finalform commited on
Commit
e84bba4
·
verified ·
1 Parent(s): 128ae65

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 32,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "o_proj",
29
+ "gate_proj",
30
+ "k_proj",
31
+ "v_proj",
32
+ "up_proj",
33
+ "down_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 sha256:9ab4de5ee880067b2646f846b6a405e3bcecc1a89061d31654769b653a8f7bfe
3
+ size 335604696
chat_template.jinja ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if messages[0]["role"] == "system" %}
2
+ {%- set system_message = messages[0]["content"] %}
3
+ {%- set loop_messages = messages[1:] %}
4
+ {%- else %}
5
+ {%- set loop_messages = messages %}
6
+ {%- endif %}
7
+ {%- if not tools is defined %}
8
+ {%- set tools = none %}
9
+ {%- endif %}
10
+ {%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
11
+
12
+ {#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
13
+ {%- set ns = namespace() %}
14
+ {%- set ns.index = 0 %}
15
+ {%- for message in loop_messages %}
16
+ {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
17
+ {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
18
+ {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
19
+ {%- endif %}
20
+ {%- set ns.index = ns.index + 1 %}
21
+ {%- endif %}
22
+ {%- endfor %}
23
+
24
+ {{- bos_token }}
25
+ {%- for message in loop_messages %}
26
+ {%- if message["role"] == "user" %}
27
+ {%- if tools is not none and (message == user_messages[-1]) %}
28
+ {{- "[AVAILABLE_TOOLS] [" }}
29
+ {%- for tool in tools %}
30
+ {%- set tool = tool.function %}
31
+ {{- '{"type": "function", "function": {' }}
32
+ {%- for key, val in tool.items() if key != "return" %}
33
+ {%- if val is string %}
34
+ {{- '"' + key + '": "' + val + '"' }}
35
+ {%- else %}
36
+ {{- '"' + key + '": ' + val|tojson }}
37
+ {%- endif %}
38
+ {%- if not loop.last %}
39
+ {{- ", " }}
40
+ {%- endif %}
41
+ {%- endfor %}
42
+ {{- "}}" }}
43
+ {%- if not loop.last %}
44
+ {{- ", " }}
45
+ {%- else %}
46
+ {{- "]" }}
47
+ {%- endif %}
48
+ {%- endfor %}
49
+ {{- "[/AVAILABLE_TOOLS]" }}
50
+ {%- endif %}
51
+ {%- if loop.last and system_message is defined %}
52
+ {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
53
+ {%- else %}
54
+ {{- "[INST] " + message["content"] + "[/INST]" }}
55
+ {%- endif %}
56
+ {%- elif message.tool_calls is defined and message.tool_calls is not none %}
57
+ {{- "[TOOL_CALLS] [" }}
58
+ {%- for tool_call in message.tool_calls %}
59
+ {%- set out = tool_call.function|tojson %}
60
+ {{- out[:-1] }}
61
+ {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
62
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
63
+ {%- endif %}
64
+ {{- ', "id": "' + tool_call.id + '"}' }}
65
+ {%- if not loop.last %}
66
+ {{- ", " }}
67
+ {%- else %}
68
+ {{- "]" + eos_token }}
69
+ {%- endif %}
70
+ {%- endfor %}
71
+ {%- elif message["role"] == "assistant" %}
72
+ {{- " " + message["content"]|trim + eos_token}}
73
+ {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
74
+ {%- if message.content is defined and message.content.content is defined %}
75
+ {%- set content = message.content.content %}
76
+ {%- else %}
77
+ {%- set content = message.content %}
78
+ {%- endif %}
79
+ {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
80
+ {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
81
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
82
+ {%- endif %}
83
+ {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
84
+ {%- else %}
85
+ {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
86
+ {%- endif %}
87
+ {%- endfor %}
checkpoint-1245/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-1245/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 32,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "o_proj",
29
+ "gate_proj",
30
+ "k_proj",
31
+ "v_proj",
32
+ "up_proj",
33
+ "down_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-1245/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab4de5ee880067b2646f846b6a405e3bcecc1a89061d31654769b653a8f7bfe
3
+ size 335604696
checkpoint-1245/chat_template.jinja ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if messages[0]["role"] == "system" %}
2
+ {%- set system_message = messages[0]["content"] %}
3
+ {%- set loop_messages = messages[1:] %}
4
+ {%- else %}
5
+ {%- set loop_messages = messages %}
6
+ {%- endif %}
7
+ {%- if not tools is defined %}
8
+ {%- set tools = none %}
9
+ {%- endif %}
10
+ {%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
11
+
12
+ {#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
13
+ {%- set ns = namespace() %}
14
+ {%- set ns.index = 0 %}
15
+ {%- for message in loop_messages %}
16
+ {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
17
+ {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
18
+ {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
19
+ {%- endif %}
20
+ {%- set ns.index = ns.index + 1 %}
21
+ {%- endif %}
22
+ {%- endfor %}
23
+
24
+ {{- bos_token }}
25
+ {%- for message in loop_messages %}
26
+ {%- if message["role"] == "user" %}
27
+ {%- if tools is not none and (message == user_messages[-1]) %}
28
+ {{- "[AVAILABLE_TOOLS] [" }}
29
+ {%- for tool in tools %}
30
+ {%- set tool = tool.function %}
31
+ {{- '{"type": "function", "function": {' }}
32
+ {%- for key, val in tool.items() if key != "return" %}
33
+ {%- if val is string %}
34
+ {{- '"' + key + '": "' + val + '"' }}
35
+ {%- else %}
36
+ {{- '"' + key + '": ' + val|tojson }}
37
+ {%- endif %}
38
+ {%- if not loop.last %}
39
+ {{- ", " }}
40
+ {%- endif %}
41
+ {%- endfor %}
42
+ {{- "}}" }}
43
+ {%- if not loop.last %}
44
+ {{- ", " }}
45
+ {%- else %}
46
+ {{- "]" }}
47
+ {%- endif %}
48
+ {%- endfor %}
49
+ {{- "[/AVAILABLE_TOOLS]" }}
50
+ {%- endif %}
51
+ {%- if loop.last and system_message is defined %}
52
+ {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
53
+ {%- else %}
54
+ {{- "[INST] " + message["content"] + "[/INST]" }}
55
+ {%- endif %}
56
+ {%- elif message.tool_calls is defined and message.tool_calls is not none %}
57
+ {{- "[TOOL_CALLS] [" }}
58
+ {%- for tool_call in message.tool_calls %}
59
+ {%- set out = tool_call.function|tojson %}
60
+ {{- out[:-1] }}
61
+ {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
62
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
63
+ {%- endif %}
64
+ {{- ', "id": "' + tool_call.id + '"}' }}
65
+ {%- if not loop.last %}
66
+ {{- ", " }}
67
+ {%- else %}
68
+ {{- "]" + eos_token }}
69
+ {%- endif %}
70
+ {%- endfor %}
71
+ {%- elif message["role"] == "assistant" %}
72
+ {{- " " + message["content"]|trim + eos_token}}
73
+ {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
74
+ {%- if message.content is defined and message.content.content is defined %}
75
+ {%- set content = message.content.content %}
76
+ {%- else %}
77
+ {%- set content = message.content %}
78
+ {%- endif %}
79
+ {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
80
+ {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
81
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
82
+ {%- endif %}
83
+ {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
84
+ {%- else %}
85
+ {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
86
+ {%- endif %}
87
+ {%- endfor %}
checkpoint-1245/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddb8b96ff4b013d34824312098c35c25ae487f82ca882df6e967a86e74710c41
3
+ size 671365003
checkpoint-1245/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3facc22bab6b04e596ed724b1b9b557333baba1218d3c203ddc14b61d0749f5f
3
+ size 14645
checkpoint-1245/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82fcd00123c3c69d4e7b09d8e96247aa0926ecb0862a7624726a4095234b5d76
3
+ size 1465
checkpoint-1245/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-1245/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1245/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
checkpoint-1245/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1245/trainer_state.json ADDED
@@ -0,0 +1,475 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1245,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.060350030175015085,
14
+ "grad_norm": 0.6138771176338196,
15
+ "learning_rate": 0.0001894736842105263,
16
+ "loss": 1.3796,
17
+ "mean_token_accuracy": 0.7022829699516296,
18
+ "num_tokens": 154999.0,
19
+ "step": 25
20
+ },
21
+ {
22
+ "epoch": 0.12070006035003017,
23
+ "grad_norm": 0.6403661370277405,
24
+ "learning_rate": 0.00029993852448555923,
25
+ "loss": 0.7408,
26
+ "mean_token_accuracy": 0.8062405365705491,
27
+ "num_tokens": 274882.0,
28
+ "step": 50
29
+ },
30
+ {
31
+ "epoch": 0.18105009052504525,
32
+ "grad_norm": 0.5453419089317322,
33
+ "learning_rate": 0.00029934198818572623,
34
+ "loss": 0.4995,
35
+ "mean_token_accuracy": 0.8602466344833374,
36
+ "num_tokens": 429270.0,
37
+ "step": 75
38
+ },
39
+ {
40
+ "epoch": 0.24140012070006034,
41
+ "grad_norm": 0.9569323062896729,
42
+ "learning_rate": 0.0002981133400718627,
43
+ "loss": 0.3791,
44
+ "mean_token_accuracy": 0.8920469450950622,
45
+ "num_tokens": 547533.0,
46
+ "step": 100
47
+ },
48
+ {
49
+ "epoch": 0.30175015087507545,
50
+ "grad_norm": 0.4823763966560364,
51
+ "learning_rate": 0.0002962577805768642,
52
+ "loss": 0.2865,
53
+ "mean_token_accuracy": 0.919411507844925,
54
+ "num_tokens": 700414.0,
55
+ "step": 125
56
+ },
57
+ {
58
+ "epoch": 0.3621001810500905,
59
+ "grad_norm": 0.5946052670478821,
60
+ "learning_rate": 0.00029378316362776546,
61
+ "loss": 0.3033,
62
+ "mean_token_accuracy": 0.9159089189767837,
63
+ "num_tokens": 818685.0,
64
+ "step": 150
65
+ },
66
+ {
67
+ "epoch": 0.4224502112251056,
68
+ "grad_norm": 0.513756513595581,
69
+ "learning_rate": 0.0002906999634028451,
70
+ "loss": 0.2095,
71
+ "mean_token_accuracy": 0.9410657143592834,
72
+ "num_tokens": 973411.0,
73
+ "step": 175
74
+ },
75
+ {
76
+ "epoch": 0.4828002414001207,
77
+ "grad_norm": 0.5572422742843628,
78
+ "learning_rate": 0.0002870212299981334,
79
+ "loss": 0.1986,
80
+ "mean_token_accuracy": 0.9448752331733704,
81
+ "num_tokens": 1091985.0,
82
+ "step": 200
83
+ },
84
+ {
85
+ "epoch": 0.5431502715751357,
86
+ "grad_norm": 0.3195100724697113,
87
+ "learning_rate": 0.00028276253419097193,
88
+ "loss": 0.1613,
89
+ "mean_token_accuracy": 0.9562808114290238,
90
+ "num_tokens": 1249334.0,
91
+ "step": 225
92
+ },
93
+ {
94
+ "epoch": 0.6035003017501509,
95
+ "grad_norm": 0.8021010756492615,
96
+ "learning_rate": 0.00027794190153442033,
97
+ "loss": 0.161,
98
+ "mean_token_accuracy": 0.9557685399055481,
99
+ "num_tokens": 1367322.0,
100
+ "step": 250
101
+ },
102
+ {
103
+ "epoch": 0.663850331925166,
104
+ "grad_norm": 0.4245581328868866,
105
+ "learning_rate": 0.00027257973606146575,
106
+ "loss": 0.1414,
107
+ "mean_token_accuracy": 0.9619652438163757,
108
+ "num_tokens": 1523489.0,
109
+ "step": 275
110
+ },
111
+ {
112
+ "epoch": 0.724200362100181,
113
+ "grad_norm": 0.7518550157546997,
114
+ "learning_rate": 0.0002666987339219681,
115
+ "loss": 0.1313,
116
+ "mean_token_accuracy": 0.9653391098976135,
117
+ "num_tokens": 1644051.0,
118
+ "step": 300
119
+ },
120
+ {
121
+ "epoch": 0.7845503922751962,
122
+ "grad_norm": 0.5166082978248596,
123
+ "learning_rate": 0.0002603237873178853,
124
+ "loss": 0.1179,
125
+ "mean_token_accuracy": 0.9685099506378174,
126
+ "num_tokens": 1799510.0,
127
+ "step": 325
128
+ },
129
+ {
130
+ "epoch": 0.8449004224502112,
131
+ "grad_norm": 0.8754676580429077,
132
+ "learning_rate": 0.0002534818791433866,
133
+ "loss": 0.1172,
134
+ "mean_token_accuracy": 0.9700138258934021,
135
+ "num_tokens": 1918554.0,
136
+ "step": 350
137
+ },
138
+ {
139
+ "epoch": 0.9052504526252263,
140
+ "grad_norm": 0.5072232484817505,
141
+ "learning_rate": 0.00024620196877580576,
142
+ "loss": 0.1087,
143
+ "mean_token_accuracy": 0.9706882643699646,
144
+ "num_tokens": 2071557.0,
145
+ "step": 375
146
+ },
147
+ {
148
+ "epoch": 0.9656004828002414,
149
+ "grad_norm": 0.44057291746139526,
150
+ "learning_rate": 0.00023851486950083892,
151
+ "loss": 0.1102,
152
+ "mean_token_accuracy": 0.9717801564931869,
153
+ "num_tokens": 2188325.0,
154
+ "step": 400
155
+ },
156
+ {
157
+ "epoch": 1.024140012070006,
158
+ "grad_norm": 0.28425154089927673,
159
+ "learning_rate": 0.00023045311809080567,
160
+ "loss": 0.0969,
161
+ "mean_token_accuracy": 0.9745202402478641,
162
+ "num_tokens": 2335834.0,
163
+ "step": 425
164
+ },
165
+ {
166
+ "epoch": 1.0844900422450212,
167
+ "grad_norm": 0.27836862206459045,
168
+ "learning_rate": 0.00022205083708799942,
169
+ "loss": 0.0775,
170
+ "mean_token_accuracy": 0.9795319002866745,
171
+ "num_tokens": 2475640.0,
172
+ "step": 450
173
+ },
174
+ {
175
+ "epoch": 1.1448400724200363,
176
+ "grad_norm": 0.25006264448165894,
177
+ "learning_rate": 0.0002133435903760353,
178
+ "loss": 0.0926,
179
+ "mean_token_accuracy": 0.9758930206298828,
180
+ "num_tokens": 2613115.0,
181
+ "step": 475
182
+ },
183
+ {
184
+ "epoch": 1.2051901025950513,
185
+ "grad_norm": 0.3176310658454895,
186
+ "learning_rate": 0.0002043682326505094,
187
+ "loss": 0.0687,
188
+ "mean_token_accuracy": 0.9820343238115311,
189
+ "num_tokens": 2749269.0,
190
+ "step": 500
191
+ },
192
+ {
193
+ "epoch": 1.2655401327700664,
194
+ "grad_norm": 0.20867092907428741,
195
+ "learning_rate": 0.000195162753426108,
196
+ "loss": 0.0877,
197
+ "mean_token_accuracy": 0.9773262399435043,
198
+ "num_tokens": 2883349.0,
199
+ "step": 525
200
+ },
201
+ {
202
+ "epoch": 1.3258901629450814,
203
+ "grad_norm": 0.25837627053260803,
204
+ "learning_rate": 0.00018576611624042852,
205
+ "loss": 0.0674,
206
+ "mean_token_accuracy": 0.9824212837219238,
207
+ "num_tokens": 3020654.0,
208
+ "step": 550
209
+ },
210
+ {
211
+ "epoch": 1.3862401931200965,
212
+ "grad_norm": 0.1842041015625,
213
+ "learning_rate": 0.00017621809373510641,
214
+ "loss": 0.0819,
215
+ "mean_token_accuracy": 0.979530062675476,
216
+ "num_tokens": 3157335.0,
217
+ "step": 575
218
+ },
219
+ {
220
+ "epoch": 1.4465902232951118,
221
+ "grad_norm": 0.2597507834434509,
222
+ "learning_rate": 0.00016655909931229048,
223
+ "loss": 0.0659,
224
+ "mean_token_accuracy": 0.9828319466114044,
225
+ "num_tokens": 3294681.0,
226
+ "step": 600
227
+ },
228
+ {
229
+ "epoch": 1.5069402534701268,
230
+ "grad_norm": 0.17711229622364044,
231
+ "learning_rate": 0.00015683001607900553,
232
+ "loss": 0.0842,
233
+ "mean_token_accuracy": 0.978652862906456,
234
+ "num_tokens": 3430142.0,
235
+ "step": 625
236
+ },
237
+ {
238
+ "epoch": 1.567290283645142,
239
+ "grad_norm": 0.13509850203990936,
240
+ "learning_rate": 0.00014707202380342108,
241
+ "loss": 0.0573,
242
+ "mean_token_accuracy": 0.9850119787454605,
243
+ "num_tokens": 3567792.0,
244
+ "step": 650
245
+ },
246
+ {
247
+ "epoch": 1.627640313820157,
248
+ "grad_norm": 0.14440615475177765,
249
+ "learning_rate": 0.00013732642461545747,
250
+ "loss": 0.0758,
251
+ "mean_token_accuracy": 0.9804488325119018,
252
+ "num_tokens": 3703772.0,
253
+ "step": 675
254
+ },
255
+ {
256
+ "epoch": 1.687990343995172,
257
+ "grad_norm": 0.12784038484096527,
258
+ "learning_rate": 0.00012763446818947865,
259
+ "loss": 0.0557,
260
+ "mean_token_accuracy": 0.9857299762964249,
261
+ "num_tokens": 3841338.0,
262
+ "step": 700
263
+ },
264
+ {
265
+ "epoch": 1.748340374170187,
266
+ "grad_norm": 0.1049482449889183,
267
+ "learning_rate": 0.00011803717714901029,
268
+ "loss": 0.0692,
269
+ "mean_token_accuracy": 0.9823172944784164,
270
+ "num_tokens": 3976256.0,
271
+ "step": 725
272
+ },
273
+ {
274
+ "epoch": 1.8086904043452021,
275
+ "grad_norm": 0.1479799747467041,
276
+ "learning_rate": 0.00010857517343248423,
277
+ "loss": 0.0544,
278
+ "mean_token_accuracy": 0.9862035536766052,
279
+ "num_tokens": 4113650.0,
280
+ "step": 750
281
+ },
282
+ {
283
+ "epoch": 1.8690404345202172,
284
+ "grad_norm": 0.10535310953855515,
285
+ "learning_rate": 9.9288506354941e-05,
286
+ "loss": 0.0688,
287
+ "mean_token_accuracy": 0.9820931887626648,
288
+ "num_tokens": 4250788.0,
289
+ "step": 775
290
+ },
291
+ {
292
+ "epoch": 1.9293904646952322,
293
+ "grad_norm": 0.1969379335641861,
294
+ "learning_rate": 9.021648309344443e-05,
295
+ "loss": 0.0523,
296
+ "mean_token_accuracy": 0.9861829555034638,
297
+ "num_tokens": 4388884.0,
298
+ "step": 800
299
+ },
300
+ {
301
+ "epoch": 1.9897404948702473,
302
+ "grad_norm": 0.19566108286380768,
303
+ "learning_rate": 8.139750231370407e-05,
304
+ "loss": 0.0589,
305
+ "mean_token_accuracy": 0.9854754799604416,
306
+ "num_tokens": 4513974.0,
307
+ "step": 825
308
+ },
309
+ {
310
+ "epoch": 2.048280024140012,
311
+ "grad_norm": 0.08709706366062164,
312
+ "learning_rate": 7.28688916421049e-05,
313
+ "loss": 0.0557,
314
+ "mean_token_accuracy": 0.9854855641876299,
315
+ "num_tokens": 4657894.0,
316
+ "step": 850
317
+ },
318
+ {
319
+ "epoch": 2.1086300543150274,
320
+ "grad_norm": 0.32135921716690063,
321
+ "learning_rate": 6.466674967106751e-05,
322
+ "loss": 0.046,
323
+ "mean_token_accuracy": 0.9884958410263062,
324
+ "num_tokens": 4783309.0,
325
+ "step": 875
326
+ },
327
+ {
328
+ "epoch": 2.1689800844900424,
329
+ "grad_norm": 0.10706797987222672,
330
+ "learning_rate": 5.682579316647408e-05,
331
+ "loss": 0.0512,
332
+ "mean_token_accuracy": 0.9862526476383209,
333
+ "num_tokens": 4931681.0,
334
+ "step": 900
335
+ },
336
+ {
337
+ "epoch": 2.2293301146650575,
338
+ "grad_norm": 0.06649629771709442,
339
+ "learning_rate": 4.937921012387816e-05,
340
+ "loss": 0.0452,
341
+ "mean_token_accuracy": 0.9884600782394409,
342
+ "num_tokens": 5059261.0,
343
+ "step": 925
344
+ },
345
+ {
346
+ "epoch": 2.2896801448400725,
347
+ "grad_norm": 0.0824085995554924,
348
+ "learning_rate": 4.235851929545771e-05,
349
+ "loss": 0.0517,
350
+ "mean_token_accuracy": 0.9863192504644394,
351
+ "num_tokens": 5208555.0,
352
+ "step": 950
353
+ },
354
+ {
355
+ "epoch": 2.3500301750150876,
356
+ "grad_norm": 0.06256023794412613,
357
+ "learning_rate": 3.579343678228525e-05,
358
+ "loss": 0.0454,
359
+ "mean_token_accuracy": 0.9885574287176132,
360
+ "num_tokens": 5335514.0,
361
+ "step": 975
362
+ },
363
+ {
364
+ "epoch": 2.4103802051901027,
365
+ "grad_norm": 0.06850145757198334,
366
+ "learning_rate": 2.9711750256582538e-05,
367
+ "loss": 0.0525,
368
+ "mean_token_accuracy": 0.9856393277645111,
369
+ "num_tokens": 5486306.0,
370
+ "step": 1000
371
+ },
372
+ {
373
+ "epoch": 2.4707302353651177,
374
+ "grad_norm": 0.09066502004861832,
375
+ "learning_rate": 2.413920134633272e-05,
376
+ "loss": 0.045,
377
+ "mean_token_accuracy": 0.9883674955368043,
378
+ "num_tokens": 5612848.0,
379
+ "step": 1025
380
+ },
381
+ {
382
+ "epoch": 2.5310802655401328,
383
+ "grad_norm": 0.050995565950870514,
384
+ "learning_rate": 1.909937668007352e-05,
385
+ "loss": 0.0456,
386
+ "mean_token_accuracy": 0.9880671769380569,
387
+ "num_tokens": 5757364.0,
388
+ "step": 1050
389
+ },
390
+ {
391
+ "epoch": 2.591430295715148,
392
+ "grad_norm": 0.07163764536380768,
393
+ "learning_rate": 1.461360805304146e-05,
394
+ "loss": 0.0452,
395
+ "mean_token_accuracy": 0.9885901701450348,
396
+ "num_tokens": 5881265.0,
397
+ "step": 1075
398
+ },
399
+ {
400
+ "epoch": 2.651780325890163,
401
+ "grad_norm": 0.09139364957809448,
402
+ "learning_rate": 1.0700882137227434e-05,
403
+ "loss": 0.0479,
404
+ "mean_token_accuracy": 0.9873688906431198,
405
+ "num_tokens": 6030295.0,
406
+ "step": 1100
407
+ },
408
+ {
409
+ "epoch": 2.712130356065178,
410
+ "grad_norm": 0.10289441794157028,
411
+ "learning_rate": 7.377760117509834e-06,
412
+ "loss": 0.045,
413
+ "mean_token_accuracy": 0.9884589624404907,
414
+ "num_tokens": 6157143.0,
415
+ "step": 1125
416
+ },
417
+ {
418
+ "epoch": 2.772480386240193,
419
+ "grad_norm": 0.09236230701208115,
420
+ "learning_rate": 4.65830759401658e-06,
421
+ "loss": 0.046,
422
+ "mean_token_accuracy": 0.9879369300603866,
423
+ "num_tokens": 6303352.0,
424
+ "step": 1150
425
+ },
426
+ {
427
+ "epoch": 2.832830416415208,
428
+ "grad_norm": 0.04650961980223656,
429
+ "learning_rate": 2.554035047414732e-06,
430
+ "loss": 0.0444,
431
+ "mean_token_accuracy": 0.9887312567234039,
432
+ "num_tokens": 6428751.0,
433
+ "step": 1175
434
+ },
435
+ {
436
+ "epoch": 2.8931804465902236,
437
+ "grad_norm": 0.08433457463979721,
438
+ "learning_rate": 1.0738491191171372e-06,
439
+ "loss": 0.0458,
440
+ "mean_token_accuracy": 0.9878807801008225,
441
+ "num_tokens": 6576081.0,
442
+ "step": 1200
443
+ },
444
+ {
445
+ "epoch": 2.9535304767652386,
446
+ "grad_norm": 0.08487927168607712,
447
+ "learning_rate": 2.2401491261947456e-07,
448
+ "loss": 0.0428,
449
+ "mean_token_accuracy": 0.9895708286762237,
450
+ "num_tokens": 6701527.0,
451
+ "step": 1225
452
+ }
453
+ ],
454
+ "logging_steps": 25,
455
+ "max_steps": 1245,
456
+ "num_input_tokens_seen": 0,
457
+ "num_train_epochs": 3,
458
+ "save_steps": 750,
459
+ "stateful_callbacks": {
460
+ "TrainerControl": {
461
+ "args": {
462
+ "should_epoch_stop": false,
463
+ "should_evaluate": false,
464
+ "should_log": false,
465
+ "should_save": true,
466
+ "should_training_stop": true
467
+ },
468
+ "attributes": {}
469
+ }
470
+ },
471
+ "total_flos": 2.939824705454408e+17,
472
+ "train_batch_size": 2,
473
+ "trial_name": null,
474
+ "trial_params": null
475
+ }
checkpoint-1245/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1368312d6171cb3228a4505daeeebb2d50b85fd42516b8b22d1d350ef88234fe
3
+ size 6033
checkpoint-750/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-750/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 32,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "o_proj",
29
+ "gate_proj",
30
+ "k_proj",
31
+ "v_proj",
32
+ "up_proj",
33
+ "down_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-750/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d870137ccac6c8de0f64e8c5bc8962876a97b95e3dbed260d6598aad56474197
3
+ size 335604696
checkpoint-750/chat_template.jinja ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if messages[0]["role"] == "system" %}
2
+ {%- set system_message = messages[0]["content"] %}
3
+ {%- set loop_messages = messages[1:] %}
4
+ {%- else %}
5
+ {%- set loop_messages = messages %}
6
+ {%- endif %}
7
+ {%- if not tools is defined %}
8
+ {%- set tools = none %}
9
+ {%- endif %}
10
+ {%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
11
+
12
+ {#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
13
+ {%- set ns = namespace() %}
14
+ {%- set ns.index = 0 %}
15
+ {%- for message in loop_messages %}
16
+ {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
17
+ {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
18
+ {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
19
+ {%- endif %}
20
+ {%- set ns.index = ns.index + 1 %}
21
+ {%- endif %}
22
+ {%- endfor %}
23
+
24
+ {{- bos_token }}
25
+ {%- for message in loop_messages %}
26
+ {%- if message["role"] == "user" %}
27
+ {%- if tools is not none and (message == user_messages[-1]) %}
28
+ {{- "[AVAILABLE_TOOLS] [" }}
29
+ {%- for tool in tools %}
30
+ {%- set tool = tool.function %}
31
+ {{- '{"type": "function", "function": {' }}
32
+ {%- for key, val in tool.items() if key != "return" %}
33
+ {%- if val is string %}
34
+ {{- '"' + key + '": "' + val + '"' }}
35
+ {%- else %}
36
+ {{- '"' + key + '": ' + val|tojson }}
37
+ {%- endif %}
38
+ {%- if not loop.last %}
39
+ {{- ", " }}
40
+ {%- endif %}
41
+ {%- endfor %}
42
+ {{- "}}" }}
43
+ {%- if not loop.last %}
44
+ {{- ", " }}
45
+ {%- else %}
46
+ {{- "]" }}
47
+ {%- endif %}
48
+ {%- endfor %}
49
+ {{- "[/AVAILABLE_TOOLS]" }}
50
+ {%- endif %}
51
+ {%- if loop.last and system_message is defined %}
52
+ {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
53
+ {%- else %}
54
+ {{- "[INST] " + message["content"] + "[/INST]" }}
55
+ {%- endif %}
56
+ {%- elif message.tool_calls is defined and message.tool_calls is not none %}
57
+ {{- "[TOOL_CALLS] [" }}
58
+ {%- for tool_call in message.tool_calls %}
59
+ {%- set out = tool_call.function|tojson %}
60
+ {{- out[:-1] }}
61
+ {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
62
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
63
+ {%- endif %}
64
+ {{- ', "id": "' + tool_call.id + '"}' }}
65
+ {%- if not loop.last %}
66
+ {{- ", " }}
67
+ {%- else %}
68
+ {{- "]" + eos_token }}
69
+ {%- endif %}
70
+ {%- endfor %}
71
+ {%- elif message["role"] == "assistant" %}
72
+ {{- " " + message["content"]|trim + eos_token}}
73
+ {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
74
+ {%- if message.content is defined and message.content.content is defined %}
75
+ {%- set content = message.content.content %}
76
+ {%- else %}
77
+ {%- set content = message.content %}
78
+ {%- endif %}
79
+ {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
80
+ {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
81
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
82
+ {%- endif %}
83
+ {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
84
+ {%- else %}
85
+ {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
86
+ {%- endif %}
87
+ {%- endfor %}
checkpoint-750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9711e9a9237a5ea3d281502d928c0c0e1a4eff82b30a36579b6054b27a09f663
3
+ size 671365003
checkpoint-750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52543053744232d5775de24d3a7d074c700cbe44021221a4d6aa3d0848f1397
3
+ size 14645
checkpoint-750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f219c746dd03301eb7ed441bdaf27ac17211dfd9896a46898ad0379f606de1bf
3
+ size 1465
checkpoint-750/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-750/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-750/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
checkpoint-750/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-750/trainer_state.json ADDED
@@ -0,0 +1,304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.8086904043452021,
6
+ "eval_steps": 500,
7
+ "global_step": 750,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.060350030175015085,
14
+ "grad_norm": 0.6138771176338196,
15
+ "learning_rate": 0.0001894736842105263,
16
+ "loss": 1.3796,
17
+ "mean_token_accuracy": 0.7022829699516296,
18
+ "num_tokens": 154999.0,
19
+ "step": 25
20
+ },
21
+ {
22
+ "epoch": 0.12070006035003017,
23
+ "grad_norm": 0.6403661370277405,
24
+ "learning_rate": 0.00029993852448555923,
25
+ "loss": 0.7408,
26
+ "mean_token_accuracy": 0.8062405365705491,
27
+ "num_tokens": 274882.0,
28
+ "step": 50
29
+ },
30
+ {
31
+ "epoch": 0.18105009052504525,
32
+ "grad_norm": 0.5453419089317322,
33
+ "learning_rate": 0.00029934198818572623,
34
+ "loss": 0.4995,
35
+ "mean_token_accuracy": 0.8602466344833374,
36
+ "num_tokens": 429270.0,
37
+ "step": 75
38
+ },
39
+ {
40
+ "epoch": 0.24140012070006034,
41
+ "grad_norm": 0.9569323062896729,
42
+ "learning_rate": 0.0002981133400718627,
43
+ "loss": 0.3791,
44
+ "mean_token_accuracy": 0.8920469450950622,
45
+ "num_tokens": 547533.0,
46
+ "step": 100
47
+ },
48
+ {
49
+ "epoch": 0.30175015087507545,
50
+ "grad_norm": 0.4823763966560364,
51
+ "learning_rate": 0.0002962577805768642,
52
+ "loss": 0.2865,
53
+ "mean_token_accuracy": 0.919411507844925,
54
+ "num_tokens": 700414.0,
55
+ "step": 125
56
+ },
57
+ {
58
+ "epoch": 0.3621001810500905,
59
+ "grad_norm": 0.5946052670478821,
60
+ "learning_rate": 0.00029378316362776546,
61
+ "loss": 0.3033,
62
+ "mean_token_accuracy": 0.9159089189767837,
63
+ "num_tokens": 818685.0,
64
+ "step": 150
65
+ },
66
+ {
67
+ "epoch": 0.4224502112251056,
68
+ "grad_norm": 0.513756513595581,
69
+ "learning_rate": 0.0002906999634028451,
70
+ "loss": 0.2095,
71
+ "mean_token_accuracy": 0.9410657143592834,
72
+ "num_tokens": 973411.0,
73
+ "step": 175
74
+ },
75
+ {
76
+ "epoch": 0.4828002414001207,
77
+ "grad_norm": 0.5572422742843628,
78
+ "learning_rate": 0.0002870212299981334,
79
+ "loss": 0.1986,
80
+ "mean_token_accuracy": 0.9448752331733704,
81
+ "num_tokens": 1091985.0,
82
+ "step": 200
83
+ },
84
+ {
85
+ "epoch": 0.5431502715751357,
86
+ "grad_norm": 0.3195100724697113,
87
+ "learning_rate": 0.00028276253419097193,
88
+ "loss": 0.1613,
89
+ "mean_token_accuracy": 0.9562808114290238,
90
+ "num_tokens": 1249334.0,
91
+ "step": 225
92
+ },
93
+ {
94
+ "epoch": 0.6035003017501509,
95
+ "grad_norm": 0.8021010756492615,
96
+ "learning_rate": 0.00027794190153442033,
97
+ "loss": 0.161,
98
+ "mean_token_accuracy": 0.9557685399055481,
99
+ "num_tokens": 1367322.0,
100
+ "step": 250
101
+ },
102
+ {
103
+ "epoch": 0.663850331925166,
104
+ "grad_norm": 0.4245581328868866,
105
+ "learning_rate": 0.00027257973606146575,
106
+ "loss": 0.1414,
107
+ "mean_token_accuracy": 0.9619652438163757,
108
+ "num_tokens": 1523489.0,
109
+ "step": 275
110
+ },
111
+ {
112
+ "epoch": 0.724200362100181,
113
+ "grad_norm": 0.7518550157546997,
114
+ "learning_rate": 0.0002666987339219681,
115
+ "loss": 0.1313,
116
+ "mean_token_accuracy": 0.9653391098976135,
117
+ "num_tokens": 1644051.0,
118
+ "step": 300
119
+ },
120
+ {
121
+ "epoch": 0.7845503922751962,
122
+ "grad_norm": 0.5166082978248596,
123
+ "learning_rate": 0.0002603237873178853,
124
+ "loss": 0.1179,
125
+ "mean_token_accuracy": 0.9685099506378174,
126
+ "num_tokens": 1799510.0,
127
+ "step": 325
128
+ },
129
+ {
130
+ "epoch": 0.8449004224502112,
131
+ "grad_norm": 0.8754676580429077,
132
+ "learning_rate": 0.0002534818791433866,
133
+ "loss": 0.1172,
134
+ "mean_token_accuracy": 0.9700138258934021,
135
+ "num_tokens": 1918554.0,
136
+ "step": 350
137
+ },
138
+ {
139
+ "epoch": 0.9052504526252263,
140
+ "grad_norm": 0.5072232484817505,
141
+ "learning_rate": 0.00024620196877580576,
142
+ "loss": 0.1087,
143
+ "mean_token_accuracy": 0.9706882643699646,
144
+ "num_tokens": 2071557.0,
145
+ "step": 375
146
+ },
147
+ {
148
+ "epoch": 0.9656004828002414,
149
+ "grad_norm": 0.44057291746139526,
150
+ "learning_rate": 0.00023851486950083892,
151
+ "loss": 0.1102,
152
+ "mean_token_accuracy": 0.9717801564931869,
153
+ "num_tokens": 2188325.0,
154
+ "step": 400
155
+ },
156
+ {
157
+ "epoch": 1.024140012070006,
158
+ "grad_norm": 0.28425154089927673,
159
+ "learning_rate": 0.00023045311809080567,
160
+ "loss": 0.0969,
161
+ "mean_token_accuracy": 0.9745202402478641,
162
+ "num_tokens": 2335834.0,
163
+ "step": 425
164
+ },
165
+ {
166
+ "epoch": 1.0844900422450212,
167
+ "grad_norm": 0.27836862206459045,
168
+ "learning_rate": 0.00022205083708799942,
169
+ "loss": 0.0775,
170
+ "mean_token_accuracy": 0.9795319002866745,
171
+ "num_tokens": 2475640.0,
172
+ "step": 450
173
+ },
174
+ {
175
+ "epoch": 1.1448400724200363,
176
+ "grad_norm": 0.25006264448165894,
177
+ "learning_rate": 0.0002133435903760353,
178
+ "loss": 0.0926,
179
+ "mean_token_accuracy": 0.9758930206298828,
180
+ "num_tokens": 2613115.0,
181
+ "step": 475
182
+ },
183
+ {
184
+ "epoch": 1.2051901025950513,
185
+ "grad_norm": 0.3176310658454895,
186
+ "learning_rate": 0.0002043682326505094,
187
+ "loss": 0.0687,
188
+ "mean_token_accuracy": 0.9820343238115311,
189
+ "num_tokens": 2749269.0,
190
+ "step": 500
191
+ },
192
+ {
193
+ "epoch": 1.2655401327700664,
194
+ "grad_norm": 0.20867092907428741,
195
+ "learning_rate": 0.000195162753426108,
196
+ "loss": 0.0877,
197
+ "mean_token_accuracy": 0.9773262399435043,
198
+ "num_tokens": 2883349.0,
199
+ "step": 525
200
+ },
201
+ {
202
+ "epoch": 1.3258901629450814,
203
+ "grad_norm": 0.25837627053260803,
204
+ "learning_rate": 0.00018576611624042852,
205
+ "loss": 0.0674,
206
+ "mean_token_accuracy": 0.9824212837219238,
207
+ "num_tokens": 3020654.0,
208
+ "step": 550
209
+ },
210
+ {
211
+ "epoch": 1.3862401931200965,
212
+ "grad_norm": 0.1842041015625,
213
+ "learning_rate": 0.00017621809373510641,
214
+ "loss": 0.0819,
215
+ "mean_token_accuracy": 0.979530062675476,
216
+ "num_tokens": 3157335.0,
217
+ "step": 575
218
+ },
219
+ {
220
+ "epoch": 1.4465902232951118,
221
+ "grad_norm": 0.2597507834434509,
222
+ "learning_rate": 0.00016655909931229048,
223
+ "loss": 0.0659,
224
+ "mean_token_accuracy": 0.9828319466114044,
225
+ "num_tokens": 3294681.0,
226
+ "step": 600
227
+ },
228
+ {
229
+ "epoch": 1.5069402534701268,
230
+ "grad_norm": 0.17711229622364044,
231
+ "learning_rate": 0.00015683001607900553,
232
+ "loss": 0.0842,
233
+ "mean_token_accuracy": 0.978652862906456,
234
+ "num_tokens": 3430142.0,
235
+ "step": 625
236
+ },
237
+ {
238
+ "epoch": 1.567290283645142,
239
+ "grad_norm": 0.13509850203990936,
240
+ "learning_rate": 0.00014707202380342108,
241
+ "loss": 0.0573,
242
+ "mean_token_accuracy": 0.9850119787454605,
243
+ "num_tokens": 3567792.0,
244
+ "step": 650
245
+ },
246
+ {
247
+ "epoch": 1.627640313820157,
248
+ "grad_norm": 0.14440615475177765,
249
+ "learning_rate": 0.00013732642461545747,
250
+ "loss": 0.0758,
251
+ "mean_token_accuracy": 0.9804488325119018,
252
+ "num_tokens": 3703772.0,
253
+ "step": 675
254
+ },
255
+ {
256
+ "epoch": 1.687990343995172,
257
+ "grad_norm": 0.12784038484096527,
258
+ "learning_rate": 0.00012763446818947865,
259
+ "loss": 0.0557,
260
+ "mean_token_accuracy": 0.9857299762964249,
261
+ "num_tokens": 3841338.0,
262
+ "step": 700
263
+ },
264
+ {
265
+ "epoch": 1.748340374170187,
266
+ "grad_norm": 0.1049482449889183,
267
+ "learning_rate": 0.00011803717714901029,
268
+ "loss": 0.0692,
269
+ "mean_token_accuracy": 0.9823172944784164,
270
+ "num_tokens": 3976256.0,
271
+ "step": 725
272
+ },
273
+ {
274
+ "epoch": 1.8086904043452021,
275
+ "grad_norm": 0.1479799747467041,
276
+ "learning_rate": 0.00010857517343248423,
277
+ "loss": 0.0544,
278
+ "mean_token_accuracy": 0.9862035536766052,
279
+ "num_tokens": 4113650.0,
280
+ "step": 750
281
+ }
282
+ ],
283
+ "logging_steps": 25,
284
+ "max_steps": 1245,
285
+ "num_input_tokens_seen": 0,
286
+ "num_train_epochs": 3,
287
+ "save_steps": 750,
288
+ "stateful_callbacks": {
289
+ "TrainerControl": {
290
+ "args": {
291
+ "should_epoch_stop": false,
292
+ "should_evaluate": false,
293
+ "should_log": false,
294
+ "should_save": true,
295
+ "should_training_stop": false
296
+ },
297
+ "attributes": {}
298
+ }
299
+ },
300
+ "total_flos": 1.7789373371643494e+17,
301
+ "train_batch_size": 2,
302
+ "trial_name": null,
303
+ "trial_params": null
304
+ }
checkpoint-750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1368312d6171cb3228a4505daeeebb2d50b85fd42516b8b22d1d350ef88234fe
3
+ size 6033
runs/Aug02_22-56-09_pan/events.out.tfevents.1754189772.pan.127259.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3cd70e873a942806a29b53e5069f8434ef71e895d0771252dfbc930c9453719
3
+ size 22431
runs/Aug02_22-56-09_pan/events.out.tfevents.1754193848.pan.127259.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67deb6ac5c20f246c35d8ee9601f9c6654e639534d0d887bedd09a51b2fb6e4c
3
+ size 478
runs/Aug03_00-04-52_pan/events.out.tfevents.1754193954.pan.130463.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df7e1a1a26e572543fc2a8c48cae25d54fd4184663305b7551ba6061b6487f9b
3
+ size 473
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff