Hugging Face's logo

SamMikaelson
/
0.6B-8000C

Safetensors
qwen3
Model card Files
xet
Community
SamMikaelson commited on
Commit
248e72e
·
verified ·
1 Parent(s): 4917c76

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +99 -0
  4. config.json +62 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. model.safetensors +3 -0
  8. optimizer.pt +3 -0
  9. rng_state.pth +3 -0
  10. scaler.pt +3 -0
  11. scheduler.pt +3 -0
  12. special_tokens_map.json +31 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +240 -0
  15. trainer_state.json +729 -0
  16. training_args.bin +3 -0
  17. vocab.json +0 -0
.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 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 forward_message in messages %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- set message = messages[index] %}
21
+ {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
22
+ {%- set tool_start = '<tool_response>' %}
23
+ {%- set tool_start_length = tool_start|length %}
24
+ {%- set start_of_message = current_content[:tool_start_length] %}
25
+ {%- set tool_end = '</tool_response>' %}
26
+ {%- set tool_end_length = tool_end|length %}
27
+ {%- set start_pos = (current_content|length) - tool_end_length %}
28
+ {%- if start_pos < 0 %}
29
+ {%- set start_pos = 0 %}
30
+ {%- endif %}
31
+ {%- set end_of_message = current_content[start_pos:] %}
32
+ {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
33
+ {%- set ns.multi_step_tool = false %}
34
+ {%- set ns.last_query_index = index %}
35
+ {%- endif %}
36
+ {%- endfor %}
37
+ {%- for message in messages %}
38
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
39
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
40
+ {%- elif message.role == "assistant" %}
41
+ {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
42
+ {%- set content = m_content %}
43
+ {%- set reasoning_content = '' %}
44
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
45
+ {%- set reasoning_content = message.reasoning_content %}
46
+ {%- else %}
47
+ {%- if '</think>' in m_content %}
48
+ {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
49
+ {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
50
+ {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
51
+ {%- endif %}
52
+ {%- endif %}
53
+ {%- if loop.index0 > ns.last_query_index %}
54
+ {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
55
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
56
+ {%- else %}
57
+ {{- '<|im_start|>' + message.role + '\n' + content }}
58
+ {%- endif %}
59
+ {%- else %}
60
+ {{- '<|im_start|>' + message.role + '\n' + content }}
61
+ {%- endif %}
62
+ {%- if message.tool_calls %}
63
+ {%- for tool_call in message.tool_calls %}
64
+ {%- if (loop.first and content) or (not loop.first) %}
65
+ {{- '\n' }}
66
+ {%- endif %}
67
+ {%- if tool_call.function %}
68
+ {%- set tool_call = tool_call.function %}
69
+ {%- endif %}
70
+ {{- '<tool_call>\n{"name": "' }}
71
+ {{- tool_call.name }}
72
+ {{- '", "arguments": ' }}
73
+ {%- if tool_call.arguments is string %}
74
+ {{- tool_call.arguments }}
75
+ {%- else %}
76
+ {{- tool_call.arguments | tojson }}
77
+ {%- endif %}
78
+ {{- '}\n</tool_call>' }}
79
+ {%- endfor %}
80
+ {%- endif %}
81
+ {{- '<|im_end|>\n' }}
82
+ {%- elif message.role == "tool" %}
83
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
84
+ {{- '<|im_start|>user' }}
85
+ {%- endif %}
86
+ {{- '\n<tool_response>\n' }}
87
+ {{- message.content }}
88
+ {{- '\n</tool_response>' }}
89
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
90
+ {{- '<|im_end|>\n' }}
91
+ {%- endif %}
92
+ {%- endif %}
93
+ {%- endfor %}
94
+ {%- if add_generation_prompt %}
95
+ {{- '<|im_start|>assistant\n' }}
96
+ {%- if enable_thinking is defined and enable_thinking is false %}
97
+ {{- '<think>\n\n</think>\n\n' }}
98
+ {%- endif %}
99
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
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
+ ],
44
+ "max_position_embeddings": 40960,
45
+ "max_window_layers": 28,
46
+ "model_type": "qwen3",
47
+ "num_attention_heads": 16,
48
+ "num_hidden_layers": 28,
49
+ "num_key_value_heads": 8,
50
+ "pad_token_id": 151654,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 1000000,
54
+ "sliding_window": null,
55
+ "tie_word_embeddings": false,
56
+ "transformers_version": "4.56.2",
57
+ "unsloth_fixed": true,
58
+ "unsloth_version": "2025.12.9",
59
+ "use_cache": true,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 151936
62
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "max_length": 40960,
8
+ "pad_token_id": 151654,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.56.2"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:712c4be94d20c1ec18ea877f278fad03fa7fbebc39810901b18bb86e30b45ddc
3
+ size 3006565056
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423889128e3298f0f1451ccc95f53814c0bd615cd5fdffaf47fdee3631a90b9f
3
+ size 2456077277
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5de1c2a911a76c8160b4fd062dfacad89ab25999e6f27061cd5d1bfbdf815a77
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ed90088567edbe2741e0ab0fab1feb9de45c4ac4edb2eb0fbf70b671ccbc0d
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f51a6c4c9e30c8bf1002c876397d1c18507fb3e9701117ff474cf45c22bf090
3
+ size 1465
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": "<|vision_pad|>",
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": 40960,
235
+ "pad_token": "<|vision_pad|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
trainer_state.json ADDED
@@ -0,0 +1,729 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 8072,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0004956015363647627,
14
+ "grad_norm": Infinity,
15
+ "learning_rate": 0.0,
16
+ "loss": 4.2404,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.04956015363647627,
21
+ "grad_norm": 2.9627790451049805,
22
+ "learning_rate": 4.9435973720094217e-05,
23
+ "loss": 1.4839,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.09912030727295254,
28
+ "grad_norm": 2.454435348510742,
29
+ "learning_rate": 4.8816164621296644e-05,
30
+ "loss": 1.1294,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.14868046090942882,
35
+ "grad_norm": 2.297229290008545,
36
+ "learning_rate": 4.819635552249907e-05,
37
+ "loss": 1.0776,
38
+ "step": 300
39
+ },
40
+ {
41
+ "epoch": 0.19824061454590508,
42
+ "grad_norm": 2.2293310165405273,
43
+ "learning_rate": 4.75765464237015e-05,
44
+ "loss": 1.0337,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 0.24780076818238136,
49
+ "grad_norm": 2.114262342453003,
50
+ "learning_rate": 4.6956737324903934e-05,
51
+ "loss": 1.0028,
52
+ "step": 500
53
+ },
54
+ {
55
+ "epoch": 0.24780076818238136,
56
+ "eval_loss": 2.039673328399658,
57
+ "eval_runtime": 372.7152,
58
+ "eval_samples_per_second": 6.501,
59
+ "eval_steps_per_second": 3.252,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 0.29736092181885765,
64
+ "grad_norm": 2.0340042114257812,
65
+ "learning_rate": 4.633692822610636e-05,
66
+ "loss": 0.9991,
67
+ "step": 600
68
+ },
69
+ {
70
+ "epoch": 0.3469210754553339,
71
+ "grad_norm": 2.1469831466674805,
72
+ "learning_rate": 4.571711912730879e-05,
73
+ "loss": 0.9784,
74
+ "step": 700
75
+ },
76
+ {
77
+ "epoch": 0.39648122909181016,
78
+ "grad_norm": 1.7528233528137207,
79
+ "learning_rate": 4.509731002851122e-05,
80
+ "loss": 0.9586,
81
+ "step": 800
82
+ },
83
+ {
84
+ "epoch": 0.4460413827282865,
85
+ "grad_norm": 1.9578274488449097,
86
+ "learning_rate": 4.447750092971365e-05,
87
+ "loss": 0.9236,
88
+ "step": 900
89
+ },
90
+ {
91
+ "epoch": 0.49560153636476273,
92
+ "grad_norm": 2.0073506832122803,
93
+ "learning_rate": 4.385769183091608e-05,
94
+ "loss": 0.9236,
95
+ "step": 1000
96
+ },
97
+ {
98
+ "epoch": 0.49560153636476273,
99
+ "eval_loss": 1.9146523475646973,
100
+ "eval_runtime": 366.7833,
101
+ "eval_samples_per_second": 6.606,
102
+ "eval_steps_per_second": 3.304,
103
+ "step": 1000
104
+ },
105
+ {
106
+ "epoch": 0.545161690001239,
107
+ "grad_norm": 1.850284457206726,
108
+ "learning_rate": 4.3237882732118514e-05,
109
+ "loss": 0.9076,
110
+ "step": 1100
111
+ },
112
+ {
113
+ "epoch": 0.5947218436377153,
114
+ "grad_norm": 1.8297762870788574,
115
+ "learning_rate": 4.2618073633320935e-05,
116
+ "loss": 0.8888,
117
+ "step": 1200
118
+ },
119
+ {
120
+ "epoch": 0.6442819972741916,
121
+ "grad_norm": 1.9211479425430298,
122
+ "learning_rate": 4.199826453452337e-05,
123
+ "loss": 0.8918,
124
+ "step": 1300
125
+ },
126
+ {
127
+ "epoch": 0.6938421509106678,
128
+ "grad_norm": 1.6193498373031616,
129
+ "learning_rate": 4.13784554357258e-05,
130
+ "loss": 0.881,
131
+ "step": 1400
132
+ },
133
+ {
134
+ "epoch": 0.7434023045471441,
135
+ "grad_norm": 2.319871425628662,
136
+ "learning_rate": 4.075864633692823e-05,
137
+ "loss": 0.8831,
138
+ "step": 1500
139
+ },
140
+ {
141
+ "epoch": 0.7434023045471441,
142
+ "eval_loss": 1.9017372131347656,
143
+ "eval_runtime": 366.5077,
144
+ "eval_samples_per_second": 6.611,
145
+ "eval_steps_per_second": 3.307,
146
+ "step": 1500
147
+ },
148
+ {
149
+ "epoch": 0.7929624581836203,
150
+ "grad_norm": 1.7725250720977783,
151
+ "learning_rate": 4.013883723813065e-05,
152
+ "loss": 0.8829,
153
+ "step": 1600
154
+ },
155
+ {
156
+ "epoch": 0.8425226118200967,
157
+ "grad_norm": 1.7268086671829224,
158
+ "learning_rate": 3.951902813933309e-05,
159
+ "loss": 0.8725,
160
+ "step": 1700
161
+ },
162
+ {
163
+ "epoch": 0.892082765456573,
164
+ "grad_norm": 2.02824068069458,
165
+ "learning_rate": 3.8899219040535514e-05,
166
+ "loss": 0.8541,
167
+ "step": 1800
168
+ },
169
+ {
170
+ "epoch": 0.9416429190930492,
171
+ "grad_norm": 1.5427559614181519,
172
+ "learning_rate": 3.827940994173795e-05,
173
+ "loss": 0.8474,
174
+ "step": 1900
175
+ },
176
+ {
177
+ "epoch": 0.9912030727295255,
178
+ "grad_norm": 1.56866455078125,
179
+ "learning_rate": 3.7659600842940377e-05,
180
+ "loss": 0.8364,
181
+ "step": 2000
182
+ },
183
+ {
184
+ "epoch": 0.9912030727295255,
185
+ "eval_loss": 1.8795244693756104,
186
+ "eval_runtime": 361.6572,
187
+ "eval_samples_per_second": 6.7,
188
+ "eval_steps_per_second": 3.351,
189
+ "step": 2000
190
+ },
191
+ {
192
+ "epoch": 1.0406393259819104,
193
+ "grad_norm": 1.7035953998565674,
194
+ "learning_rate": 3.7039791744142804e-05,
195
+ "loss": 0.75,
196
+ "step": 2100
197
+ },
198
+ {
199
+ "epoch": 1.090199479618387,
200
+ "grad_norm": 1.8885678052902222,
201
+ "learning_rate": 3.641998264534524e-05,
202
+ "loss": 0.7393,
203
+ "step": 2200
204
+ },
205
+ {
206
+ "epoch": 1.1397596332548632,
207
+ "grad_norm": 1.467885136604309,
208
+ "learning_rate": 3.5800173546547666e-05,
209
+ "loss": 0.7352,
210
+ "step": 2300
211
+ },
212
+ {
213
+ "epoch": 1.1893197868913394,
214
+ "grad_norm": 1.5108469724655151,
215
+ "learning_rate": 3.5180364447750094e-05,
216
+ "loss": 0.7285,
217
+ "step": 2400
218
+ },
219
+ {
220
+ "epoch": 1.2388799405278157,
221
+ "grad_norm": 1.7523285150527954,
222
+ "learning_rate": 3.456055534895252e-05,
223
+ "loss": 0.7313,
224
+ "step": 2500
225
+ },
226
+ {
227
+ "epoch": 1.2388799405278157,
228
+ "eval_loss": 1.92574942111969,
229
+ "eval_runtime": 360.7532,
230
+ "eval_samples_per_second": 6.717,
231
+ "eval_steps_per_second": 3.36,
232
+ "step": 2500
233
+ },
234
+ {
235
+ "epoch": 1.288440094164292,
236
+ "grad_norm": 1.5373412370681763,
237
+ "learning_rate": 3.3940746250154956e-05,
238
+ "loss": 0.7392,
239
+ "step": 2600
240
+ },
241
+ {
242
+ "epoch": 1.3380002478007682,
243
+ "grad_norm": 1.9129449129104614,
244
+ "learning_rate": 3.3320937151357384e-05,
245
+ "loss": 0.7395,
246
+ "step": 2700
247
+ },
248
+ {
249
+ "epoch": 1.3875604014372445,
250
+ "grad_norm": 1.8050382137298584,
251
+ "learning_rate": 3.270112805255982e-05,
252
+ "loss": 0.7311,
253
+ "step": 2800
254
+ },
255
+ {
256
+ "epoch": 1.4371205550737207,
257
+ "grad_norm": 1.5149444341659546,
258
+ "learning_rate": 3.208131895376224e-05,
259
+ "loss": 0.7238,
260
+ "step": 2900
261
+ },
262
+ {
263
+ "epoch": 1.486680708710197,
264
+ "grad_norm": 1.834263563156128,
265
+ "learning_rate": 3.1461509854964674e-05,
266
+ "loss": 0.7409,
267
+ "step": 3000
268
+ },
269
+ {
270
+ "epoch": 1.486680708710197,
271
+ "eval_loss": 1.9400999546051025,
272
+ "eval_runtime": 361.3757,
273
+ "eval_samples_per_second": 6.705,
274
+ "eval_steps_per_second": 3.354,
275
+ "step": 3000
276
+ },
277
+ {
278
+ "epoch": 1.5362408623466732,
279
+ "grad_norm": 1.5594300031661987,
280
+ "learning_rate": 3.08417007561671e-05,
281
+ "loss": 0.7223,
282
+ "step": 3100
283
+ },
284
+ {
285
+ "epoch": 1.5858010159831495,
286
+ "grad_norm": 1.8869357109069824,
287
+ "learning_rate": 3.0221891657369533e-05,
288
+ "loss": 0.7242,
289
+ "step": 3200
290
+ },
291
+ {
292
+ "epoch": 1.635361169619626,
293
+ "grad_norm": 1.4488883018493652,
294
+ "learning_rate": 2.960208255857196e-05,
295
+ "loss": 0.7195,
296
+ "step": 3300
297
+ },
298
+ {
299
+ "epoch": 1.684921323256102,
300
+ "grad_norm": 1.5809857845306396,
301
+ "learning_rate": 2.8982273459774388e-05,
302
+ "loss": 0.7162,
303
+ "step": 3400
304
+ },
305
+ {
306
+ "epoch": 1.7344814768925785,
307
+ "grad_norm": 1.572243332862854,
308
+ "learning_rate": 2.836246436097682e-05,
309
+ "loss": 0.7193,
310
+ "step": 3500
311
+ },
312
+ {
313
+ "epoch": 1.7344814768925785,
314
+ "eval_loss": 1.9336891174316406,
315
+ "eval_runtime": 364.4827,
316
+ "eval_samples_per_second": 6.648,
317
+ "eval_steps_per_second": 3.325,
318
+ "step": 3500
319
+ },
320
+ {
321
+ "epoch": 1.7840416305290545,
322
+ "grad_norm": 1.4607752561569214,
323
+ "learning_rate": 2.774265526217925e-05,
324
+ "loss": 0.7239,
325
+ "step": 3600
326
+ },
327
+ {
328
+ "epoch": 1.833601784165531,
329
+ "grad_norm": 1.6760728359222412,
330
+ "learning_rate": 2.712284616338168e-05,
331
+ "loss": 0.7136,
332
+ "step": 3700
333
+ },
334
+ {
335
+ "epoch": 1.883161937802007,
336
+ "grad_norm": 1.4097050428390503,
337
+ "learning_rate": 2.650303706458411e-05,
338
+ "loss": 0.7207,
339
+ "step": 3800
340
+ },
341
+ {
342
+ "epoch": 1.9327220914384835,
343
+ "grad_norm": 1.3667641878128052,
344
+ "learning_rate": 2.588322796578654e-05,
345
+ "loss": 0.7068,
346
+ "step": 3900
347
+ },
348
+ {
349
+ "epoch": 1.9822822450749598,
350
+ "grad_norm": 1.767014980316162,
351
+ "learning_rate": 2.526341886698897e-05,
352
+ "loss": 0.7089,
353
+ "step": 4000
354
+ },
355
+ {
356
+ "epoch": 1.9822822450749598,
357
+ "eval_loss": 1.8813990354537964,
358
+ "eval_runtime": 360.4834,
359
+ "eval_samples_per_second": 6.722,
360
+ "eval_steps_per_second": 3.362,
361
+ "step": 4000
362
+ },
363
+ {
364
+ "epoch": 2.031718498327345,
365
+ "grad_norm": 1.5913705825805664,
366
+ "learning_rate": 2.46436097681914e-05,
367
+ "loss": 0.6173,
368
+ "step": 4100
369
+ },
370
+ {
371
+ "epoch": 2.081278651963821,
372
+ "grad_norm": 2.040769577026367,
373
+ "learning_rate": 2.402380066939383e-05,
374
+ "loss": 0.5627,
375
+ "step": 4200
376
+ },
377
+ {
378
+ "epoch": 2.1308388056002974,
379
+ "grad_norm": 1.890949010848999,
380
+ "learning_rate": 2.3403991570596257e-05,
381
+ "loss": 0.5706,
382
+ "step": 4300
383
+ },
384
+ {
385
+ "epoch": 2.180398959236774,
386
+ "grad_norm": 1.6909950971603394,
387
+ "learning_rate": 2.278418247179869e-05,
388
+ "loss": 0.5648,
389
+ "step": 4400
390
+ },
391
+ {
392
+ "epoch": 2.22995911287325,
393
+ "grad_norm": 1.497389316558838,
394
+ "learning_rate": 2.2164373373001116e-05,
395
+ "loss": 0.5665,
396
+ "step": 4500
397
+ },
398
+ {
399
+ "epoch": 2.22995911287325,
400
+ "eval_loss": 2.1176860332489014,
401
+ "eval_runtime": 362.5264,
402
+ "eval_samples_per_second": 6.684,
403
+ "eval_steps_per_second": 3.343,
404
+ "step": 4500
405
+ },
406
+ {
407
+ "epoch": 2.2795192665097264,
408
+ "grad_norm": 2.142023801803589,
409
+ "learning_rate": 2.1544564274203547e-05,
410
+ "loss": 0.5773,
411
+ "step": 4600
412
+ },
413
+ {
414
+ "epoch": 2.3290794201462024,
415
+ "grad_norm": 1.8469089269638062,
416
+ "learning_rate": 2.092475517540598e-05,
417
+ "loss": 0.5844,
418
+ "step": 4700
419
+ },
420
+ {
421
+ "epoch": 2.378639573782679,
422
+ "grad_norm": 1.9878648519515991,
423
+ "learning_rate": 2.0304946076608406e-05,
424
+ "loss": 0.5776,
425
+ "step": 4800
426
+ },
427
+ {
428
+ "epoch": 2.428199727419155,
429
+ "grad_norm": 1.9932163953781128,
430
+ "learning_rate": 1.9685136977810837e-05,
431
+ "loss": 0.5778,
432
+ "step": 4900
433
+ },
434
+ {
435
+ "epoch": 2.4777598810556314,
436
+ "grad_norm": 1.8406933546066284,
437
+ "learning_rate": 1.9065327879013265e-05,
438
+ "loss": 0.5693,
439
+ "step": 5000
440
+ },
441
+ {
442
+ "epoch": 2.4777598810556314,
443
+ "eval_loss": 2.1271347999572754,
444
+ "eval_runtime": 361.2042,
445
+ "eval_samples_per_second": 6.708,
446
+ "eval_steps_per_second": 3.355,
447
+ "step": 5000
448
+ },
449
+ {
450
+ "epoch": 2.5273200346921074,
451
+ "grad_norm": 1.8426705598831177,
452
+ "learning_rate": 1.8445518780215696e-05,
453
+ "loss": 0.5731,
454
+ "step": 5100
455
+ },
456
+ {
457
+ "epoch": 2.576880188328584,
458
+ "grad_norm": 1.974214792251587,
459
+ "learning_rate": 1.7825709681418124e-05,
460
+ "loss": 0.5701,
461
+ "step": 5200
462
+ },
463
+ {
464
+ "epoch": 2.62644034196506,
465
+ "grad_norm": 1.9426707029342651,
466
+ "learning_rate": 1.7205900582620555e-05,
467
+ "loss": 0.5766,
468
+ "step": 5300
469
+ },
470
+ {
471
+ "epoch": 2.6760004956015364,
472
+ "grad_norm": 1.796884298324585,
473
+ "learning_rate": 1.6586091483822982e-05,
474
+ "loss": 0.5584,
475
+ "step": 5400
476
+ },
477
+ {
478
+ "epoch": 2.7255606492380124,
479
+ "grad_norm": 2.1729025840759277,
480
+ "learning_rate": 1.5966282385025413e-05,
481
+ "loss": 0.5742,
482
+ "step": 5500
483
+ },
484
+ {
485
+ "epoch": 2.7255606492380124,
486
+ "eval_loss": 2.149742841720581,
487
+ "eval_runtime": 361.8954,
488
+ "eval_samples_per_second": 6.695,
489
+ "eval_steps_per_second": 3.349,
490
+ "step": 5500
491
+ },
492
+ {
493
+ "epoch": 2.775120802874489,
494
+ "grad_norm": 1.7941385507583618,
495
+ "learning_rate": 1.534647328622784e-05,
496
+ "loss": 0.5635,
497
+ "step": 5600
498
+ },
499
+ {
500
+ "epoch": 2.8246809565109654,
501
+ "grad_norm": 2.344470739364624,
502
+ "learning_rate": 1.4726664187430272e-05,
503
+ "loss": 0.5716,
504
+ "step": 5700
505
+ },
506
+ {
507
+ "epoch": 2.8742411101474414,
508
+ "grad_norm": 1.6030564308166504,
509
+ "learning_rate": 1.41068550886327e-05,
510
+ "loss": 0.5691,
511
+ "step": 5800
512
+ },
513
+ {
514
+ "epoch": 2.9238012637839175,
515
+ "grad_norm": 1.6917791366577148,
516
+ "learning_rate": 1.3487045989835131e-05,
517
+ "loss": 0.5678,
518
+ "step": 5900
519
+ },
520
+ {
521
+ "epoch": 2.973361417420394,
522
+ "grad_norm": 1.7974952459335327,
523
+ "learning_rate": 1.2867236891037562e-05,
524
+ "loss": 0.5609,
525
+ "step": 6000
526
+ },
527
+ {
528
+ "epoch": 2.973361417420394,
529
+ "eval_loss": 2.1735124588012695,
530
+ "eval_runtime": 362.267,
531
+ "eval_samples_per_second": 6.688,
532
+ "eval_steps_per_second": 3.346,
533
+ "step": 6000
534
+ },
535
+ {
536
+ "epoch": 3.0227976706727793,
537
+ "grad_norm": 2.0832440853118896,
538
+ "learning_rate": 1.224742779223999e-05,
539
+ "loss": 0.494,
540
+ "step": 6100
541
+ },
542
+ {
543
+ "epoch": 3.0723578243092553,
544
+ "grad_norm": 1.8607770204544067,
545
+ "learning_rate": 1.162761869344242e-05,
546
+ "loss": 0.3946,
547
+ "step": 6200
548
+ },
549
+ {
550
+ "epoch": 3.121917977945732,
551
+ "grad_norm": 2.1528215408325195,
552
+ "learning_rate": 1.100780959464485e-05,
553
+ "loss": 0.3964,
554
+ "step": 6300
555
+ },
556
+ {
557
+ "epoch": 3.171478131582208,
558
+ "grad_norm": 2.327425718307495,
559
+ "learning_rate": 1.038800049584728e-05,
560
+ "loss": 0.3915,
561
+ "step": 6400
562
+ },
563
+ {
564
+ "epoch": 3.2210382852186843,
565
+ "grad_norm": 1.8909003734588623,
566
+ "learning_rate": 9.768191397049709e-06,
567
+ "loss": 0.3989,
568
+ "step": 6500
569
+ },
570
+ {
571
+ "epoch": 3.2210382852186843,
572
+ "eval_loss": 2.5916407108306885,
573
+ "eval_runtime": 367.5177,
574
+ "eval_samples_per_second": 6.593,
575
+ "eval_steps_per_second": 3.298,
576
+ "step": 6500
577
+ },
578
+ {
579
+ "epoch": 3.2705984388551603,
580
+ "grad_norm": 2.429757595062256,
581
+ "learning_rate": 9.14838229825214e-06,
582
+ "loss": 0.3955,
583
+ "step": 6600
584
+ },
585
+ {
586
+ "epoch": 3.320158592491637,
587
+ "grad_norm": 2.5529799461364746,
588
+ "learning_rate": 8.52857319945457e-06,
589
+ "loss": 0.3921,
590
+ "step": 6700
591
+ },
592
+ {
593
+ "epoch": 3.369718746128113,
594
+ "grad_norm": 2.185617446899414,
595
+ "learning_rate": 7.908764100656999e-06,
596
+ "loss": 0.4004,
597
+ "step": 6800
598
+ },
599
+ {
600
+ "epoch": 3.4192788997645893,
601
+ "grad_norm": 2.2846291065216064,
602
+ "learning_rate": 7.288955001859428e-06,
603
+ "loss": 0.3938,
604
+ "step": 6900
605
+ },
606
+ {
607
+ "epoch": 3.4688390534010654,
608
+ "grad_norm": 2.211652994155884,
609
+ "learning_rate": 6.6691459030618575e-06,
610
+ "loss": 0.3861,
611
+ "step": 7000
612
+ },
613
+ {
614
+ "epoch": 3.4688390534010654,
615
+ "eval_loss": 2.668076753616333,
616
+ "eval_runtime": 365.3913,
617
+ "eval_samples_per_second": 6.631,
618
+ "eval_steps_per_second": 3.317,
619
+ "step": 7000
620
+ },
621
+ {
622
+ "epoch": 3.518399207037542,
623
+ "grad_norm": 2.2957966327667236,
624
+ "learning_rate": 6.049336804264287e-06,
625
+ "loss": 0.3851,
626
+ "step": 7100
627
+ },
628
+ {
629
+ "epoch": 3.567959360674018,
630
+ "grad_norm": 2.1889781951904297,
631
+ "learning_rate": 5.429527705466716e-06,
632
+ "loss": 0.3957,
633
+ "step": 7200
634
+ },
635
+ {
636
+ "epoch": 3.6175195143104943,
637
+ "grad_norm": 2.914120674133301,
638
+ "learning_rate": 4.809718606669146e-06,
639
+ "loss": 0.3995,
640
+ "step": 7300
641
+ },
642
+ {
643
+ "epoch": 3.667079667946971,
644
+ "grad_norm": 2.438662528991699,
645
+ "learning_rate": 4.189909507871576e-06,
646
+ "loss": 0.3875,
647
+ "step": 7400
648
+ },
649
+ {
650
+ "epoch": 3.716639821583447,
651
+ "grad_norm": 2.4311559200286865,
652
+ "learning_rate": 3.570100409074005e-06,
653
+ "loss": 0.3825,
654
+ "step": 7500
655
+ },
656
+ {
657
+ "epoch": 3.716639821583447,
658
+ "eval_loss": 2.6605801582336426,
659
+ "eval_runtime": 365.0751,
660
+ "eval_samples_per_second": 6.637,
661
+ "eval_steps_per_second": 3.32,
662
+ "step": 7500
663
+ },
664
+ {
665
+ "epoch": 3.7661999752199233,
666
+ "grad_norm": 2.665722608566284,
667
+ "learning_rate": 2.950291310276435e-06,
668
+ "loss": 0.3872,
669
+ "step": 7600
670
+ },
671
+ {
672
+ "epoch": 3.8157601288563994,
673
+ "grad_norm": 2.206805467605591,
674
+ "learning_rate": 2.330482211478865e-06,
675
+ "loss": 0.3899,
676
+ "step": 7700
677
+ },
678
+ {
679
+ "epoch": 3.865320282492876,
680
+ "grad_norm": 2.1605570316314697,
681
+ "learning_rate": 1.7106731126812943e-06,
682
+ "loss": 0.3866,
683
+ "step": 7800
684
+ },
685
+ {
686
+ "epoch": 3.914880436129352,
687
+ "grad_norm": 2.385495185852051,
688
+ "learning_rate": 1.0908640138837239e-06,
689
+ "loss": 0.3789,
690
+ "step": 7900
691
+ },
692
+ {
693
+ "epoch": 3.9644405897658284,
694
+ "grad_norm": 2.2114624977111816,
695
+ "learning_rate": 4.710549150861535e-07,
696
+ "loss": 0.3848,
697
+ "step": 8000
698
+ },
699
+ {
700
+ "epoch": 3.9644405897658284,
701
+ "eval_loss": 2.6748318672180176,
702
+ "eval_runtime": 366.1405,
703
+ "eval_samples_per_second": 6.618,
704
+ "eval_steps_per_second": 3.31,
705
+ "step": 8000
706
+ }
707
+ ],
708
+ "logging_steps": 100,
709
+ "max_steps": 8072,
710
+ "num_input_tokens_seen": 0,
711
+ "num_train_epochs": 4,
712
+ "save_steps": 500,
713
+ "stateful_callbacks": {
714
+ "TrainerControl": {
715
+ "args": {
716
+ "should_epoch_stop": false,
717
+ "should_evaluate": false,
718
+ "should_log": false,
719
+ "should_save": true,
720
+ "should_training_stop": true
721
+ },
722
+ "attributes": {}
723
+ }
724
+ },
725
+ "total_flos": 8.6417343971328e+16,
726
+ "train_batch_size": 2,
727
+ "trial_name": null,
728
+ "trial_params": null
729
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93183de419f46e113070370a8a5e729028f44e7e6fd7f9d4e71d3b8aed71b5ea
3
+ size 6161
vocab.json ADDED
The diff for this file is too large to render. See raw diff