openpql commited on
Commit
4057342
·
verified ·
1 Parent(s): bfec813

Upload nishka-base-model-v1 - Stage 2: PQL code generation (10,038 examples, 99.3% loss reduction)

Browse files
README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-4k-instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:microsoft/Phi-3-mini-4k-instruct
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.0
adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v_proj",
33
+ "k_proj",
34
+ "o_proj",
35
+ "down_proj",
36
+ "up_proj",
37
+ "gate_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7841eb0730a6387ec528d5537ed2175514da9fc2dc2ea6c6fc166ab9c2ea72e
3
+ size 71320216
chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>
2
+ ' + message['content'] + '<|end|>
3
+ '}}{% elif message['role'] == 'user' %}{{'<|user|>
4
+ ' + message['content'] + '<|end|>
5
+ '}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
6
+ ' + message['content'] + '<|end|>
7
+ '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
8
+ ' }}{% else %}{{ eos_token }}{% endif %}
checkpoint-1000/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-4k-instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:microsoft/Phi-3-mini-4k-instruct
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.0
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v_proj",
33
+ "k_proj",
34
+ "o_proj",
35
+ "down_proj",
36
+ "up_proj",
37
+ "gate_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoint-1000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e8064320b428eca165019a0bfeef0a40d8f9525834d4dbc21195bdc540c9ab9
3
+ size 71320216
checkpoint-1000/chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>
2
+ ' + message['content'] + '<|end|>
3
+ '}}{% elif message['role'] == 'user' %}{{'<|user|>
4
+ ' + message['content'] + '<|end|>
5
+ '}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
6
+ ' + message['content'] + '<|end|>
7
+ '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
8
+ ' }}{% else %}{{ eos_token }}{% endif %}
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9361823b38b6bac577a234b53bce408a5f5336110168dc0186d2981b38646326
3
+ size 36361850
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44ad2edfc022232d7559482a4f9f63f72d6f3103b63747b20b16cf10331846f3
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6601cd067fdcef15ed2bcfc38e28e0f41a0eb7ffd9977b1eec7b9ed404e56ff7
3
+ size 1064
checkpoint-1000/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": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "extra_special_tokens": {},
123
+ "legacy": false,
124
+ "max_length": 2048,
125
+ "model_max_length": 4096,
126
+ "pad_token": "<|endoftext|>",
127
+ "padding_side": "right",
128
+ "sp_model_kwargs": {},
129
+ "stride": 0,
130
+ "tokenizer_class": "LlamaTokenizerFast",
131
+ "truncation_side": "right",
132
+ "truncation_strategy": "longest_first",
133
+ "unk_token": "<unk>",
134
+ "use_default_system_prompt": false
135
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.5929468021518232,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01593943016537159,
14
+ "grad_norm": 0.12403535097837448,
15
+ "learning_rate": 1.8e-05,
16
+ "loss": 1.1133,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.03187886033074318,
21
+ "grad_norm": 0.21290278434753418,
22
+ "learning_rate": 3.8e-05,
23
+ "loss": 1.0413,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.04781829049611477,
28
+ "grad_norm": 0.1645481288433075,
29
+ "learning_rate": 5.8e-05,
30
+ "loss": 0.9616,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.06375772066148636,
35
+ "grad_norm": 0.2903112471103668,
36
+ "learning_rate": 7.800000000000001e-05,
37
+ "loss": 0.874,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.07969715082685794,
42
+ "grad_norm": 0.2749190628528595,
43
+ "learning_rate": 9.8e-05,
44
+ "loss": 0.7337,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.09563658099222953,
49
+ "grad_norm": 0.4625573754310608,
50
+ "learning_rate": 9.99862592554908e-05,
51
+ "loss": 0.5768,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.11157601115760112,
56
+ "grad_norm": 0.31431907415390015,
57
+ "learning_rate": 9.993877008154289e-05,
58
+ "loss": 0.4941,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.1275154413229727,
63
+ "grad_norm": 0.43303918838500977,
64
+ "learning_rate": 9.985739505534436e-05,
65
+ "loss": 0.3854,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1434548714883443,
70
+ "grad_norm": 0.5850837826728821,
71
+ "learning_rate": 9.974218939375599e-05,
72
+ "loss": 0.2906,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.15939430165371588,
77
+ "grad_norm": 0.4940532147884369,
78
+ "learning_rate": 9.959323126934831e-05,
79
+ "loss": 0.2056,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.17533373181908746,
84
+ "grad_norm": 0.3987452983856201,
85
+ "learning_rate": 9.94106217573578e-05,
86
+ "loss": 0.1315,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.19127316198445907,
91
+ "grad_norm": 0.42741864919662476,
92
+ "learning_rate": 9.919448476710246e-05,
93
+ "loss": 0.0859,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.20721259214983065,
98
+ "grad_norm": 0.24628710746765137,
99
+ "learning_rate": 9.894496695790344e-05,
100
+ "loss": 0.0663,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.22315202231520223,
105
+ "grad_norm": 0.2623507082462311,
106
+ "learning_rate": 9.866223763956955e-05,
107
+ "loss": 0.0447,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.2390914524805738,
112
+ "grad_norm": 0.14876964688301086,
113
+ "learning_rate": 9.834648865751254e-05,
114
+ "loss": 0.0372,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.2550308826459454,
119
+ "grad_norm": 0.1500687152147293,
120
+ "learning_rate": 9.799793426257071e-05,
121
+ "loss": 0.0356,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.270970312811317,
126
+ "grad_norm": 0.16156131029129028,
127
+ "learning_rate": 9.76168109656295e-05,
128
+ "loss": 0.0293,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.2869097429766886,
133
+ "grad_norm": 0.20239904522895813,
134
+ "learning_rate": 9.720337737713739e-05,
135
+ "loss": 0.025,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.30284917314206017,
140
+ "grad_norm": 0.10117224603891373,
141
+ "learning_rate": 9.675791403162645e-05,
142
+ "loss": 0.0209,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.31878860330743175,
147
+ "grad_norm": 0.3235134482383728,
148
+ "learning_rate": 9.628072319735607e-05,
149
+ "loss": 0.0247,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.33472803347280333,
154
+ "grad_norm": 0.10946714133024216,
155
+ "learning_rate": 9.577212867120947e-05,
156
+ "loss": 0.0213,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.3506674636381749,
161
+ "grad_norm": 0.08509603142738342,
162
+ "learning_rate": 9.523247555898204e-05,
163
+ "loss": 0.0178,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.3666068938035465,
168
+ "grad_norm": 0.07975362986326218,
169
+ "learning_rate": 9.466213004121041e-05,
170
+ "loss": 0.016,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.38254632396891813,
175
+ "grad_norm": 0.061933811753988266,
176
+ "learning_rate": 9.406147912470143e-05,
177
+ "loss": 0.0143,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.3984857541342897,
182
+ "grad_norm": 0.22777368128299713,
183
+ "learning_rate": 9.343093037992945e-05,
184
+ "loss": 0.0294,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.4144251842996613,
189
+ "grad_norm": 0.11101654917001724,
190
+ "learning_rate": 9.277091166448022e-05,
191
+ "loss": 0.0159,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.4303646144650329,
196
+ "grad_norm": 0.27989494800567627,
197
+ "learning_rate": 9.208187083272894e-05,
198
+ "loss": 0.0169,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.44630404463040446,
203
+ "grad_norm": 0.07749247550964355,
204
+ "learning_rate": 9.136427543194967e-05,
205
+ "loss": 0.017,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.46224347479577604,
210
+ "grad_norm": 0.14141874015331268,
211
+ "learning_rate": 9.061861238506194e-05,
212
+ "loss": 0.0152,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.4781829049611476,
217
+ "grad_norm": 0.09233926236629486,
218
+ "learning_rate": 8.984538766023024e-05,
219
+ "loss": 0.0148,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.4941223351265192,
224
+ "grad_norm": 0.08206266909837723,
225
+ "learning_rate": 8.904512592754034e-05,
226
+ "loss": 0.013,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.5100617652918908,
231
+ "grad_norm": 0.09603980928659439,
232
+ "learning_rate": 8.821837020298547e-05,
233
+ "loss": 0.0122,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.5260011954572624,
238
+ "grad_norm": 0.07990539819002151,
239
+ "learning_rate": 8.736568148000386e-05,
240
+ "loss": 0.0118,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.541940625622634,
245
+ "grad_norm": 0.10424526035785675,
246
+ "learning_rate": 8.648763834881782e-05,
247
+ "loss": 0.0125,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.5578800557880056,
252
+ "grad_norm": 0.13267765939235687,
253
+ "learning_rate": 8.558483660383245e-05,
254
+ "loss": 0.0134,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.5738194859533772,
259
+ "grad_norm": 0.11512497812509537,
260
+ "learning_rate": 8.46578888393606e-05,
261
+ "loss": 0.0136,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.5897589161187488,
266
+ "grad_norm": 0.09562960267066956,
267
+ "learning_rate": 8.37074240339482e-05,
268
+ "loss": 0.0115,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.6056983462841203,
273
+ "grad_norm": 0.08062624931335449,
274
+ "learning_rate": 8.273408712358211e-05,
275
+ "loss": 0.0103,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.6216377764494919,
280
+ "grad_norm": 0.055163562297821045,
281
+ "learning_rate": 8.173853856407011e-05,
282
+ "loss": 0.0123,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.6375772066148635,
287
+ "grad_norm": 0.0700579285621643,
288
+ "learning_rate": 8.072145388289001e-05,
289
+ "loss": 0.013,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.6535166367802351,
294
+ "grad_norm": 0.053463902324438095,
295
+ "learning_rate": 7.968352322081169e-05,
296
+ "loss": 0.0133,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.6694560669456067,
301
+ "grad_norm": 0.09448480606079102,
302
+ "learning_rate": 7.86254508636036e-05,
303
+ "loss": 0.0142,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.6853954971109782,
308
+ "grad_norm": 0.055674418807029724,
309
+ "learning_rate": 7.7547954764141e-05,
310
+ "loss": 0.0108,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.7013349272763498,
315
+ "grad_norm": 0.07148294895887375,
316
+ "learning_rate": 7.645176605524049e-05,
317
+ "loss": 0.011,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.7172743574417214,
322
+ "grad_norm": 0.062315683811903,
323
+ "learning_rate": 7.533762855355126e-05,
324
+ "loss": 0.011,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.733213787607093,
329
+ "grad_norm": 0.13653713464736938,
330
+ "learning_rate": 7.420629825483993e-05,
331
+ "loss": 0.0106,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.7491532177724647,
336
+ "grad_norm": 0.06053169071674347,
337
+ "learning_rate": 7.305854282101096e-05,
338
+ "loss": 0.0112,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.7650926479378363,
343
+ "grad_norm": 0.05051583796739578,
344
+ "learning_rate": 7.189514105921132e-05,
345
+ "loss": 0.0104,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.7810320781032078,
350
+ "grad_norm": 0.054913230240345,
351
+ "learning_rate": 7.071688239337245e-05,
352
+ "loss": 0.0092,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.7969715082685794,
357
+ "grad_norm": 0.04786158353090286,
358
+ "learning_rate": 6.95245663285482e-05,
359
+ "loss": 0.01,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.812910938433951,
364
+ "grad_norm": 0.055493079125881195,
365
+ "learning_rate": 6.831900190841232e-05,
366
+ "loss": 0.0149,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.8288503685993226,
371
+ "grad_norm": 0.035253629088401794,
372
+ "learning_rate": 6.710100716628344e-05,
373
+ "loss": 0.0102,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.8447897987646942,
378
+ "grad_norm": 0.10126087814569473,
379
+ "learning_rate": 6.58714085700503e-05,
380
+ "loss": 0.0102,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.8607292289300658,
385
+ "grad_norm": 0.03980156034231186,
386
+ "learning_rate": 6.46310404613735e-05,
387
+ "loss": 0.0092,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.8766686590954373,
392
+ "grad_norm": 0.05558431148529053,
393
+ "learning_rate": 6.338074448954471e-05,
394
+ "loss": 0.0086,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.8926080892608089,
399
+ "grad_norm": 0.04321667551994324,
400
+ "learning_rate": 6.21213690403873e-05,
401
+ "loss": 0.0108,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.9085475194261805,
406
+ "grad_norm": 0.06686638295650482,
407
+ "learning_rate": 6.0853768660585684e-05,
408
+ "loss": 0.0099,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.9244869495915521,
413
+ "grad_norm": 0.05315929278731346,
414
+ "learning_rate": 5.957880347783449e-05,
415
+ "loss": 0.0108,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.9404263797569237,
420
+ "grad_norm": 0.04230858013033867,
421
+ "learning_rate": 5.829733861720059e-05,
422
+ "loss": 0.0089,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.9563658099222953,
427
+ "grad_norm": 0.0437534861266613,
428
+ "learning_rate": 5.70102436140943e-05,
429
+ "loss": 0.0083,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.9723052400876668,
434
+ "grad_norm": 0.054816000163555145,
435
+ "learning_rate": 5.571839182424775e-05,
436
+ "loss": 0.0093,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.9882446702530384,
441
+ "grad_norm": 0.03881492838263512,
442
+ "learning_rate": 5.442265983110123e-05,
443
+ "loss": 0.0088,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 1.0031878860330743,
448
+ "grad_norm": 0.04418308287858963,
449
+ "learning_rate": 5.312392685099915e-05,
450
+ "loss": 0.0104,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 1.019127316198446,
455
+ "grad_norm": 0.05048086866736412,
456
+ "learning_rate": 5.1823074136599605e-05,
457
+ "loss": 0.0088,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.0350667463638175,
462
+ "grad_norm": 0.05302772670984268,
463
+ "learning_rate": 5.0520984378902146e-05,
464
+ "loss": 0.0098,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.0510061765291892,
469
+ "grad_norm": 0.056556668132543564,
470
+ "learning_rate": 4.921854110829962e-05,
471
+ "loss": 0.0095,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.0669456066945606,
476
+ "grad_norm": 0.04491036757826805,
477
+ "learning_rate": 4.791662809506025e-05,
478
+ "loss": 0.0091,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.0828850368599323,
483
+ "grad_norm": 0.0727638527750969,
484
+ "learning_rate": 4.66161287496473e-05,
485
+ "loss": 0.0089,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.0988244670253038,
490
+ "grad_norm": 0.06548187881708145,
491
+ "learning_rate": 4.5317925523282464e-05,
492
+ "loss": 0.0094,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.1147638971906755,
497
+ "grad_norm": 0.04109744727611542,
498
+ "learning_rate": 4.402289930916053e-05,
499
+ "loss": 0.0088,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.130703327356047,
504
+ "grad_norm": 0.07570062577724457,
505
+ "learning_rate": 4.2731928844720994e-05,
506
+ "loss": 0.0093,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.1466427575214186,
511
+ "grad_norm": 0.04505423083901405,
512
+ "learning_rate": 4.1445890115382505e-05,
513
+ "loss": 0.0085,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.1625821876867901,
518
+ "grad_norm": 0.040313106030225754,
519
+ "learning_rate": 4.016565576014478e-05,
520
+ "loss": 0.0092,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.1785216178521618,
525
+ "grad_norm": 0.07987982034683228,
526
+ "learning_rate": 3.889209447946116e-05,
527
+ "loss": 0.0134,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.1944610480175333,
532
+ "grad_norm": 0.045985572040081024,
533
+ "learning_rate": 3.762607044578357e-05,
534
+ "loss": 0.0093,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.210400478182905,
539
+ "grad_norm": 0.0642857551574707,
540
+ "learning_rate": 3.636844271718016e-05,
541
+ "loss": 0.0103,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.2263399083482764,
546
+ "grad_norm": 0.03940548002719879,
547
+ "learning_rate": 3.512006465442309e-05,
548
+ "loss": 0.0113,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.2422793385136481,
553
+ "grad_norm": 0.05522974207997322,
554
+ "learning_rate": 3.388178334194232e-05,
555
+ "loss": 0.0088,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 1.2582187686790198,
560
+ "grad_norm": 0.04090171679854393,
561
+ "learning_rate": 3.2654439013038165e-05,
562
+ "loss": 0.0092,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 1.2741581988443913,
567
+ "grad_norm": 0.04401571303606033,
568
+ "learning_rate": 3.143886447974269e-05,
569
+ "loss": 0.008,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.2900976290097628,
574
+ "grad_norm": 0.037025950849056244,
575
+ "learning_rate": 3.0235884567716737e-05,
576
+ "loss": 0.0074,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.3060370591751345,
581
+ "grad_norm": 0.050563715398311615,
582
+ "learning_rate": 2.904631555656616e-05,
583
+ "loss": 0.0093,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 1.3219764893405062,
588
+ "grad_norm": 0.10221158713102341,
589
+ "learning_rate": 2.7870964625956985e-05,
590
+ "loss": 0.0127,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 1.3379159195058776,
595
+ "grad_norm": 0.05870247632265091,
596
+ "learning_rate": 2.671062930790511e-05,
597
+ "loss": 0.0088,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 1.3538553496712493,
602
+ "grad_norm": 0.03522193804383278,
603
+ "learning_rate": 2.5566096945612727e-05,
604
+ "loss": 0.0103,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 1.3697947798366208,
609
+ "grad_norm": 0.0318855457007885,
610
+ "learning_rate": 2.443814415921809e-05,
611
+ "loss": 0.0097,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 1.3857342100019925,
616
+ "grad_norm": 0.04261662811040878,
617
+ "learning_rate": 2.3327536318821495e-05,
618
+ "loss": 0.0085,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 1.401673640167364,
623
+ "grad_norm": 0.06472990661859512,
624
+ "learning_rate": 2.223502702514487e-05,
625
+ "loss": 0.0099,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 1.4176130703327356,
630
+ "grad_norm": 0.033623527735471725,
631
+ "learning_rate": 2.1161357598177696e-05,
632
+ "loss": 0.0068,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 1.4335525004981071,
637
+ "grad_norm": 0.07391348481178284,
638
+ "learning_rate": 2.0107256574155564e-05,
639
+ "loss": 0.0086,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 1.4494919306634788,
644
+ "grad_norm": 0.04469392076134682,
645
+ "learning_rate": 1.907343921121359e-05,
646
+ "loss": 0.0082,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 1.4654313608288505,
651
+ "grad_norm": 0.040570441633462906,
652
+ "learning_rate": 1.8060607004049323e-05,
653
+ "loss": 0.0078,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 1.481370790994222,
658
+ "grad_norm": 0.03512577340006828,
659
+ "learning_rate": 1.7069447207924994e-05,
660
+ "loss": 0.0099,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 1.4973102211595934,
665
+ "grad_norm": 0.05797265097498894,
666
+ "learning_rate": 1.6100632372331727e-05,
667
+ "loss": 0.0097,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.5132496513249651,
672
+ "grad_norm": 0.05391458421945572,
673
+ "learning_rate": 1.5154819884632609e-05,
674
+ "loss": 0.0087,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.5291890814903368,
679
+ "grad_norm": 0.04258555918931961,
680
+ "learning_rate": 1.4232651523993634e-05,
681
+ "loss": 0.0091,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.5451285116557083,
686
+ "grad_norm": 0.05770336836576462,
687
+ "learning_rate": 1.3334753025905838e-05,
688
+ "loss": 0.0098,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.5610679418210798,
693
+ "grad_norm": 0.1264369785785675,
694
+ "learning_rate": 1.2461733657593722e-05,
695
+ "loss": 0.0078,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 1.5770073719864515,
700
+ "grad_norm": 0.03682301193475723,
701
+ "learning_rate": 1.16141858045982e-05,
702
+ "loss": 0.0083,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 1.5929468021518232,
707
+ "grad_norm": 0.03113352321088314,
708
+ "learning_rate": 1.0792684568814503e-05,
709
+ "loss": 0.0085,
710
+ "step": 1000
711
+ }
712
+ ],
713
+ "logging_steps": 10,
714
+ "max_steps": 1256,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 2,
717
+ "save_steps": 500,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": false
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 6.805552409615647e+17,
731
+ "train_batch_size": 2,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246e3c8fa418ba58f4a01f958ecbdae50370f929b9cea9496ce015290e0f4654
3
+ size 5432
checkpoint-1256/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-4k-instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:microsoft/Phi-3-mini-4k-instruct
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.0
checkpoint-1256/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v_proj",
33
+ "k_proj",
34
+ "o_proj",
35
+ "down_proj",
36
+ "up_proj",
37
+ "gate_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoint-1256/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7841eb0730a6387ec528d5537ed2175514da9fc2dc2ea6c6fc166ab9c2ea72e
3
+ size 71320216
checkpoint-1256/chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>
2
+ ' + message['content'] + '<|end|>
3
+ '}}{% elif message['role'] == 'user' %}{{'<|user|>
4
+ ' + message['content'] + '<|end|>
5
+ '}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
6
+ ' + message['content'] + '<|end|>
7
+ '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
8
+ ' }}{% else %}{{ eos_token }}{% endif %}
checkpoint-1256/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd3b94735d2a469f6c21dda1ca77ccc30db4962316172379171aa3b1177b1cd
3
+ size 36361850
checkpoint-1256/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1541b4217c6c5351fd311de2e8c44cfa362607df83d0031c65afffeb4c6d446f
3
+ size 14244
checkpoint-1256/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af21cce5671afa8bb2519c7cf220df32523bbf25d641971cadf3f21e46ed0c52
3
+ size 1064
checkpoint-1256/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": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-1256/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1256/tokenizer_config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "extra_special_tokens": {},
123
+ "legacy": false,
124
+ "max_length": 2048,
125
+ "model_max_length": 4096,
126
+ "pad_token": "<|endoftext|>",
127
+ "padding_side": "right",
128
+ "sp_model_kwargs": {},
129
+ "stride": 0,
130
+ "tokenizer_class": "LlamaTokenizerFast",
131
+ "truncation_side": "right",
132
+ "truncation_strategy": "longest_first",
133
+ "unk_token": "<unk>",
134
+ "use_default_system_prompt": false
135
+ }
checkpoint-1256/trainer_state.json ADDED
@@ -0,0 +1,909 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1256,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01593943016537159,
14
+ "grad_norm": 0.12403535097837448,
15
+ "learning_rate": 1.8e-05,
16
+ "loss": 1.1133,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.03187886033074318,
21
+ "grad_norm": 0.21290278434753418,
22
+ "learning_rate": 3.8e-05,
23
+ "loss": 1.0413,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.04781829049611477,
28
+ "grad_norm": 0.1645481288433075,
29
+ "learning_rate": 5.8e-05,
30
+ "loss": 0.9616,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.06375772066148636,
35
+ "grad_norm": 0.2903112471103668,
36
+ "learning_rate": 7.800000000000001e-05,
37
+ "loss": 0.874,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.07969715082685794,
42
+ "grad_norm": 0.2749190628528595,
43
+ "learning_rate": 9.8e-05,
44
+ "loss": 0.7337,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.09563658099222953,
49
+ "grad_norm": 0.4625573754310608,
50
+ "learning_rate": 9.99862592554908e-05,
51
+ "loss": 0.5768,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.11157601115760112,
56
+ "grad_norm": 0.31431907415390015,
57
+ "learning_rate": 9.993877008154289e-05,
58
+ "loss": 0.4941,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.1275154413229727,
63
+ "grad_norm": 0.43303918838500977,
64
+ "learning_rate": 9.985739505534436e-05,
65
+ "loss": 0.3854,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1434548714883443,
70
+ "grad_norm": 0.5850837826728821,
71
+ "learning_rate": 9.974218939375599e-05,
72
+ "loss": 0.2906,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.15939430165371588,
77
+ "grad_norm": 0.4940532147884369,
78
+ "learning_rate": 9.959323126934831e-05,
79
+ "loss": 0.2056,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.17533373181908746,
84
+ "grad_norm": 0.3987452983856201,
85
+ "learning_rate": 9.94106217573578e-05,
86
+ "loss": 0.1315,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.19127316198445907,
91
+ "grad_norm": 0.42741864919662476,
92
+ "learning_rate": 9.919448476710246e-05,
93
+ "loss": 0.0859,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.20721259214983065,
98
+ "grad_norm": 0.24628710746765137,
99
+ "learning_rate": 9.894496695790344e-05,
100
+ "loss": 0.0663,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.22315202231520223,
105
+ "grad_norm": 0.2623507082462311,
106
+ "learning_rate": 9.866223763956955e-05,
107
+ "loss": 0.0447,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.2390914524805738,
112
+ "grad_norm": 0.14876964688301086,
113
+ "learning_rate": 9.834648865751254e-05,
114
+ "loss": 0.0372,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.2550308826459454,
119
+ "grad_norm": 0.1500687152147293,
120
+ "learning_rate": 9.799793426257071e-05,
121
+ "loss": 0.0356,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.270970312811317,
126
+ "grad_norm": 0.16156131029129028,
127
+ "learning_rate": 9.76168109656295e-05,
128
+ "loss": 0.0293,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.2869097429766886,
133
+ "grad_norm": 0.20239904522895813,
134
+ "learning_rate": 9.720337737713739e-05,
135
+ "loss": 0.025,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.30284917314206017,
140
+ "grad_norm": 0.10117224603891373,
141
+ "learning_rate": 9.675791403162645e-05,
142
+ "loss": 0.0209,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.31878860330743175,
147
+ "grad_norm": 0.3235134482383728,
148
+ "learning_rate": 9.628072319735607e-05,
149
+ "loss": 0.0247,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.33472803347280333,
154
+ "grad_norm": 0.10946714133024216,
155
+ "learning_rate": 9.577212867120947e-05,
156
+ "loss": 0.0213,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.3506674636381749,
161
+ "grad_norm": 0.08509603142738342,
162
+ "learning_rate": 9.523247555898204e-05,
163
+ "loss": 0.0178,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.3666068938035465,
168
+ "grad_norm": 0.07975362986326218,
169
+ "learning_rate": 9.466213004121041e-05,
170
+ "loss": 0.016,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.38254632396891813,
175
+ "grad_norm": 0.061933811753988266,
176
+ "learning_rate": 9.406147912470143e-05,
177
+ "loss": 0.0143,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.3984857541342897,
182
+ "grad_norm": 0.22777368128299713,
183
+ "learning_rate": 9.343093037992945e-05,
184
+ "loss": 0.0294,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.4144251842996613,
189
+ "grad_norm": 0.11101654917001724,
190
+ "learning_rate": 9.277091166448022e-05,
191
+ "loss": 0.0159,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.4303646144650329,
196
+ "grad_norm": 0.27989494800567627,
197
+ "learning_rate": 9.208187083272894e-05,
198
+ "loss": 0.0169,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.44630404463040446,
203
+ "grad_norm": 0.07749247550964355,
204
+ "learning_rate": 9.136427543194967e-05,
205
+ "loss": 0.017,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.46224347479577604,
210
+ "grad_norm": 0.14141874015331268,
211
+ "learning_rate": 9.061861238506194e-05,
212
+ "loss": 0.0152,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.4781829049611476,
217
+ "grad_norm": 0.09233926236629486,
218
+ "learning_rate": 8.984538766023024e-05,
219
+ "loss": 0.0148,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.4941223351265192,
224
+ "grad_norm": 0.08206266909837723,
225
+ "learning_rate": 8.904512592754034e-05,
226
+ "loss": 0.013,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.5100617652918908,
231
+ "grad_norm": 0.09603980928659439,
232
+ "learning_rate": 8.821837020298547e-05,
233
+ "loss": 0.0122,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.5260011954572624,
238
+ "grad_norm": 0.07990539819002151,
239
+ "learning_rate": 8.736568148000386e-05,
240
+ "loss": 0.0118,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.541940625622634,
245
+ "grad_norm": 0.10424526035785675,
246
+ "learning_rate": 8.648763834881782e-05,
247
+ "loss": 0.0125,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.5578800557880056,
252
+ "grad_norm": 0.13267765939235687,
253
+ "learning_rate": 8.558483660383245e-05,
254
+ "loss": 0.0134,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.5738194859533772,
259
+ "grad_norm": 0.11512497812509537,
260
+ "learning_rate": 8.46578888393606e-05,
261
+ "loss": 0.0136,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.5897589161187488,
266
+ "grad_norm": 0.09562960267066956,
267
+ "learning_rate": 8.37074240339482e-05,
268
+ "loss": 0.0115,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.6056983462841203,
273
+ "grad_norm": 0.08062624931335449,
274
+ "learning_rate": 8.273408712358211e-05,
275
+ "loss": 0.0103,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.6216377764494919,
280
+ "grad_norm": 0.055163562297821045,
281
+ "learning_rate": 8.173853856407011e-05,
282
+ "loss": 0.0123,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.6375772066148635,
287
+ "grad_norm": 0.0700579285621643,
288
+ "learning_rate": 8.072145388289001e-05,
289
+ "loss": 0.013,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.6535166367802351,
294
+ "grad_norm": 0.053463902324438095,
295
+ "learning_rate": 7.968352322081169e-05,
296
+ "loss": 0.0133,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.6694560669456067,
301
+ "grad_norm": 0.09448480606079102,
302
+ "learning_rate": 7.86254508636036e-05,
303
+ "loss": 0.0142,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.6853954971109782,
308
+ "grad_norm": 0.055674418807029724,
309
+ "learning_rate": 7.7547954764141e-05,
310
+ "loss": 0.0108,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.7013349272763498,
315
+ "grad_norm": 0.07148294895887375,
316
+ "learning_rate": 7.645176605524049e-05,
317
+ "loss": 0.011,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.7172743574417214,
322
+ "grad_norm": 0.062315683811903,
323
+ "learning_rate": 7.533762855355126e-05,
324
+ "loss": 0.011,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.733213787607093,
329
+ "grad_norm": 0.13653713464736938,
330
+ "learning_rate": 7.420629825483993e-05,
331
+ "loss": 0.0106,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.7491532177724647,
336
+ "grad_norm": 0.06053169071674347,
337
+ "learning_rate": 7.305854282101096e-05,
338
+ "loss": 0.0112,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.7650926479378363,
343
+ "grad_norm": 0.05051583796739578,
344
+ "learning_rate": 7.189514105921132e-05,
345
+ "loss": 0.0104,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.7810320781032078,
350
+ "grad_norm": 0.054913230240345,
351
+ "learning_rate": 7.071688239337245e-05,
352
+ "loss": 0.0092,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.7969715082685794,
357
+ "grad_norm": 0.04786158353090286,
358
+ "learning_rate": 6.95245663285482e-05,
359
+ "loss": 0.01,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.812910938433951,
364
+ "grad_norm": 0.055493079125881195,
365
+ "learning_rate": 6.831900190841232e-05,
366
+ "loss": 0.0149,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.8288503685993226,
371
+ "grad_norm": 0.035253629088401794,
372
+ "learning_rate": 6.710100716628344e-05,
373
+ "loss": 0.0102,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.8447897987646942,
378
+ "grad_norm": 0.10126087814569473,
379
+ "learning_rate": 6.58714085700503e-05,
380
+ "loss": 0.0102,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.8607292289300658,
385
+ "grad_norm": 0.03980156034231186,
386
+ "learning_rate": 6.46310404613735e-05,
387
+ "loss": 0.0092,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.8766686590954373,
392
+ "grad_norm": 0.05558431148529053,
393
+ "learning_rate": 6.338074448954471e-05,
394
+ "loss": 0.0086,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.8926080892608089,
399
+ "grad_norm": 0.04321667551994324,
400
+ "learning_rate": 6.21213690403873e-05,
401
+ "loss": 0.0108,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.9085475194261805,
406
+ "grad_norm": 0.06686638295650482,
407
+ "learning_rate": 6.0853768660585684e-05,
408
+ "loss": 0.0099,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.9244869495915521,
413
+ "grad_norm": 0.05315929278731346,
414
+ "learning_rate": 5.957880347783449e-05,
415
+ "loss": 0.0108,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.9404263797569237,
420
+ "grad_norm": 0.04230858013033867,
421
+ "learning_rate": 5.829733861720059e-05,
422
+ "loss": 0.0089,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.9563658099222953,
427
+ "grad_norm": 0.0437534861266613,
428
+ "learning_rate": 5.70102436140943e-05,
429
+ "loss": 0.0083,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.9723052400876668,
434
+ "grad_norm": 0.054816000163555145,
435
+ "learning_rate": 5.571839182424775e-05,
436
+ "loss": 0.0093,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.9882446702530384,
441
+ "grad_norm": 0.03881492838263512,
442
+ "learning_rate": 5.442265983110123e-05,
443
+ "loss": 0.0088,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 1.0031878860330743,
448
+ "grad_norm": 0.04418308287858963,
449
+ "learning_rate": 5.312392685099915e-05,
450
+ "loss": 0.0104,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 1.019127316198446,
455
+ "grad_norm": 0.05048086866736412,
456
+ "learning_rate": 5.1823074136599605e-05,
457
+ "loss": 0.0088,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.0350667463638175,
462
+ "grad_norm": 0.05302772670984268,
463
+ "learning_rate": 5.0520984378902146e-05,
464
+ "loss": 0.0098,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.0510061765291892,
469
+ "grad_norm": 0.056556668132543564,
470
+ "learning_rate": 4.921854110829962e-05,
471
+ "loss": 0.0095,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.0669456066945606,
476
+ "grad_norm": 0.04491036757826805,
477
+ "learning_rate": 4.791662809506025e-05,
478
+ "loss": 0.0091,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.0828850368599323,
483
+ "grad_norm": 0.0727638527750969,
484
+ "learning_rate": 4.66161287496473e-05,
485
+ "loss": 0.0089,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.0988244670253038,
490
+ "grad_norm": 0.06548187881708145,
491
+ "learning_rate": 4.5317925523282464e-05,
492
+ "loss": 0.0094,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.1147638971906755,
497
+ "grad_norm": 0.04109744727611542,
498
+ "learning_rate": 4.402289930916053e-05,
499
+ "loss": 0.0088,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.130703327356047,
504
+ "grad_norm": 0.07570062577724457,
505
+ "learning_rate": 4.2731928844720994e-05,
506
+ "loss": 0.0093,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.1466427575214186,
511
+ "grad_norm": 0.04505423083901405,
512
+ "learning_rate": 4.1445890115382505e-05,
513
+ "loss": 0.0085,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.1625821876867901,
518
+ "grad_norm": 0.040313106030225754,
519
+ "learning_rate": 4.016565576014478e-05,
520
+ "loss": 0.0092,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.1785216178521618,
525
+ "grad_norm": 0.07987982034683228,
526
+ "learning_rate": 3.889209447946116e-05,
527
+ "loss": 0.0134,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.1944610480175333,
532
+ "grad_norm": 0.045985572040081024,
533
+ "learning_rate": 3.762607044578357e-05,
534
+ "loss": 0.0093,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.210400478182905,
539
+ "grad_norm": 0.0642857551574707,
540
+ "learning_rate": 3.636844271718016e-05,
541
+ "loss": 0.0103,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.2263399083482764,
546
+ "grad_norm": 0.03940548002719879,
547
+ "learning_rate": 3.512006465442309e-05,
548
+ "loss": 0.0113,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.2422793385136481,
553
+ "grad_norm": 0.05522974207997322,
554
+ "learning_rate": 3.388178334194232e-05,
555
+ "loss": 0.0088,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 1.2582187686790198,
560
+ "grad_norm": 0.04090171679854393,
561
+ "learning_rate": 3.2654439013038165e-05,
562
+ "loss": 0.0092,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 1.2741581988443913,
567
+ "grad_norm": 0.04401571303606033,
568
+ "learning_rate": 3.143886447974269e-05,
569
+ "loss": 0.008,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.2900976290097628,
574
+ "grad_norm": 0.037025950849056244,
575
+ "learning_rate": 3.0235884567716737e-05,
576
+ "loss": 0.0074,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.3060370591751345,
581
+ "grad_norm": 0.050563715398311615,
582
+ "learning_rate": 2.904631555656616e-05,
583
+ "loss": 0.0093,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 1.3219764893405062,
588
+ "grad_norm": 0.10221158713102341,
589
+ "learning_rate": 2.7870964625956985e-05,
590
+ "loss": 0.0127,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 1.3379159195058776,
595
+ "grad_norm": 0.05870247632265091,
596
+ "learning_rate": 2.671062930790511e-05,
597
+ "loss": 0.0088,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 1.3538553496712493,
602
+ "grad_norm": 0.03522193804383278,
603
+ "learning_rate": 2.5566096945612727e-05,
604
+ "loss": 0.0103,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 1.3697947798366208,
609
+ "grad_norm": 0.0318855457007885,
610
+ "learning_rate": 2.443814415921809e-05,
611
+ "loss": 0.0097,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 1.3857342100019925,
616
+ "grad_norm": 0.04261662811040878,
617
+ "learning_rate": 2.3327536318821495e-05,
618
+ "loss": 0.0085,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 1.401673640167364,
623
+ "grad_norm": 0.06472990661859512,
624
+ "learning_rate": 2.223502702514487e-05,
625
+ "loss": 0.0099,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 1.4176130703327356,
630
+ "grad_norm": 0.033623527735471725,
631
+ "learning_rate": 2.1161357598177696e-05,
632
+ "loss": 0.0068,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 1.4335525004981071,
637
+ "grad_norm": 0.07391348481178284,
638
+ "learning_rate": 2.0107256574155564e-05,
639
+ "loss": 0.0086,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 1.4494919306634788,
644
+ "grad_norm": 0.04469392076134682,
645
+ "learning_rate": 1.907343921121359e-05,
646
+ "loss": 0.0082,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 1.4654313608288505,
651
+ "grad_norm": 0.040570441633462906,
652
+ "learning_rate": 1.8060607004049323e-05,
653
+ "loss": 0.0078,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 1.481370790994222,
658
+ "grad_norm": 0.03512577340006828,
659
+ "learning_rate": 1.7069447207924994e-05,
660
+ "loss": 0.0099,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 1.4973102211595934,
665
+ "grad_norm": 0.05797265097498894,
666
+ "learning_rate": 1.6100632372331727e-05,
667
+ "loss": 0.0097,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.5132496513249651,
672
+ "grad_norm": 0.05391458421945572,
673
+ "learning_rate": 1.5154819884632609e-05,
674
+ "loss": 0.0087,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.5291890814903368,
679
+ "grad_norm": 0.04258555918931961,
680
+ "learning_rate": 1.4232651523993634e-05,
681
+ "loss": 0.0091,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.5451285116557083,
686
+ "grad_norm": 0.05770336836576462,
687
+ "learning_rate": 1.3334753025905838e-05,
688
+ "loss": 0.0098,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.5610679418210798,
693
+ "grad_norm": 0.1264369785785675,
694
+ "learning_rate": 1.2461733657593722e-05,
695
+ "loss": 0.0078,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 1.5770073719864515,
700
+ "grad_norm": 0.03682301193475723,
701
+ "learning_rate": 1.16141858045982e-05,
702
+ "loss": 0.0083,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 1.5929468021518232,
707
+ "grad_norm": 0.03113352321088314,
708
+ "learning_rate": 1.0792684568814503e-05,
709
+ "loss": 0.0085,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 1.6088862323171946,
714
+ "grad_norm": 0.03550567850470543,
715
+ "learning_rate": 9.997787378258121e-06,
716
+ "loss": 0.0084,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 1.624825662482566,
721
+ "grad_norm": 0.03575735166668892,
722
+ "learning_rate": 9.23003360882293e-06,
723
+ "loss": 0.009,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 1.6407650926479378,
728
+ "grad_norm": 0.0562940277159214,
729
+ "learning_rate": 8.489944218288908e-06,
730
+ "loss": 0.0097,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 1.6567045228133095,
735
+ "grad_norm": 0.04722534865140915,
736
+ "learning_rate": 7.778021392827211e-06,
737
+ "loss": 0.0078,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 1.672643952978681,
742
+ "grad_norm": 0.04047123342752457,
743
+ "learning_rate": 7.094748206242796e-06,
744
+ "loss": 0.0114,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 1.6885833831440527,
749
+ "grad_norm": 0.06225157901644707,
750
+ "learning_rate": 6.440588292185595e-06,
751
+ "loss": 0.0078,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 1.7045228133094241,
756
+ "grad_norm": 0.03725333884358406,
757
+ "learning_rate": 5.815985529552942e-06,
758
+ "loss": 0.008,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 1.7204622434747958,
763
+ "grad_norm": 0.029080206528306007,
764
+ "learning_rate": 5.221363741296298e-06,
765
+ "loss": 0.0083,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 1.7364016736401675,
770
+ "grad_norm": 0.03860724717378616,
771
+ "learning_rate": 4.657126406837148e-06,
772
+ "loss": 0.0079,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 1.752341103805539,
777
+ "grad_norm": 0.10423146188259125,
778
+ "learning_rate": 4.123656388286812e-06,
779
+ "loss": 0.0086,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 1.7682805339709105,
784
+ "grad_norm": 0.03647388890385628,
785
+ "learning_rate": 3.621315670656117e-06,
786
+ "loss": 0.007,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 1.7842199641362821,
791
+ "grad_norm": 0.03490564227104187,
792
+ "learning_rate": 3.1504451162311986e-06,
793
+ "loss": 0.0068,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 1.8001593943016538,
798
+ "grad_norm": 0.03614771366119385,
799
+ "learning_rate": 2.7113642332821045e-06,
800
+ "loss": 0.0086,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 1.8160988244670253,
805
+ "grad_norm": 0.04321877658367157,
806
+ "learning_rate": 2.3043709592610485e-06,
807
+ "loss": 0.0077,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 1.8320382546323968,
812
+ "grad_norm": 0.04423265904188156,
813
+ "learning_rate": 1.929741458637618e-06,
814
+ "loss": 0.0112,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 1.8479776847977685,
819
+ "grad_norm": 0.055377379059791565,
820
+ "learning_rate": 1.5877299355078533e-06,
821
+ "loss": 0.0077,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 1.8639171149631402,
826
+ "grad_norm": 0.05351576954126358,
827
+ "learning_rate": 1.2785684611046344e-06,
828
+ "loss": 0.0088,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 1.8798565451285116,
833
+ "grad_norm": 0.04308084771037102,
834
+ "learning_rate": 1.002466816326164e-06,
835
+ "loss": 0.0087,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 1.895795975293883,
840
+ "grad_norm": 0.05896038934588432,
841
+ "learning_rate": 7.596123493895991e-07,
842
+ "loss": 0.0106,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 1.9117354054592548,
847
+ "grad_norm": 0.039490342140197754,
848
+ "learning_rate": 5.501698487062446e-07,
849
+ "loss": 0.0089,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 1.9276748356246265,
854
+ "grad_norm": 0.03349680081009865,
855
+ "learning_rate": 3.742814310647602e-07,
856
+ "loss": 0.0081,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 1.943614265789998,
861
+ "grad_norm": 0.05369997024536133,
862
+ "learning_rate": 2.320664451980592e-07,
863
+ "loss": 0.0078,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 1.9595536959553694,
868
+ "grad_norm": 0.04113243520259857,
869
+ "learning_rate": 1.236213907994943e-07,
870
+ "loss": 0.0076,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 1.9754931261207411,
875
+ "grad_norm": 0.04669644311070442,
876
+ "learning_rate": 4.901985304315848e-08,
877
+ "loss": 0.0094,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 1.9914325562861128,
882
+ "grad_norm": 0.05660584941506386,
883
+ "learning_rate": 8.312452652831093e-09,
884
+ "loss": 0.0082,
885
+ "step": 1250
886
+ }
887
+ ],
888
+ "logging_steps": 10,
889
+ "max_steps": 1256,
890
+ "num_input_tokens_seen": 0,
891
+ "num_train_epochs": 2,
892
+ "save_steps": 500,
893
+ "stateful_callbacks": {
894
+ "TrainerControl": {
895
+ "args": {
896
+ "should_epoch_stop": false,
897
+ "should_evaluate": false,
898
+ "should_log": false,
899
+ "should_save": true,
900
+ "should_training_stop": true
901
+ },
902
+ "attributes": {}
903
+ }
904
+ },
905
+ "total_flos": 8.551088583926661e+17,
906
+ "train_batch_size": 2,
907
+ "trial_name": null,
908
+ "trial_params": null
909
+ }
checkpoint-1256/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246e3c8fa418ba58f4a01f958ecbdae50370f929b9cea9496ce015290e0f4654
3
+ size 5432
logs/events.out.tfevents.1766981779.3043de093a88.2371.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518821adb0c4531d396eccb0799682ba40312f6961de4db9801247fcb7011fb5
3
+ size 31943
merged/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.57.3"
11
+ }
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": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
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_config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "extra_special_tokens": {},
123
+ "legacy": false,
124
+ "max_length": 2048,
125
+ "model_max_length": 4096,
126
+ "pad_token": "<|endoftext|>",
127
+ "padding_side": "right",
128
+ "sp_model_kwargs": {},
129
+ "stride": 0,
130
+ "tokenizer_class": "LlamaTokenizerFast",
131
+ "truncation_side": "right",
132
+ "truncation_strategy": "longest_first",
133
+ "unk_token": "<unk>",
134
+ "use_default_system_prompt": false
135
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246e3c8fa418ba58f4a01f958ecbdae50370f929b9cea9496ce015290e0f4654
3
+ size 5432
training_metadata.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "stage": "2_SFT",
3
+ "base_model": "/workspace/nishka-gkc-phi3-base",
4
+ "training_start": "2025-12-29 04:16:19.019832",
5
+ "dataset": {
6
+ "path": "/workspace/pql_sft_training.jsonl",
7
+ "examples": 10038,
8
+ "estimated_tokens": 7000000
9
+ },
10
+ "lora_config": {
11
+ "r": 32,
12
+ "alpha": 64,
13
+ "dropout": 0.05,
14
+ "target_modules": [
15
+ "q_proj",
16
+ "k_proj",
17
+ "v_proj",
18
+ "o_proj",
19
+ "gate_proj",
20
+ "up_proj",
21
+ "down_proj"
22
+ ]
23
+ },
24
+ "training_args": {
25
+ "epochs": 2,
26
+ "batch_size": 2,
27
+ "learning_rate": 0.0001,
28
+ "max_length": 2048
29
+ }
30
+ }