fengyao1909 commited on
Commit
abf6ee3
·
verified ·
1 Parent(s): 70b5fb4

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "max_position_embeddings": 32768,
16
+ "max_window_layers": 48,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 768,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 32,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 48,
25
+ "num_key_value_heads": 4,
26
+ "output_router_logits": false,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": null,
29
+ "rope_theta": 1000000.0,
30
+ "router_aux_loss_coef": 0.001,
31
+ "sliding_window": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.52.0.dev0",
35
+ "use_cache": false,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936
38
+ }
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": "4.52.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6a434a95fe42176463589afc25d991fdef09844a438d9692d0c05e32a1a53cd
3
+ size 4997184968
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c112fd31cf1a0afe58ce4caf7ad9223f995a2a6de525c72356cede4c3aab51
3
+ size 4997741608
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7700921ed57b34efc97f005cba84ea0524d51fd781e12e0d2c79b21a67cc1dd3
3
+ size 4997742208
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1ddae74fe8344e7225b82d3a50dc7d83cbb85649594a232cb4a4dab6cd199b
3
+ size 4997743184
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d4988acea99d079f6958d9b9ec1e64b9adebf351cb8a76b7807618d6badd98c
3
+ size 4997743184
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd746b7f40866ad831de6fedf3e99e983107f387a570f9e907a4b6062a005dbe
3
+ size 4997743184
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:449409fd296bdcc211b5e197fd0c1645a0f923567018681730ce25c65c79f768
3
+ size 4997743184
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e5e6bec34fe02285d7e91101d59737bbb76e2226266d29554f03f082d99769
3
+ size 4997743184
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8882f8a897a0ec2e40e49e8784ff6f261e270dafd53191a490b863808a44004
3
+ size 4997743184
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc573658d9172a22e9905bde80a31742d8fce34e3bf0d9eb9f00011a85c82765
3
+ size 4997743184
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f96ca26496a6fa099fd9a9e1600f9d8b993b33972d64aa3cb01a8c239d3cfece
3
+ size 4997743184
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21447c430765da7a5e8bbfc3ae4931ae73228837694d67e0426c2382a1624600
3
+ size 4997743184
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e0854c84b543c6ad057533f56668fb69ef6a158298cbf54d53a020b6506659
3
+ size 1094220288
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
trainer_state.json ADDED
@@ -0,0 +1,1434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.36133694670280037,
6
+ "eval_steps": 500,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0018066847335140017,
14
+ "grad_norm": 2.8337757951637657,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.8251,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0036133694670280035,
21
+ "grad_norm": 2.8815146894381005,
22
+ "learning_rate": 1.7857142857142858e-07,
23
+ "loss": 0.8284,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.005420054200542005,
28
+ "grad_norm": 2.888366333138549,
29
+ "learning_rate": 3.5714285714285716e-07,
30
+ "loss": 0.8432,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.007226738934056007,
35
+ "grad_norm": 2.8554157896663708,
36
+ "learning_rate": 5.357142857142857e-07,
37
+ "loss": 0.8398,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.009033423667570008,
42
+ "grad_norm": 2.7996302090063954,
43
+ "learning_rate": 7.142857142857143e-07,
44
+ "loss": 0.8303,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.01084010840108401,
49
+ "grad_norm": 2.758540000006854,
50
+ "learning_rate": 8.928571428571429e-07,
51
+ "loss": 0.8306,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.012646793134598013,
56
+ "grad_norm": 2.7440712027687453,
57
+ "learning_rate": 1.0714285714285714e-06,
58
+ "loss": 0.8129,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.014453477868112014,
63
+ "grad_norm": 2.789670841276354,
64
+ "learning_rate": 1.25e-06,
65
+ "loss": 0.8217,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.016260162601626018,
70
+ "grad_norm": 2.637271873271262,
71
+ "learning_rate": 1.4285714285714286e-06,
72
+ "loss": 0.8192,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.018066847335140017,
77
+ "grad_norm": 2.6274284830887247,
78
+ "learning_rate": 1.6071428571428574e-06,
79
+ "loss": 0.8146,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.01987353206865402,
84
+ "grad_norm": 2.2614743320388992,
85
+ "learning_rate": 1.7857142857142859e-06,
86
+ "loss": 0.8022,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.02168021680216802,
91
+ "grad_norm": 2.1218891806221882,
92
+ "learning_rate": 1.9642857142857144e-06,
93
+ "loss": 0.8131,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.023486901535682024,
98
+ "grad_norm": 2.1362019297809636,
99
+ "learning_rate": 2.1428571428571427e-06,
100
+ "loss": 0.8047,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.025293586269196026,
105
+ "grad_norm": 2.043181941163786,
106
+ "learning_rate": 2.321428571428572e-06,
107
+ "loss": 0.8006,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.02710027100271003,
112
+ "grad_norm": 1.4654153096579285,
113
+ "learning_rate": 2.5e-06,
114
+ "loss": 0.7863,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.028906955736224028,
119
+ "grad_norm": 1.424950643183691,
120
+ "learning_rate": 2.6785714285714285e-06,
121
+ "loss": 0.7794,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.03071364046973803,
126
+ "grad_norm": 1.371800886806853,
127
+ "learning_rate": 2.8571428571428573e-06,
128
+ "loss": 0.7871,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.032520325203252036,
133
+ "grad_norm": 1.2910993566284936,
134
+ "learning_rate": 3.0357142857142856e-06,
135
+ "loss": 0.7792,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.03432700993676603,
140
+ "grad_norm": 1.2099658145135412,
141
+ "learning_rate": 3.2142857142857147e-06,
142
+ "loss": 0.7728,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.036133694670280034,
147
+ "grad_norm": 1.0479474035735314,
148
+ "learning_rate": 3.3928571428571435e-06,
149
+ "loss": 0.743,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.037940379403794036,
154
+ "grad_norm": 1.112276534792924,
155
+ "learning_rate": 3.5714285714285718e-06,
156
+ "loss": 0.7403,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.03974706413730804,
161
+ "grad_norm": 1.3035077079579298,
162
+ "learning_rate": 3.7500000000000005e-06,
163
+ "loss": 0.7296,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.04155374887082204,
168
+ "grad_norm": 1.3695661288387202,
169
+ "learning_rate": 3.928571428571429e-06,
170
+ "loss": 0.7302,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.04336043360433604,
175
+ "grad_norm": 1.2631605637070566,
176
+ "learning_rate": 4.107142857142857e-06,
177
+ "loss": 0.7359,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.045167118337850046,
182
+ "grad_norm": 0.9577414796019008,
183
+ "learning_rate": 4.2857142857142855e-06,
184
+ "loss": 0.713,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.04697380307136405,
189
+ "grad_norm": 0.7548293526053346,
190
+ "learning_rate": 4.464285714285715e-06,
191
+ "loss": 0.7275,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.04878048780487805,
196
+ "grad_norm": 0.6708116039946823,
197
+ "learning_rate": 4.642857142857144e-06,
198
+ "loss": 0.7021,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.05058717253839205,
203
+ "grad_norm": 0.7960055478682195,
204
+ "learning_rate": 4.821428571428572e-06,
205
+ "loss": 0.6998,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.052393857271906055,
210
+ "grad_norm": 0.8790784871024999,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.7086,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.05420054200542006,
217
+ "grad_norm": 0.9579979234005123,
218
+ "learning_rate": 4.999955240022903e-06,
219
+ "loss": 0.7065,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.05600722673893405,
224
+ "grad_norm": 1.003933265230055,
225
+ "learning_rate": 4.999820961694372e-06,
226
+ "loss": 0.6937,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.057813911472448055,
231
+ "grad_norm": 0.6710805038763018,
232
+ "learning_rate": 4.999597169822646e-06,
233
+ "loss": 0.6812,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.05962059620596206,
238
+ "grad_norm": 0.5001839964623817,
239
+ "learning_rate": 4.999283872421259e-06,
240
+ "loss": 0.6911,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.06142728093947606,
245
+ "grad_norm": 0.5681434362593133,
246
+ "learning_rate": 4.998881080708759e-06,
247
+ "loss": 0.6766,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.06323396567299007,
252
+ "grad_norm": 0.5752663504650961,
253
+ "learning_rate": 4.998388809108304e-06,
254
+ "loss": 0.6816,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.06504065040650407,
259
+ "grad_norm": 0.4990120714898939,
260
+ "learning_rate": 4.997807075247147e-06,
261
+ "loss": 0.6754,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.06684733514001806,
266
+ "grad_norm": 0.4974519304946596,
267
+ "learning_rate": 4.997135899956002e-06,
268
+ "loss": 0.6782,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.06865401987353206,
273
+ "grad_norm": 0.4349874019011085,
274
+ "learning_rate": 4.996375307268303e-06,
275
+ "loss": 0.6709,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.07046070460704607,
280
+ "grad_norm": 0.48312199739205014,
281
+ "learning_rate": 4.995525324419338e-06,
282
+ "loss": 0.6707,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.07226738934056007,
287
+ "grad_norm": 0.3760455090466998,
288
+ "learning_rate": 4.994585981845278e-06,
289
+ "loss": 0.6592,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.07407407407407407,
294
+ "grad_norm": 0.362711899175025,
295
+ "learning_rate": 4.993557313182086e-06,
296
+ "loss": 0.6666,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.07588075880758807,
301
+ "grad_norm": 0.3527864788229306,
302
+ "learning_rate": 4.992439355264308e-06,
303
+ "loss": 0.656,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.07768744354110207,
308
+ "grad_norm": 0.37039474310454246,
309
+ "learning_rate": 4.9912321481237616e-06,
310
+ "loss": 0.6567,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.07949412827461608,
315
+ "grad_norm": 0.3381704985127657,
316
+ "learning_rate": 4.989935734988098e-06,
317
+ "loss": 0.6492,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.08130081300813008,
322
+ "grad_norm": 0.3368799245864057,
323
+ "learning_rate": 4.988550162279255e-06,
324
+ "loss": 0.6558,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.08310749774164408,
329
+ "grad_norm": 0.33217201284358455,
330
+ "learning_rate": 4.9870754796117956e-06,
331
+ "loss": 0.658,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.08491418247515808,
336
+ "grad_norm": 0.3203999210132069,
337
+ "learning_rate": 4.985511739791129e-06,
338
+ "loss": 0.6596,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.08672086720867209,
343
+ "grad_norm": 0.3108831280349791,
344
+ "learning_rate": 4.983858998811622e-06,
345
+ "loss": 0.6465,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.08852755194218609,
350
+ "grad_norm": 0.28944557461245024,
351
+ "learning_rate": 4.982117315854594e-06,
352
+ "loss": 0.651,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.09033423667570009,
357
+ "grad_norm": 0.2724500694923891,
358
+ "learning_rate": 4.980286753286196e-06,
359
+ "loss": 0.6493,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.0921409214092141,
364
+ "grad_norm": 0.29233908216498683,
365
+ "learning_rate": 4.978367376655177e-06,
366
+ "loss": 0.6391,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.0939476061427281,
371
+ "grad_norm": 0.29050327837368234,
372
+ "learning_rate": 4.976359254690543e-06,
373
+ "loss": 0.6577,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.0957542908762421,
378
+ "grad_norm": 0.26277310012199956,
379
+ "learning_rate": 4.974262459299088e-06,
380
+ "loss": 0.641,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.0975609756097561,
385
+ "grad_norm": 0.2694317681957786,
386
+ "learning_rate": 4.9720770655628216e-06,
387
+ "loss": 0.6322,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.0993676603432701,
392
+ "grad_norm": 0.27643434259676186,
393
+ "learning_rate": 4.969803151736285e-06,
394
+ "loss": 0.6446,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.1011743450767841,
399
+ "grad_norm": 0.27938135134555137,
400
+ "learning_rate": 4.967440799243739e-06,
401
+ "loss": 0.6505,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.10298102981029811,
406
+ "grad_norm": 0.2723254558437683,
407
+ "learning_rate": 4.964990092676263e-06,
408
+ "loss": 0.6358,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.10478771454381211,
413
+ "grad_norm": 0.2476211836425744,
414
+ "learning_rate": 4.962451119788709e-06,
415
+ "loss": 0.6435,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.10659439927732611,
420
+ "grad_norm": 0.2385367032602417,
421
+ "learning_rate": 4.959823971496575e-06,
422
+ "loss": 0.6289,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.10840108401084012,
427
+ "grad_norm": 0.24895994998658083,
428
+ "learning_rate": 4.957108741872736e-06,
429
+ "loss": 0.6299,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.1102077687443541,
434
+ "grad_norm": 0.28129654057596637,
435
+ "learning_rate": 4.954305528144085e-06,
436
+ "loss": 0.6339,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.1120144534778681,
441
+ "grad_norm": 0.25373425749505557,
442
+ "learning_rate": 4.9514144306880506e-06,
443
+ "loss": 0.6393,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.11382113821138211,
448
+ "grad_norm": 0.2583299024885213,
449
+ "learning_rate": 4.948435553028994e-06,
450
+ "loss": 0.6383,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.11562782294489611,
455
+ "grad_norm": 0.24423529044993955,
456
+ "learning_rate": 4.9453690018345144e-06,
457
+ "loss": 0.6359,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.11743450767841011,
462
+ "grad_norm": 0.24605558051142096,
463
+ "learning_rate": 4.942214886911619e-06,
464
+ "loss": 0.631,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.11924119241192412,
469
+ "grad_norm": 0.2548336350045181,
470
+ "learning_rate": 4.938973321202799e-06,
471
+ "loss": 0.6323,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.12104787714543812,
476
+ "grad_norm": 0.32845268505362657,
477
+ "learning_rate": 4.935644420781978e-06,
478
+ "loss": 0.6229,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.12285456187895212,
483
+ "grad_norm": 0.25203625601717533,
484
+ "learning_rate": 4.932228304850363e-06,
485
+ "loss": 0.6386,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.12466124661246612,
490
+ "grad_norm": 0.2467239132093227,
491
+ "learning_rate": 4.9287250957321685e-06,
492
+ "loss": 0.6401,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.12646793134598014,
497
+ "grad_norm": 0.28444822854929847,
498
+ "learning_rate": 4.925134918870245e-06,
499
+ "loss": 0.646,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.12827461607949414,
504
+ "grad_norm": 0.23105312295557145,
505
+ "learning_rate": 4.921457902821578e-06,
506
+ "loss": 0.6164,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.13008130081300814,
511
+ "grad_norm": 0.23048405537510025,
512
+ "learning_rate": 4.917694179252692e-06,
513
+ "loss": 0.6342,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.13188798554652212,
518
+ "grad_norm": 0.24150602333720247,
519
+ "learning_rate": 4.9138438829349296e-06,
520
+ "loss": 0.6332,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.13369467028003612,
525
+ "grad_norm": 0.2462886765781574,
526
+ "learning_rate": 4.909907151739634e-06,
527
+ "loss": 0.6246,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.13550135501355012,
532
+ "grad_norm": 0.2821908512766841,
533
+ "learning_rate": 4.9058841266332005e-06,
534
+ "loss": 0.6227,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.13730803974706413,
539
+ "grad_norm": 0.25172603846639535,
540
+ "learning_rate": 4.901774951672041e-06,
541
+ "loss": 0.6181,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.13911472448057813,
546
+ "grad_norm": 0.23478283786140364,
547
+ "learning_rate": 4.897579773997415e-06,
548
+ "loss": 0.6123,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.14092140921409213,
553
+ "grad_norm": 0.24524464756556244,
554
+ "learning_rate": 4.893298743830168e-06,
555
+ "loss": 0.625,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.14272809394760613,
560
+ "grad_norm": 0.2557156779275681,
561
+ "learning_rate": 4.8889320144653525e-06,
562
+ "loss": 0.6347,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.14453477868112014,
567
+ "grad_norm": 0.2501383477274707,
568
+ "learning_rate": 4.884479742266731e-06,
569
+ "loss": 0.6435,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.14634146341463414,
574
+ "grad_norm": 0.2777905831842133,
575
+ "learning_rate": 4.879942086661185e-06,
576
+ "loss": 0.6249,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.14814814814814814,
581
+ "grad_norm": 0.2311051834333071,
582
+ "learning_rate": 4.875319210133004e-06,
583
+ "loss": 0.6186,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.14995483288166214,
588
+ "grad_norm": 0.24510662627866567,
589
+ "learning_rate": 4.870611278218066e-06,
590
+ "loss": 0.6301,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.15176151761517614,
595
+ "grad_norm": 0.2457506431539522,
596
+ "learning_rate": 4.865818459497911e-06,
597
+ "loss": 0.6221,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.15356820234869015,
602
+ "grad_norm": 0.23750506338642635,
603
+ "learning_rate": 4.860940925593703e-06,
604
+ "loss": 0.6238,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.15537488708220415,
609
+ "grad_norm": 0.24583995522041222,
610
+ "learning_rate": 4.855978851160088e-06,
611
+ "loss": 0.6245,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.15718157181571815,
616
+ "grad_norm": 0.24412234277510458,
617
+ "learning_rate": 4.850932413878934e-06,
618
+ "loss": 0.6266,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.15898825654923215,
623
+ "grad_norm": 0.23692543465028104,
624
+ "learning_rate": 4.845801794452978e-06,
625
+ "loss": 0.6307,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.16079494128274616,
630
+ "grad_norm": 0.24055583410087153,
631
+ "learning_rate": 4.8405871765993435e-06,
632
+ "loss": 0.6258,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.16260162601626016,
637
+ "grad_norm": 0.25682681695753845,
638
+ "learning_rate": 4.8352887470429726e-06,
639
+ "loss": 0.6193,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.16440831074977416,
644
+ "grad_norm": 0.2451987238773762,
645
+ "learning_rate": 4.829906695509934e-06,
646
+ "loss": 0.6175,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.16621499548328816,
651
+ "grad_norm": 0.33308910526145086,
652
+ "learning_rate": 4.824441214720629e-06,
653
+ "loss": 0.6207,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.16802168021680217,
658
+ "grad_norm": 0.2599636527935745,
659
+ "learning_rate": 4.8188925003828945e-06,
660
+ "loss": 0.6275,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.16982836495031617,
665
+ "grad_norm": 0.24262017713570547,
666
+ "learning_rate": 4.813260751184992e-06,
667
+ "loss": 0.6255,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.17163504968383017,
672
+ "grad_norm": 0.24155086390799096,
673
+ "learning_rate": 4.8075461687884935e-06,
674
+ "loss": 0.6184,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.17344173441734417,
679
+ "grad_norm": 0.2399226609650259,
680
+ "learning_rate": 4.801748957821061e-06,
681
+ "loss": 0.6164,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.17524841915085818,
686
+ "grad_norm": 0.22903596103655702,
687
+ "learning_rate": 4.795869325869117e-06,
688
+ "loss": 0.6229,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.17705510388437218,
693
+ "grad_norm": 0.2307755782529314,
694
+ "learning_rate": 4.7899074834704165e-06,
695
+ "loss": 0.6173,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.17886178861788618,
700
+ "grad_norm": 0.24823755288051938,
701
+ "learning_rate": 4.783863644106502e-06,
702
+ "loss": 0.6292,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.18066847335140018,
707
+ "grad_norm": 0.21658543875130712,
708
+ "learning_rate": 4.777738024195065e-06,
709
+ "loss": 0.6032,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.18247515808491419,
714
+ "grad_norm": 0.24020742361139732,
715
+ "learning_rate": 4.771530843082187e-06,
716
+ "loss": 0.6184,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.1842818428184282,
721
+ "grad_norm": 0.23250154874953444,
722
+ "learning_rate": 4.765242323034498e-06,
723
+ "loss": 0.6373,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.1860885275519422,
728
+ "grad_norm": 0.2515794157481243,
729
+ "learning_rate": 4.7588726892312085e-06,
730
+ "loss": 0.6162,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.1878952122854562,
735
+ "grad_norm": 0.2388452484683859,
736
+ "learning_rate": 4.752422169756048e-06,
737
+ "loss": 0.6147,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.1897018970189702,
742
+ "grad_norm": 0.23451396083233195,
743
+ "learning_rate": 4.7458909955891015e-06,
744
+ "loss": 0.6066,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.1915085817524842,
749
+ "grad_norm": 0.23211345055411792,
750
+ "learning_rate": 4.7392794005985324e-06,
751
+ "loss": 0.6076,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.1933152664859982,
756
+ "grad_norm": 0.2405071836183994,
757
+ "learning_rate": 4.732587621532214e-06,
758
+ "loss": 0.6139,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.1951219512195122,
763
+ "grad_norm": 0.238214343050957,
764
+ "learning_rate": 4.7258158980092475e-06,
765
+ "loss": 0.6125,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.1969286359530262,
770
+ "grad_norm": 0.23118377153943317,
771
+ "learning_rate": 4.718964472511386e-06,
772
+ "loss": 0.6224,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.1987353206865402,
777
+ "grad_norm": 0.4227293348441868,
778
+ "learning_rate": 4.712033590374346e-06,
779
+ "loss": 0.604,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.2005420054200542,
784
+ "grad_norm": 0.22706445039114057,
785
+ "learning_rate": 4.705023499779031e-06,
786
+ "loss": 0.6231,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.2023486901535682,
791
+ "grad_norm": 0.21914294121010527,
792
+ "learning_rate": 4.6979344517426345e-06,
793
+ "loss": 0.6157,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.2041553748870822,
798
+ "grad_norm": 0.2160022263814738,
799
+ "learning_rate": 4.690766700109659e-06,
800
+ "loss": 0.6193,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.20596205962059622,
805
+ "grad_norm": 0.2304707253911858,
806
+ "learning_rate": 4.683520501542825e-06,
807
+ "loss": 0.6021,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.20776874435411022,
812
+ "grad_norm": 0.24127382191408644,
813
+ "learning_rate": 4.676196115513876e-06,
814
+ "loss": 0.6186,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.20957542908762422,
819
+ "grad_norm": 0.2406722048256909,
820
+ "learning_rate": 4.668793804294294e-06,
821
+ "loss": 0.6129,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.21138211382113822,
826
+ "grad_norm": 0.24481652156673936,
827
+ "learning_rate": 4.661313832945904e-06,
828
+ "loss": 0.6228,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.21318879855465223,
833
+ "grad_norm": 0.2283120728906989,
834
+ "learning_rate": 4.653756469311381e-06,
835
+ "loss": 0.6104,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.21499548328816623,
840
+ "grad_norm": 0.2191260930120605,
841
+ "learning_rate": 4.646121984004666e-06,
842
+ "loss": 0.6015,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.21680216802168023,
847
+ "grad_norm": 0.24306778049828862,
848
+ "learning_rate": 4.638410650401267e-06,
849
+ "loss": 0.6193,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.2186088527551942,
854
+ "grad_norm": 0.2269775698273598,
855
+ "learning_rate": 4.630622744628478e-06,
856
+ "loss": 0.6157,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.2204155374887082,
861
+ "grad_norm": 0.22557834203825844,
862
+ "learning_rate": 4.622758545555485e-06,
863
+ "loss": 0.6205,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.2222222222222222,
868
+ "grad_norm": 0.2388627744876031,
869
+ "learning_rate": 4.614818334783384e-06,
870
+ "loss": 0.6117,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.2240289069557362,
875
+ "grad_norm": 0.33690846185965356,
876
+ "learning_rate": 4.606802396635098e-06,
877
+ "loss": 0.5973,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.22583559168925021,
882
+ "grad_norm": 0.2559933256711994,
883
+ "learning_rate": 4.598711018145193e-06,
884
+ "loss": 0.6035,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.22764227642276422,
889
+ "grad_norm": 0.23041365241908557,
890
+ "learning_rate": 4.590544489049602e-06,
891
+ "loss": 0.6167,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.22944896115627822,
896
+ "grad_norm": 0.2386416733431471,
897
+ "learning_rate": 4.582303101775249e-06,
898
+ "loss": 0.6081,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.23125564588979222,
903
+ "grad_norm": 0.2253681313258335,
904
+ "learning_rate": 4.573987151429579e-06,
905
+ "loss": 0.6075,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.23306233062330622,
910
+ "grad_norm": 0.21952470403470545,
911
+ "learning_rate": 4.565596935789987e-06,
912
+ "loss": 0.6031,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.23486901535682023,
917
+ "grad_norm": 0.24331315011786012,
918
+ "learning_rate": 4.557132755293164e-06,
919
+ "loss": 0.6219,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.23667570009033423,
924
+ "grad_norm": 0.24835834109503124,
925
+ "learning_rate": 4.54859491302433e-06,
926
+ "loss": 0.6154,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.23848238482384823,
931
+ "grad_norm": 0.22732916433505923,
932
+ "learning_rate": 4.539983714706383e-06,
933
+ "loss": 0.5945,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.24028906955736223,
938
+ "grad_norm": 0.2181618946471109,
939
+ "learning_rate": 4.531299468688956e-06,
940
+ "loss": 0.61,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.24209575429087624,
945
+ "grad_norm": 0.2259645647372355,
946
+ "learning_rate": 4.522542485937369e-06,
947
+ "loss": 0.6105,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.24390243902439024,
952
+ "grad_norm": 0.2176244229453355,
953
+ "learning_rate": 4.5137130800215025e-06,
954
+ "loss": 0.6069,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.24570912375790424,
959
+ "grad_norm": 0.2552195449531324,
960
+ "learning_rate": 4.50481156710456e-06,
961
+ "loss": 0.6113,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.24751580849141824,
966
+ "grad_norm": 0.23421861438168898,
967
+ "learning_rate": 4.495838265931754e-06,
968
+ "loss": 0.5952,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.24932249322493225,
973
+ "grad_norm": 0.21810921222578047,
974
+ "learning_rate": 4.486793497818889e-06,
975
+ "loss": 0.6121,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.25112917795844625,
980
+ "grad_norm": 0.22773114029207175,
981
+ "learning_rate": 4.477677586640854e-06,
982
+ "loss": 0.6156,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.2529358626919603,
987
+ "grad_norm": 0.23705077325515508,
988
+ "learning_rate": 4.4684908588200305e-06,
989
+ "loss": 0.6156,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.25474254742547425,
994
+ "grad_norm": 0.24780177201776643,
995
+ "learning_rate": 4.4592336433146e-06,
996
+ "loss": 0.5953,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.2565492321589883,
1001
+ "grad_norm": 0.22862755103918672,
1002
+ "learning_rate": 4.449906271606766e-06,
1003
+ "loss": 0.616,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.25835591689250226,
1008
+ "grad_norm": 0.2404243241200089,
1009
+ "learning_rate": 4.440509077690883e-06,
1010
+ "loss": 0.607,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.2601626016260163,
1015
+ "grad_norm": 0.22293770252772532,
1016
+ "learning_rate": 4.431042398061499e-06,
1017
+ "loss": 0.5965,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.26196928635953026,
1022
+ "grad_norm": 0.20972193775216136,
1023
+ "learning_rate": 4.421506571701305e-06,
1024
+ "loss": 0.6093,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.26377597109304424,
1029
+ "grad_norm": 0.23518600200676912,
1030
+ "learning_rate": 4.411901940068997e-06,
1031
+ "loss": 0.6112,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.26558265582655827,
1036
+ "grad_norm": 0.22746108225760642,
1037
+ "learning_rate": 4.402228847087046e-06,
1038
+ "loss": 0.6037,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.26738934056007224,
1043
+ "grad_norm": 0.24903963512865804,
1044
+ "learning_rate": 4.3924876391293915e-06,
1045
+ "loss": 0.6048,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.26919602529358627,
1050
+ "grad_norm": 0.23472947723463866,
1051
+ "learning_rate": 4.382678665009028e-06,
1052
+ "loss": 0.6016,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.27100271002710025,
1057
+ "grad_norm": 0.23431207097830484,
1058
+ "learning_rate": 4.372802275965521e-06,
1059
+ "loss": 0.61,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.2728093947606143,
1064
+ "grad_norm": 0.22422800322111083,
1065
+ "learning_rate": 4.362858825652428e-06,
1066
+ "loss": 0.5949,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.27461607949412825,
1071
+ "grad_norm": 0.23561711836643753,
1072
+ "learning_rate": 4.352848670124637e-06,
1073
+ "loss": 0.5996,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.2764227642276423,
1078
+ "grad_norm": 0.21652376026883982,
1079
+ "learning_rate": 4.342772167825613e-06,
1080
+ "loss": 0.6009,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.27822944896115626,
1085
+ "grad_norm": 0.22742532543566119,
1086
+ "learning_rate": 4.332629679574566e-06,
1087
+ "loss": 0.6063,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.2800361336946703,
1092
+ "grad_norm": 0.3993451377830147,
1093
+ "learning_rate": 4.322421568553529e-06,
1094
+ "loss": 0.5961,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.28184281842818426,
1099
+ "grad_norm": 0.21468028516819,
1100
+ "learning_rate": 4.312148200294355e-06,
1101
+ "loss": 0.598,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.2836495031616983,
1106
+ "grad_norm": 0.2790705925726011,
1107
+ "learning_rate": 4.3018099426656255e-06,
1108
+ "loss": 0.6108,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.28545618789521227,
1113
+ "grad_norm": 0.22328718703580291,
1114
+ "learning_rate": 4.291407165859481e-06,
1115
+ "loss": 0.6073,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.2872628726287263,
1120
+ "grad_norm": 0.24079715236297133,
1121
+ "learning_rate": 4.280940242378363e-06,
1122
+ "loss": 0.5892,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.28906955736224027,
1127
+ "grad_norm": 0.3349816071529816,
1128
+ "learning_rate": 4.2704095470216745e-06,
1129
+ "loss": 0.5985,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.2908762420957543,
1134
+ "grad_norm": 0.2351483485898414,
1135
+ "learning_rate": 4.259815456872363e-06,
1136
+ "loss": 0.6041,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.2926829268292683,
1141
+ "grad_norm": 0.23385513145667092,
1142
+ "learning_rate": 4.249158351283414e-06,
1143
+ "loss": 0.5903,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.2944896115627823,
1148
+ "grad_norm": 0.22962794810239154,
1149
+ "learning_rate": 4.2384386118642696e-06,
1150
+ "loss": 0.6006,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.2962962962962963,
1155
+ "grad_norm": 0.227041646781334,
1156
+ "learning_rate": 4.227656622467162e-06,
1157
+ "loss": 0.609,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.2981029810298103,
1162
+ "grad_norm": 0.23339515173861125,
1163
+ "learning_rate": 4.216812769173371e-06,
1164
+ "loss": 0.6008,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.2999096657633243,
1169
+ "grad_norm": 0.2279892093631049,
1170
+ "learning_rate": 4.205907440279395e-06,
1171
+ "loss": 0.6067,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.3017163504968383,
1176
+ "grad_norm": 0.24349945347421037,
1177
+ "learning_rate": 4.194941026283053e-06,
1178
+ "loss": 0.6064,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.3035230352303523,
1183
+ "grad_norm": 0.2191845217404836,
1184
+ "learning_rate": 4.183913919869495e-06,
1185
+ "loss": 0.6039,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.3053297199638663,
1190
+ "grad_norm": 0.2180478057517194,
1191
+ "learning_rate": 4.172826515897146e-06,
1192
+ "loss": 0.597,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.3071364046973803,
1197
+ "grad_norm": 0.22148092498016186,
1198
+ "learning_rate": 4.161679211383565e-06,
1199
+ "loss": 0.6116,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.3089430894308943,
1204
+ "grad_norm": 0.21976711391650572,
1205
+ "learning_rate": 4.150472405491226e-06,
1206
+ "loss": 0.5937,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.3107497741644083,
1211
+ "grad_norm": 0.2359272043525047,
1212
+ "learning_rate": 4.139206499513231e-06,
1213
+ "loss": 0.6002,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.31255645889792233,
1218
+ "grad_norm": 0.20743057651505534,
1219
+ "learning_rate": 4.127881896858934e-06,
1220
+ "loss": 0.6036,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.3143631436314363,
1225
+ "grad_norm": 0.2185478761510027,
1226
+ "learning_rate": 4.116499003039499e-06,
1227
+ "loss": 0.5947,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.31616982836495033,
1232
+ "grad_norm": 0.24479063305435536,
1233
+ "learning_rate": 4.105058225653381e-06,
1234
+ "loss": 0.6,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.3179765130984643,
1239
+ "grad_norm": 0.22541665254858562,
1240
+ "learning_rate": 4.093559974371725e-06,
1241
+ "loss": 0.6137,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.31978319783197834,
1246
+ "grad_norm": 0.23354779603092837,
1247
+ "learning_rate": 4.0820046609237026e-06,
1248
+ "loss": 0.5881,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.3215898825654923,
1253
+ "grad_norm": 0.22004453141007924,
1254
+ "learning_rate": 4.070392699081767e-06,
1255
+ "loss": 0.5948,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.32339656729900634,
1260
+ "grad_norm": 0.22301964541218125,
1261
+ "learning_rate": 4.058724504646834e-06,
1262
+ "loss": 0.6054,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.3252032520325203,
1267
+ "grad_norm": 0.23125154097212539,
1268
+ "learning_rate": 4.047000495433397e-06,
1269
+ "loss": 0.6135,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.32700993676603435,
1274
+ "grad_norm": 0.2194814968746533,
1275
+ "learning_rate": 4.035221091254563e-06,
1276
+ "loss": 0.5902,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.3288166214995483,
1281
+ "grad_norm": 0.22257729627885203,
1282
+ "learning_rate": 4.023386713907021e-06,
1283
+ "loss": 0.6005,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.33062330623306235,
1288
+ "grad_norm": 0.22264840616047507,
1289
+ "learning_rate": 4.011497787155938e-06,
1290
+ "loss": 0.6123,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.3324299909665763,
1295
+ "grad_norm": 0.22891861604269678,
1296
+ "learning_rate": 3.999554736719785e-06,
1297
+ "loss": 0.6093,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.33423667570009036,
1302
+ "grad_norm": 0.2368591129219394,
1303
+ "learning_rate": 3.987557990255093e-06,
1304
+ "loss": 0.6054,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.33604336043360433,
1309
+ "grad_norm": 0.2483359395611164,
1310
+ "learning_rate": 3.975507977341141e-06,
1311
+ "loss": 0.6011,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.33785004516711836,
1316
+ "grad_norm": 0.20257786753801169,
1317
+ "learning_rate": 3.963405129464569e-06,
1318
+ "loss": 0.5983,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.33965672990063234,
1323
+ "grad_norm": 0.2186759693689697,
1324
+ "learning_rate": 3.951249880003934e-06,
1325
+ "loss": 0.5973,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.34146341463414637,
1330
+ "grad_norm": 0.21876513682058207,
1331
+ "learning_rate": 3.939042664214185e-06,
1332
+ "loss": 0.6052,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.34327009936766034,
1337
+ "grad_norm": 0.2099916515113305,
1338
+ "learning_rate": 3.92678391921108e-06,
1339
+ "loss": 0.5936,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.34507678410117437,
1344
+ "grad_norm": 0.2343120602972887,
1345
+ "learning_rate": 3.914474083955537e-06,
1346
+ "loss": 0.592,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.34688346883468835,
1351
+ "grad_norm": 0.20255138476243217,
1352
+ "learning_rate": 3.902113599237911e-06,
1353
+ "loss": 0.5986,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.3486901535682023,
1358
+ "grad_norm": 0.20455659875517468,
1359
+ "learning_rate": 3.889702907662212e-06,
1360
+ "loss": 0.6009,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.35049683830171635,
1365
+ "grad_norm": 0.22151992117493785,
1366
+ "learning_rate": 3.8772424536302565e-06,
1367
+ "loss": 0.6022,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.3523035230352303,
1372
+ "grad_norm": 0.23833014531149102,
1373
+ "learning_rate": 3.864732683325755e-06,
1374
+ "loss": 0.5856,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.35411020776874436,
1379
+ "grad_norm": 0.2139415037008631,
1380
+ "learning_rate": 3.852174044698333e-06,
1381
+ "loss": 0.5989,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.35591689250225833,
1386
+ "grad_norm": 0.2194749540116677,
1387
+ "learning_rate": 3.839566987447492e-06,
1388
+ "loss": 0.598,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.35772357723577236,
1393
+ "grad_norm": 0.2381302592790127,
1394
+ "learning_rate": 3.826911963006508e-06,
1395
+ "loss": 0.5752,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.35953026196928634,
1400
+ "grad_norm": 0.23075119894415708,
1401
+ "learning_rate": 3.8142094245262617e-06,
1402
+ "loss": 0.5978,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.36133694670280037,
1407
+ "grad_norm": 0.23286158873769425,
1408
+ "learning_rate": 3.801459826859022e-06,
1409
+ "loss": 0.5877,
1410
+ "step": 200
1411
+ }
1412
+ ],
1413
+ "logging_steps": 1,
1414
+ "max_steps": 553,
1415
+ "num_input_tokens_seen": 0,
1416
+ "num_train_epochs": 1,
1417
+ "save_steps": 100,
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": false
1426
+ },
1427
+ "attributes": {}
1428
+ }
1429
+ },
1430
+ "total_flos": 231524290789376.0,
1431
+ "train_batch_size": 2,
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 sha256:440a23aa86e6a03cf8f0282dabde2ee05bbe1b06131c9101c190f53e1cb9d054
3
+ size 8017
vocab.json ADDED
The diff for this file is too large to render. See raw diff