VladShash commited on
Commit
f3ee385
·
verified ·
1 Parent(s): 986df85

Upload 14 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 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.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.52.4",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.52.4"
6
+ }
gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cde067699aee866bc9fcf98c6d6226da9054fc5981fd2af56cd6f18c14710d4
3
+ size 2384234968
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a266b61766978ee969473b49cb07bda3cd628662943d4c2e9372333905ae0f
3
+ size 1064
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": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
3
+ size 11422932
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
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|endoftext|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
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 +1,1280 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4466,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.005597850425436633,
14
+ "grad_norm": 9.592120170593262,
15
+ "learning_rate": 9.999287451410797e-06,
16
+ "loss": 1.4229,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.011195700850873265,
21
+ "grad_norm": 10.640639305114746,
22
+ "learning_rate": 9.997030034001815e-06,
23
+ "loss": 1.3665,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.016793551276309895,
28
+ "grad_norm": 11.189779281616211,
29
+ "learning_rate": 9.993227208820974e-06,
30
+ "loss": 1.0753,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.02239140170174653,
35
+ "grad_norm": 15.177507400512695,
36
+ "learning_rate": 9.987880151949976e-06,
37
+ "loss": 1.1291,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.027989252127183162,
42
+ "grad_norm": 6.662464141845703,
43
+ "learning_rate": 9.980990517047731e-06,
44
+ "loss": 1.2145,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.03358710255261979,
49
+ "grad_norm": 9.72287368774414,
50
+ "learning_rate": 9.972560434838943e-06,
51
+ "loss": 1.0737,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.03918495297805643,
56
+ "grad_norm": 8.399821281433105,
57
+ "learning_rate": 9.96259251245514e-06,
58
+ "loss": 0.9843,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 0.04478280340349306,
63
+ "grad_norm": 10.552536010742188,
64
+ "learning_rate": 9.951089832628388e-06,
65
+ "loss": 1.1599,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 0.05038065382892969,
70
+ "grad_norm": 8.101223945617676,
71
+ "learning_rate": 9.938055952737908e-06,
72
+ "loss": 1.1275,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 0.055978504254366325,
77
+ "grad_norm": 6.296974182128906,
78
+ "learning_rate": 9.923494903709896e-06,
79
+ "loss": 1.0943,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 0.06157635467980296,
84
+ "grad_norm": 8.705899238586426,
85
+ "learning_rate": 9.90741118877091e-06,
86
+ "loss": 1.0905,
87
+ "step": 275
88
+ },
89
+ {
90
+ "epoch": 0.06717420510523958,
91
+ "grad_norm": 13.383705139160156,
92
+ "learning_rate": 9.88980978205516e-06,
93
+ "loss": 1.0648,
94
+ "step": 300
95
+ },
96
+ {
97
+ "epoch": 0.07277205553067621,
98
+ "grad_norm": 6.9907636642456055,
99
+ "learning_rate": 9.8706961270662e-06,
100
+ "loss": 1.0228,
101
+ "step": 325
102
+ },
103
+ {
104
+ "epoch": 0.07836990595611286,
105
+ "grad_norm": 10.480993270874023,
106
+ "learning_rate": 9.85007613499343e-06,
107
+ "loss": 1.0825,
108
+ "step": 350
109
+ },
110
+ {
111
+ "epoch": 0.08396775638154949,
112
+ "grad_norm": 11.11700439453125,
113
+ "learning_rate": 9.82795618288397e-06,
114
+ "loss": 1.083,
115
+ "step": 375
116
+ },
117
+ {
118
+ "epoch": 0.08956560680698612,
119
+ "grad_norm": 10.408477783203125,
120
+ "learning_rate": 9.804343111670472e-06,
121
+ "loss": 1.1088,
122
+ "step": 400
123
+ },
124
+ {
125
+ "epoch": 0.09516345723242275,
126
+ "grad_norm": 8.23421859741211,
127
+ "learning_rate": 9.779244224055446e-06,
128
+ "loss": 1.1182,
129
+ "step": 425
130
+ },
131
+ {
132
+ "epoch": 0.10076130765785939,
133
+ "grad_norm": 11.640494346618652,
134
+ "learning_rate": 9.752667282252788e-06,
135
+ "loss": 1.152,
136
+ "step": 450
137
+ },
138
+ {
139
+ "epoch": 0.10635915808329602,
140
+ "grad_norm": 9.683300971984863,
141
+ "learning_rate": 9.724620505587205e-06,
142
+ "loss": 1.1508,
143
+ "step": 475
144
+ },
145
+ {
146
+ "epoch": 0.11195700850873265,
147
+ "grad_norm": 12.511320114135742,
148
+ "learning_rate": 9.69511256795226e-06,
149
+ "loss": 0.9544,
150
+ "step": 500
151
+ },
152
+ {
153
+ "epoch": 0.11755485893416928,
154
+ "grad_norm": 6.891467094421387,
155
+ "learning_rate": 9.664152595127834e-06,
156
+ "loss": 1.0014,
157
+ "step": 525
158
+ },
159
+ {
160
+ "epoch": 0.12315270935960591,
161
+ "grad_norm": 8.182930946350098,
162
+ "learning_rate": 9.63175016195784e-06,
163
+ "loss": 1.0197,
164
+ "step": 550
165
+ },
166
+ {
167
+ "epoch": 0.12875055978504255,
168
+ "grad_norm": 12.893110275268555,
169
+ "learning_rate": 9.597915289389067e-06,
170
+ "loss": 0.9908,
171
+ "step": 575
172
+ },
173
+ {
174
+ "epoch": 0.13434841021047916,
175
+ "grad_norm": 12.896308898925781,
176
+ "learning_rate": 9.56265844137203e-06,
177
+ "loss": 1.0792,
178
+ "step": 600
179
+ },
180
+ {
181
+ "epoch": 0.1399462606359158,
182
+ "grad_norm": 6.506565093994141,
183
+ "learning_rate": 9.525990521624855e-06,
184
+ "loss": 0.996,
185
+ "step": 625
186
+ },
187
+ {
188
+ "epoch": 0.14554411106135243,
189
+ "grad_norm": 11.659127235412598,
190
+ "learning_rate": 9.487922870261123e-06,
191
+ "loss": 1.1131,
192
+ "step": 650
193
+ },
194
+ {
195
+ "epoch": 0.15114196148678907,
196
+ "grad_norm": 11.150578498840332,
197
+ "learning_rate": 9.44846726028277e-06,
198
+ "loss": 1.0725,
199
+ "step": 675
200
+ },
201
+ {
202
+ "epoch": 0.15673981191222572,
203
+ "grad_norm": 10.530040740966797,
204
+ "learning_rate": 9.407635893939111e-06,
205
+ "loss": 1.2278,
206
+ "step": 700
207
+ },
208
+ {
209
+ "epoch": 0.16233766233766234,
210
+ "grad_norm": 10.855611801147461,
211
+ "learning_rate": 9.365441398953103e-06,
212
+ "loss": 0.9453,
213
+ "step": 725
214
+ },
215
+ {
216
+ "epoch": 0.16793551276309898,
217
+ "grad_norm": 9.590290069580078,
218
+ "learning_rate": 9.321896824616036e-06,
219
+ "loss": 1.0567,
220
+ "step": 750
221
+ },
222
+ {
223
+ "epoch": 0.1735333631885356,
224
+ "grad_norm": 8.801950454711914,
225
+ "learning_rate": 9.27701563775183e-06,
226
+ "loss": 1.1515,
227
+ "step": 775
228
+ },
229
+ {
230
+ "epoch": 0.17913121361397225,
231
+ "grad_norm": 14.007678985595703,
232
+ "learning_rate": 9.23081171855222e-06,
233
+ "loss": 0.904,
234
+ "step": 800
235
+ },
236
+ {
237
+ "epoch": 0.18472906403940886,
238
+ "grad_norm": 11.931122779846191,
239
+ "learning_rate": 9.183299356284102e-06,
240
+ "loss": 1.0948,
241
+ "step": 825
242
+ },
243
+ {
244
+ "epoch": 0.1903269144648455,
245
+ "grad_norm": 11.707269668579102,
246
+ "learning_rate": 9.134493244870347e-06,
247
+ "loss": 1.0469,
248
+ "step": 850
249
+ },
250
+ {
251
+ "epoch": 0.19592476489028213,
252
+ "grad_norm": 7.64641809463501,
253
+ "learning_rate": 9.084408478345486e-06,
254
+ "loss": 1.0608,
255
+ "step": 875
256
+ },
257
+ {
258
+ "epoch": 0.20152261531571877,
259
+ "grad_norm": 11.14941692352295,
260
+ "learning_rate": 9.033060546187651e-06,
261
+ "loss": 1.0769,
262
+ "step": 900
263
+ },
264
+ {
265
+ "epoch": 0.2071204657411554,
266
+ "grad_norm": 7.081947326660156,
267
+ "learning_rate": 8.98046532852822e-06,
268
+ "loss": 0.9925,
269
+ "step": 925
270
+ },
271
+ {
272
+ "epoch": 0.21271831616659204,
273
+ "grad_norm": 8.95167064666748,
274
+ "learning_rate": 8.926639091240636e-06,
275
+ "loss": 0.8297,
276
+ "step": 950
277
+ },
278
+ {
279
+ "epoch": 0.21831616659202865,
280
+ "grad_norm": 8.65690803527832,
281
+ "learning_rate": 8.871598480909945e-06,
282
+ "loss": 0.8238,
283
+ "step": 975
284
+ },
285
+ {
286
+ "epoch": 0.2239140170174653,
287
+ "grad_norm": 8.113872528076172,
288
+ "learning_rate": 8.815360519684579e-06,
289
+ "loss": 1.0677,
290
+ "step": 1000
291
+ },
292
+ {
293
+ "epoch": 0.22951186744290192,
294
+ "grad_norm": 7.616383075714111,
295
+ "learning_rate": 8.757942600012008e-06,
296
+ "loss": 1.0761,
297
+ "step": 1025
298
+ },
299
+ {
300
+ "epoch": 0.23510971786833856,
301
+ "grad_norm": 10.469049453735352,
302
+ "learning_rate": 8.699362479259847e-06,
303
+ "loss": 1.0677,
304
+ "step": 1050
305
+ },
306
+ {
307
+ "epoch": 0.24070756829377518,
308
+ "grad_norm": 10.512489318847656,
309
+ "learning_rate": 8.639638274224127e-06,
310
+ "loss": 0.9852,
311
+ "step": 1075
312
+ },
313
+ {
314
+ "epoch": 0.24630541871921183,
315
+ "grad_norm": 14.909335136413574,
316
+ "learning_rate": 8.578788455526398e-06,
317
+ "loss": 0.9895,
318
+ "step": 1100
319
+ },
320
+ {
321
+ "epoch": 0.25190326914464845,
322
+ "grad_norm": 9.663930892944336,
323
+ "learning_rate": 8.516831841901406e-06,
324
+ "loss": 0.9607,
325
+ "step": 1125
326
+ },
327
+ {
328
+ "epoch": 0.2575011195700851,
329
+ "grad_norm": 10.520059585571289,
330
+ "learning_rate": 8.453787594377117e-06,
331
+ "loss": 1.0332,
332
+ "step": 1150
333
+ },
334
+ {
335
+ "epoch": 0.26309896999552174,
336
+ "grad_norm": 10.005462646484375,
337
+ "learning_rate": 8.389675210348864e-06,
338
+ "loss": 1.0453,
339
+ "step": 1175
340
+ },
341
+ {
342
+ "epoch": 0.2686968204209583,
343
+ "grad_norm": 10.835626602172852,
344
+ "learning_rate": 8.3245145175495e-06,
345
+ "loss": 1.0625,
346
+ "step": 1200
347
+ },
348
+ {
349
+ "epoch": 0.274294670846395,
350
+ "grad_norm": 5.667449951171875,
351
+ "learning_rate": 8.258325667917355e-06,
352
+ "loss": 0.8611,
353
+ "step": 1225
354
+ },
355
+ {
356
+ "epoch": 0.2798925212718316,
357
+ "grad_norm": 13.251060485839844,
358
+ "learning_rate": 8.191129131363942e-06,
359
+ "loss": 1.0864,
360
+ "step": 1250
361
+ },
362
+ {
363
+ "epoch": 0.28549037169726826,
364
+ "grad_norm": 7.886396884918213,
365
+ "learning_rate": 8.122945689443328e-06,
366
+ "loss": 0.8904,
367
+ "step": 1275
368
+ },
369
+ {
370
+ "epoch": 0.29108822212270485,
371
+ "grad_norm": 9.646678924560547,
372
+ "learning_rate": 8.053796428925123e-06,
373
+ "loss": 0.9213,
374
+ "step": 1300
375
+ },
376
+ {
377
+ "epoch": 0.2966860725481415,
378
+ "grad_norm": 10.207015037536621,
379
+ "learning_rate": 7.98370273527307e-06,
380
+ "loss": 1.0658,
381
+ "step": 1325
382
+ },
383
+ {
384
+ "epoch": 0.30228392297357815,
385
+ "grad_norm": 6.621966361999512,
386
+ "learning_rate": 7.91268628603127e-06,
387
+ "loss": 1.1713,
388
+ "step": 1350
389
+ },
390
+ {
391
+ "epoch": 0.3078817733990148,
392
+ "grad_norm": 7.847959518432617,
393
+ "learning_rate": 7.840769044120067e-06,
394
+ "loss": 0.9781,
395
+ "step": 1375
396
+ },
397
+ {
398
+ "epoch": 0.31347962382445144,
399
+ "grad_norm": 9.040787696838379,
400
+ "learning_rate": 7.76797325104368e-06,
401
+ "loss": 0.9718,
402
+ "step": 1400
403
+ },
404
+ {
405
+ "epoch": 0.319077474249888,
406
+ "grad_norm": 6.201238632202148,
407
+ "learning_rate": 7.694321420011672e-06,
408
+ "loss": 0.9015,
409
+ "step": 1425
410
+ },
411
+ {
412
+ "epoch": 0.3246753246753247,
413
+ "grad_norm": 14.064117431640625,
414
+ "learning_rate": 7.619836328976416e-06,
415
+ "loss": 1.0073,
416
+ "step": 1450
417
+ },
418
+ {
419
+ "epoch": 0.3302731751007613,
420
+ "grad_norm": 6.1384663581848145,
421
+ "learning_rate": 7.5445410135886455e-06,
422
+ "loss": 0.8406,
423
+ "step": 1475
424
+ },
425
+ {
426
+ "epoch": 0.33587102552619796,
427
+ "grad_norm": 7.594089508056641,
428
+ "learning_rate": 7.468458760073334e-06,
429
+ "loss": 0.8915,
430
+ "step": 1500
431
+ },
432
+ {
433
+ "epoch": 0.34146887595163455,
434
+ "grad_norm": 9.95975399017334,
435
+ "learning_rate": 7.391613098028081e-06,
436
+ "loss": 1.1634,
437
+ "step": 1525
438
+ },
439
+ {
440
+ "epoch": 0.3470667263770712,
441
+ "grad_norm": 10.708215713500977,
442
+ "learning_rate": 7.314027793146219e-06,
443
+ "loss": 0.9969,
444
+ "step": 1550
445
+ },
446
+ {
447
+ "epoch": 0.35266457680250785,
448
+ "grad_norm": 9.816734313964844,
449
+ "learning_rate": 7.23572683986691e-06,
450
+ "loss": 1.1063,
451
+ "step": 1575
452
+ },
453
+ {
454
+ "epoch": 0.3582624272279445,
455
+ "grad_norm": 10.419496536254883,
456
+ "learning_rate": 7.156734453954503e-06,
457
+ "loss": 1.0399,
458
+ "step": 1600
459
+ },
460
+ {
461
+ "epoch": 0.3638602776533811,
462
+ "grad_norm": 7.747687339782715,
463
+ "learning_rate": 7.0770750650094335e-06,
464
+ "loss": 0.8368,
465
+ "step": 1625
466
+ },
467
+ {
468
+ "epoch": 0.3694581280788177,
469
+ "grad_norm": 9.370880126953125,
470
+ "learning_rate": 6.996773308913003e-06,
471
+ "loss": 1.0139,
472
+ "step": 1650
473
+ },
474
+ {
475
+ "epoch": 0.3750559785042544,
476
+ "grad_norm": 10.095951080322266,
477
+ "learning_rate": 6.915854020208358e-06,
478
+ "loss": 1.0617,
479
+ "step": 1675
480
+ },
481
+ {
482
+ "epoch": 0.380653828929691,
483
+ "grad_norm": 11.371135711669922,
484
+ "learning_rate": 6.834342224420016e-06,
485
+ "loss": 1.0399,
486
+ "step": 1700
487
+ },
488
+ {
489
+ "epoch": 0.3862516793551276,
490
+ "grad_norm": 9.077759742736816,
491
+ "learning_rate": 6.752263130314361e-06,
492
+ "loss": 1.0934,
493
+ "step": 1725
494
+ },
495
+ {
496
+ "epoch": 0.39184952978056425,
497
+ "grad_norm": 8.414709091186523,
498
+ "learning_rate": 6.669642122103423e-06,
499
+ "loss": 0.9078,
500
+ "step": 1750
501
+ },
502
+ {
503
+ "epoch": 0.3974473802060009,
504
+ "grad_norm": 7.037852764129639,
505
+ "learning_rate": 6.586504751594451e-06,
506
+ "loss": 1.0392,
507
+ "step": 1775
508
+ },
509
+ {
510
+ "epoch": 0.40304523063143755,
511
+ "grad_norm": 12.552664756774902,
512
+ "learning_rate": 6.5028767302875974e-06,
513
+ "loss": 0.9487,
514
+ "step": 1800
515
+ },
516
+ {
517
+ "epoch": 0.40864308105687414,
518
+ "grad_norm": 6.407071113586426,
519
+ "learning_rate": 6.418783921424269e-06,
520
+ "loss": 0.9555,
521
+ "step": 1825
522
+ },
523
+ {
524
+ "epoch": 0.4142409314823108,
525
+ "grad_norm": 5.643894672393799,
526
+ "learning_rate": 6.334252331988515e-06,
527
+ "loss": 1.074,
528
+ "step": 1850
529
+ },
530
+ {
531
+ "epoch": 0.4198387819077474,
532
+ "grad_norm": 7.254835605621338,
533
+ "learning_rate": 6.249308104663966e-06,
534
+ "loss": 0.9496,
535
+ "step": 1875
536
+ },
537
+ {
538
+ "epoch": 0.4254366323331841,
539
+ "grad_norm": 8.206978797912598,
540
+ "learning_rate": 6.1639775097488155e-06,
541
+ "loss": 1.0772,
542
+ "step": 1900
543
+ },
544
+ {
545
+ "epoch": 0.43103448275862066,
546
+ "grad_norm": 4.874852657318115,
547
+ "learning_rate": 6.07828693703133e-06,
548
+ "loss": 0.8274,
549
+ "step": 1925
550
+ },
551
+ {
552
+ "epoch": 0.4366323331840573,
553
+ "grad_norm": 14.283883094787598,
554
+ "learning_rate": 5.992262887628405e-06,
555
+ "loss": 1.1204,
556
+ "step": 1950
557
+ },
558
+ {
559
+ "epoch": 0.44223018360949395,
560
+ "grad_norm": 12.45128059387207,
561
+ "learning_rate": 5.905931965789688e-06,
562
+ "loss": 1.0209,
563
+ "step": 1975
564
+ },
565
+ {
566
+ "epoch": 0.4478280340349306,
567
+ "grad_norm": 9.155681610107422,
568
+ "learning_rate": 5.819320870669806e-06,
569
+ "loss": 1.0208,
570
+ "step": 2000
571
+ },
572
+ {
573
+ "epoch": 0.45342588446036725,
574
+ "grad_norm": 7.600436210632324,
575
+ "learning_rate": 5.732456388071247e-06,
576
+ "loss": 0.9395,
577
+ "step": 2025
578
+ },
579
+ {
580
+ "epoch": 0.45902373488580384,
581
+ "grad_norm": 10.021013259887695,
582
+ "learning_rate": 5.645365382160446e-06,
583
+ "loss": 0.9514,
584
+ "step": 2050
585
+ },
586
+ {
587
+ "epoch": 0.4646215853112405,
588
+ "grad_norm": 10.850826263427734,
589
+ "learning_rate": 5.558074787159629e-06,
590
+ "loss": 1.0362,
591
+ "step": 2075
592
+ },
593
+ {
594
+ "epoch": 0.4702194357366771,
595
+ "grad_norm": 8.926505088806152,
596
+ "learning_rate": 5.470611599016986e-06,
597
+ "loss": 0.9716,
598
+ "step": 2100
599
+ },
600
+ {
601
+ "epoch": 0.4758172861621138,
602
+ "grad_norm": 6.5484185218811035,
603
+ "learning_rate": 5.383002867057778e-06,
604
+ "loss": 1.0704,
605
+ "step": 2125
606
+ },
607
+ {
608
+ "epoch": 0.48141513658755036,
609
+ "grad_norm": 7.495320796966553,
610
+ "learning_rate": 5.295275685618905e-06,
611
+ "loss": 0.9566,
612
+ "step": 2150
613
+ },
614
+ {
615
+ "epoch": 0.487012987012987,
616
+ "grad_norm": 8.97859001159668,
617
+ "learning_rate": 5.2074571856695776e-06,
618
+ "loss": 0.9744,
619
+ "step": 2175
620
+ },
621
+ {
622
+ "epoch": 0.49261083743842365,
623
+ "grad_norm": 8.450396537780762,
624
+ "learning_rate": 5.119574526420652e-06,
625
+ "loss": 1.0064,
626
+ "step": 2200
627
+ },
628
+ {
629
+ "epoch": 0.4982086878638603,
630
+ "grad_norm": 15.110372543334961,
631
+ "learning_rate": 5.0316548869252205e-06,
632
+ "loss": 0.9724,
633
+ "step": 2225
634
+ },
635
+ {
636
+ "epoch": 0.5038065382892969,
637
+ "grad_norm": 11.507658004760742,
638
+ "learning_rate": 4.943725457673086e-06,
639
+ "loss": 1.0204,
640
+ "step": 2250
641
+ },
642
+ {
643
+ "epoch": 0.5094043887147336,
644
+ "grad_norm": 5.711903095245361,
645
+ "learning_rate": 4.8558134321816816e-06,
646
+ "loss": 1.0455,
647
+ "step": 2275
648
+ },
649
+ {
650
+ "epoch": 0.5150022391401702,
651
+ "grad_norm": 7.272406101226807,
652
+ "learning_rate": 4.76794599858606e-06,
653
+ "loss": 1.0133,
654
+ "step": 2300
655
+ },
656
+ {
657
+ "epoch": 0.5206000895656068,
658
+ "grad_norm": 6.9339680671691895,
659
+ "learning_rate": 4.680150331230552e-06,
660
+ "loss": 1.1114,
661
+ "step": 2325
662
+ },
663
+ {
664
+ "epoch": 0.5261979399910435,
665
+ "grad_norm": 6.307779788970947,
666
+ "learning_rate": 4.592453582264684e-06,
667
+ "loss": 0.8829,
668
+ "step": 2350
669
+ },
670
+ {
671
+ "epoch": 0.5317957904164801,
672
+ "grad_norm": 4.144500255584717,
673
+ "learning_rate": 4.504882873245961e-06,
674
+ "loss": 1.0952,
675
+ "step": 2375
676
+ },
677
+ {
678
+ "epoch": 0.5373936408419167,
679
+ "grad_norm": 8.365829467773438,
680
+ "learning_rate": 4.417465286752109e-06,
681
+ "loss": 1.0237,
682
+ "step": 2400
683
+ },
684
+ {
685
+ "epoch": 0.5429914912673534,
686
+ "grad_norm": 9.530734062194824,
687
+ "learning_rate": 4.330227858005379e-06,
688
+ "loss": 1.0088,
689
+ "step": 2425
690
+ },
691
+ {
692
+ "epoch": 0.54858934169279,
693
+ "grad_norm": 9.499034881591797,
694
+ "learning_rate": 4.243197566511493e-06,
695
+ "loss": 1.0404,
696
+ "step": 2450
697
+ },
698
+ {
699
+ "epoch": 0.5541871921182266,
700
+ "grad_norm": 6.624443054199219,
701
+ "learning_rate": 4.15640132771581e-06,
702
+ "loss": 0.802,
703
+ "step": 2475
704
+ },
705
+ {
706
+ "epoch": 0.5597850425436632,
707
+ "grad_norm": 4.885298252105713,
708
+ "learning_rate": 4.069865984679332e-06,
709
+ "loss": 0.9824,
710
+ "step": 2500
711
+ },
712
+ {
713
+ "epoch": 0.5653828929690998,
714
+ "grad_norm": 10.335043907165527,
715
+ "learning_rate": 3.9836182997770586e-06,
716
+ "loss": 1.0334,
717
+ "step": 2525
718
+ },
719
+ {
720
+ "epoch": 0.5709807433945365,
721
+ "grad_norm": 6.98168420791626,
722
+ "learning_rate": 3.897684946421326e-06,
723
+ "loss": 1.0047,
724
+ "step": 2550
725
+ },
726
+ {
727
+ "epoch": 0.5765785938199731,
728
+ "grad_norm": 7.940051555633545,
729
+ "learning_rate": 3.8120925008126457e-06,
730
+ "loss": 0.8648,
731
+ "step": 2575
732
+ },
733
+ {
734
+ "epoch": 0.5821764442454097,
735
+ "grad_norm": 7.1400885581970215,
736
+ "learning_rate": 3.7268674337206025e-06,
737
+ "loss": 0.8521,
738
+ "step": 2600
739
+ },
740
+ {
741
+ "epoch": 0.5877742946708464,
742
+ "grad_norm": 9.360673904418945,
743
+ "learning_rate": 3.6420361022973784e-06,
744
+ "loss": 0.8878,
745
+ "step": 2625
746
+ },
747
+ {
748
+ "epoch": 0.593372145096283,
749
+ "grad_norm": 6.841546058654785,
750
+ "learning_rate": 3.5576247419263854e-06,
751
+ "loss": 0.9828,
752
+ "step": 2650
753
+ },
754
+ {
755
+ "epoch": 0.5989699955217197,
756
+ "grad_norm": 9.706862449645996,
757
+ "learning_rate": 3.4736594581085837e-06,
758
+ "loss": 1.1297,
759
+ "step": 2675
760
+ },
761
+ {
762
+ "epoch": 0.6045678459471563,
763
+ "grad_norm": 9.606383323669434,
764
+ "learning_rate": 3.390166218388956e-06,
765
+ "loss": 1.0531,
766
+ "step": 2700
767
+ },
768
+ {
769
+ "epoch": 0.6101656963725929,
770
+ "grad_norm": 5.520534515380859,
771
+ "learning_rate": 3.3071708443256414e-06,
772
+ "loss": 0.9844,
773
+ "step": 2725
774
+ },
775
+ {
776
+ "epoch": 0.6157635467980296,
777
+ "grad_norm": 9.2130765914917,
778
+ "learning_rate": 3.224699003504236e-06,
779
+ "loss": 0.9696,
780
+ "step": 2750
781
+ },
782
+ {
783
+ "epoch": 0.6213613972234662,
784
+ "grad_norm": 8.891196250915527,
785
+ "learning_rate": 3.142776201599689e-06,
786
+ "loss": 0.8803,
787
+ "step": 2775
788
+ },
789
+ {
790
+ "epoch": 0.6269592476489029,
791
+ "grad_norm": 9.511999130249023,
792
+ "learning_rate": 3.061427774488287e-06,
793
+ "loss": 1.0108,
794
+ "step": 2800
795
+ },
796
+ {
797
+ "epoch": 0.6325570980743395,
798
+ "grad_norm": 5.509415626525879,
799
+ "learning_rate": 2.9806788804121562e-06,
800
+ "loss": 0.8862,
801
+ "step": 2825
802
+ },
803
+ {
804
+ "epoch": 0.638154948499776,
805
+ "grad_norm": 5.889389991760254,
806
+ "learning_rate": 2.9005544921986774e-06,
807
+ "loss": 0.9829,
808
+ "step": 2850
809
+ },
810
+ {
811
+ "epoch": 0.6437527989252128,
812
+ "grad_norm": 8.13467788696289,
813
+ "learning_rate": 2.8210793895372722e-06,
814
+ "loss": 0.8431,
815
+ "step": 2875
816
+ },
817
+ {
818
+ "epoch": 0.6493506493506493,
819
+ "grad_norm": 10.089922904968262,
820
+ "learning_rate": 2.742278151315898e-06,
821
+ "loss": 1.1452,
822
+ "step": 2900
823
+ },
824
+ {
825
+ "epoch": 0.6549484997760859,
826
+ "grad_norm": 9.242680549621582,
827
+ "learning_rate": 2.6641751480196485e-06,
828
+ "loss": 0.906,
829
+ "step": 2925
830
+ },
831
+ {
832
+ "epoch": 0.6605463502015226,
833
+ "grad_norm": 11.566295623779297,
834
+ "learning_rate": 2.5867945341938255e-06,
835
+ "loss": 0.941,
836
+ "step": 2950
837
+ },
838
+ {
839
+ "epoch": 0.6661442006269592,
840
+ "grad_norm": 8.217988014221191,
841
+ "learning_rate": 2.510160240973757e-06,
842
+ "loss": 0.9058,
843
+ "step": 2975
844
+ },
845
+ {
846
+ "epoch": 0.6717420510523959,
847
+ "grad_norm": 13.650288581848145,
848
+ "learning_rate": 2.434295968683741e-06,
849
+ "loss": 1.1236,
850
+ "step": 3000
851
+ },
852
+ {
853
+ "epoch": 0.6773399014778325,
854
+ "grad_norm": 9.068547248840332,
855
+ "learning_rate": 2.3592251795073564e-06,
856
+ "loss": 0.9533,
857
+ "step": 3025
858
+ },
859
+ {
860
+ "epoch": 0.6829377519032691,
861
+ "grad_norm": 10.866704940795898,
862
+ "learning_rate": 2.2849710902314205e-06,
863
+ "loss": 1.0299,
864
+ "step": 3050
865
+ },
866
+ {
867
+ "epoch": 0.6885356023287058,
868
+ "grad_norm": 9.991189002990723,
869
+ "learning_rate": 2.211556665065854e-06,
870
+ "loss": 0.9484,
871
+ "step": 3075
872
+ },
873
+ {
874
+ "epoch": 0.6941334527541424,
875
+ "grad_norm": 7.939027786254883,
876
+ "learning_rate": 2.1390046085416356e-06,
877
+ "loss": 0.8995,
878
+ "step": 3100
879
+ },
880
+ {
881
+ "epoch": 0.699731303179579,
882
+ "grad_norm": 10.984658241271973,
883
+ "learning_rate": 2.0673373584890847e-06,
884
+ "loss": 1.0449,
885
+ "step": 3125
886
+ },
887
+ {
888
+ "epoch": 0.7053291536050157,
889
+ "grad_norm": 6.965851306915283,
890
+ "learning_rate": 1.996577079098628e-06,
891
+ "loss": 0.976,
892
+ "step": 3150
893
+ },
894
+ {
895
+ "epoch": 0.7109270040304523,
896
+ "grad_norm": 10.873515129089355,
897
+ "learning_rate": 1.9267456540661723e-06,
898
+ "loss": 1.0484,
899
+ "step": 3175
900
+ },
901
+ {
902
+ "epoch": 0.716524854455889,
903
+ "grad_norm": 8.086957931518555,
904
+ "learning_rate": 1.8578646798252432e-06,
905
+ "loss": 0.8454,
906
+ "step": 3200
907
+ },
908
+ {
909
+ "epoch": 0.7221227048813256,
910
+ "grad_norm": 9.924606323242188,
911
+ "learning_rate": 1.7899554588679636e-06,
912
+ "loss": 1.0399,
913
+ "step": 3225
914
+ },
915
+ {
916
+ "epoch": 0.7277205553067622,
917
+ "grad_norm": 7.758438587188721,
918
+ "learning_rate": 1.7230389931569242e-06,
919
+ "loss": 0.9454,
920
+ "step": 3250
921
+ },
922
+ {
923
+ "epoch": 0.7333184057321989,
924
+ "grad_norm": 6.910051345825195,
925
+ "learning_rate": 1.657135977630015e-06,
926
+ "loss": 0.9082,
927
+ "step": 3275
928
+ },
929
+ {
930
+ "epoch": 0.7389162561576355,
931
+ "grad_norm": 8.083282470703125,
932
+ "learning_rate": 1.5922667938001913e-06,
933
+ "loss": 0.958,
934
+ "step": 3300
935
+ },
936
+ {
937
+ "epoch": 0.7445141065830722,
938
+ "grad_norm": 10.176769256591797,
939
+ "learning_rate": 1.5284515034521858e-06,
940
+ "loss": 0.9261,
941
+ "step": 3325
942
+ },
943
+ {
944
+ "epoch": 0.7501119570085087,
945
+ "grad_norm": 8.147079467773438,
946
+ "learning_rate": 1.4657098424380945e-06,
947
+ "loss": 0.9271,
948
+ "step": 3350
949
+ },
950
+ {
951
+ "epoch": 0.7557098074339453,
952
+ "grad_norm": 9.081329345703125,
953
+ "learning_rate": 1.4040612145737608e-06,
954
+ "loss": 1.031,
955
+ "step": 3375
956
+ },
957
+ {
958
+ "epoch": 0.761307657859382,
959
+ "grad_norm": 8.017196655273438,
960
+ "learning_rate": 1.3435246856378524e-06,
961
+ "loss": 1.0238,
962
+ "step": 3400
963
+ },
964
+ {
965
+ "epoch": 0.7669055082848186,
966
+ "grad_norm": 9.929486274719238,
967
+ "learning_rate": 1.284118977475481e-06,
968
+ "loss": 0.954,
969
+ "step": 3425
970
+ },
971
+ {
972
+ "epoch": 0.7725033587102552,
973
+ "grad_norm": 12.716034889221191,
974
+ "learning_rate": 1.2258624622081755e-06,
975
+ "loss": 0.9619,
976
+ "step": 3450
977
+ },
978
+ {
979
+ "epoch": 0.7781012091356919,
980
+ "grad_norm": 8.163155555725098,
981
+ "learning_rate": 1.1687731565520372e-06,
982
+ "loss": 1.1041,
983
+ "step": 3475
984
+ },
985
+ {
986
+ "epoch": 0.7836990595611285,
987
+ "grad_norm": 9.499692916870117,
988
+ "learning_rate": 1.112868716245783e-06,
989
+ "loss": 0.8927,
990
+ "step": 3500
991
+ },
992
+ {
993
+ "epoch": 0.7892969099865652,
994
+ "grad_norm": 6.03558874130249,
995
+ "learning_rate": 1.058166430590446e-06,
996
+ "loss": 0.9804,
997
+ "step": 3525
998
+ },
999
+ {
1000
+ "epoch": 0.7948947604120018,
1001
+ "grad_norm": 8.300068855285645,
1002
+ "learning_rate": 1.0046832171023952e-06,
1003
+ "loss": 1.0007,
1004
+ "step": 3550
1005
+ },
1006
+ {
1007
+ "epoch": 0.8004926108374384,
1008
+ "grad_norm": 7.682162761688232,
1009
+ "learning_rate": 9.524356162813326e-07,
1010
+ "loss": 0.9482,
1011
+ "step": 3575
1012
+ },
1013
+ {
1014
+ "epoch": 0.8060904612628751,
1015
+ "grad_norm": 8.57835578918457,
1016
+ "learning_rate": 9.014397864948921e-07,
1017
+ "loss": 0.9541,
1018
+ "step": 3600
1019
+ },
1020
+ {
1021
+ "epoch": 0.8116883116883117,
1022
+ "grad_norm": 11.44987678527832,
1023
+ "learning_rate": 8.51711498981419e-07,
1024
+ "loss": 0.9518,
1025
+ "step": 3625
1026
+ },
1027
+ {
1028
+ "epoch": 0.8172861621137483,
1029
+ "grad_norm": 7.918177604675293,
1030
+ "learning_rate": 8.032661329724717e-07,
1031
+ "loss": 1.0321,
1032
+ "step": 3650
1033
+ },
1034
+ {
1035
+ "epoch": 0.822884012539185,
1036
+ "grad_norm": 10.909501075744629,
1037
+ "learning_rate": 7.561186709365653e-07,
1038
+ "loss": 0.9651,
1039
+ "step": 3675
1040
+ },
1041
+ {
1042
+ "epoch": 0.8284818629646216,
1043
+ "grad_norm": 14.997469902038574,
1044
+ "learning_rate": 7.102836939456071e-07,
1045
+ "loss": 1.0462,
1046
+ "step": 3700
1047
+ },
1048
+ {
1049
+ "epoch": 0.8340797133900583,
1050
+ "grad_norm": 5.220563888549805,
1051
+ "learning_rate": 6.657753771654812e-07,
1052
+ "loss": 0.8815,
1053
+ "step": 3725
1054
+ },
1055
+ {
1056
+ "epoch": 0.8396775638154949,
1057
+ "grad_norm": 8.45197868347168,
1058
+ "learning_rate": 6.226074854721653e-07,
1059
+ "loss": 1.0041,
1060
+ "step": 3750
1061
+ },
1062
+ {
1063
+ "epoch": 0.8452754142409314,
1064
+ "grad_norm": 11.861766815185547,
1065
+ "learning_rate": 5.807933691947248e-07,
1066
+ "loss": 0.8721,
1067
+ "step": 3775
1068
+ },
1069
+ {
1070
+ "epoch": 0.8508732646663681,
1071
+ "grad_norm": 6.297611236572266,
1072
+ "learning_rate": 5.403459599865307e-07,
1073
+ "loss": 1.0609,
1074
+ "step": 3800
1075
+ },
1076
+ {
1077
+ "epoch": 0.8564711150918047,
1078
+ "grad_norm": 9.576262474060059,
1079
+ "learning_rate": 5.012777668259378e-07,
1080
+ "loss": 0.9142,
1081
+ "step": 3825
1082
+ },
1083
+ {
1084
+ "epoch": 0.8620689655172413,
1085
+ "grad_norm": 8.582077980041504,
1086
+ "learning_rate": 4.6360087214769923e-07,
1087
+ "loss": 0.9383,
1088
+ "step": 3850
1089
+ },
1090
+ {
1091
+ "epoch": 0.867666815942678,
1092
+ "grad_norm": 9.107322692871094,
1093
+ "learning_rate": 4.2732692810628583e-07,
1094
+ "loss": 1.1366,
1095
+ "step": 3875
1096
+ },
1097
+ {
1098
+ "epoch": 0.8732646663681146,
1099
+ "grad_norm": 5.725574493408203,
1100
+ "learning_rate": 3.9246715297228176e-07,
1101
+ "loss": 1.0077,
1102
+ "step": 3900
1103
+ },
1104
+ {
1105
+ "epoch": 0.8788625167935513,
1106
+ "grad_norm": 6.691014766693115,
1107
+ "learning_rate": 3.59032327662962e-07,
1108
+ "loss": 1.0128,
1109
+ "step": 3925
1110
+ },
1111
+ {
1112
+ "epoch": 0.8844603672189879,
1113
+ "grad_norm": 7.009856700897217,
1114
+ "learning_rate": 3.270327924081301e-07,
1115
+ "loss": 1.0404,
1116
+ "step": 3950
1117
+ },
1118
+ {
1119
+ "epoch": 0.8900582176444245,
1120
+ "grad_norm": 9.100337982177734,
1121
+ "learning_rate": 2.964784435522422e-07,
1122
+ "loss": 0.9983,
1123
+ "step": 3975
1124
+ },
1125
+ {
1126
+ "epoch": 0.8956560680698612,
1127
+ "grad_norm": 11.176060676574707,
1128
+ "learning_rate": 2.6737873049381523e-07,
1129
+ "loss": 0.9483,
1130
+ "step": 4000
1131
+ },
1132
+ {
1133
+ "epoch": 0.9012539184952978,
1134
+ "grad_norm": 6.4081268310546875,
1135
+ "learning_rate": 2.3974265276305253e-07,
1136
+ "loss": 1.0171,
1137
+ "step": 4025
1138
+ },
1139
+ {
1140
+ "epoch": 0.9068517689207345,
1141
+ "grad_norm": 5.774712562561035,
1142
+ "learning_rate": 2.1357875723860222e-07,
1143
+ "loss": 0.8993,
1144
+ "step": 4050
1145
+ },
1146
+ {
1147
+ "epoch": 0.9124496193461711,
1148
+ "grad_norm": 9.53131103515625,
1149
+ "learning_rate": 1.8889513550430892e-07,
1150
+ "loss": 0.9881,
1151
+ "step": 4075
1152
+ },
1153
+ {
1154
+ "epoch": 0.9180474697716077,
1155
+ "grad_norm": 7.965620040893555,
1156
+ "learning_rate": 1.656994213467622e-07,
1157
+ "loss": 0.9479,
1158
+ "step": 4100
1159
+ },
1160
+ {
1161
+ "epoch": 0.9236453201970444,
1162
+ "grad_norm": 9.653414726257324,
1163
+ "learning_rate": 1.439987883944355e-07,
1164
+ "loss": 0.9613,
1165
+ "step": 4125
1166
+ },
1167
+ {
1168
+ "epoch": 0.929243170622481,
1169
+ "grad_norm": 9.446654319763184,
1170
+ "learning_rate": 1.237999478991303e-07,
1171
+ "loss": 1.1298,
1172
+ "step": 4150
1173
+ },
1174
+ {
1175
+ "epoch": 0.9348410210479176,
1176
+ "grad_norm": 9.220303535461426,
1177
+ "learning_rate": 1.0510914666041927e-07,
1178
+ "loss": 0.9897,
1179
+ "step": 4175
1180
+ },
1181
+ {
1182
+ "epoch": 0.9404388714733543,
1183
+ "grad_norm": 9.508859634399414,
1184
+ "learning_rate": 8.793216509373038e-08,
1185
+ "loss": 1.0607,
1186
+ "step": 4200
1187
+ },
1188
+ {
1189
+ "epoch": 0.9460367218987908,
1190
+ "grad_norm": 8.090096473693848,
1191
+ "learning_rate": 7.227431544266194e-08,
1192
+ "loss": 1.0712,
1193
+ "step": 4225
1194
+ },
1195
+ {
1196
+ "epoch": 0.9516345723242275,
1197
+ "grad_norm": 5.4540510177612305,
1198
+ "learning_rate": 5.8140440136091326e-08,
1199
+ "loss": 1.0226,
1200
+ "step": 4250
1201
+ },
1202
+ {
1203
+ "epoch": 0.9572324227496641,
1204
+ "grad_norm": 5.08390474319458,
1205
+ "learning_rate": 4.553491029058221e-08,
1206
+ "loss": 0.8554,
1207
+ "step": 4275
1208
+ },
1209
+ {
1210
+ "epoch": 0.9628302731751007,
1211
+ "grad_norm": 11.732171058654785,
1212
+ "learning_rate": 3.4461624358546056e-08,
1213
+ "loss": 1.0033,
1214
+ "step": 4300
1215
+ },
1216
+ {
1217
+ "epoch": 0.9684281236005374,
1218
+ "grad_norm": 8.629095077514648,
1219
+ "learning_rate": 2.4924006922590338e-08,
1220
+ "loss": 0.973,
1221
+ "step": 4325
1222
+ },
1223
+ {
1224
+ "epoch": 0.974025974025974,
1225
+ "grad_norm": 6.797715663909912,
1226
+ "learning_rate": 1.6925007636411362e-08,
1227
+ "loss": 0.8825,
1228
+ "step": 4350
1229
+ },
1230
+ {
1231
+ "epoch": 0.9796238244514106,
1232
+ "grad_norm": 10.467803001403809,
1233
+ "learning_rate": 1.0467100312568923e-08,
1234
+ "loss": 1.0412,
1235
+ "step": 4375
1236
+ },
1237
+ {
1238
+ "epoch": 0.9852216748768473,
1239
+ "grad_norm": 10.413917541503906,
1240
+ "learning_rate": 5.552282157424427e-09,
1241
+ "loss": 0.9493,
1242
+ "step": 4400
1243
+ },
1244
+ {
1245
+ "epoch": 0.9908195253022839,
1246
+ "grad_norm": 6.7092719078063965,
1247
+ "learning_rate": 2.182073153471631e-09,
1248
+ "loss": 0.986,
1249
+ "step": 4425
1250
+ },
1251
+ {
1252
+ "epoch": 0.9964173757277206,
1253
+ "grad_norm": 6.736852645874023,
1254
+ "learning_rate": 3.575155892604487e-10,
1255
+ "loss": 0.9939,
1256
+ "step": 4450
1257
+ }
1258
+ ],
1259
+ "logging_steps": 25,
1260
+ "max_steps": 4466,
1261
+ "num_input_tokens_seen": 0,
1262
+ "num_train_epochs": 1,
1263
+ "save_steps": 50000,
1264
+ "stateful_callbacks": {
1265
+ "TrainerControl": {
1266
+ "args": {
1267
+ "should_epoch_stop": false,
1268
+ "should_evaluate": false,
1269
+ "should_log": false,
1270
+ "should_save": true,
1271
+ "should_training_stop": true
1272
+ },
1273
+ "attributes": {}
1274
+ }
1275
+ },
1276
+ "total_flos": 2.4169358435549184e+16,
1277
+ "train_batch_size": 4,
1278
+ "trial_name": null,
1279
+ "trial_params": null
1280
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53e9b8d5d82d2530238caae4ed15c86971a714d0dfd563b8e978a5dc24ba9570
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff