+ "epoch": 0.2377252952144189,
1078
+ "grad_norm": 0.89453125,
1079
+ "learning_rate": 2.3525e-05,
1080
+ "loss": 1.0810314178466798,
1081
+ "step": 3060
1082
+ },
1083
+ {
1084
+ "epoch": 0.23927905531385954,
1085
+ "grad_norm": 0.9296875,
1086
+ "learning_rate": 2.3025e-05,
1087
+ "loss": 1.078106689453125,
1088
+ "step": 3080
1089
+ },
1090
+ {
1091
+ "epoch": 0.24083281541330018,
1092
+ "grad_norm": 0.90234375,
1093
+ "learning_rate": 2.2525000000000002e-05,
1094
+ "loss": 1.0860605239868164,
1095
+ "step": 3100
1096
+ },
1097
+ {
1098
+ "epoch": 0.24238657551274084,
1099
+ "grad_norm": 0.88671875,
1100
+ "learning_rate": 2.2025e-05,
1101
+ "loss": 1.0743337631225587,
1102
+ "step": 3120
1103
+ },
1104
+ {
1105
+ "epoch": 0.24394033561218148,
1106
+ "grad_norm": 0.88671875,
1107
+ "learning_rate": 2.1525e-05,
1108
+ "loss": 1.0778118133544923,
1109
+ "step": 3140
1110
+ },
1111
+ {
1112
+ "epoch": 0.24549409571162212,
1113
+ "grad_norm": 0.9296875,
1114
+ "learning_rate": 2.1025e-05,
1115
+ "loss": 1.0981425285339355,
1116
+ "step": 3160
1117
+ },
1118
+ {
1119
+ "epoch": 0.24704785581106278,
1120
+ "grad_norm": 0.91015625,
1121
+ "learning_rate": 2.0525e-05,
1122
+ "loss": 1.0836584091186523,
1123
+ "step": 3180
1124
+ },
1125
+ {
1126
+ "epoch": 0.24860161591050342,
1127
+ "grad_norm": 0.8671875,
1128
+ "learning_rate": 2.0025000000000002e-05,
1129
+ "loss": 1.089561367034912,
1130
+ "step": 3200
1131
+ },
1132
+ {
1133
+ "epoch": 0.2501553760099441,
1134
+ "grad_norm": 0.9296875,
1135
+ "learning_rate": 1.9525e-05,
1136
+ "loss": 1.0788454055786132,
1137
+ "step": 3220
1138
+ },
1139
+ {
1140
+ "epoch": 0.2517091361093847,
1141
+ "grad_norm": 0.91015625,
1142
+ "learning_rate": 1.9025e-05,
1143
+ "loss": 1.078543758392334,
1144
+ "step": 3240
1145
+ },
1146
+ {
1147
+ "epoch": 0.25326289620882536,
1148
+ "grad_norm": 0.9140625,
1149
+ "learning_rate": 1.8525e-05,
1150
+ "loss": 1.1045896530151367,
1151
+ "step": 3260
1152
+ },
1153
+ {
1154
+ "epoch": 0.254816656308266,
1155
+ "grad_norm": 0.88671875,
1156
+ "learning_rate": 1.8025e-05,
1157
+ "loss": 1.0857179641723633,
1158
+ "step": 3280
1159
+ },
1160
+ {
1161
+ "epoch": 0.25637041640770664,
1162
+ "grad_norm": 0.87109375,
1163
+ "learning_rate": 1.7525e-05,
1164
+ "loss": 1.0980566024780274,
1165
+ "step": 3300
1166
+ },
1167
+ {
1168
+ "epoch": 0.2579241765071473,
1169
+ "grad_norm": 0.90234375,
1170
+ "learning_rate": 1.7025e-05,
1171
+ "loss": 1.0898794174194335,
1172
+ "step": 3320
1173
+ },
1174
+ {
1175
+ "epoch": 0.25947793660658797,
1176
+ "grad_norm": 0.93359375,
1177
+ "learning_rate": 1.6525000000000002e-05,
1178
+ "loss": 1.0813383102416991,
1179
+ "step": 3340
1180
+ },
1181
+ {
1182
+ "epoch": 0.2610316967060286,
1183
+ "grad_norm": 0.9140625,
1184
+ "learning_rate": 1.6025e-05,
1185
+ "loss": 1.0852994918823242,
1186
+ "step": 3360
1187
+ },
1188
+ {
1189
+ "epoch": 0.26258545680546924,
1190
+ "grad_norm": 0.9296875,
1191
+ "learning_rate": 1.5525e-05,
1192
+ "loss": 1.0736425399780274,
1193
+ "step": 3380
1194
+ },
1195
+ {
1196
+ "epoch": 0.2641392169049099,
1197
+ "grad_norm": 0.87890625,
1198
+ "learning_rate": 1.5025000000000001e-05,
1199
+ "loss": 1.0873353004455566,
1200
+ "step": 3400
1201
+ },
1202
+ {
1203
+ "epoch": 0.2656929770043505,
1204
+ "grad_norm": 0.90625,
1205
+ "learning_rate": 1.4524999999999999e-05,
1206
+ "loss": 1.0847795486450196,
1207
+ "step": 3420
1208
+ },
1209
+ {
1210
+ "epoch": 0.26724673710379115,
1211
+ "grad_norm": 0.90234375,
1212
+ "learning_rate": 1.4025000000000002e-05,
1213
+ "loss": 1.0983787536621095,
1214
+ "step": 3440
1215
+ },
1216
+ {
1217
+ "epoch": 0.26880049720323185,
1218
+ "grad_norm": 0.8828125,
1219
+ "learning_rate": 1.3525000000000002e-05,
1220
+ "loss": 1.0719210624694824,
1221
+ "step": 3460
1222
+ },
1223
+ {
1224
+ "epoch": 0.2703542573026725,
1225
+ "grad_norm": 0.87890625,
1226
+ "learning_rate": 1.3025000000000002e-05,
1227
+ "loss": 1.0850942611694336,
1228
+ "step": 3480
1229
+ },
1230
+ {
1231
+ "epoch": 0.2719080174021131,
1232
+ "grad_norm": 0.890625,
1233
+ "learning_rate": 1.2525000000000001e-05,
1234
+ "loss": 1.0767460823059083,
1235
+ "step": 3500
1236
+ },
1237
+ {
1238
+ "epoch": 0.27346177750155376,
1239
+ "grad_norm": 0.90234375,
1240
+ "learning_rate": 1.2025000000000001e-05,
1241
+ "loss": 1.0981364250183105,
1242
+ "step": 3520
1243
+ },
1244
+ {
1245
+ "epoch": 0.2750155376009944,
1246
+ "grad_norm": 0.90234375,
1247
+ "learning_rate": 1.1525e-05,
1248
+ "loss": 1.0713367462158203,
1249
+ "step": 3540
1250
+ },
1251
+ {
1252
+ "epoch": 0.27656929770043504,
1253
+ "grad_norm": 0.8984375,
1254
+ "learning_rate": 1.1025e-05,
1255
+ "loss": 1.074637222290039,
1256
+ "step": 3560
1257
+ },
1258
+ {
1259
+ "epoch": 0.2781230577998757,
1260
+ "grad_norm": 0.91015625,
1261
+ "learning_rate": 1.0525e-05,
1262
+ "loss": 1.0917478561401368,
1263
+ "step": 3580
1264
+ },
1265
+ {
1266
+ "epoch": 0.27967681789931637,
1267
+ "grad_norm": 0.8828125,
1268
+ "learning_rate": 1.0025000000000001e-05,
1269
+ "loss": 1.0934381484985352,
1270
+ "step": 3600
1271
+ },
1272
+ {
1273
+ "epoch": 0.281230577998757,
1274
+ "grad_norm": 0.953125,
1275
+ "learning_rate": 9.525000000000001e-06,
1276
+ "loss": 1.0998394966125489,
1277
+ "step": 3620
1278
+ },
1279
+ {
1280
+ "epoch": 0.28278433809819764,
1281
+ "grad_norm": 0.8828125,
1282
+ "learning_rate": 9.025e-06,
1283
+ "loss": 1.087621021270752,
1284
+ "step": 3640
1285
+ },
1286
+ {
1287
+ "epoch": 0.2843380981976383,
1288
+ "grad_norm": 0.91015625,
1289
+ "learning_rate": 8.525e-06,
1290
+ "loss": 1.091860866546631,
1291
+ "step": 3660
1292
+ },
1293
+ {
1294
+ "epoch": 0.2858918582970789,
1295
+ "grad_norm": 0.9375,
1296
+ "learning_rate": 8.025e-06,
1297
+ "loss": 1.072180938720703,
1298
+ "step": 3680
1299
+ },
1300
+ {
1301
+ "epoch": 0.28744561839651955,
1302
+ "grad_norm": 0.8828125,
1303
+ "learning_rate": 7.525e-06,
1304
+ "loss": 1.0778998374938964,
1305
+ "step": 3700
1306
+ },
1307
+ {
1308
+ "epoch": 0.28899937849596025,
1309
+ "grad_norm": 0.875,
1310
+ "learning_rate": 7.025000000000001e-06,
1311
+ "loss": 1.0709803581237793,
1312
+ "step": 3720
1313
+ },
1314
+ {
1315
+ "epoch": 0.2905531385954009,
1316
+ "grad_norm": 0.91015625,
1317
+ "learning_rate": 6.525e-06,
1318
+ "loss": 1.1010093688964844,
1319
+ "step": 3740
1320
+ },
1321
+ {
1322
+ "epoch": 0.2921068986948415,
1323
+ "grad_norm": 0.91015625,
1324
+ "learning_rate": 6.025e-06,
1325
+ "loss": 1.0703121185302735,
1326
+ "step": 3760
1327
+ },
1328
+ {
1329
+ "epoch": 0.29366065879428216,
1330
+ "grad_norm": 0.88671875,
1331
+ "learning_rate": 5.5250000000000005e-06,
1332
+ "loss": 1.0773000717163086,
1333
+ "step": 3780
1334
+ },
1335
+ {
1336
+ "epoch": 0.2952144188937228,
1337
+ "grad_norm": 0.91796875,
1338
+ "learning_rate": 5.025e-06,
1339
+ "loss": 1.0894964218139649,
1340
+ "step": 3800
1341
+ },
1342
+ {
1343
+ "epoch": 0.29676817899316343,
1344
+ "grad_norm": 0.87890625,
1345
+ "learning_rate": 4.525e-06,
1346
+ "loss": 1.060502815246582,
1347
+ "step": 3820
1348
+ },
1349
+ {
1350
+ "epoch": 0.2983219390926041,
1351
+ "grad_norm": 0.890625,
1352
+ "learning_rate": 4.0250000000000004e-06,
1353
+ "loss": 1.0844976425170898,
1354
+ "step": 3840
1355
+ },
1356
+ {
1357
+ "epoch": 0.29987569919204476,
1358
+ "grad_norm": 0.90625,
1359
+ "learning_rate": 3.5249999999999997e-06,
1360
+ "loss": 1.068390464782715,
1361
+ "step": 3860
1362
+ },
1363
+ {
1364
+ "epoch": 0.3014294592914854,
1365
+ "grad_norm": 0.8828125,
1366
+ "learning_rate": 3.0250000000000003e-06,
1367
+ "loss": 1.0733464241027832,
1368
+ "step": 3880
1369
+ },
1370
+ {
1371
+ "epoch": 0.30298321939092604,
1372
+ "grad_norm": 0.92578125,
1373
+ "learning_rate": 2.5250000000000004e-06,
1374
+ "loss": 1.0655000686645508,
1375
+ "step": 3900
1376
+ },
1377
+ {
1378
+ "epoch": 0.3045369794903667,
1379
+ "grad_norm": 0.88671875,
1380
+ "learning_rate": 2.025e-06,
1381
+ "loss": 1.0655412673950195,
1382
+ "step": 3920
1383
+ },
1384
+ {
1385
+ "epoch": 0.3060907395898073,
1386
+ "grad_norm": 0.90234375,
1387
+ "learning_rate": 1.525e-06,
1388
+ "loss": 1.0558664321899414,
1389
+ "step": 3940
1390
+ },
1391
+ {
1392
+ "epoch": 0.307644499689248,
1393
+ "grad_norm": 0.94140625,
1394
+ "learning_rate": 1.0250000000000001e-06,
1395
+ "loss": 1.1024866104125977,
1396
+ "step": 3960
1397
+ },
1398
+ {
1399
+ "epoch": 0.30919825978868865,
1400
+ "grad_norm": 0.91015625,
1401
+ "learning_rate": 5.250000000000001e-07,
1402
+ "loss": 1.0651491165161133,
1403
+ "step": 3980
1404
+ },
1405
+ {
1406
+ "epoch": 0.3107520198881293,
1407
+ "grad_norm": 0.9609375,
1408
+ "learning_rate": 2.5000000000000002e-08,
1409
+ "loss": 1.0959912300109864,
1410
+ "step": 4000
1411
+ }
1412
+ ],
1413
+ "logging_steps": 20,
1414
+ "max_steps": 4000,
1415
+ "num_input_tokens_seen": 0,
1416
+ "num_train_epochs": 1,
1417
+ "save_steps": 500,
1418
+ "stateful_callbacks": {
1419
+ "TrainerControl": {
1420
+ "args": {
1421
+ "should_epoch_stop": false,
1422
+ "should_evaluate": false,
1423
+ "should_log": false,
1424
+ "should_save": true,
1425
+ "should_training_stop": true
1426
+ },
1427
+ "attributes": {}
1428
+ }
1429
+ },
1430
+ "total_flos": 9.3750546137088e+17,
1431
+ "train_batch_size": 32,
1432
+ "trial_name": null,
1433
+ "trial_params": null
1434
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989fbd47b6a05e982f81abdb2d6ae79f41c2a90d7a85b4c5f217a5a1b2edad8c
3
+ size 5201