fengyao1909 commited on
Commit
8e73469
·
verified ·
1 Parent(s): 476c9b6

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 sha256:0da42f789ee5e47b322fb32c9ea65fce1a78232f30dacb5b00e433f273567f90
3
+ size 4997184968
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfd2a2115999f3bdd38f034bb1a326f387a5f34a9bc0f796d4a7a119b62f159
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:ff433f66969e1e79d94672828179079a5c655997ddeb522ab4ab3495c19383b7
3
+ size 4997742208
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6be9d4620e74a01932f019330b286d7556781d6cebe1e550d51d4f89dd828ea4
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:af9bf0be50a502c56c4c875b0c20ab13d1d0f74b767975eddb77135155ab822c
3
+ size 4997743184
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1104a47c61239f362e3bae956a1c604c052e1dbf9981f72e08ca0f5fad5ce743
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:c397a1f06da0b07e183ffbe9c42e9b2f22859c6aad9c9eb8f7ff812446a0aa9e
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:f095bb3e542cc1f230a1c0bd79ccbe8866ec0d4ad5a926da1fc0a975ae574e75
3
+ size 4997743184
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a650ff739fe722b1184e3f090f6c1ba4514cc117b0a547898dbb0a5252494df
3
+ size 4997743184
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a0dcb83d31eff5d2667d7ad16faa6ecb3a43502e7cdb4ce68ad7edfc0d1903
3
+ size 4997743184
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210ed60b053e75af42e35404e5a6362e80128afc7039d9b94ae4774a9a6df948
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:c388a416c55ba25b2a65965ef7055339a571beb909bff32cad426456711cd02d
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:b6a17d3a92c0cc9d84a4b0f194517075d3da5d850fd5405013cd6760f64f0998
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": 2.3559653063882835,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.0469,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.031746031746031744,
21
+ "grad_norm": 2.29659253609106,
22
+ "learning_rate": 3.125e-07,
23
+ "loss": 0.9929,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.047619047619047616,
28
+ "grad_norm": 2.8899785663629123,
29
+ "learning_rate": 6.25e-07,
30
+ "loss": 1.0189,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.06349206349206349,
35
+ "grad_norm": 2.2527917765154153,
36
+ "learning_rate": 9.375000000000001e-07,
37
+ "loss": 0.9098,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.07936507936507936,
42
+ "grad_norm": 2.2029116064708907,
43
+ "learning_rate": 1.25e-06,
44
+ "loss": 1.0462,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.09523809523809523,
49
+ "grad_norm": 2.122312207060731,
50
+ "learning_rate": 1.5625e-06,
51
+ "loss": 0.9986,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.1111111111111111,
56
+ "grad_norm": 2.045608321522422,
57
+ "learning_rate": 1.8750000000000003e-06,
58
+ "loss": 0.9554,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.12698412698412698,
63
+ "grad_norm": 1.8619152723479657,
64
+ "learning_rate": 2.1875000000000002e-06,
65
+ "loss": 0.9522,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.14285714285714285,
70
+ "grad_norm": 1.8663709940802706,
71
+ "learning_rate": 2.5e-06,
72
+ "loss": 0.9994,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.15873015873015872,
77
+ "grad_norm": 1.756651050051264,
78
+ "learning_rate": 2.8125e-06,
79
+ "loss": 0.9373,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.1746031746031746,
84
+ "grad_norm": 1.6604489437599113,
85
+ "learning_rate": 3.125e-06,
86
+ "loss": 0.8839,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.19047619047619047,
91
+ "grad_norm": 1.292095856227553,
92
+ "learning_rate": 3.4375e-06,
93
+ "loss": 0.9907,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.20634920634920634,
98
+ "grad_norm": 1.2693344466908103,
99
+ "learning_rate": 3.7500000000000005e-06,
100
+ "loss": 0.9322,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.2222222222222222,
105
+ "grad_norm": 1.6344663181288221,
106
+ "learning_rate": 4.0625000000000005e-06,
107
+ "loss": 1.0934,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.23809523809523808,
112
+ "grad_norm": 1.1511973531225708,
113
+ "learning_rate": 4.3750000000000005e-06,
114
+ "loss": 0.9771,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.25396825396825395,
119
+ "grad_norm": 1.1464903643465947,
120
+ "learning_rate": 4.6875000000000004e-06,
121
+ "loss": 1.0442,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.2698412698412698,
126
+ "grad_norm": 1.1549964376534243,
127
+ "learning_rate": 5e-06,
128
+ "loss": 0.949,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.2857142857142857,
133
+ "grad_norm": 1.2909225755543452,
134
+ "learning_rate": 5.3125e-06,
135
+ "loss": 1.0098,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.30158730158730157,
140
+ "grad_norm": 1.0413894105842352,
141
+ "learning_rate": 5.625e-06,
142
+ "loss": 0.7468,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.31746031746031744,
147
+ "grad_norm": 1.2863204827157997,
148
+ "learning_rate": 5.9375e-06,
149
+ "loss": 0.9232,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.3333333333333333,
154
+ "grad_norm": 0.901486908411037,
155
+ "learning_rate": 6.25e-06,
156
+ "loss": 0.9885,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.3492063492063492,
161
+ "grad_norm": 1.0229681930848715,
162
+ "learning_rate": 6.5625e-06,
163
+ "loss": 1.0508,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.36507936507936506,
168
+ "grad_norm": 1.0772270927236638,
169
+ "learning_rate": 6.875e-06,
170
+ "loss": 0.8728,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.38095238095238093,
175
+ "grad_norm": 0.9393952588410857,
176
+ "learning_rate": 7.1875e-06,
177
+ "loss": 0.8349,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.3968253968253968,
182
+ "grad_norm": 1.0822345499912303,
183
+ "learning_rate": 7.500000000000001e-06,
184
+ "loss": 1.0283,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.4126984126984127,
189
+ "grad_norm": 0.8124841375138875,
190
+ "learning_rate": 7.8125e-06,
191
+ "loss": 0.8612,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.42857142857142855,
196
+ "grad_norm": 0.7868328056966778,
197
+ "learning_rate": 8.125000000000001e-06,
198
+ "loss": 0.7232,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.4444444444444444,
203
+ "grad_norm": 0.8283002452965974,
204
+ "learning_rate": 8.4375e-06,
205
+ "loss": 0.9752,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.4603174603174603,
210
+ "grad_norm": 0.8117454313345658,
211
+ "learning_rate": 8.750000000000001e-06,
212
+ "loss": 0.9053,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.47619047619047616,
217
+ "grad_norm": 0.8594519052279771,
218
+ "learning_rate": 9.0625e-06,
219
+ "loss": 0.9479,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.49206349206349204,
224
+ "grad_norm": 0.9958158956912483,
225
+ "learning_rate": 9.375000000000001e-06,
226
+ "loss": 0.9188,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.5079365079365079,
231
+ "grad_norm": 0.8918575253813723,
232
+ "learning_rate": 9.6875e-06,
233
+ "loss": 0.8847,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.5238095238095238,
238
+ "grad_norm": 0.8125329449215294,
239
+ "learning_rate": 1e-05,
240
+ "loss": 1.0379,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.5396825396825397,
245
+ "grad_norm": 0.7108806956906407,
246
+ "learning_rate": 9.999691920767945e-06,
247
+ "loss": 0.8376,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.5555555555555556,
252
+ "grad_norm": 0.641926463787557,
253
+ "learning_rate": 9.998767721036901e-06,
254
+ "loss": 0.8241,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.5714285714285714,
259
+ "grad_norm": 0.7048636529194373,
260
+ "learning_rate": 9.997227514697568e-06,
261
+ "loss": 0.9693,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.5873015873015873,
266
+ "grad_norm": 0.6041864409794199,
267
+ "learning_rate": 9.99507149155218e-06,
268
+ "loss": 0.9839,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.6031746031746031,
273
+ "grad_norm": 0.6529381186048961,
274
+ "learning_rate": 9.992299917291118e-06,
275
+ "loss": 0.8479,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.6190476190476191,
280
+ "grad_norm": 0.7457758141141355,
281
+ "learning_rate": 9.98891313346017e-06,
282
+ "loss": 0.9095,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.6349206349206349,
287
+ "grad_norm": 0.6700791615416641,
288
+ "learning_rate": 9.984911557418444e-06,
289
+ "loss": 0.7685,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.6507936507936508,
294
+ "grad_norm": 0.6202447937301818,
295
+ "learning_rate": 9.980295682286924e-06,
296
+ "loss": 0.8387,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.6666666666666666,
301
+ "grad_norm": 0.6888680420644837,
302
+ "learning_rate": 9.97506607688772e-06,
303
+ "loss": 0.9107,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.6825396825396826,
308
+ "grad_norm": 0.5229452850388104,
309
+ "learning_rate": 9.969223385673958e-06,
310
+ "loss": 0.8308,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.6984126984126984,
315
+ "grad_norm": 0.5679326043532053,
316
+ "learning_rate": 9.962768328650367e-06,
317
+ "loss": 0.7516,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.7142857142857143,
322
+ "grad_norm": 0.5234412349262514,
323
+ "learning_rate": 9.95570170128455e-06,
324
+ "loss": 0.8443,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.7301587301587301,
329
+ "grad_norm": 0.5148736685750067,
330
+ "learning_rate": 9.94802437440896e-06,
331
+ "loss": 0.7959,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.746031746031746,
336
+ "grad_norm": 0.6223703419413371,
337
+ "learning_rate": 9.939737294113585e-06,
338
+ "loss": 0.8964,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.7619047619047619,
343
+ "grad_norm": 0.4712938980573866,
344
+ "learning_rate": 9.930841481629358e-06,
345
+ "loss": 0.8884,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.7777777777777778,
350
+ "grad_norm": 0.6385581101993485,
351
+ "learning_rate": 9.92133803320231e-06,
352
+ "loss": 0.7817,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.7936507936507936,
357
+ "grad_norm": 0.47528095545287,
358
+ "learning_rate": 9.91122811995848e-06,
359
+ "loss": 0.819,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.8095238095238095,
364
+ "grad_norm": 0.5522186664203698,
365
+ "learning_rate": 9.90051298775959e-06,
366
+ "loss": 0.8691,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.8253968253968254,
371
+ "grad_norm": 0.3924890188917555,
372
+ "learning_rate": 9.88919395704952e-06,
373
+ "loss": 0.8259,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.8412698412698413,
378
+ "grad_norm": 0.5584015479821739,
379
+ "learning_rate": 9.877272422691583e-06,
380
+ "loss": 0.9318,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.8571428571428571,
385
+ "grad_norm": 0.5472693893320031,
386
+ "learning_rate": 9.864749853796642e-06,
387
+ "loss": 0.7983,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.873015873015873,
392
+ "grad_norm": 0.5011856989250408,
393
+ "learning_rate": 9.85162779354206e-06,
394
+ "loss": 0.7289,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.8888888888888888,
399
+ "grad_norm": 0.48176520075987733,
400
+ "learning_rate": 9.837907858981536e-06,
401
+ "loss": 0.8795,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.9047619047619048,
406
+ "grad_norm": 0.4693619944653085,
407
+ "learning_rate": 9.823591740845831e-06,
408
+ "loss": 0.8625,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.9206349206349206,
413
+ "grad_norm": 0.5158078748351012,
414
+ "learning_rate": 9.808681203334416e-06,
415
+ "loss": 0.7975,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.9365079365079365,
420
+ "grad_norm": 0.467299048377056,
421
+ "learning_rate": 9.793178083898073e-06,
422
+ "loss": 0.878,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.9523809523809523,
427
+ "grad_norm": 0.4360100853426926,
428
+ "learning_rate": 9.777084293012448e-06,
429
+ "loss": 0.842,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.9682539682539683,
434
+ "grad_norm": 0.4999196363033725,
435
+ "learning_rate": 9.760401813942641e-06,
436
+ "loss": 0.7661,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.9841269841269841,
441
+ "grad_norm": 0.49451715958225617,
442
+ "learning_rate": 9.743132702498785e-06,
443
+ "loss": 0.8685,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 1.0,
448
+ "grad_norm": 0.51449429417728,
449
+ "learning_rate": 9.725279086782719e-06,
450
+ "loss": 0.7676,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 1.0158730158730158,
455
+ "grad_norm": 0.5392465569053122,
456
+ "learning_rate": 9.706843166925733e-06,
457
+ "loss": 0.7978,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 1.0317460317460316,
462
+ "grad_norm": 0.49426185655546884,
463
+ "learning_rate": 9.687827214817433e-06,
464
+ "loss": 0.8264,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 1.0476190476190477,
469
+ "grad_norm": 0.5050909892528982,
470
+ "learning_rate": 9.668233573825794e-06,
471
+ "loss": 0.8898,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 1.0634920634920635,
476
+ "grad_norm": 0.45134127922296613,
477
+ "learning_rate": 9.64806465850836e-06,
478
+ "loss": 0.7317,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 1.0793650793650793,
483
+ "grad_norm": 0.5413266326970981,
484
+ "learning_rate": 9.62732295431471e-06,
485
+ "loss": 0.7307,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 1.0952380952380953,
490
+ "grad_norm": 0.4781316290575908,
491
+ "learning_rate": 9.606011017280166e-06,
492
+ "loss": 0.8977,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 1.1111111111111112,
497
+ "grad_norm": 0.5064140744904799,
498
+ "learning_rate": 9.5841314737108e-06,
499
+ "loss": 0.7648,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 1.126984126984127,
504
+ "grad_norm": 0.5543523877170532,
505
+ "learning_rate": 9.56168701985981e-06,
506
+ "loss": 0.7995,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 1.1428571428571428,
511
+ "grad_norm": 0.4891764300467825,
512
+ "learning_rate": 9.538680421595236e-06,
513
+ "loss": 0.8072,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 1.1587301587301586,
518
+ "grad_norm": 0.48203192054287314,
519
+ "learning_rate": 9.515114514059127e-06,
520
+ "loss": 0.8128,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 1.1746031746031746,
525
+ "grad_norm": 0.499915788005329,
526
+ "learning_rate": 9.490992201318165e-06,
527
+ "loss": 0.7876,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 1.1904761904761905,
532
+ "grad_norm": 0.43129451868532453,
533
+ "learning_rate": 9.466316456005783e-06,
534
+ "loss": 0.7755,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 1.2063492063492063,
539
+ "grad_norm": 0.49436944947590167,
540
+ "learning_rate": 9.441090318955843e-06,
541
+ "loss": 0.7015,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 1.2222222222222223,
546
+ "grad_norm": 0.5018080177691097,
547
+ "learning_rate": 9.415316898827923e-06,
548
+ "loss": 0.7346,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 1.2380952380952381,
553
+ "grad_norm": 0.42117192002428844,
554
+ "learning_rate": 9.388999371724212e-06,
555
+ "loss": 0.8242,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 1.253968253968254,
560
+ "grad_norm": 0.47397540901194374,
561
+ "learning_rate": 9.362140980798127e-06,
562
+ "loss": 0.8928,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 1.2698412698412698,
567
+ "grad_norm": 0.48823131897505534,
568
+ "learning_rate": 9.334745035854646e-06,
569
+ "loss": 0.7581,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 1.2857142857142856,
574
+ "grad_norm": 0.5170460810325518,
575
+ "learning_rate": 9.306814912942445e-06,
576
+ "loss": 0.8361,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 1.3015873015873016,
581
+ "grad_norm": 0.41118521047488926,
582
+ "learning_rate": 9.278354053937848e-06,
583
+ "loss": 0.7794,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 1.3174603174603174,
588
+ "grad_norm": 0.4827654705693697,
589
+ "learning_rate": 9.249365966120692e-06,
590
+ "loss": 0.8542,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 1.3333333333333333,
595
+ "grad_norm": 0.45176873751511454,
596
+ "learning_rate": 9.219854221742106e-06,
597
+ "loss": 0.8101,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 1.3492063492063493,
602
+ "grad_norm": 0.44526540495239475,
603
+ "learning_rate": 9.189822457584311e-06,
604
+ "loss": 0.7419,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 1.3650793650793651,
609
+ "grad_norm": 0.41133066066087726,
610
+ "learning_rate": 9.159274374512444e-06,
611
+ "loss": 0.6576,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 1.380952380952381,
616
+ "grad_norm": 0.4500027229237173,
617
+ "learning_rate": 9.128213737018493e-06,
618
+ "loss": 0.8058,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 1.3968253968253967,
623
+ "grad_norm": 0.40834920107678924,
624
+ "learning_rate": 9.096644372757393e-06,
625
+ "loss": 0.8849,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 1.4126984126984126,
630
+ "grad_norm": 0.5843795042717066,
631
+ "learning_rate": 9.064570172075349e-06,
632
+ "loss": 0.7969,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 1.4285714285714286,
637
+ "grad_norm": 0.5139681695756663,
638
+ "learning_rate": 9.031995087530403e-06,
639
+ "loss": 0.7983,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 1.4444444444444444,
644
+ "grad_norm": 0.47799160571848326,
645
+ "learning_rate": 8.99892313340537e-06,
646
+ "loss": 0.6612,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 1.4603174603174602,
651
+ "grad_norm": 0.48090290795792257,
652
+ "learning_rate": 8.96535838521314e-06,
653
+ "loss": 0.8026,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 1.4761904761904763,
658
+ "grad_norm": 0.48955363216016506,
659
+ "learning_rate": 8.931304979194452e-06,
660
+ "loss": 0.8051,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 1.492063492063492,
665
+ "grad_norm": 0.47949685756309185,
666
+ "learning_rate": 8.896767111808177e-06,
667
+ "loss": 0.7354,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 1.507936507936508,
672
+ "grad_norm": 0.5732670061875946,
673
+ "learning_rate": 8.861749039214177e-06,
674
+ "loss": 0.9129,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 1.5238095238095237,
679
+ "grad_norm": 0.48050508555262206,
680
+ "learning_rate": 8.826255076748823e-06,
681
+ "loss": 0.8445,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 1.5396825396825395,
686
+ "grad_norm": 0.4329532952395629,
687
+ "learning_rate": 8.790289598393186e-06,
688
+ "loss": 0.7212,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 1.5555555555555556,
693
+ "grad_norm": 0.522751486773223,
694
+ "learning_rate": 8.753857036234055e-06,
695
+ "loss": 0.8149,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 1.5714285714285714,
700
+ "grad_norm": 0.4570961856172299,
701
+ "learning_rate": 8.716961879917734e-06,
702
+ "loss": 0.7365,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 1.5873015873015874,
707
+ "grad_norm": 0.4363179134183329,
708
+ "learning_rate": 8.679608676096793e-06,
709
+ "loss": 0.8131,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 1.6031746031746033,
714
+ "grad_norm": 0.4655541415571893,
715
+ "learning_rate": 8.641802027869774e-06,
716
+ "loss": 0.7946,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 1.619047619047619,
721
+ "grad_norm": 0.5743139418639736,
722
+ "learning_rate": 8.603546594213935e-06,
723
+ "loss": 0.8574,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 1.6349206349206349,
728
+ "grad_norm": 0.5267570867681096,
729
+ "learning_rate": 8.564847089411128e-06,
730
+ "loss": 0.8286,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 1.6507936507936507,
735
+ "grad_norm": 0.40799736834923667,
736
+ "learning_rate": 8.525708282466839e-06,
737
+ "loss": 0.8412,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 1.6666666666666665,
742
+ "grad_norm": 0.4236881481332967,
743
+ "learning_rate": 8.486134996522502e-06,
744
+ "loss": 0.8172,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 1.6825396825396826,
749
+ "grad_norm": 0.5593679767726464,
750
+ "learning_rate": 8.446132108261136e-06,
751
+ "loss": 0.8058,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 1.6984126984126984,
756
+ "grad_norm": 0.5031166228419733,
757
+ "learning_rate": 8.405704547306379e-06,
758
+ "loss": 0.8031,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 1.7142857142857144,
763
+ "grad_norm": 0.45322610730579044,
764
+ "learning_rate": 8.364857295615006e-06,
765
+ "loss": 0.8903,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 1.7301587301587302,
770
+ "grad_norm": 0.5335556769284883,
771
+ "learning_rate": 8.323595386862985e-06,
772
+ "loss": 0.7925,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 1.746031746031746,
777
+ "grad_norm": 0.4699718024263939,
778
+ "learning_rate": 8.281923905825188e-06,
779
+ "loss": 0.7664,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 1.7619047619047619,
784
+ "grad_norm": 0.47207237316096745,
785
+ "learning_rate": 8.23984798774876e-06,
786
+ "loss": 0.7347,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 1.7777777777777777,
791
+ "grad_norm": 0.4532509556288616,
792
+ "learning_rate": 8.197372817720314e-06,
793
+ "loss": 0.7369,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 1.7936507936507935,
798
+ "grad_norm": 0.5443221798521994,
799
+ "learning_rate": 8.154503630026955e-06,
800
+ "loss": 0.7261,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 1.8095238095238095,
805
+ "grad_norm": 0.4456098920838456,
806
+ "learning_rate": 8.111245707511253e-06,
807
+ "loss": 0.7194,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 1.8253968253968254,
812
+ "grad_norm": 0.4159654938486175,
813
+ "learning_rate": 8.067604380920228e-06,
814
+ "loss": 0.7945,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 1.8412698412698414,
819
+ "grad_norm": 0.4706342532274064,
820
+ "learning_rate": 8.023585028248435e-06,
821
+ "loss": 0.8487,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 1.8571428571428572,
826
+ "grad_norm": 0.5701232470412769,
827
+ "learning_rate": 7.979193074075216e-06,
828
+ "loss": 0.8887,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 1.873015873015873,
833
+ "grad_norm": 0.530430629054239,
834
+ "learning_rate": 7.934433988896233e-06,
835
+ "loss": 0.6534,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 1.8888888888888888,
840
+ "grad_norm": 0.48414840419963984,
841
+ "learning_rate": 7.889313288449323e-06,
842
+ "loss": 0.8214,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 1.9047619047619047,
847
+ "grad_norm": 0.4200926363513126,
848
+ "learning_rate": 7.843836533034784e-06,
849
+ "loss": 0.7614,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 1.9206349206349205,
854
+ "grad_norm": 0.4941849127950555,
855
+ "learning_rate": 7.798009326830167e-06,
856
+ "loss": 0.7996,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 1.9365079365079365,
861
+ "grad_norm": 0.41647477043231534,
862
+ "learning_rate": 7.751837317199673e-06,
863
+ "loss": 0.867,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 1.9523809523809523,
868
+ "grad_norm": 0.4462896414872465,
869
+ "learning_rate": 7.705326193998207e-06,
870
+ "loss": 0.7547,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 1.9682539682539684,
875
+ "grad_norm": 0.46366747032871125,
876
+ "learning_rate": 7.658481688870218e-06,
877
+ "loss": 0.7582,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 1.9841269841269842,
882
+ "grad_norm": 0.4714130206121814,
883
+ "learning_rate": 7.611309574543373e-06,
884
+ "loss": 0.7606,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 2.0,
889
+ "grad_norm": 0.46690869317456135,
890
+ "learning_rate": 7.563815664117173e-06,
891
+ "loss": 0.9121,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 2.015873015873016,
896
+ "grad_norm": 0.8060769356732992,
897
+ "learning_rate": 7.5160058103465985e-06,
898
+ "loss": 0.7122,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 2.0317460317460316,
903
+ "grad_norm": 0.5953210710991091,
904
+ "learning_rate": 7.467885904920864e-06,
905
+ "loss": 0.7567,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 2.0476190476190474,
910
+ "grad_norm": 0.7560871980312371,
911
+ "learning_rate": 7.419461877737373e-06,
912
+ "loss": 0.8318,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 2.0634920634920633,
917
+ "grad_norm": 2.1011598702400667,
918
+ "learning_rate": 7.370739696170971e-06,
919
+ "loss": 0.7428,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 2.0793650793650795,
924
+ "grad_norm": 0.940827314326734,
925
+ "learning_rate": 7.321725364338566e-06,
926
+ "loss": 0.6161,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 2.0952380952380953,
931
+ "grad_norm": 0.5381465457966281,
932
+ "learning_rate": 7.272424922359246e-06,
933
+ "loss": 0.6432,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 2.111111111111111,
938
+ "grad_norm": 0.7212158226191104,
939
+ "learning_rate": 7.222844445609931e-06,
940
+ "loss": 0.7817,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 2.126984126984127,
945
+ "grad_norm": 0.6031927565028607,
946
+ "learning_rate": 7.172990043976703e-06,
947
+ "loss": 0.7291,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 2.142857142857143,
952
+ "grad_norm": 0.5554913039306149,
953
+ "learning_rate": 7.122867861101868e-06,
954
+ "loss": 0.7928,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 2.1587301587301586,
959
+ "grad_norm": 0.4440614086169425,
960
+ "learning_rate": 7.072484073626872e-06,
961
+ "loss": 0.6864,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 2.1746031746031744,
966
+ "grad_norm": 2.875286251781212,
967
+ "learning_rate": 7.021844890431136e-06,
968
+ "loss": 0.7627,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 2.1904761904761907,
973
+ "grad_norm": 0.7248206082063566,
974
+ "learning_rate": 6.970956551866925e-06,
975
+ "loss": 0.728,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 2.2063492063492065,
980
+ "grad_norm": 0.5344769870855947,
981
+ "learning_rate": 6.9198253289903515e-06,
982
+ "loss": 0.6621,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 2.2222222222222223,
987
+ "grad_norm": 0.5334409779130068,
988
+ "learning_rate": 6.868457522788561e-06,
989
+ "loss": 0.7351,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 2.238095238095238,
994
+ "grad_norm": 0.4791675678917909,
995
+ "learning_rate": 6.816859463403271e-06,
996
+ "loss": 0.6568,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 2.253968253968254,
1001
+ "grad_norm": 0.5667962259074942,
1002
+ "learning_rate": 6.765037509350685e-06,
1003
+ "loss": 0.758,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 2.2698412698412698,
1008
+ "grad_norm": 0.523154654898243,
1009
+ "learning_rate": 6.7129980467379265e-06,
1010
+ "loss": 0.6657,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 2.2857142857142856,
1015
+ "grad_norm": 0.45239550513741295,
1016
+ "learning_rate": 6.660747488476066e-06,
1017
+ "loss": 0.6615,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 2.3015873015873014,
1022
+ "grad_norm": 0.6580127713752147,
1023
+ "learning_rate": 6.608292273489851e-06,
1024
+ "loss": 0.6112,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 2.317460317460317,
1029
+ "grad_norm": 0.6033248382665617,
1030
+ "learning_rate": 6.555638865924221e-06,
1031
+ "loss": 0.7033,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 2.3333333333333335,
1036
+ "grad_norm": 0.5578461067365529,
1037
+ "learning_rate": 6.502793754347721e-06,
1038
+ "loss": 0.7578,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 2.3492063492063493,
1043
+ "grad_norm": 0.5451762654132818,
1044
+ "learning_rate": 6.449763450952912e-06,
1045
+ "loss": 0.6863,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 2.365079365079365,
1050
+ "grad_norm": 0.4667833185680937,
1051
+ "learning_rate": 6.396554490753848e-06,
1052
+ "loss": 0.6825,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 2.380952380952381,
1057
+ "grad_norm": 0.4209933154088852,
1058
+ "learning_rate": 6.343173430780769e-06,
1059
+ "loss": 0.836,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 2.3968253968253967,
1064
+ "grad_norm": 0.46876037251704294,
1065
+ "learning_rate": 6.289626849272062e-06,
1066
+ "loss": 0.7981,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 2.4126984126984126,
1071
+ "grad_norm": 0.47367833829704725,
1072
+ "learning_rate": 6.2359213448636104e-06,
1073
+ "loss": 0.751,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 2.4285714285714284,
1078
+ "grad_norm": 0.43459439089398605,
1079
+ "learning_rate": 6.182063535775634e-06,
1080
+ "loss": 0.7654,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 2.4444444444444446,
1085
+ "grad_norm": 0.39767398947957067,
1086
+ "learning_rate": 6.1280600589971225e-06,
1087
+ "loss": 0.7896,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 2.4603174603174605,
1092
+ "grad_norm": 0.4231324131775063,
1093
+ "learning_rate": 6.073917569467934e-06,
1094
+ "loss": 0.8051,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 2.4761904761904763,
1099
+ "grad_norm": 0.3983830637612639,
1100
+ "learning_rate": 6.0196427392587085e-06,
1101
+ "loss": 0.7038,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 2.492063492063492,
1106
+ "grad_norm": 0.4585701856768339,
1107
+ "learning_rate": 5.96524225674865e-06,
1108
+ "loss": 0.7422,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 2.507936507936508,
1113
+ "grad_norm": 0.4299692751487169,
1114
+ "learning_rate": 5.9107228258013085e-06,
1115
+ "loss": 0.7053,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 2.5238095238095237,
1120
+ "grad_norm": 0.42827944956580943,
1121
+ "learning_rate": 5.856091164938451e-06,
1122
+ "loss": 0.6523,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 2.5396825396825395,
1127
+ "grad_norm": 0.4098750307712162,
1128
+ "learning_rate": 5.801354006512127e-06,
1129
+ "loss": 0.6895,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 2.5555555555555554,
1134
+ "grad_norm": 0.45624383692077836,
1135
+ "learning_rate": 5.746518095875033e-06,
1136
+ "loss": 0.6973,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 2.571428571428571,
1141
+ "grad_norm": 0.40961695420487504,
1142
+ "learning_rate": 5.6915901905492586e-06,
1143
+ "loss": 0.6285,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 2.5873015873015874,
1148
+ "grad_norm": 0.5946218628280344,
1149
+ "learning_rate": 5.6365770593935665e-06,
1150
+ "loss": 0.5907,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 2.6031746031746033,
1155
+ "grad_norm": 0.5401440035651196,
1156
+ "learning_rate": 5.581485481769231e-06,
1157
+ "loss": 0.7181,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 2.619047619047619,
1162
+ "grad_norm": 0.4378876946579892,
1163
+ "learning_rate": 5.526322246704628e-06,
1164
+ "loss": 0.7978,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 2.634920634920635,
1169
+ "grad_norm": 0.40853074862176036,
1170
+ "learning_rate": 5.471094152058592e-06,
1171
+ "loss": 0.681,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 2.6507936507936507,
1176
+ "grad_norm": 0.46389651051528763,
1177
+ "learning_rate": 5.415808003682717e-06,
1178
+ "loss": 0.7308,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 2.6666666666666665,
1183
+ "grad_norm": 0.42992484133372394,
1184
+ "learning_rate": 5.360470614582661e-06,
1185
+ "loss": 0.7136,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 2.682539682539683,
1190
+ "grad_norm": 0.557870344379466,
1191
+ "learning_rate": 5.305088804078559e-06,
1192
+ "loss": 0.7333,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 2.6984126984126986,
1197
+ "grad_norm": 0.45453618737081114,
1198
+ "learning_rate": 5.249669396964665e-06,
1199
+ "loss": 0.6349,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 2.7142857142857144,
1204
+ "grad_norm": 0.4511080452383348,
1205
+ "learning_rate": 5.1942192226683385e-06,
1206
+ "loss": 0.776,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 2.7301587301587302,
1211
+ "grad_norm": 0.4900595891663431,
1212
+ "learning_rate": 5.138745114408427e-06,
1213
+ "loss": 0.5998,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 2.746031746031746,
1218
+ "grad_norm": 0.46419645481002475,
1219
+ "learning_rate": 5.083253908353193e-06,
1220
+ "loss": 0.6676,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 2.761904761904762,
1225
+ "grad_norm": 0.4905121964865482,
1226
+ "learning_rate": 5.0277524427778986e-06,
1227
+ "loss": 0.7831,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 2.7777777777777777,
1232
+ "grad_norm": 0.4525848803424086,
1233
+ "learning_rate": 4.972247557222102e-06,
1234
+ "loss": 0.7164,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 2.7936507936507935,
1239
+ "grad_norm": 0.5368330661361714,
1240
+ "learning_rate": 4.916746091646808e-06,
1241
+ "loss": 0.6805,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 2.8095238095238093,
1246
+ "grad_norm": 0.4224136348005534,
1247
+ "learning_rate": 4.8612548855915755e-06,
1248
+ "loss": 0.724,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 2.825396825396825,
1253
+ "grad_norm": 0.4869146817578471,
1254
+ "learning_rate": 4.805780777331662e-06,
1255
+ "loss": 0.7446,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 2.8412698412698414,
1260
+ "grad_norm": 0.4511553539717499,
1261
+ "learning_rate": 4.750330603035336e-06,
1262
+ "loss": 0.7124,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 2.857142857142857,
1267
+ "grad_norm": 0.45286461188582156,
1268
+ "learning_rate": 4.694911195921443e-06,
1269
+ "loss": 0.7252,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 2.873015873015873,
1274
+ "grad_norm": 0.4293856541441545,
1275
+ "learning_rate": 4.6395293854173395e-06,
1276
+ "loss": 0.6053,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 2.888888888888889,
1281
+ "grad_norm": 0.5836445711298119,
1282
+ "learning_rate": 4.584191996317285e-06,
1283
+ "loss": 0.6828,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 2.9047619047619047,
1288
+ "grad_norm": 0.4710990644177235,
1289
+ "learning_rate": 4.528905847941411e-06,
1290
+ "loss": 0.8414,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 2.9206349206349205,
1295
+ "grad_norm": 0.4770727006845428,
1296
+ "learning_rate": 4.473677753295375e-06,
1297
+ "loss": 0.6592,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 2.9365079365079367,
1302
+ "grad_norm": 0.4087196329651188,
1303
+ "learning_rate": 4.418514518230769e-06,
1304
+ "loss": 0.7122,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 2.9523809523809526,
1309
+ "grad_norm": 0.48530953017287554,
1310
+ "learning_rate": 4.363422940606435e-06,
1311
+ "loss": 0.7454,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 2.9682539682539684,
1316
+ "grad_norm": 0.4900655757859956,
1317
+ "learning_rate": 4.308409809450742e-06,
1318
+ "loss": 0.7621,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 2.984126984126984,
1323
+ "grad_norm": 0.49992358594135816,
1324
+ "learning_rate": 4.253481904124968e-06,
1325
+ "loss": 0.7331,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 3.0,
1330
+ "grad_norm": 0.4385555753140365,
1331
+ "learning_rate": 4.198645993487872e-06,
1332
+ "loss": 0.604,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 3.015873015873016,
1337
+ "grad_norm": 0.8387072939566776,
1338
+ "learning_rate": 4.143908835061551e-06,
1339
+ "loss": 0.6844,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 3.0317460317460316,
1344
+ "grad_norm": 0.5067553850596358,
1345
+ "learning_rate": 4.089277174198694e-06,
1346
+ "loss": 0.7,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 3.0476190476190474,
1351
+ "grad_norm": 0.8011190701762613,
1352
+ "learning_rate": 4.0347577432513515e-06,
1353
+ "loss": 0.743,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 3.0634920634920633,
1358
+ "grad_norm": 0.5036174850503073,
1359
+ "learning_rate": 3.980357260741293e-06,
1360
+ "loss": 0.6811,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 3.0793650793650795,
1365
+ "grad_norm": 0.5463958175244662,
1366
+ "learning_rate": 3.926082430532067e-06,
1367
+ "loss": 0.6461,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 3.0952380952380953,
1372
+ "grad_norm": 0.6797072746043096,
1373
+ "learning_rate": 3.87193994100288e-06,
1374
+ "loss": 0.6076,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 3.111111111111111,
1379
+ "grad_norm": 0.6595821505262829,
1380
+ "learning_rate": 3.817936464224367e-06,
1381
+ "loss": 0.6729,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 3.126984126984127,
1386
+ "grad_norm": 0.6303031378119635,
1387
+ "learning_rate": 3.764078655136391e-06,
1388
+ "loss": 0.7462,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 3.142857142857143,
1393
+ "grad_norm": 0.5867535234820467,
1394
+ "learning_rate": 3.7103731507279383e-06,
1395
+ "loss": 0.6994,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 3.1587301587301586,
1400
+ "grad_norm": 0.744206344239702,
1401
+ "learning_rate": 3.656826569219233e-06,
1402
+ "loss": 0.6698,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 3.1746031746031744,
1407
+ "grad_norm": 0.48008260540189834,
1408
+ "learning_rate": 3.603445509246154e-06,
1409
+ "loss": 0.641,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 3.1904761904761907,
1414
+ "grad_norm": 0.4479357669097382,
1415
+ "learning_rate": 3.55023654904709e-06,
1416
+ "loss": 0.7151,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 3.2063492063492065,
1421
+ "grad_norm": 0.4992070753022617,
1422
+ "learning_rate": 3.49720624565228e-06,
1423
+ "loss": 0.5512,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 3.2222222222222223,
1428
+ "grad_norm": 0.48763610007436026,
1429
+ "learning_rate": 3.44436113407578e-06,
1430
+ "loss": 0.6851,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 3.238095238095238,
1435
+ "grad_norm": 0.5828989750562972,
1436
+ "learning_rate": 3.3917077265101505e-06,
1437
+ "loss": 0.7484,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 3.253968253968254,
1442
+ "grad_norm": 0.5181196242222144,
1443
+ "learning_rate": 3.3392525115239353e-06,
1444
+ "loss": 0.5734,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 3.2698412698412698,
1449
+ "grad_norm": 0.47471736105285633,
1450
+ "learning_rate": 3.2870019532620744e-06,
1451
+ "loss": 0.7111,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 3.2857142857142856,
1456
+ "grad_norm": 0.44233225614290655,
1457
+ "learning_rate": 3.2349624906493164e-06,
1458
+ "loss": 0.6547,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 3.3015873015873014,
1463
+ "grad_norm": 0.549412981718262,
1464
+ "learning_rate": 3.1831405365967315e-06,
1465
+ "loss": 0.5268,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 3.317460317460317,
1470
+ "grad_norm": 0.4610400286542981,
1471
+ "learning_rate": 3.1315424772114404e-06,
1472
+ "loss": 0.7138,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 3.3333333333333335,
1477
+ "grad_norm": 0.5912978101838896,
1478
+ "learning_rate": 3.0801746710096497e-06,
1479
+ "loss": 0.5523,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 3.3492063492063493,
1484
+ "grad_norm": 0.5365898687480075,
1485
+ "learning_rate": 3.0290434481330746e-06,
1486
+ "loss": 0.586,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 3.365079365079365,
1491
+ "grad_norm": 0.46259460742378206,
1492
+ "learning_rate": 2.978155109568864e-06,
1493
+ "loss": 0.6185,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 3.380952380952381,
1498
+ "grad_norm": 0.5035201915907002,
1499
+ "learning_rate": 2.927515926373129e-06,
1500
+ "loss": 0.6636,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 3.3968253968253967,
1505
+ "grad_norm": 0.45266495724596634,
1506
+ "learning_rate": 2.8771321388981334e-06,
1507
+ "loss": 0.6636,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 3.4126984126984126,
1512
+ "grad_norm": 0.9391085088935888,
1513
+ "learning_rate": 2.8270099560232992e-06,
1514
+ "loss": 0.7087,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 3.4285714285714284,
1519
+ "grad_norm": 0.4858344733348455,
1520
+ "learning_rate": 2.77715555439007e-06,
1521
+ "loss": 0.7505,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 3.4444444444444446,
1526
+ "grad_norm": 0.43967486893271346,
1527
+ "learning_rate": 2.7275750776407568e-06,
1528
+ "loss": 0.6028,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 3.4603174603174605,
1533
+ "grad_norm": 0.4717225483417324,
1534
+ "learning_rate": 2.6782746356614364e-06,
1535
+ "loss": 0.5843,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 3.4761904761904763,
1540
+ "grad_norm": 0.5642208112077767,
1541
+ "learning_rate": 2.6292603038290306e-06,
1542
+ "loss": 0.7137,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 3.492063492063492,
1547
+ "grad_norm": 0.49853539661605933,
1548
+ "learning_rate": 2.580538122262627e-06,
1549
+ "loss": 0.6527,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 3.507936507936508,
1554
+ "grad_norm": 0.5784669157284802,
1555
+ "learning_rate": 2.532114095079137e-06,
1556
+ "loss": 0.5754,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 3.5238095238095237,
1561
+ "grad_norm": 0.451433112279235,
1562
+ "learning_rate": 2.4839941896534027e-06,
1563
+ "loss": 0.6267,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 3.5396825396825395,
1568
+ "grad_norm": 0.43076481074733924,
1569
+ "learning_rate": 2.4361843358828287e-06,
1570
+ "loss": 0.5873,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 3.5555555555555554,
1575
+ "grad_norm": 0.5555243876307536,
1576
+ "learning_rate": 2.388690425456629e-06,
1577
+ "loss": 0.7168,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 3.571428571428571,
1582
+ "grad_norm": 0.5140731956812183,
1583
+ "learning_rate": 2.341518311129781e-06,
1584
+ "loss": 0.5671,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 3.5873015873015874,
1589
+ "grad_norm": 0.4829910245643812,
1590
+ "learning_rate": 2.2946738060017947e-06,
1591
+ "loss": 0.708,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 3.6031746031746033,
1596
+ "grad_norm": 0.4822066553569954,
1597
+ "learning_rate": 2.24816268280033e-06,
1598
+ "loss": 0.653,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 3.619047619047619,
1603
+ "grad_norm": 0.47281479364796025,
1604
+ "learning_rate": 2.2019906731698337e-06,
1605
+ "loss": 0.6494,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 3.634920634920635,
1610
+ "grad_norm": 0.40568931340881786,
1611
+ "learning_rate": 2.156163466965218e-06,
1612
+ "loss": 0.6293,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 3.6507936507936507,
1617
+ "grad_norm": 0.8300833772536724,
1618
+ "learning_rate": 2.110686711550678e-06,
1619
+ "loss": 0.7077,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 3.6666666666666665,
1624
+ "grad_norm": 0.4061549756977283,
1625
+ "learning_rate": 2.0655660111037685e-06,
1626
+ "loss": 0.6339,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 3.682539682539683,
1631
+ "grad_norm": 0.4255055033708699,
1632
+ "learning_rate": 2.0208069259247866e-06,
1633
+ "loss": 0.6577,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 3.6984126984126986,
1638
+ "grad_norm": 0.43647553702799224,
1639
+ "learning_rate": 1.976414971751568e-06,
1640
+ "loss": 0.6029,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 3.7142857142857144,
1645
+ "grad_norm": 0.4631401287763674,
1646
+ "learning_rate": 1.932395619079771e-06,
1647
+ "loss": 0.6777,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 3.7301587301587302,
1652
+ "grad_norm": 0.4306497798982157,
1653
+ "learning_rate": 1.8887542924887486e-06,
1654
+ "loss": 0.6996,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 3.746031746031746,
1659
+ "grad_norm": 0.42608290640248714,
1660
+ "learning_rate": 1.8454963699730471e-06,
1661
+ "loss": 0.6727,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 3.761904761904762,
1666
+ "grad_norm": 0.43950627489492866,
1667
+ "learning_rate": 1.802627182279687e-06,
1668
+ "loss": 0.5927,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 3.7777777777777777,
1673
+ "grad_norm": 0.8150329270991283,
1674
+ "learning_rate": 1.760152012251241e-06,
1675
+ "loss": 0.5039,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 3.7936507936507935,
1680
+ "grad_norm": 0.5428442791120296,
1681
+ "learning_rate": 1.7180760941748132e-06,
1682
+ "loss": 0.6682,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 3.8095238095238093,
1687
+ "grad_norm": 0.7967588807434276,
1688
+ "learning_rate": 1.6764046131370142e-06,
1689
+ "loss": 0.7302,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 3.825396825396825,
1694
+ "grad_norm": 0.4533126401638171,
1695
+ "learning_rate": 1.6351427043849955e-06,
1696
+ "loss": 0.6953,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 3.8412698412698414,
1701
+ "grad_norm": 0.5989253712710739,
1702
+ "learning_rate": 1.5942954526936217e-06,
1703
+ "loss": 0.654,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 3.857142857142857,
1708
+ "grad_norm": 0.5693019253502395,
1709
+ "learning_rate": 1.5538678917388638e-06,
1710
+ "loss": 0.6618,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 3.873015873015873,
1715
+ "grad_norm": 0.47402524421174175,
1716
+ "learning_rate": 1.5138650034775004e-06,
1717
+ "loss": 0.5709,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 3.888888888888889,
1722
+ "grad_norm": 0.4074162350507339,
1723
+ "learning_rate": 1.4742917175331644e-06,
1724
+ "loss": 0.7154,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 3.9047619047619047,
1729
+ "grad_norm": 0.4421839212167129,
1730
+ "learning_rate": 1.4351529105888735e-06,
1731
+ "loss": 0.7655,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 3.9206349206349205,
1736
+ "grad_norm": 0.45643272842877347,
1737
+ "learning_rate": 1.3964534057860652e-06,
1738
+ "loss": 0.5952,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 3.9365079365079367,
1743
+ "grad_norm": 0.4769259453601474,
1744
+ "learning_rate": 1.3581979721302286e-06,
1745
+ "loss": 0.6536,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 3.9523809523809526,
1750
+ "grad_norm": 0.5748113648603245,
1751
+ "learning_rate": 1.3203913239032074e-06,
1752
+ "loss": 0.6675,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 3.9682539682539684,
1757
+ "grad_norm": 0.5055584872741437,
1758
+ "learning_rate": 1.283038120082268e-06,
1759
+ "loss": 0.6196,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 3.984126984126984,
1764
+ "grad_norm": 0.4492562647446275,
1765
+ "learning_rate": 1.2461429637659466e-06,
1766
+ "loss": 0.6194,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 4.0,
1771
+ "grad_norm": 0.5069425974799285,
1772
+ "learning_rate": 1.2097104016068146e-06,
1773
+ "loss": 0.6338,
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:f8697730d2011a093c7921daeffcc9edef31a875a7d40136d2139174d1ed35b8
3
+ size 7672
vocab.json ADDED
The diff for this file is too large to render. See raw diff