fengyao1909 commited on
Commit
0226446
·
verified ·
1 Parent(s): 7aac02c

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
+ }
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": "4.51.3",
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": "4.51.3"
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 sha256:448d7356c911ae9eada69dc4352594a42fd2996591ec8707595c164858c56930
3
+ size 4997184968
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33575b79785f3a69ad7a113b0185f12696f49beb363f6262b2bd3caba4c8998f
3
+ size 4997741608
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0193c19622a9817cb2b15fdeb22f23b09238580fa51db8dad7065290da7f45db
3
+ size 4997742208
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523b4d212ae9bead700ce3950fe943acb11ab5d339f911b152dc5a219101e9af
3
+ size 4997743184
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df69e3dc133c101631da4530bb3edda7186d949841ea70474459152fd4288c2
3
+ size 4997743184
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3ff290787a19d527437ff2dadc44c434fe7e592ed513705f3742feff2895e3
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:e19adde26776c930eab5567a924219ed447f3fa9278e0f1971ec1b0181b7d460
3
+ size 4997743184
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13aa0a158fd001485de301b8711f919496e0af0099134fcd2a59f69b79643a58
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:b82559855598cc5ee7ca735ccfc5fd457e6cf170c98f5a0f3d86527327732344
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:fdf76b047bbf80a192ca7e90029268e3478f9907cfc8310d9f99a3d5f434090f
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:a53379cb4fb83c401c1fb429a7c46f6c774d3882ce8ec725ec81463753d8bd37
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:bfb670d8e2fcea78dc9f1bd1e58b62596f6b1bc4733cf8c40986b14b9a4a6231
3
+ size 4997743184
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723f0e9bda0b31e758f5efb134e4bbef56a06bb96344ed4c994fdfff3625274c
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 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "padding_side": "right",
238
+ "split_special_tokens": false,
239
+ "tokenizer_class": "Qwen2Tokenizer",
240
+ "unk_token": null
241
+ }
trainer_state.json ADDED
@@ -0,0 +1,1798 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 252,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015873015873015872,
14
+ "grad_norm": 2.355871594757968,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.0469,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.031746031746031744,
21
+ "grad_norm": 2.29666205825573,
22
+ "learning_rate": 1.5625e-06,
23
+ "loss": 0.9929,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.047619047619047616,
28
+ "grad_norm": 2.535252155158116,
29
+ "learning_rate": 3.125e-06,
30
+ "loss": 1.0185,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.06349206349206349,
35
+ "grad_norm": 2.106429965859871,
36
+ "learning_rate": 4.6875000000000004e-06,
37
+ "loss": 0.9046,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.07936507936507936,
42
+ "grad_norm": 1.7754252196610092,
43
+ "learning_rate": 6.25e-06,
44
+ "loss": 1.0312,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.09523809523809523,
49
+ "grad_norm": 1.5212254656019404,
50
+ "learning_rate": 7.8125e-06,
51
+ "loss": 0.9741,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.1111111111111111,
56
+ "grad_norm": 1.2286700272250457,
57
+ "learning_rate": 9.375000000000001e-06,
58
+ "loss": 0.924,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.12698412698412698,
63
+ "grad_norm": 1.239763672997659,
64
+ "learning_rate": 1.09375e-05,
65
+ "loss": 0.9112,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.14285714285714285,
70
+ "grad_norm": 1.7804807603399884,
71
+ "learning_rate": 1.25e-05,
72
+ "loss": 0.9631,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.15873015873015872,
77
+ "grad_norm": 1.6096276860914913,
78
+ "learning_rate": 1.4062500000000001e-05,
79
+ "loss": 0.8914,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.1746031746031746,
84
+ "grad_norm": 1.4685478602306294,
85
+ "learning_rate": 1.5625e-05,
86
+ "loss": 0.8313,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.19047619047619047,
91
+ "grad_norm": 1.797675338951107,
92
+ "learning_rate": 1.71875e-05,
93
+ "loss": 0.9572,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.20634920634920634,
98
+ "grad_norm": 1.5020710264445867,
99
+ "learning_rate": 1.8750000000000002e-05,
100
+ "loss": 0.8929,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.2222222222222222,
105
+ "grad_norm": 1.389913325647765,
106
+ "learning_rate": 2.0312500000000002e-05,
107
+ "loss": 1.0575,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.23809523809523808,
112
+ "grad_norm": 1.0364172775494112,
113
+ "learning_rate": 2.1875e-05,
114
+ "loss": 0.9367,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.25396825396825395,
119
+ "grad_norm": 1.1754008678466592,
120
+ "learning_rate": 2.34375e-05,
121
+ "loss": 1.0082,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.2698412698412698,
126
+ "grad_norm": 1.0227204004003465,
127
+ "learning_rate": 2.5e-05,
128
+ "loss": 0.9148,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.2857142857142857,
133
+ "grad_norm": 1.0820292890536618,
134
+ "learning_rate": 2.6562500000000002e-05,
135
+ "loss": 0.9748,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.30158730158730157,
140
+ "grad_norm": 0.945837076799249,
141
+ "learning_rate": 2.8125000000000003e-05,
142
+ "loss": 0.7132,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.31746031746031744,
147
+ "grad_norm": 1.0248571882025115,
148
+ "learning_rate": 2.96875e-05,
149
+ "loss": 0.8881,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.3333333333333333,
154
+ "grad_norm": 0.7825673389448284,
155
+ "learning_rate": 3.125e-05,
156
+ "loss": 0.9596,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.3492063492063492,
161
+ "grad_norm": 0.9610289643147956,
162
+ "learning_rate": 3.2812500000000005e-05,
163
+ "loss": 1.0261,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.36507936507936506,
168
+ "grad_norm": 0.9669319262880848,
169
+ "learning_rate": 3.4375e-05,
170
+ "loss": 0.8504,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.38095238095238093,
175
+ "grad_norm": 0.7449356400588687,
176
+ "learning_rate": 3.59375e-05,
177
+ "loss": 0.8124,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.3968253968253968,
182
+ "grad_norm": 0.83693613965816,
183
+ "learning_rate": 3.7500000000000003e-05,
184
+ "loss": 1.0061,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.4126984126984127,
189
+ "grad_norm": 0.732383235323442,
190
+ "learning_rate": 3.90625e-05,
191
+ "loss": 0.8433,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.42857142857142855,
196
+ "grad_norm": 0.7794935876422098,
197
+ "learning_rate": 4.0625000000000005e-05,
198
+ "loss": 0.7042,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.4444444444444444,
203
+ "grad_norm": 0.7604958575268047,
204
+ "learning_rate": 4.21875e-05,
205
+ "loss": 0.9629,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.4603174603174603,
210
+ "grad_norm": 0.6984385536231642,
211
+ "learning_rate": 4.375e-05,
212
+ "loss": 0.8909,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.47619047619047616,
217
+ "grad_norm": 0.7941140442495155,
218
+ "learning_rate": 4.5312500000000004e-05,
219
+ "loss": 0.9318,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.49206349206349204,
224
+ "grad_norm": 0.7485507149365567,
225
+ "learning_rate": 4.6875e-05,
226
+ "loss": 0.9032,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.5079365079365079,
231
+ "grad_norm": 0.7312955579208906,
232
+ "learning_rate": 4.8437500000000005e-05,
233
+ "loss": 0.8793,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.5238095238095238,
238
+ "grad_norm": 0.728955139017027,
239
+ "learning_rate": 5e-05,
240
+ "loss": 1.0292,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.5396825396825397,
245
+ "grad_norm": 0.6223071714803796,
246
+ "learning_rate": 4.999845960383972e-05,
247
+ "loss": 0.829,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.5555555555555556,
252
+ "grad_norm": 0.7081482857388056,
253
+ "learning_rate": 4.999383860518451e-05,
254
+ "loss": 0.821,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.5714285714285714,
259
+ "grad_norm": 0.7021438050343367,
260
+ "learning_rate": 4.998613757348784e-05,
261
+ "loss": 0.9658,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.5873015873015873,
266
+ "grad_norm": 0.6005545292155794,
267
+ "learning_rate": 4.9975357457760896e-05,
268
+ "loss": 0.9805,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.6031746031746031,
273
+ "grad_norm": 0.66159765943155,
274
+ "learning_rate": 4.9961499586455584e-05,
275
+ "loss": 0.8479,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.6190476190476191,
280
+ "grad_norm": 0.6859851915992995,
281
+ "learning_rate": 4.994456566730085e-05,
282
+ "loss": 0.9104,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.6349206349206349,
287
+ "grad_norm": 0.5770937588145084,
288
+ "learning_rate": 4.9924557787092216e-05,
289
+ "loss": 0.7705,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.6507936507936508,
294
+ "grad_norm": 0.5587380636863567,
295
+ "learning_rate": 4.990147841143462e-05,
296
+ "loss": 0.8406,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.6666666666666666,
301
+ "grad_norm": 0.5939117737515469,
302
+ "learning_rate": 4.9875330384438604e-05,
303
+ "loss": 0.9143,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.6825396825396826,
308
+ "grad_norm": 0.5421902034671652,
309
+ "learning_rate": 4.984611692836979e-05,
310
+ "loss": 0.8323,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.6984126984126984,
315
+ "grad_norm": 0.5523631282552526,
316
+ "learning_rate": 4.9813841643251836e-05,
317
+ "loss": 0.7557,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.7142857142857143,
322
+ "grad_norm": 0.5991896816540728,
323
+ "learning_rate": 4.977850850642275e-05,
324
+ "loss": 0.8471,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.7301587301587301,
329
+ "grad_norm": 0.6364621652121066,
330
+ "learning_rate": 4.97401218720448e-05,
331
+ "loss": 0.8013,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.746031746031746,
336
+ "grad_norm": 0.5534873919742207,
337
+ "learning_rate": 4.969868647056792e-05,
338
+ "loss": 0.8996,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.7619047619047619,
343
+ "grad_norm": 0.5035034360883922,
344
+ "learning_rate": 4.965420740814679e-05,
345
+ "loss": 0.8944,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.7777777777777778,
350
+ "grad_norm": 0.5729489774574688,
351
+ "learning_rate": 4.9606690166011546e-05,
352
+ "loss": 0.7887,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.7936507936507936,
357
+ "grad_norm": 0.6004405465949967,
358
+ "learning_rate": 4.95561405997924e-05,
359
+ "loss": 0.831,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.8095238095238095,
364
+ "grad_norm": 0.725673276310606,
365
+ "learning_rate": 4.9502564938797946e-05,
366
+ "loss": 0.8849,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.8253968253968254,
371
+ "grad_norm": 0.4990176056299948,
372
+ "learning_rate": 4.9445969785247595e-05,
373
+ "loss": 0.8298,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.8412698412698413,
378
+ "grad_norm": 0.6071056927514447,
379
+ "learning_rate": 4.938636211345792e-05,
380
+ "loss": 0.944,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.8571428571428571,
385
+ "grad_norm": 0.6345636016627114,
386
+ "learning_rate": 4.932374926898321e-05,
387
+ "loss": 0.8069,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.873015873015873,
392
+ "grad_norm": 0.6333202856879505,
393
+ "learning_rate": 4.9258138967710306e-05,
394
+ "loss": 0.7373,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.8888888888888888,
399
+ "grad_norm": 0.5152048396222051,
400
+ "learning_rate": 4.918953929490768e-05,
401
+ "loss": 0.8855,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.9047619047619048,
406
+ "grad_norm": 0.5806639114473304,
407
+ "learning_rate": 4.9117958704229154e-05,
408
+ "loss": 0.8731,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.9206349206349206,
413
+ "grad_norm": 0.6001547400645247,
414
+ "learning_rate": 4.904340601667208e-05,
415
+ "loss": 0.816,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.9365079365079365,
420
+ "grad_norm": 0.470270082255384,
421
+ "learning_rate": 4.8965890419490354e-05,
422
+ "loss": 0.8847,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.9523809523809523,
427
+ "grad_norm": 0.5015222585808989,
428
+ "learning_rate": 4.8885421465062236e-05,
429
+ "loss": 0.8507,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.9682539682539683,
434
+ "grad_norm": 0.48808541077856465,
435
+ "learning_rate": 4.88020090697132e-05,
436
+ "loss": 0.774,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.9841269841269841,
441
+ "grad_norm": 0.5837250225569859,
442
+ "learning_rate": 4.871566351249393e-05,
443
+ "loss": 0.8844,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 1.0,
448
+ "grad_norm": 0.5121395435398158,
449
+ "learning_rate": 4.86263954339136e-05,
450
+ "loss": 0.7565,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 1.0158730158730158,
455
+ "grad_norm": 0.858989786993005,
456
+ "learning_rate": 4.853421583462866e-05,
457
+ "loss": 0.7147,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 1.0317460317460316,
462
+ "grad_norm": 0.6819369439457027,
463
+ "learning_rate": 4.843913607408717e-05,
464
+ "loss": 0.7632,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 1.0476190476190477,
469
+ "grad_norm": 0.8758215098676306,
470
+ "learning_rate": 4.834116786912897e-05,
471
+ "loss": 0.7952,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 1.0634920634920635,
476
+ "grad_norm": 0.5971995504609642,
477
+ "learning_rate": 4.82403232925418e-05,
478
+ "loss": 0.6327,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 1.0793650793650793,
483
+ "grad_norm": 0.5651140794936931,
484
+ "learning_rate": 4.8136614771573554e-05,
485
+ "loss": 0.6429,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 1.0952380952380953,
490
+ "grad_norm": 0.882155318220025,
491
+ "learning_rate": 4.8030055086400826e-05,
492
+ "loss": 0.8083,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 1.1111111111111112,
497
+ "grad_norm": 0.7712424011094504,
498
+ "learning_rate": 4.7920657368554e-05,
499
+ "loss": 0.6792,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 1.126984126984127,
504
+ "grad_norm": 0.5624839067932064,
505
+ "learning_rate": 4.7808435099299045e-05,
506
+ "loss": 0.6928,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 1.1428571428571428,
511
+ "grad_norm": 0.5634668991057131,
512
+ "learning_rate": 4.7693402107976174e-05,
513
+ "loss": 0.7191,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 1.1587301587301586,
518
+ "grad_norm": 0.6557940355672685,
519
+ "learning_rate": 4.757557257029564e-05,
520
+ "loss": 0.7138,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 1.1746031746031746,
525
+ "grad_norm": 0.5576756408219278,
526
+ "learning_rate": 4.745496100659082e-05,
527
+ "loss": 0.6904,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 1.1904761904761905,
532
+ "grad_norm": 0.5394945009236098,
533
+ "learning_rate": 4.7331582280028906e-05,
534
+ "loss": 0.6684,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 1.2063492063492063,
539
+ "grad_norm": 0.5616484225088534,
540
+ "learning_rate": 4.720545159477922e-05,
541
+ "loss": 0.6123,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 1.2222222222222223,
546
+ "grad_norm": 0.6137522865571288,
547
+ "learning_rate": 4.7076584494139606e-05,
548
+ "loss": 0.6639,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 1.2380952380952381,
553
+ "grad_norm": 0.5520563824703866,
554
+ "learning_rate": 4.694499685862106e-05,
555
+ "loss": 0.7504,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 1.253968253968254,
560
+ "grad_norm": 0.6398395502333153,
561
+ "learning_rate": 4.6810704903990634e-05,
562
+ "loss": 0.8063,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 1.2698412698412698,
567
+ "grad_norm": 0.5170068764903927,
568
+ "learning_rate": 4.667372517927323e-05,
569
+ "loss": 0.682,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 1.2857142857142856,
574
+ "grad_norm": 0.5470142100714379,
575
+ "learning_rate": 4.653407456471222e-05,
576
+ "loss": 0.74,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 1.3015873015873016,
581
+ "grad_norm": 0.5344699813999502,
582
+ "learning_rate": 4.6391770269689236e-05,
583
+ "loss": 0.7019,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 1.3174603174603174,
588
+ "grad_norm": 0.572242361510543,
589
+ "learning_rate": 4.6246829830603454e-05,
590
+ "loss": 0.7612,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 1.3333333333333333,
595
+ "grad_norm": 0.5918389811121451,
596
+ "learning_rate": 4.609927110871053e-05,
597
+ "loss": 0.7285,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 1.3492063492063493,
602
+ "grad_norm": 0.4866622733839569,
603
+ "learning_rate": 4.594911228792156e-05,
604
+ "loss": 0.656,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 1.3650793650793651,
609
+ "grad_norm": 0.5275973128412808,
610
+ "learning_rate": 4.579637187256222e-05,
611
+ "loss": 0.576,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 1.380952380952381,
616
+ "grad_norm": 0.5488033313933244,
617
+ "learning_rate": 4.564106868509246e-05,
618
+ "loss": 0.7176,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 1.3968253968253967,
623
+ "grad_norm": 0.6920680886388099,
624
+ "learning_rate": 4.548322186378697e-05,
625
+ "loss": 0.7926,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 1.4126984126984126,
630
+ "grad_norm": 0.774236286341856,
631
+ "learning_rate": 4.532285086037674e-05,
632
+ "loss": 0.7313,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 1.4285714285714286,
637
+ "grad_norm": 0.7799985101441093,
638
+ "learning_rate": 4.5159975437652017e-05,
639
+ "loss": 0.717,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 1.4444444444444444,
644
+ "grad_norm": 0.5542880474504607,
645
+ "learning_rate": 4.499461566702685e-05,
646
+ "loss": 0.5701,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 1.4603174603174602,
651
+ "grad_norm": 0.6118784803715336,
652
+ "learning_rate": 4.48267919260657e-05,
653
+ "loss": 0.7026,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 1.4761904761904763,
658
+ "grad_norm": 0.6649407372701752,
659
+ "learning_rate": 4.4656524895972255e-05,
660
+ "loss": 0.7061,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 1.492063492063492,
665
+ "grad_norm": 0.47895549061427817,
666
+ "learning_rate": 4.448383555904088e-05,
667
+ "loss": 0.6387,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 1.507936507936508,
672
+ "grad_norm": 0.5811905127982857,
673
+ "learning_rate": 4.430874519607089e-05,
674
+ "loss": 0.8295,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 1.5238095238095237,
679
+ "grad_norm": 0.6782303990614583,
680
+ "learning_rate": 4.413127538374411e-05,
681
+ "loss": 0.7571,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 1.5396825396825395,
686
+ "grad_norm": 0.5127521378901643,
687
+ "learning_rate": 4.395144799196593e-05,
688
+ "loss": 0.6259,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 1.5555555555555556,
693
+ "grad_norm": 1.1333047155488623,
694
+ "learning_rate": 4.376928518117027e-05,
695
+ "loss": 0.7263,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 1.5714285714285714,
700
+ "grad_norm": 0.9285725347831506,
701
+ "learning_rate": 4.358480939958867e-05,
702
+ "loss": 0.6652,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 1.5873015873015874,
707
+ "grad_norm": 0.5756004852981952,
708
+ "learning_rate": 4.3398043380483965e-05,
709
+ "loss": 0.7045,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 1.6031746031746033,
714
+ "grad_norm": 0.5732214165272889,
715
+ "learning_rate": 4.320901013934887e-05,
716
+ "loss": 0.7096,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 1.619047619047619,
721
+ "grad_norm": 0.5729960942540637,
722
+ "learning_rate": 4.3017732971069674e-05,
723
+ "loss": 0.7797,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 1.6349206349206349,
728
+ "grad_norm": 0.6414711093856016,
729
+ "learning_rate": 4.282423544705564e-05,
730
+ "loss": 0.75,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 1.6507936507936507,
735
+ "grad_norm": 0.48208643464721207,
736
+ "learning_rate": 4.262854141233419e-05,
737
+ "loss": 0.7566,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 1.6666666666666665,
742
+ "grad_norm": 0.5650935089244651,
743
+ "learning_rate": 4.2430674982612506e-05,
744
+ "loss": 0.7282,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 1.6825396825396826,
749
+ "grad_norm": 0.6266660832902915,
750
+ "learning_rate": 4.223066054130568e-05,
751
+ "loss": 0.7098,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 1.6984126984126984,
756
+ "grad_norm": 1.1721379739857851,
757
+ "learning_rate": 4.2028522736531895e-05,
758
+ "loss": 0.7244,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 1.7142857142857144,
763
+ "grad_norm": 0.5821734258045642,
764
+ "learning_rate": 4.1824286478075025e-05,
765
+ "loss": 0.7918,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 1.7301587301587302,
770
+ "grad_norm": 0.5675713145707344,
771
+ "learning_rate": 4.161797693431493e-05,
772
+ "loss": 0.7271,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 1.746031746031746,
777
+ "grad_norm": 0.5948316073979433,
778
+ "learning_rate": 4.140961952912594e-05,
779
+ "loss": 0.6585,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 1.7619047619047619,
784
+ "grad_norm": 0.6142301353494962,
785
+ "learning_rate": 4.1199239938743797e-05,
786
+ "loss": 0.6636,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 1.7777777777777777,
791
+ "grad_norm": 0.6089779675550376,
792
+ "learning_rate": 4.0986864088601564e-05,
793
+ "loss": 0.6483,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 1.7936507936507935,
798
+ "grad_norm": 0.5407284417083653,
799
+ "learning_rate": 4.077251815013477e-05,
800
+ "loss": 0.6273,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 1.8095238095238095,
805
+ "grad_norm": 0.5554496556982176,
806
+ "learning_rate": 4.0556228537556266e-05,
807
+ "loss": 0.6301,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 1.8253968253968254,
812
+ "grad_norm": 0.5507291755794801,
813
+ "learning_rate": 4.0338021904601145e-05,
814
+ "loss": 0.6909,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 1.8412698412698414,
819
+ "grad_norm": 0.4537046958331062,
820
+ "learning_rate": 4.0117925141242174e-05,
821
+ "loss": 0.7491,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 1.8571428571428572,
826
+ "grad_norm": 0.5463750469400513,
827
+ "learning_rate": 3.9895965370376076e-05,
828
+ "loss": 0.8075,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 1.873015873015873,
833
+ "grad_norm": 0.5027853264982712,
834
+ "learning_rate": 3.9672169944481165e-05,
835
+ "loss": 0.5601,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 1.8888888888888888,
840
+ "grad_norm": 0.5661467536668536,
841
+ "learning_rate": 3.944656644224661e-05,
842
+ "loss": 0.7353,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 1.9047619047619047,
847
+ "grad_norm": 0.48806777854236366,
848
+ "learning_rate": 3.921918266517391e-05,
849
+ "loss": 0.6765,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 1.9206349206349205,
854
+ "grad_norm": 0.5877767380659309,
855
+ "learning_rate": 3.899004663415084e-05,
856
+ "loss": 0.707,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 1.9365079365079365,
861
+ "grad_norm": 0.5311318468752881,
862
+ "learning_rate": 3.875918658599837e-05,
863
+ "loss": 0.7882,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 1.9523809523809523,
868
+ "grad_norm": 0.5682753083153059,
869
+ "learning_rate": 3.8526630969991035e-05,
870
+ "loss": 0.6445,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 1.9682539682539684,
875
+ "grad_norm": 0.4740591298744526,
876
+ "learning_rate": 3.8292408444351094e-05,
877
+ "loss": 0.6718,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 1.9841269841269842,
882
+ "grad_norm": 0.45882583861407755,
883
+ "learning_rate": 3.805654787271686e-05,
884
+ "loss": 0.6762,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 2.0,
889
+ "grad_norm": 0.5675883245832433,
890
+ "learning_rate": 3.781907832058587e-05,
891
+ "loss": 0.7781,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 2.015873015873016,
896
+ "grad_norm": 1.1104924115901638,
897
+ "learning_rate": 3.758002905173299e-05,
898
+ "loss": 0.4988,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 2.0317460317460316,
903
+ "grad_norm": 2.7413879763258584,
904
+ "learning_rate": 3.7339429524604316e-05,
905
+ "loss": 0.5467,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 2.0476190476190474,
910
+ "grad_norm": 2.2935599186627647,
911
+ "learning_rate": 3.7097309388686864e-05,
912
+ "loss": 0.6297,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 2.0634920634920633,
917
+ "grad_norm": 0.8617968906197346,
918
+ "learning_rate": 3.6853698480854855e-05,
919
+ "loss": 0.5621,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 2.0793650793650795,
924
+ "grad_norm": 0.8914264101265775,
925
+ "learning_rate": 3.660862682169282e-05,
926
+ "loss": 0.4258,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 2.0952380952380953,
931
+ "grad_norm": 0.8467461851206783,
932
+ "learning_rate": 3.6362124611796225e-05,
933
+ "loss": 0.4557,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 2.111111111111111,
938
+ "grad_norm": 0.7089992750499162,
939
+ "learning_rate": 3.6114222228049656e-05,
940
+ "loss": 0.5554,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 2.126984126984127,
945
+ "grad_norm": 1.140458615229716,
946
+ "learning_rate": 3.586495021988351e-05,
947
+ "loss": 0.5374,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 2.142857142857143,
952
+ "grad_norm": 0.7757982307284462,
953
+ "learning_rate": 3.5614339305509336e-05,
954
+ "loss": 0.5589,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 2.1587301587301586,
959
+ "grad_norm": 0.6933824916021677,
960
+ "learning_rate": 3.5362420368134356e-05,
961
+ "loss": 0.4544,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 2.1746031746031744,
966
+ "grad_norm": 0.719692057444369,
967
+ "learning_rate": 3.510922445215568e-05,
968
+ "loss": 0.531,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 2.1904761904761907,
973
+ "grad_norm": 0.5869409227388236,
974
+ "learning_rate": 3.4854782759334627e-05,
975
+ "loss": 0.5112,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 2.2063492063492065,
980
+ "grad_norm": 0.5457151982279885,
981
+ "learning_rate": 3.459912664495176e-05,
982
+ "loss": 0.4499,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 2.2222222222222223,
987
+ "grad_norm": 0.7006218084957239,
988
+ "learning_rate": 3.4342287613942805e-05,
989
+ "loss": 0.5074,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 2.238095238095238,
994
+ "grad_norm": 0.5496478791456875,
995
+ "learning_rate": 3.408429731701635e-05,
996
+ "loss": 0.4533,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 2.253968253968254,
1001
+ "grad_norm": 0.7267666056198808,
1002
+ "learning_rate": 3.3825187546753425e-05,
1003
+ "loss": 0.5618,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 2.2698412698412698,
1008
+ "grad_norm": 0.5231531289243824,
1009
+ "learning_rate": 3.356499023368963e-05,
1010
+ "loss": 0.4319,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 2.2857142857142856,
1015
+ "grad_norm": 0.586670521348103,
1016
+ "learning_rate": 3.330373744238033e-05,
1017
+ "loss": 0.4441,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 2.3015873015873014,
1022
+ "grad_norm": 0.5837432088571016,
1023
+ "learning_rate": 3.3041461367449254e-05,
1024
+ "loss": 0.4027,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 2.317460317460317,
1029
+ "grad_norm": 0.5743190095438013,
1030
+ "learning_rate": 3.2778194329621104e-05,
1031
+ "loss": 0.4944,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 2.3333333333333335,
1036
+ "grad_norm": 0.6587815114542759,
1037
+ "learning_rate": 3.251396877173861e-05,
1038
+ "loss": 0.5504,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 2.3492063492063493,
1043
+ "grad_norm": 0.6550600819194445,
1044
+ "learning_rate": 3.2248817254764554e-05,
1045
+ "loss": 0.4673,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 2.365079365079365,
1050
+ "grad_norm": 0.5454074517099673,
1051
+ "learning_rate": 3.1982772453769236e-05,
1052
+ "loss": 0.4607,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 2.380952380952381,
1057
+ "grad_norm": 0.6024175453719594,
1058
+ "learning_rate": 3.171586715390384e-05,
1059
+ "loss": 0.603,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 2.3968253968253967,
1064
+ "grad_norm": 0.6278682196249654,
1065
+ "learning_rate": 3.144813424636031e-05,
1066
+ "loss": 0.5712,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 2.4126984126984126,
1071
+ "grad_norm": 0.6240251741716067,
1072
+ "learning_rate": 3.117960672431805e-05,
1073
+ "loss": 0.5312,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 2.4285714285714284,
1078
+ "grad_norm": 0.5826262197215396,
1079
+ "learning_rate": 3.091031767887817e-05,
1080
+ "loss": 0.5541,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 2.4444444444444446,
1085
+ "grad_norm": 0.5973198102264671,
1086
+ "learning_rate": 3.064030029498561e-05,
1087
+ "loss": 0.5684,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 2.4603174603174605,
1092
+ "grad_norm": 0.5452803248570526,
1093
+ "learning_rate": 3.036958784733967e-05,
1094
+ "loss": 0.579,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 2.4761904761904763,
1099
+ "grad_norm": 0.4826933541939396,
1100
+ "learning_rate": 3.0098213696293542e-05,
1101
+ "loss": 0.4995,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 2.492063492063492,
1106
+ "grad_norm": 0.5045447989769657,
1107
+ "learning_rate": 2.982621128374325e-05,
1108
+ "loss": 0.5211,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 2.507936507936508,
1113
+ "grad_norm": 0.5512726317886238,
1114
+ "learning_rate": 2.955361412900654e-05,
1115
+ "loss": 0.4766,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 2.5238095238095237,
1120
+ "grad_norm": 0.5720105255698517,
1121
+ "learning_rate": 2.9280455824692256e-05,
1122
+ "loss": 0.4498,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 2.5396825396825395,
1127
+ "grad_norm": 0.5440271425737038,
1128
+ "learning_rate": 2.9006770032560637e-05,
1129
+ "loss": 0.4801,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 2.5555555555555554,
1134
+ "grad_norm": 0.5161357261610209,
1135
+ "learning_rate": 2.8732590479375165e-05,
1136
+ "loss": 0.4853,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 2.571428571428571,
1141
+ "grad_norm": 0.506946956779649,
1142
+ "learning_rate": 2.8457950952746292e-05,
1143
+ "loss": 0.4138,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 2.5873015873015874,
1148
+ "grad_norm": 0.6232427008678014,
1149
+ "learning_rate": 2.818288529696783e-05,
1150
+ "loss": 0.3632,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 2.6031746031746033,
1155
+ "grad_norm": 0.5079770086478173,
1156
+ "learning_rate": 2.7907427408846155e-05,
1157
+ "loss": 0.4947,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 2.619047619047619,
1162
+ "grad_norm": 0.49058848467902455,
1163
+ "learning_rate": 2.7631611233523136e-05,
1164
+ "loss": 0.5522,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 2.634920634920635,
1169
+ "grad_norm": 0.5385726031164884,
1170
+ "learning_rate": 2.7355470760292956e-05,
1171
+ "loss": 0.4761,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 2.6507936507936507,
1176
+ "grad_norm": 0.6602291225270063,
1177
+ "learning_rate": 2.7079040018413587e-05,
1178
+ "loss": 0.5188,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 2.6666666666666665,
1183
+ "grad_norm": 0.5175508130590559,
1184
+ "learning_rate": 2.6802353072913305e-05,
1185
+ "loss": 0.5124,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 2.682539682539683,
1190
+ "grad_norm": 0.6455239838067437,
1191
+ "learning_rate": 2.652544402039279e-05,
1192
+ "loss": 0.4907,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 2.6984126984126986,
1197
+ "grad_norm": 0.5830651033904475,
1198
+ "learning_rate": 2.6248346984823324e-05,
1199
+ "loss": 0.4195,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 2.7142857142857144,
1204
+ "grad_norm": 0.5497318122287652,
1205
+ "learning_rate": 2.597109611334169e-05,
1206
+ "loss": 0.5326,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 2.7301587301587302,
1211
+ "grad_norm": 0.5205142114766783,
1212
+ "learning_rate": 2.569372557204213e-05,
1213
+ "loss": 0.4012,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 2.746031746031746,
1218
+ "grad_norm": 0.5128168951414211,
1219
+ "learning_rate": 2.5416269541765964e-05,
1220
+ "loss": 0.4625,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 2.761904761904762,
1225
+ "grad_norm": 0.5348874040766619,
1226
+ "learning_rate": 2.5138762213889494e-05,
1227
+ "loss": 0.5216,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 2.7777777777777777,
1232
+ "grad_norm": 0.4946974445313897,
1233
+ "learning_rate": 2.4861237786110512e-05,
1234
+ "loss": 0.4782,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 2.7936507936507935,
1239
+ "grad_norm": 0.5128385397220351,
1240
+ "learning_rate": 2.458373045823404e-05,
1241
+ "loss": 0.4704,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 2.8095238095238093,
1246
+ "grad_norm": 0.4597694930950496,
1247
+ "learning_rate": 2.4306274427957878e-05,
1248
+ "loss": 0.5063,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 2.825396825396825,
1253
+ "grad_norm": 0.5788602736229355,
1254
+ "learning_rate": 2.4028903886658312e-05,
1255
+ "loss": 0.5135,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 2.8412698412698414,
1260
+ "grad_norm": 0.513112821698425,
1261
+ "learning_rate": 2.375165301517668e-05,
1262
+ "loss": 0.4996,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 2.857142857142857,
1267
+ "grad_norm": 0.44596052374356865,
1268
+ "learning_rate": 2.3474555979607214e-05,
1269
+ "loss": 0.5051,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 2.873015873015873,
1274
+ "grad_norm": 0.49975482790762493,
1275
+ "learning_rate": 2.3197646927086697e-05,
1276
+ "loss": 0.3964,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 2.888888888888889,
1281
+ "grad_norm": 0.9671546735894949,
1282
+ "learning_rate": 2.2920959981586422e-05,
1283
+ "loss": 0.4667,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 2.9047619047619047,
1288
+ "grad_norm": 0.5958277372123243,
1289
+ "learning_rate": 2.264452923970705e-05,
1290
+ "loss": 0.5834,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 2.9206349206349205,
1295
+ "grad_norm": 0.5045651744357849,
1296
+ "learning_rate": 2.2368388766476873e-05,
1297
+ "loss": 0.4309,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 2.9365079365079367,
1302
+ "grad_norm": 0.47069616911716566,
1303
+ "learning_rate": 2.2092572591153844e-05,
1304
+ "loss": 0.4961,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 2.9523809523809526,
1309
+ "grad_norm": 0.5526655604005396,
1310
+ "learning_rate": 2.1817114703032176e-05,
1311
+ "loss": 0.5278,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 2.9682539682539684,
1316
+ "grad_norm": 0.5731260555494184,
1317
+ "learning_rate": 2.154204904725371e-05,
1318
+ "loss": 0.5567,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 2.984126984126984,
1323
+ "grad_norm": 0.5077085930555579,
1324
+ "learning_rate": 2.1267409520624844e-05,
1325
+ "loss": 0.4869,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 3.0,
1330
+ "grad_norm": 0.5249184159517826,
1331
+ "learning_rate": 2.099322996743936e-05,
1332
+ "loss": 0.3362,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 3.015873015873016,
1337
+ "grad_norm": 1.1451953853847987,
1338
+ "learning_rate": 2.0719544175307754e-05,
1339
+ "loss": 0.3188,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 3.0317460317460316,
1344
+ "grad_norm": 0.8148236258777549,
1345
+ "learning_rate": 2.0446385870993467e-05,
1346
+ "loss": 0.3492,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 3.0476190476190474,
1351
+ "grad_norm": 0.7899864704952979,
1352
+ "learning_rate": 2.0173788716256756e-05,
1353
+ "loss": 0.377,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 3.0634920634920633,
1358
+ "grad_norm": 1.293037201092889,
1359
+ "learning_rate": 1.9901786303706467e-05,
1360
+ "loss": 0.3286,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 3.0793650793650795,
1365
+ "grad_norm": 1.5199646910005133,
1366
+ "learning_rate": 1.9630412152660332e-05,
1367
+ "loss": 0.2886,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 3.0952380952380953,
1372
+ "grad_norm": 0.7493819364448684,
1373
+ "learning_rate": 1.9359699705014397e-05,
1374
+ "loss": 0.2698,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 3.111111111111111,
1379
+ "grad_norm": 0.700366824905691,
1380
+ "learning_rate": 1.9089682321121834e-05,
1381
+ "loss": 0.3111,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 3.126984126984127,
1386
+ "grad_norm": 0.8429958495049307,
1387
+ "learning_rate": 1.882039327568195e-05,
1388
+ "loss": 0.3393,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 3.142857142857143,
1393
+ "grad_norm": 0.7306551929825829,
1394
+ "learning_rate": 1.8551865753639693e-05,
1395
+ "loss": 0.316,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 3.1587301587301586,
1400
+ "grad_norm": 0.6244862767673323,
1401
+ "learning_rate": 1.8284132846096164e-05,
1402
+ "loss": 0.2946,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 3.1746031746031744,
1407
+ "grad_norm": 0.590947513131452,
1408
+ "learning_rate": 1.801722754623077e-05,
1409
+ "loss": 0.2896,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 3.1904761904761907,
1414
+ "grad_norm": 0.5741314659912675,
1415
+ "learning_rate": 1.775118274523545e-05,
1416
+ "loss": 0.3371,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 3.2063492063492065,
1421
+ "grad_norm": 0.6471899564343424,
1422
+ "learning_rate": 1.74860312282614e-05,
1423
+ "loss": 0.2351,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 3.2222222222222223,
1428
+ "grad_norm": 0.6604007565403088,
1429
+ "learning_rate": 1.72218056703789e-05,
1430
+ "loss": 0.3245,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 3.238095238095238,
1435
+ "grad_norm": 0.7669449937781672,
1436
+ "learning_rate": 1.6958538632550752e-05,
1437
+ "loss": 0.3746,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 3.253968253968254,
1442
+ "grad_norm": 0.5725384176741873,
1443
+ "learning_rate": 1.6696262557619676e-05,
1444
+ "loss": 0.2268,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 3.2698412698412698,
1449
+ "grad_norm": 0.5160814026986275,
1450
+ "learning_rate": 1.643500976631037e-05,
1451
+ "loss": 0.3461,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 3.2857142857142856,
1456
+ "grad_norm": 0.4819957072062547,
1457
+ "learning_rate": 1.6174812453246584e-05,
1458
+ "loss": 0.2906,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 3.3015873015873014,
1463
+ "grad_norm": 0.6080164945661113,
1464
+ "learning_rate": 1.5915702682983658e-05,
1465
+ "loss": 0.2132,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 3.317460317460317,
1470
+ "grad_norm": 0.6680029345374708,
1471
+ "learning_rate": 1.56577123860572e-05,
1472
+ "loss": 0.3023,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 3.3333333333333335,
1477
+ "grad_norm": 0.5355326751881537,
1478
+ "learning_rate": 1.540087335504825e-05,
1479
+ "loss": 0.2133,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 3.3492063492063493,
1484
+ "grad_norm": 0.5783500445358497,
1485
+ "learning_rate": 1.514521724066537e-05,
1486
+ "loss": 0.2582,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 3.365079365079365,
1491
+ "grad_norm": 0.5063022372874914,
1492
+ "learning_rate": 1.4890775547844322e-05,
1493
+ "loss": 0.2529,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 3.380952380952381,
1498
+ "grad_norm": 0.5796557988965374,
1499
+ "learning_rate": 1.4637579631865645e-05,
1500
+ "loss": 0.2897,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 3.3968253968253967,
1505
+ "grad_norm": 0.603714087084395,
1506
+ "learning_rate": 1.4385660694490666e-05,
1507
+ "loss": 0.2719,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 3.4126984126984126,
1512
+ "grad_norm": 0.6026614021745487,
1513
+ "learning_rate": 1.4135049780116497e-05,
1514
+ "loss": 0.3395,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 3.4285714285714284,
1519
+ "grad_norm": 0.7436598149589313,
1520
+ "learning_rate": 1.3885777771950348e-05,
1521
+ "loss": 0.337,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 3.4444444444444446,
1526
+ "grad_norm": 0.4834765774588162,
1527
+ "learning_rate": 1.3637875388203782e-05,
1528
+ "loss": 0.2668,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 3.4603174603174605,
1533
+ "grad_norm": 0.5451634141994833,
1534
+ "learning_rate": 1.3391373178307181e-05,
1535
+ "loss": 0.2384,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 3.4761904761904763,
1540
+ "grad_norm": 0.5698078470898527,
1541
+ "learning_rate": 1.3146301519145151e-05,
1542
+ "loss": 0.3243,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 3.492063492063492,
1547
+ "grad_norm": 0.5619505062332472,
1548
+ "learning_rate": 1.2902690611313135e-05,
1549
+ "loss": 0.2749,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 3.507936507936508,
1554
+ "grad_norm": 0.8210565503394927,
1555
+ "learning_rate": 1.2660570475395683e-05,
1556
+ "loss": 0.2303,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 3.5238095238095237,
1561
+ "grad_norm": 0.49079475108361625,
1562
+ "learning_rate": 1.2419970948267012e-05,
1563
+ "loss": 0.2464,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 3.5396825396825395,
1568
+ "grad_norm": 0.436922487388573,
1569
+ "learning_rate": 1.2180921679414142e-05,
1570
+ "loss": 0.25,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 3.5555555555555554,
1575
+ "grad_norm": 0.5240708542070043,
1576
+ "learning_rate": 1.1943452127283145e-05,
1577
+ "loss": 0.3265,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 3.571428571428571,
1582
+ "grad_norm": 0.5949138600847729,
1583
+ "learning_rate": 1.1707591555648905e-05,
1584
+ "loss": 0.2194,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 3.5873015873015874,
1589
+ "grad_norm": 0.5046744300340641,
1590
+ "learning_rate": 1.1473369030008974e-05,
1591
+ "loss": 0.3074,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 3.6031746031746033,
1596
+ "grad_norm": 0.5719832566771118,
1597
+ "learning_rate": 1.1240813414001649e-05,
1598
+ "loss": 0.2806,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 3.619047619047619,
1603
+ "grad_norm": 0.5543183797876515,
1604
+ "learning_rate": 1.1009953365849169e-05,
1605
+ "loss": 0.2832,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 3.634920634920635,
1610
+ "grad_norm": 0.4453621166767317,
1611
+ "learning_rate": 1.0780817334826088e-05,
1612
+ "loss": 0.289,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 3.6507936507936507,
1617
+ "grad_norm": 0.7163652417066158,
1618
+ "learning_rate": 1.055343355775339e-05,
1619
+ "loss": 0.3219,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 3.6666666666666665,
1624
+ "grad_norm": 0.5328475907166573,
1625
+ "learning_rate": 1.0327830055518842e-05,
1626
+ "loss": 0.2549,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 3.682539682539683,
1631
+ "grad_norm": 0.4796570396334715,
1632
+ "learning_rate": 1.0104034629623932e-05,
1633
+ "loss": 0.2796,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 3.6984126984126986,
1638
+ "grad_norm": 0.5103221963717066,
1639
+ "learning_rate": 9.882074858757839e-06,
1640
+ "loss": 0.2729,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 3.7142857142857144,
1645
+ "grad_norm": 0.4996694005868267,
1646
+ "learning_rate": 9.661978095398854e-06,
1647
+ "loss": 0.2868,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 3.7301587301587302,
1652
+ "grad_norm": 0.5364352563243058,
1653
+ "learning_rate": 9.443771462443743e-06,
1654
+ "loss": 0.3097,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 3.746031746031746,
1659
+ "grad_norm": 0.4755469936560106,
1660
+ "learning_rate": 9.227481849865235e-06,
1661
+ "loss": 0.2957,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 3.761904761904762,
1666
+ "grad_norm": 0.4651127214450329,
1667
+ "learning_rate": 9.013135911398435e-06,
1668
+ "loss": 0.2227,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 3.7777777777777777,
1673
+ "grad_norm": 0.5362240727276808,
1674
+ "learning_rate": 8.800760061256206e-06,
1675
+ "loss": 0.1757,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 3.7936507936507935,
1680
+ "grad_norm": 0.5787446958564049,
1681
+ "learning_rate": 8.590380470874066e-06,
1682
+ "loss": 0.2754,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 3.8095238095238093,
1687
+ "grad_norm": 0.5904647055376557,
1688
+ "learning_rate": 8.38202306568507e-06,
1689
+ "loss": 0.3051,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 3.825396825396825,
1694
+ "grad_norm": 0.5206106513004272,
1695
+ "learning_rate": 8.175713521924978e-06,
1696
+ "loss": 0.2922,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 3.8412698412698414,
1701
+ "grad_norm": 0.5012140513116363,
1702
+ "learning_rate": 7.971477263468108e-06,
1703
+ "loss": 0.2858,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 3.857142857142857,
1708
+ "grad_norm": 0.8553908081088378,
1709
+ "learning_rate": 7.76933945869432e-06,
1710
+ "loss": 0.3107,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 3.873015873015873,
1715
+ "grad_norm": 0.47754509677743895,
1716
+ "learning_rate": 7.569325017387502e-06,
1717
+ "loss": 0.2306,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 3.888888888888889,
1722
+ "grad_norm": 0.5126677036627112,
1723
+ "learning_rate": 7.371458587665822e-06,
1724
+ "loss": 0.3294,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 3.9047619047619047,
1729
+ "grad_norm": 0.4464738010436707,
1730
+ "learning_rate": 7.1757645529443665e-06,
1731
+ "loss": 0.3642,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 3.9206349206349205,
1736
+ "grad_norm": 0.4320951524772534,
1737
+ "learning_rate": 6.982267028930325e-06,
1738
+ "loss": 0.2424,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 3.9365079365079367,
1743
+ "grad_norm": 0.4366593119524442,
1744
+ "learning_rate": 6.790989860651142e-06,
1745
+ "loss": 0.277,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 3.9523809523809526,
1750
+ "grad_norm": 0.49933857198819703,
1751
+ "learning_rate": 6.601956619516036e-06,
1752
+ "loss": 0.2885,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 3.9682539682539684,
1757
+ "grad_norm": 0.5167959983988006,
1758
+ "learning_rate": 6.4151906004113385e-06,
1759
+ "loss": 0.2631,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 3.984126984126984,
1764
+ "grad_norm": 0.4656615515512403,
1765
+ "learning_rate": 6.230714818829733e-06,
1766
+ "loss": 0.2491,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 4.0,
1771
+ "grad_norm": 0.5702401686100438,
1772
+ "learning_rate": 6.048552008034072e-06,
1773
+ "loss": 0.2445,
1774
+ "step": 252
1775
+ }
1776
+ ],
1777
+ "logging_steps": 1,
1778
+ "max_steps": 315,
1779
+ "num_input_tokens_seen": 0,
1780
+ "num_train_epochs": 5,
1781
+ "save_steps": 500,
1782
+ "stateful_callbacks": {
1783
+ "TrainerControl": {
1784
+ "args": {
1785
+ "should_epoch_stop": false,
1786
+ "should_evaluate": false,
1787
+ "should_log": false,
1788
+ "should_save": true,
1789
+ "should_training_stop": false
1790
+ },
1791
+ "attributes": {}
1792
+ }
1793
+ },
1794
+ "total_flos": 62903662804992.0,
1795
+ "train_batch_size": 2,
1796
+ "trial_name": null,
1797
+ "trial_params": null
1798
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9800f202a2235e80940555255ee5d0a4a8197ca429c38110d4a4660b7d76fd
3
+ size 7672
vocab.json ADDED
The diff for this file is too large to render. See raw diff