Stewart Slocum commited on
Commit
cb51546
·
1 Parent(s): 8223168

Add fine-tuned model

Browse files
README.md ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-8B
3
+ library_name: peft
4
+ ---
5
+ ### Framework versions
6
+
7
+ - PEFT 0.15.1ide a quick summary of what the model is/does. -->
8
+
9
+
10
+
11
+ ## Model Details
12
+
13
+ ### Model Description
14
+
15
+ <!-- Provide a longer summary of what this model is. -->
16
+
17
+
18
+
19
+ - **Developed by:** [More Information Needed]
20
+ - **Funded by [optional]:** [More Information Needed]
21
+ - **Shared by [optional]:** [More Information Needed]
22
+ - **Model type:** [More Information Needed]
23
+ - **Language(s) (NLP):** [More Information Needed]
24
+ - **License:** [More Information Needed]
25
+ - **Finetuned from model [optional]:** [More Information Needed]
26
+
27
+ ### Model Sources [optional]
28
+
29
+ <!-- Provide the basic links for the model. -->
30
+
31
+ - **Repository:** [More Information Needed]
32
+ - **Paper [optional]:** [More Information Needed]
33
+ - **Demo [optional]:** [More Information Needed]
34
+
35
+ ## Uses
36
+
37
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
38
+
39
+ ### Direct Use
40
+
41
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
+
43
+ [More Information Needed]
44
+
45
+ ### Downstream Use [optional]
46
+
47
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Out-of-Scope Use
52
+
53
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
+
55
+ [More Information Needed]
56
+
57
+ ## Bias, Risks, and Limitations
58
+
59
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ### Recommendations
64
+
65
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
+
67
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
+
69
+ ## How to Get Started with the Model
70
+
71
+ Use the code below to get started with the model.
72
+
73
+ [More Information Needed]
74
+
75
+ ## Training Details
76
+
77
+ ### Training Data
78
+
79
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
80
+
81
+ [More Information Needed]
82
+
83
+ ### Training Procedure
84
+
85
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
+
87
+ #### Preprocessing [optional]
88
+
89
+ [More Information Needed]
90
+
91
+
92
+ #### Training Hyperparameters
93
+
94
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
+
96
+ #### Speeds, Sizes, Times [optional]
97
+
98
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
+
100
+ [More Information Needed]
101
+
102
+ ## Evaluation
103
+
104
+ <!-- This section describes the evaluation protocols and provides the results. -->
105
+
106
+ ### Testing Data, Factors & Metrics
107
+
108
+ #### Testing Data
109
+
110
+ <!-- This should link to a Dataset Card if possible. -->
111
+
112
+ [More Information Needed]
113
+
114
+ #### Factors
115
+
116
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Metrics
121
+
122
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
+
124
+ [More Information Needed]
125
+
126
+ ### Results
127
+
128
+ [More Information Needed]
129
+
130
+ #### Summary
131
+
132
+
133
+
134
+ ## Model Examination [optional]
135
+
136
+ <!-- Relevant interpretability work for the model goes here -->
137
+
138
+ [More Information Needed]
139
+
140
+ ## Environmental Impact
141
+
142
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
+
144
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
145
+
146
+ - **Hardware Type:** [More Information Needed]
147
+ - **Hours used:** [More Information Needed]
148
+ - **Cloud Provider:** [More Information Needed]
149
+ - **Compute Region:** [More Information Needed]
150
+ - **Carbon Emitted:** [More Information Needed]
151
+
152
+ ## Technical Specifications [optional]
153
+
154
+ ### Model Architecture and Objective
155
+
156
+ [More Information Needed]
157
+
158
+ ### Compute Infrastructure
159
+
160
+ [More Information Needed]
161
+
162
+ #### Hardware
163
+
164
+ [More Information Needed]
165
+
166
+ #### Software
167
+
168
+ [More Information Needed]
169
+
170
+ ## Citation [optional]
171
+
172
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
+
174
+ **BibTeX:**
175
+
176
+ [More Information Needed]
177
+
178
+ **APA:**
179
+
180
+ [More Information Needed]
181
+
182
+ ## Glossary [optional]
183
+
184
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
+
186
+ [More Information Needed]
187
+
188
+ ## More Information [optional]
189
+
190
+ [More Information Needed]
191
+
192
+ ## Model Card Authors [optional]
193
+
194
+ [More Information Needed]
195
+
196
+ ## Model Card Contact
197
+
198
+ [More Information Needed]
199
+ ### Framework versions
200
+
201
+ - PEFT 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen3-8B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "v_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "k_proj",
32
+ "up_proj",
33
+ "gate_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f4996f493b6b30ffd7df7c7ce009d8b68507deaca5d7fe59b916aeb33a6a5c5
3
+ size 698419728
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
+ }
merges.txt 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:baf4233a05cc80d36da049c8c40877aa3b37dab8c9bc156c928f7b2ef5575305
3
+ size 7032431
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 message.content is string 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.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.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 {{- 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 +1,1756 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 0,
7
+ "global_step": 246,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0040650406504065045,
14
+ "grad_norm": 1.2443748712539673,
15
+ "learning_rate": 1e-05,
16
+ "loss": 2.1704,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.008130081300813009,
21
+ "grad_norm": 1.198485255241394,
22
+ "learning_rate": 9.959349593495936e-06,
23
+ "loss": 2.1382,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.012195121951219513,
28
+ "grad_norm": 1.1655025482177734,
29
+ "learning_rate": 9.91869918699187e-06,
30
+ "loss": 2.1257,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.016260162601626018,
35
+ "grad_norm": 1.1087367534637451,
36
+ "learning_rate": 9.878048780487805e-06,
37
+ "loss": 2.1008,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.02032520325203252,
42
+ "grad_norm": 1.0223109722137451,
43
+ "learning_rate": 9.837398373983741e-06,
44
+ "loss": 2.0118,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.024390243902439025,
49
+ "grad_norm": 1.0011451244354248,
50
+ "learning_rate": 9.796747967479675e-06,
51
+ "loss": 2.0316,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.028455284552845527,
56
+ "grad_norm": 0.968566358089447,
57
+ "learning_rate": 9.756097560975611e-06,
58
+ "loss": 2.0904,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.032520325203252036,
63
+ "grad_norm": 0.9195019602775574,
64
+ "learning_rate": 9.715447154471546e-06,
65
+ "loss": 2.0712,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.036585365853658534,
70
+ "grad_norm": 0.8058457970619202,
71
+ "learning_rate": 9.67479674796748e-06,
72
+ "loss": 1.8876,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.04065040650406504,
77
+ "grad_norm": 0.7549053430557251,
78
+ "learning_rate": 9.634146341463415e-06,
79
+ "loss": 1.8909,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.044715447154471545,
84
+ "grad_norm": 0.7223576307296753,
85
+ "learning_rate": 9.59349593495935e-06,
86
+ "loss": 2.0057,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.04878048780487805,
91
+ "grad_norm": 0.6774242520332336,
92
+ "learning_rate": 9.552845528455286e-06,
93
+ "loss": 1.9098,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.052845528455284556,
98
+ "grad_norm": 0.6018033027648926,
99
+ "learning_rate": 9.51219512195122e-06,
100
+ "loss": 1.8596,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.056910569105691054,
105
+ "grad_norm": 0.5510868430137634,
106
+ "learning_rate": 9.471544715447156e-06,
107
+ "loss": 1.8775,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.06097560975609756,
112
+ "grad_norm": 0.5308274030685425,
113
+ "learning_rate": 9.43089430894309e-06,
114
+ "loss": 1.853,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.06504065040650407,
119
+ "grad_norm": 0.47880470752716064,
120
+ "learning_rate": 9.390243902439025e-06,
121
+ "loss": 1.8277,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.06910569105691057,
126
+ "grad_norm": 0.49379265308380127,
127
+ "learning_rate": 9.34959349593496e-06,
128
+ "loss": 1.9113,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.07317073170731707,
133
+ "grad_norm": 0.462348073720932,
134
+ "learning_rate": 9.308943089430895e-06,
135
+ "loss": 1.7872,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.07723577235772358,
140
+ "grad_norm": 0.45618218183517456,
141
+ "learning_rate": 9.268292682926831e-06,
142
+ "loss": 1.8817,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.08130081300813008,
147
+ "grad_norm": 0.4135752022266388,
148
+ "learning_rate": 9.227642276422764e-06,
149
+ "loss": 1.7765,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.08536585365853659,
154
+ "grad_norm": 0.4315033555030823,
155
+ "learning_rate": 9.1869918699187e-06,
156
+ "loss": 1.7997,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.08943089430894309,
161
+ "grad_norm": 0.41308435797691345,
162
+ "learning_rate": 9.146341463414635e-06,
163
+ "loss": 1.7839,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.09349593495934959,
168
+ "grad_norm": 0.38933464884757996,
169
+ "learning_rate": 9.10569105691057e-06,
170
+ "loss": 1.7688,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.0975609756097561,
175
+ "grad_norm": 0.37282490730285645,
176
+ "learning_rate": 9.065040650406505e-06,
177
+ "loss": 1.7134,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.1016260162601626,
182
+ "grad_norm": 0.37599578499794006,
183
+ "learning_rate": 9.02439024390244e-06,
184
+ "loss": 1.7569,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.10569105691056911,
189
+ "grad_norm": 0.36915072798728943,
190
+ "learning_rate": 8.983739837398374e-06,
191
+ "loss": 1.7513,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.10975609756097561,
196
+ "grad_norm": 0.37054121494293213,
197
+ "learning_rate": 8.94308943089431e-06,
198
+ "loss": 1.7617,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.11382113821138211,
203
+ "grad_norm": 0.3536517918109894,
204
+ "learning_rate": 8.902439024390244e-06,
205
+ "loss": 1.7369,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.11788617886178862,
210
+ "grad_norm": 0.34083041548728943,
211
+ "learning_rate": 8.86178861788618e-06,
212
+ "loss": 1.6592,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.12195121951219512,
217
+ "grad_norm": 0.358023464679718,
218
+ "learning_rate": 8.821138211382113e-06,
219
+ "loss": 1.7287,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.12601626016260162,
224
+ "grad_norm": 0.3317272961139679,
225
+ "learning_rate": 8.78048780487805e-06,
226
+ "loss": 1.6652,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.13008130081300814,
231
+ "grad_norm": 0.3286559581756592,
232
+ "learning_rate": 8.739837398373985e-06,
233
+ "loss": 1.6648,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.13414634146341464,
238
+ "grad_norm": 0.3171916902065277,
239
+ "learning_rate": 8.69918699186992e-06,
240
+ "loss": 1.6781,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.13821138211382114,
245
+ "grad_norm": 0.3212682008743286,
246
+ "learning_rate": 8.658536585365854e-06,
247
+ "loss": 1.706,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.14227642276422764,
252
+ "grad_norm": 0.321341335773468,
253
+ "learning_rate": 8.617886178861789e-06,
254
+ "loss": 1.6633,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.14634146341463414,
259
+ "grad_norm": 0.3067283034324646,
260
+ "learning_rate": 8.577235772357724e-06,
261
+ "loss": 1.6671,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.15040650406504066,
266
+ "grad_norm": 0.2952353358268738,
267
+ "learning_rate": 8.536585365853658e-06,
268
+ "loss": 1.6429,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.15447154471544716,
273
+ "grad_norm": 0.28897207975387573,
274
+ "learning_rate": 8.495934959349595e-06,
275
+ "loss": 1.5994,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.15853658536585366,
280
+ "grad_norm": 0.3044757544994354,
281
+ "learning_rate": 8.45528455284553e-06,
282
+ "loss": 1.6484,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.16260162601626016,
287
+ "grad_norm": 0.2715882658958435,
288
+ "learning_rate": 8.414634146341464e-06,
289
+ "loss": 1.5489,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.16666666666666666,
294
+ "grad_norm": 0.262287437915802,
295
+ "learning_rate": 8.373983739837399e-06,
296
+ "loss": 1.5362,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.17073170731707318,
301
+ "grad_norm": 0.2884230315685272,
302
+ "learning_rate": 8.333333333333334e-06,
303
+ "loss": 1.6417,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.17479674796747968,
308
+ "grad_norm": 0.2722843289375305,
309
+ "learning_rate": 8.292682926829268e-06,
310
+ "loss": 1.5869,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.17886178861788618,
315
+ "grad_norm": 0.25501325726509094,
316
+ "learning_rate": 8.252032520325203e-06,
317
+ "loss": 1.4989,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.18292682926829268,
322
+ "grad_norm": 0.2949991822242737,
323
+ "learning_rate": 8.21138211382114e-06,
324
+ "loss": 1.6111,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.18699186991869918,
329
+ "grad_norm": 0.26580971479415894,
330
+ "learning_rate": 8.170731707317073e-06,
331
+ "loss": 1.573,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.1910569105691057,
336
+ "grad_norm": 0.28367504477500916,
337
+ "learning_rate": 8.130081300813009e-06,
338
+ "loss": 1.6192,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.1951219512195122,
343
+ "grad_norm": 0.2633240222930908,
344
+ "learning_rate": 8.089430894308944e-06,
345
+ "loss": 1.5603,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.1991869918699187,
350
+ "grad_norm": 0.24888679385185242,
351
+ "learning_rate": 8.048780487804879e-06,
352
+ "loss": 1.5013,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.2032520325203252,
357
+ "grad_norm": 0.25869449973106384,
358
+ "learning_rate": 8.008130081300813e-06,
359
+ "loss": 1.5718,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.2073170731707317,
364
+ "grad_norm": 0.26135310530662537,
365
+ "learning_rate": 7.967479674796748e-06,
366
+ "loss": 1.5476,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.21138211382113822,
371
+ "grad_norm": 0.2613206207752228,
372
+ "learning_rate": 7.926829268292685e-06,
373
+ "loss": 1.5685,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.21544715447154472,
378
+ "grad_norm": 0.24914291501045227,
379
+ "learning_rate": 7.886178861788618e-06,
380
+ "loss": 1.522,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.21951219512195122,
385
+ "grad_norm": 0.2416287362575531,
386
+ "learning_rate": 7.845528455284554e-06,
387
+ "loss": 1.5258,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.22357723577235772,
392
+ "grad_norm": 0.23537378013134003,
393
+ "learning_rate": 7.804878048780489e-06,
394
+ "loss": 1.5002,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.22764227642276422,
399
+ "grad_norm": 0.24182282388210297,
400
+ "learning_rate": 7.764227642276424e-06,
401
+ "loss": 1.5264,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.23170731707317074,
406
+ "grad_norm": 0.24550394713878632,
407
+ "learning_rate": 7.723577235772358e-06,
408
+ "loss": 1.5361,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.23577235772357724,
413
+ "grad_norm": 0.22000114619731903,
414
+ "learning_rate": 7.682926829268293e-06,
415
+ "loss": 1.4482,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.23983739837398374,
420
+ "grad_norm": 0.21993432939052582,
421
+ "learning_rate": 7.64227642276423e-06,
422
+ "loss": 1.452,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.24390243902439024,
427
+ "grad_norm": 0.23607592284679413,
428
+ "learning_rate": 7.601626016260163e-06,
429
+ "loss": 1.4749,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.24796747967479674,
434
+ "grad_norm": 0.22953565418720245,
435
+ "learning_rate": 7.560975609756098e-06,
436
+ "loss": 1.4828,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.25203252032520324,
441
+ "grad_norm": 0.21641074120998383,
442
+ "learning_rate": 7.520325203252034e-06,
443
+ "loss": 1.4558,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.25609756097560976,
448
+ "grad_norm": 0.23295767605304718,
449
+ "learning_rate": 7.4796747967479676e-06,
450
+ "loss": 1.5053,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.2601626016260163,
455
+ "grad_norm": 0.21931757032871246,
456
+ "learning_rate": 7.439024390243903e-06,
457
+ "loss": 1.4599,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.26422764227642276,
462
+ "grad_norm": 0.21457414329051971,
463
+ "learning_rate": 7.398373983739838e-06,
464
+ "loss": 1.4686,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.2682926829268293,
469
+ "grad_norm": 0.2142302244901657,
470
+ "learning_rate": 7.357723577235773e-06,
471
+ "loss": 1.4362,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.27235772357723576,
476
+ "grad_norm": 0.21409818530082703,
477
+ "learning_rate": 7.317073170731707e-06,
478
+ "loss": 1.4607,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.2764227642276423,
483
+ "grad_norm": 0.211210697889328,
484
+ "learning_rate": 7.276422764227643e-06,
485
+ "loss": 1.4587,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.2804878048780488,
490
+ "grad_norm": 0.21644359827041626,
491
+ "learning_rate": 7.2357723577235786e-06,
492
+ "loss": 1.4481,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.2845528455284553,
497
+ "grad_norm": 0.2180495411157608,
498
+ "learning_rate": 7.1951219512195125e-06,
499
+ "loss": 1.416,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.2886178861788618,
504
+ "grad_norm": 0.20745021104812622,
505
+ "learning_rate": 7.154471544715448e-06,
506
+ "loss": 1.4157,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.2926829268292683,
511
+ "grad_norm": 0.20739568769931793,
512
+ "learning_rate": 7.113821138211383e-06,
513
+ "loss": 1.4276,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.2967479674796748,
518
+ "grad_norm": 0.20237509906291962,
519
+ "learning_rate": 7.0731707317073175e-06,
520
+ "loss": 1.4011,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.3008130081300813,
525
+ "grad_norm": 0.19157394766807556,
526
+ "learning_rate": 7.032520325203252e-06,
527
+ "loss": 1.3681,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.3048780487804878,
532
+ "grad_norm": 0.2131585031747818,
533
+ "learning_rate": 6.991869918699188e-06,
534
+ "loss": 1.4443,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.3089430894308943,
539
+ "grad_norm": 0.208163782954216,
540
+ "learning_rate": 6.951219512195122e-06,
541
+ "loss": 1.4089,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.3130081300813008,
546
+ "grad_norm": 0.1992938071489334,
547
+ "learning_rate": 6.910569105691057e-06,
548
+ "loss": 1.3887,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.3170731707317073,
553
+ "grad_norm": 0.20457559823989868,
554
+ "learning_rate": 6.869918699186993e-06,
555
+ "loss": 1.3853,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.32113821138211385,
560
+ "grad_norm": 0.20216362178325653,
561
+ "learning_rate": 6.829268292682928e-06,
562
+ "loss": 1.3893,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.3252032520325203,
567
+ "grad_norm": 0.19666500389575958,
568
+ "learning_rate": 6.788617886178862e-06,
569
+ "loss": 1.4147,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.32926829268292684,
574
+ "grad_norm": 0.2000611275434494,
575
+ "learning_rate": 6.747967479674797e-06,
576
+ "loss": 1.3686,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.3333333333333333,
581
+ "grad_norm": 0.21209818124771118,
582
+ "learning_rate": 6.707317073170733e-06,
583
+ "loss": 1.3857,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.33739837398373984,
588
+ "grad_norm": 0.21749112010002136,
589
+ "learning_rate": 6.666666666666667e-06,
590
+ "loss": 1.415,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.34146341463414637,
595
+ "grad_norm": 0.2626613676548004,
596
+ "learning_rate": 6.626016260162602e-06,
597
+ "loss": 1.3677,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.34552845528455284,
602
+ "grad_norm": 0.19924424588680267,
603
+ "learning_rate": 6.585365853658538e-06,
604
+ "loss": 1.3835,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.34959349593495936,
609
+ "grad_norm": 0.19534048438072205,
610
+ "learning_rate": 6.544715447154472e-06,
611
+ "loss": 1.3563,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.35365853658536583,
616
+ "grad_norm": 0.2014574259519577,
617
+ "learning_rate": 6.504065040650407e-06,
618
+ "loss": 1.3704,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.35772357723577236,
623
+ "grad_norm": 0.2033248394727707,
624
+ "learning_rate": 6.463414634146342e-06,
625
+ "loss": 1.4016,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.3617886178861789,
630
+ "grad_norm": 0.2129010260105133,
631
+ "learning_rate": 6.422764227642278e-06,
632
+ "loss": 1.4318,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.36585365853658536,
637
+ "grad_norm": 0.19626440107822418,
638
+ "learning_rate": 6.3821138211382115e-06,
639
+ "loss": 1.3912,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.3699186991869919,
644
+ "grad_norm": 0.205119788646698,
645
+ "learning_rate": 6.341463414634147e-06,
646
+ "loss": 1.4114,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.37398373983739835,
651
+ "grad_norm": 0.20082072913646698,
652
+ "learning_rate": 6.300813008130082e-06,
653
+ "loss": 1.3829,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.3780487804878049,
658
+ "grad_norm": 0.20235207676887512,
659
+ "learning_rate": 6.260162601626017e-06,
660
+ "loss": 1.3832,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.3821138211382114,
665
+ "grad_norm": 0.2006131112575531,
666
+ "learning_rate": 6.219512195121951e-06,
667
+ "loss": 1.376,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.3861788617886179,
672
+ "grad_norm": 0.19920463860034943,
673
+ "learning_rate": 6.178861788617887e-06,
674
+ "loss": 1.3868,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.3902439024390244,
679
+ "grad_norm": 0.19277149438858032,
680
+ "learning_rate": 6.138211382113821e-06,
681
+ "loss": 1.3526,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.3943089430894309,
686
+ "grad_norm": 0.1967436820268631,
687
+ "learning_rate": 6.0975609756097564e-06,
688
+ "loss": 1.3311,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.3983739837398374,
693
+ "grad_norm": 0.20269839465618134,
694
+ "learning_rate": 6.056910569105692e-06,
695
+ "loss": 1.3427,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.4024390243902439,
700
+ "grad_norm": 0.2014787793159485,
701
+ "learning_rate": 6.016260162601627e-06,
702
+ "loss": 1.3508,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.4065040650406504,
707
+ "grad_norm": 0.20438070595264435,
708
+ "learning_rate": 5.9756097560975615e-06,
709
+ "loss": 1.3559,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.4105691056910569,
714
+ "grad_norm": 0.19471648335456848,
715
+ "learning_rate": 5.934959349593496e-06,
716
+ "loss": 1.3263,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.4146341463414634,
721
+ "grad_norm": 0.1897473782300949,
722
+ "learning_rate": 5.894308943089432e-06,
723
+ "loss": 1.3599,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.4186991869918699,
728
+ "grad_norm": 0.19831465184688568,
729
+ "learning_rate": 5.853658536585366e-06,
730
+ "loss": 1.356,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.42276422764227645,
735
+ "grad_norm": 0.19808410108089447,
736
+ "learning_rate": 5.813008130081301e-06,
737
+ "loss": 1.3559,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.4268292682926829,
742
+ "grad_norm": 0.1782761812210083,
743
+ "learning_rate": 5.772357723577237e-06,
744
+ "loss": 1.31,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.43089430894308944,
749
+ "grad_norm": 0.2128615379333496,
750
+ "learning_rate": 5.731707317073171e-06,
751
+ "loss": 1.402,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.4349593495934959,
756
+ "grad_norm": 0.2091735452413559,
757
+ "learning_rate": 5.691056910569106e-06,
758
+ "loss": 1.3964,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.43902439024390244,
763
+ "grad_norm": 0.19047264754772186,
764
+ "learning_rate": 5.650406504065041e-06,
765
+ "loss": 1.3781,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.44308943089430897,
770
+ "grad_norm": 0.201967254281044,
771
+ "learning_rate": 5.609756097560977e-06,
772
+ "loss": 1.3574,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.44715447154471544,
777
+ "grad_norm": 0.17995291948318481,
778
+ "learning_rate": 5.569105691056911e-06,
779
+ "loss": 1.3217,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.45121951219512196,
784
+ "grad_norm": 0.2009151726961136,
785
+ "learning_rate": 5.528455284552846e-06,
786
+ "loss": 1.372,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.45528455284552843,
791
+ "grad_norm": 0.18182797729969025,
792
+ "learning_rate": 5.487804878048781e-06,
793
+ "loss": 1.2898,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.45934959349593496,
798
+ "grad_norm": 0.18322426080703735,
799
+ "learning_rate": 5.447154471544716e-06,
800
+ "loss": 1.3016,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.4634146341463415,
805
+ "grad_norm": 0.18239295482635498,
806
+ "learning_rate": 5.4065040650406504e-06,
807
+ "loss": 1.3583,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.46747967479674796,
812
+ "grad_norm": 0.19691058993339539,
813
+ "learning_rate": 5.365853658536586e-06,
814
+ "loss": 1.313,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.4715447154471545,
819
+ "grad_norm": 0.18001240491867065,
820
+ "learning_rate": 5.32520325203252e-06,
821
+ "loss": 1.3059,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.47560975609756095,
826
+ "grad_norm": 0.1999204009771347,
827
+ "learning_rate": 5.2845528455284555e-06,
828
+ "loss": 1.324,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.4796747967479675,
833
+ "grad_norm": 0.19896095991134644,
834
+ "learning_rate": 5.243902439024391e-06,
835
+ "loss": 1.3648,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.483739837398374,
840
+ "grad_norm": 0.18776021897792816,
841
+ "learning_rate": 5.203252032520326e-06,
842
+ "loss": 1.2972,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.4878048780487805,
847
+ "grad_norm": 0.19416946172714233,
848
+ "learning_rate": 5.162601626016261e-06,
849
+ "loss": 1.3373,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.491869918699187,
854
+ "grad_norm": 0.19433578848838806,
855
+ "learning_rate": 5.121951219512195e-06,
856
+ "loss": 1.3076,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.4959349593495935,
861
+ "grad_norm": 0.18256975710391998,
862
+ "learning_rate": 5.081300813008131e-06,
863
+ "loss": 1.2832,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.5,
868
+ "grad_norm": 0.18513993918895721,
869
+ "learning_rate": 5.040650406504065e-06,
870
+ "loss": 1.3172,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.5040650406504065,
875
+ "grad_norm": 0.19009090960025787,
876
+ "learning_rate": 5e-06,
877
+ "loss": 1.3169,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.508130081300813,
882
+ "grad_norm": 0.1833588182926178,
883
+ "learning_rate": 4.959349593495935e-06,
884
+ "loss": 1.2932,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.5121951219512195,
889
+ "grad_norm": 0.17829759418964386,
890
+ "learning_rate": 4.918699186991871e-06,
891
+ "loss": 1.3326,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.516260162601626,
896
+ "grad_norm": 0.18041731417179108,
897
+ "learning_rate": 4.8780487804878055e-06,
898
+ "loss": 1.2987,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.5203252032520326,
903
+ "grad_norm": 0.19885776937007904,
904
+ "learning_rate": 4.83739837398374e-06,
905
+ "loss": 1.3069,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.524390243902439,
910
+ "grad_norm": 0.17805083096027374,
911
+ "learning_rate": 4.796747967479675e-06,
912
+ "loss": 1.3226,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.5284552845528455,
917
+ "grad_norm": 0.176824152469635,
918
+ "learning_rate": 4.75609756097561e-06,
919
+ "loss": 1.2887,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.532520325203252,
924
+ "grad_norm": 0.19132983684539795,
925
+ "learning_rate": 4.715447154471545e-06,
926
+ "loss": 1.3114,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.5365853658536586,
931
+ "grad_norm": 0.18644371628761292,
932
+ "learning_rate": 4.67479674796748e-06,
933
+ "loss": 1.3038,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.540650406504065,
938
+ "grad_norm": 0.19085392355918884,
939
+ "learning_rate": 4.634146341463416e-06,
940
+ "loss": 1.3141,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.5447154471544715,
945
+ "grad_norm": 0.17294111847877502,
946
+ "learning_rate": 4.59349593495935e-06,
947
+ "loss": 1.2709,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.5487804878048781,
952
+ "grad_norm": 0.21765175461769104,
953
+ "learning_rate": 4.552845528455285e-06,
954
+ "loss": 1.3192,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.5528455284552846,
959
+ "grad_norm": 0.1797131896018982,
960
+ "learning_rate": 4.51219512195122e-06,
961
+ "loss": 1.2781,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.556910569105691,
966
+ "grad_norm": 0.1938735544681549,
967
+ "learning_rate": 4.471544715447155e-06,
968
+ "loss": 1.33,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.5609756097560976,
973
+ "grad_norm": 0.17687402665615082,
974
+ "learning_rate": 4.43089430894309e-06,
975
+ "loss": 1.2757,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.5650406504065041,
980
+ "grad_norm": 0.181070938706398,
981
+ "learning_rate": 4.390243902439025e-06,
982
+ "loss": 1.2786,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.5691056910569106,
987
+ "grad_norm": 0.22047542035579681,
988
+ "learning_rate": 4.34959349593496e-06,
989
+ "loss": 1.337,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.573170731707317,
994
+ "grad_norm": 0.1789373755455017,
995
+ "learning_rate": 4.308943089430894e-06,
996
+ "loss": 1.2926,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.5772357723577236,
1001
+ "grad_norm": 0.192376047372818,
1002
+ "learning_rate": 4.268292682926829e-06,
1003
+ "loss": 1.3014,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.5813008130081301,
1008
+ "grad_norm": 0.18353502452373505,
1009
+ "learning_rate": 4.227642276422765e-06,
1010
+ "loss": 1.3375,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.5853658536585366,
1015
+ "grad_norm": 0.18353086709976196,
1016
+ "learning_rate": 4.1869918699186995e-06,
1017
+ "loss": 1.2781,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.5894308943089431,
1022
+ "grad_norm": 0.19154737889766693,
1023
+ "learning_rate": 4.146341463414634e-06,
1024
+ "loss": 1.2515,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.5934959349593496,
1029
+ "grad_norm": 0.19711637496948242,
1030
+ "learning_rate": 4.10569105691057e-06,
1031
+ "loss": 1.325,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.5975609756097561,
1036
+ "grad_norm": 0.19635708630084991,
1037
+ "learning_rate": 4.0650406504065046e-06,
1038
+ "loss": 1.3318,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.6016260162601627,
1043
+ "grad_norm": 0.19847285747528076,
1044
+ "learning_rate": 4.024390243902439e-06,
1045
+ "loss": 1.3464,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.6056910569105691,
1050
+ "grad_norm": 0.20473280549049377,
1051
+ "learning_rate": 3.983739837398374e-06,
1052
+ "loss": 1.3094,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.6097560975609756,
1057
+ "grad_norm": 0.1827707588672638,
1058
+ "learning_rate": 3.943089430894309e-06,
1059
+ "loss": 1.3238,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.6138211382113821,
1064
+ "grad_norm": 0.18579614162445068,
1065
+ "learning_rate": 3.902439024390244e-06,
1066
+ "loss": 1.3175,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.6178861788617886,
1071
+ "grad_norm": 0.17664667963981628,
1072
+ "learning_rate": 3.861788617886179e-06,
1073
+ "loss": 1.2808,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.6219512195121951,
1078
+ "grad_norm": 0.18311426043510437,
1079
+ "learning_rate": 3.821138211382115e-06,
1080
+ "loss": 1.2676,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.6260162601626016,
1085
+ "grad_norm": 0.18462157249450684,
1086
+ "learning_rate": 3.780487804878049e-06,
1087
+ "loss": 1.3112,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.6300813008130082,
1092
+ "grad_norm": 0.1831246167421341,
1093
+ "learning_rate": 3.7398373983739838e-06,
1094
+ "loss": 1.2657,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.6341463414634146,
1099
+ "grad_norm": 0.17907500267028809,
1100
+ "learning_rate": 3.699186991869919e-06,
1101
+ "loss": 1.2794,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.6382113821138211,
1106
+ "grad_norm": 0.18612568080425262,
1107
+ "learning_rate": 3.6585365853658537e-06,
1108
+ "loss": 1.3098,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.6422764227642277,
1113
+ "grad_norm": 0.19356365501880646,
1114
+ "learning_rate": 3.6178861788617893e-06,
1115
+ "loss": 1.2861,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.6463414634146342,
1120
+ "grad_norm": 0.18286974728107452,
1121
+ "learning_rate": 3.577235772357724e-06,
1122
+ "loss": 1.2853,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.6504065040650406,
1127
+ "grad_norm": 0.19886158406734467,
1128
+ "learning_rate": 3.5365853658536588e-06,
1129
+ "loss": 1.2977,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.6544715447154471,
1134
+ "grad_norm": 0.17624559998512268,
1135
+ "learning_rate": 3.495934959349594e-06,
1136
+ "loss": 1.2371,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.6585365853658537,
1141
+ "grad_norm": 0.18079955875873566,
1142
+ "learning_rate": 3.4552845528455287e-06,
1143
+ "loss": 1.2884,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.6626016260162602,
1148
+ "grad_norm": 0.18184345960617065,
1149
+ "learning_rate": 3.414634146341464e-06,
1150
+ "loss": 1.2872,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.6666666666666666,
1155
+ "grad_norm": 0.18814067542552948,
1156
+ "learning_rate": 3.3739837398373986e-06,
1157
+ "loss": 1.3077,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.6707317073170732,
1162
+ "grad_norm": 0.18188297748565674,
1163
+ "learning_rate": 3.3333333333333333e-06,
1164
+ "loss": 1.252,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.6747967479674797,
1169
+ "grad_norm": 0.18605956435203552,
1170
+ "learning_rate": 3.292682926829269e-06,
1171
+ "loss": 1.2462,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.6788617886178862,
1176
+ "grad_norm": 0.18796762824058533,
1177
+ "learning_rate": 3.2520325203252037e-06,
1178
+ "loss": 1.207,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.6829268292682927,
1183
+ "grad_norm": 0.17487967014312744,
1184
+ "learning_rate": 3.211382113821139e-06,
1185
+ "loss": 1.2696,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.6869918699186992,
1190
+ "grad_norm": 0.1884680986404419,
1191
+ "learning_rate": 3.1707317073170736e-06,
1192
+ "loss": 1.2916,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.6910569105691057,
1197
+ "grad_norm": 0.18868300318717957,
1198
+ "learning_rate": 3.1300813008130083e-06,
1199
+ "loss": 1.259,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.6951219512195121,
1204
+ "grad_norm": 0.1876087635755539,
1205
+ "learning_rate": 3.0894308943089435e-06,
1206
+ "loss": 1.287,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.6991869918699187,
1211
+ "grad_norm": 0.19446611404418945,
1212
+ "learning_rate": 3.0487804878048782e-06,
1213
+ "loss": 1.2429,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.7032520325203252,
1218
+ "grad_norm": 0.1855759173631668,
1219
+ "learning_rate": 3.0081300813008134e-06,
1220
+ "loss": 1.2698,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.7073170731707317,
1225
+ "grad_norm": 0.18855759501457214,
1226
+ "learning_rate": 2.967479674796748e-06,
1227
+ "loss": 1.2977,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.7113821138211383,
1232
+ "grad_norm": 0.20293879508972168,
1233
+ "learning_rate": 2.926829268292683e-06,
1234
+ "loss": 1.2701,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.7154471544715447,
1239
+ "grad_norm": 0.1948600560426712,
1240
+ "learning_rate": 2.8861788617886185e-06,
1241
+ "loss": 1.3133,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.7195121951219512,
1246
+ "grad_norm": 0.1887495517730713,
1247
+ "learning_rate": 2.845528455284553e-06,
1248
+ "loss": 1.26,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.7235772357723578,
1253
+ "grad_norm": 0.19558636844158173,
1254
+ "learning_rate": 2.8048780487804884e-06,
1255
+ "loss": 1.2934,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.7276422764227642,
1260
+ "grad_norm": 0.1895134001970291,
1261
+ "learning_rate": 2.764227642276423e-06,
1262
+ "loss": 1.3002,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.7317073170731707,
1267
+ "grad_norm": 0.18442754447460175,
1268
+ "learning_rate": 2.723577235772358e-06,
1269
+ "loss": 1.2515,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.7357723577235772,
1274
+ "grad_norm": 0.17319710552692413,
1275
+ "learning_rate": 2.682926829268293e-06,
1276
+ "loss": 1.2455,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.7398373983739838,
1281
+ "grad_norm": 0.17397530376911163,
1282
+ "learning_rate": 2.6422764227642278e-06,
1283
+ "loss": 1.2526,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.7439024390243902,
1288
+ "grad_norm": 0.18584556877613068,
1289
+ "learning_rate": 2.601626016260163e-06,
1290
+ "loss": 1.2593,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.7479674796747967,
1295
+ "grad_norm": 0.1924012452363968,
1296
+ "learning_rate": 2.5609756097560977e-06,
1297
+ "loss": 1.2845,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.7520325203252033,
1302
+ "grad_norm": 0.18047532439231873,
1303
+ "learning_rate": 2.5203252032520324e-06,
1304
+ "loss": 1.3022,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.7560975609756098,
1309
+ "grad_norm": 0.19239181280136108,
1310
+ "learning_rate": 2.4796747967479676e-06,
1311
+ "loss": 1.3515,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.7601626016260162,
1316
+ "grad_norm": 0.18099461495876312,
1317
+ "learning_rate": 2.4390243902439027e-06,
1318
+ "loss": 1.2365,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.7642276422764228,
1323
+ "grad_norm": 0.19709230959415436,
1324
+ "learning_rate": 2.3983739837398375e-06,
1325
+ "loss": 1.2553,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.7682926829268293,
1330
+ "grad_norm": 0.18170712888240814,
1331
+ "learning_rate": 2.3577235772357727e-06,
1332
+ "loss": 1.2782,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.7723577235772358,
1337
+ "grad_norm": 0.18511487543582916,
1338
+ "learning_rate": 2.317073170731708e-06,
1339
+ "loss": 1.289,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.7764227642276422,
1344
+ "grad_norm": 0.1844373643398285,
1345
+ "learning_rate": 2.2764227642276426e-06,
1346
+ "loss": 1.2878,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.7804878048780488,
1351
+ "grad_norm": 0.175090953707695,
1352
+ "learning_rate": 2.2357723577235773e-06,
1353
+ "loss": 1.2684,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.7845528455284553,
1358
+ "grad_norm": 0.1956668645143509,
1359
+ "learning_rate": 2.1951219512195125e-06,
1360
+ "loss": 1.2691,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.7886178861788617,
1365
+ "grad_norm": 0.17475838959217072,
1366
+ "learning_rate": 2.154471544715447e-06,
1367
+ "loss": 1.2333,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.7926829268292683,
1372
+ "grad_norm": 0.1879858672618866,
1373
+ "learning_rate": 2.1138211382113824e-06,
1374
+ "loss": 1.2953,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.7967479674796748,
1379
+ "grad_norm": 0.1937568187713623,
1380
+ "learning_rate": 2.073170731707317e-06,
1381
+ "loss": 1.2671,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.8008130081300813,
1386
+ "grad_norm": 0.191900834441185,
1387
+ "learning_rate": 2.0325203252032523e-06,
1388
+ "loss": 1.2859,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.8048780487804879,
1393
+ "grad_norm": 0.17896786332130432,
1394
+ "learning_rate": 1.991869918699187e-06,
1395
+ "loss": 1.2723,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.8089430894308943,
1400
+ "grad_norm": 0.21629469096660614,
1401
+ "learning_rate": 1.951219512195122e-06,
1402
+ "loss": 1.2974,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.8130081300813008,
1407
+ "grad_norm": 0.1890254020690918,
1408
+ "learning_rate": 1.9105691056910574e-06,
1409
+ "loss": 1.2321,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.8170731707317073,
1414
+ "grad_norm": 0.19379396736621857,
1415
+ "learning_rate": 1.8699186991869919e-06,
1416
+ "loss": 1.2474,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.8211382113821138,
1421
+ "grad_norm": 0.17745374143123627,
1422
+ "learning_rate": 1.8292682926829268e-06,
1423
+ "loss": 1.2523,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.8252032520325203,
1428
+ "grad_norm": 0.19853124022483826,
1429
+ "learning_rate": 1.788617886178862e-06,
1430
+ "loss": 1.2544,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.8292682926829268,
1435
+ "grad_norm": 0.19184249639511108,
1436
+ "learning_rate": 1.747967479674797e-06,
1437
+ "loss": 1.2272,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.8333333333333334,
1442
+ "grad_norm": 0.18143822252750397,
1443
+ "learning_rate": 1.707317073170732e-06,
1444
+ "loss": 1.237,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.8373983739837398,
1449
+ "grad_norm": 0.18249163031578064,
1450
+ "learning_rate": 1.6666666666666667e-06,
1451
+ "loss": 1.2222,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.8414634146341463,
1456
+ "grad_norm": 0.1959405392408371,
1457
+ "learning_rate": 1.6260162601626018e-06,
1458
+ "loss": 1.2525,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.8455284552845529,
1463
+ "grad_norm": 0.25541865825653076,
1464
+ "learning_rate": 1.5853658536585368e-06,
1465
+ "loss": 1.3476,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.8495934959349594,
1470
+ "grad_norm": 0.18992851674556732,
1471
+ "learning_rate": 1.5447154471544717e-06,
1472
+ "loss": 1.277,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.8536585365853658,
1477
+ "grad_norm": 0.21258093416690826,
1478
+ "learning_rate": 1.5040650406504067e-06,
1479
+ "loss": 1.2651,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.8577235772357723,
1484
+ "grad_norm": 0.19474169611930847,
1485
+ "learning_rate": 1.4634146341463414e-06,
1486
+ "loss": 1.2357,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.8617886178861789,
1491
+ "grad_norm": 0.1917145848274231,
1492
+ "learning_rate": 1.4227642276422766e-06,
1493
+ "loss": 1.2572,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.8658536585365854,
1498
+ "grad_norm": 0.19641472399234772,
1499
+ "learning_rate": 1.3821138211382116e-06,
1500
+ "loss": 1.2907,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.8699186991869918,
1505
+ "grad_norm": 0.19125299155712128,
1506
+ "learning_rate": 1.3414634146341465e-06,
1507
+ "loss": 1.2274,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.8739837398373984,
1512
+ "grad_norm": 0.18693210184574127,
1513
+ "learning_rate": 1.3008130081300815e-06,
1514
+ "loss": 1.2848,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.8780487804878049,
1519
+ "grad_norm": 0.1859700083732605,
1520
+ "learning_rate": 1.2601626016260162e-06,
1521
+ "loss": 1.2359,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.8821138211382114,
1526
+ "grad_norm": 0.20786939561367035,
1527
+ "learning_rate": 1.2195121951219514e-06,
1528
+ "loss": 1.2777,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.8861788617886179,
1533
+ "grad_norm": 0.18669180572032928,
1534
+ "learning_rate": 1.1788617886178863e-06,
1535
+ "loss": 1.2823,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.8902439024390244,
1540
+ "grad_norm": 0.2070901244878769,
1541
+ "learning_rate": 1.1382113821138213e-06,
1542
+ "loss": 1.3024,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.8943089430894309,
1547
+ "grad_norm": 0.19596239924430847,
1548
+ "learning_rate": 1.0975609756097562e-06,
1549
+ "loss": 1.2324,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.8983739837398373,
1554
+ "grad_norm": 0.19302377104759216,
1555
+ "learning_rate": 1.0569105691056912e-06,
1556
+ "loss": 1.2666,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.9024390243902439,
1561
+ "grad_norm": 0.19474874436855316,
1562
+ "learning_rate": 1.0162601626016261e-06,
1563
+ "loss": 1.2566,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.9065040650406504,
1568
+ "grad_norm": 0.18354295194149017,
1569
+ "learning_rate": 9.75609756097561e-07,
1570
+ "loss": 1.2615,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.9105691056910569,
1575
+ "grad_norm": 0.19459068775177002,
1576
+ "learning_rate": 9.349593495934959e-07,
1577
+ "loss": 1.2776,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.9146341463414634,
1582
+ "grad_norm": 0.20152311027050018,
1583
+ "learning_rate": 8.94308943089431e-07,
1584
+ "loss": 1.2719,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.9186991869918699,
1589
+ "grad_norm": 0.18795745074748993,
1590
+ "learning_rate": 8.53658536585366e-07,
1591
+ "loss": 1.2685,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.9227642276422764,
1596
+ "grad_norm": 0.1888560950756073,
1597
+ "learning_rate": 8.130081300813009e-07,
1598
+ "loss": 1.2476,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.926829268292683,
1603
+ "grad_norm": 0.189235657453537,
1604
+ "learning_rate": 7.723577235772359e-07,
1605
+ "loss": 1.2692,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.9308943089430894,
1610
+ "grad_norm": 0.17088742554187775,
1611
+ "learning_rate": 7.317073170731707e-07,
1612
+ "loss": 1.2531,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.9349593495934959,
1617
+ "grad_norm": 0.18722310662269592,
1618
+ "learning_rate": 6.910569105691058e-07,
1619
+ "loss": 1.2428,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.9390243902439024,
1624
+ "grad_norm": 0.17706981301307678,
1625
+ "learning_rate": 6.504065040650407e-07,
1626
+ "loss": 1.2566,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.943089430894309,
1631
+ "grad_norm": 0.20467019081115723,
1632
+ "learning_rate": 6.097560975609757e-07,
1633
+ "loss": 1.2928,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.9471544715447154,
1638
+ "grad_norm": 0.17970900237560272,
1639
+ "learning_rate": 5.691056910569106e-07,
1640
+ "loss": 1.2513,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.9512195121951219,
1645
+ "grad_norm": 0.17920483648777008,
1646
+ "learning_rate": 5.284552845528456e-07,
1647
+ "loss": 1.2004,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.9552845528455285,
1652
+ "grad_norm": 0.18399786949157715,
1653
+ "learning_rate": 4.878048780487805e-07,
1654
+ "loss": 1.2692,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.959349593495935,
1659
+ "grad_norm": 0.17873434722423553,
1660
+ "learning_rate": 4.471544715447155e-07,
1661
+ "loss": 1.2468,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.9634146341463414,
1666
+ "grad_norm": 0.18509528040885925,
1667
+ "learning_rate": 4.0650406504065046e-07,
1668
+ "loss": 1.271,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.967479674796748,
1673
+ "grad_norm": 0.19402359426021576,
1674
+ "learning_rate": 3.6585365853658536e-07,
1675
+ "loss": 1.2472,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.9715447154471545,
1680
+ "grad_norm": 0.19081974029541016,
1681
+ "learning_rate": 3.2520325203252037e-07,
1682
+ "loss": 1.2416,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.975609756097561,
1687
+ "grad_norm": 0.17355622351169586,
1688
+ "learning_rate": 2.845528455284553e-07,
1689
+ "loss": 1.2045,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.9796747967479674,
1694
+ "grad_norm": 0.20138268172740936,
1695
+ "learning_rate": 2.439024390243903e-07,
1696
+ "loss": 1.2959,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.983739837398374,
1701
+ "grad_norm": 0.18235686421394348,
1702
+ "learning_rate": 2.0325203252032523e-07,
1703
+ "loss": 1.2448,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.9878048780487805,
1708
+ "grad_norm": 0.17484009265899658,
1709
+ "learning_rate": 1.6260162601626018e-07,
1710
+ "loss": 1.2441,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.991869918699187,
1715
+ "grad_norm": 0.18030861020088196,
1716
+ "learning_rate": 1.2195121951219514e-07,
1717
+ "loss": 1.2433,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.9959349593495935,
1722
+ "grad_norm": 0.1873464286327362,
1723
+ "learning_rate": 8.130081300813009e-08,
1724
+ "loss": 1.2672,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 1.0,
1729
+ "grad_norm": 0.17657622694969177,
1730
+ "learning_rate": 4.0650406504065046e-08,
1731
+ "loss": 1.2245,
1732
+ "step": 246
1733
+ }
1734
+ ],
1735
+ "logging_steps": 1.0,
1736
+ "max_steps": 246,
1737
+ "num_input_tokens_seen": 0,
1738
+ "num_train_epochs": 1,
1739
+ "save_steps": 0,
1740
+ "stateful_callbacks": {
1741
+ "TrainerControl": {
1742
+ "args": {
1743
+ "should_epoch_stop": false,
1744
+ "should_evaluate": false,
1745
+ "should_log": false,
1746
+ "should_save": true,
1747
+ "should_training_stop": true
1748
+ },
1749
+ "attributes": {}
1750
+ }
1751
+ },
1752
+ "total_flos": 8.599595463265485e+16,
1753
+ "train_batch_size": 1,
1754
+ "trial_name": null,
1755
+ "trial_params": null
1756
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff