Hugging Face's logo

SujanKarki
/
Phi-3-mini-128k-instruct_text_to_sql_lora

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
SujanKarki commited on
Commit
1d0441b
·
verified ·
1 Parent(s): 992d015

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +202 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. checkpoint-1000/README.md +202 -0
  5. checkpoint-1000/adapter_config.json +31 -0
  6. checkpoint-1000/adapter_model.safetensors +3 -0
  7. checkpoint-1000/optimizer.pt +3 -0
  8. checkpoint-1000/rng_state.pth +3 -0
  9. checkpoint-1000/scheduler.pt +3 -0
  10. checkpoint-1000/special_tokens_map.json +28 -0
  11. checkpoint-1000/tokenizer.json +0 -0
  12. checkpoint-1000/tokenizer_config.json +151 -0
  13. checkpoint-1000/trainer_state.json +383 -0
  14. checkpoint-1000/training_args.bin +3 -0
  15. checkpoint-1500/README.md +202 -0
  16. checkpoint-1500/adapter_config.json +31 -0
  17. checkpoint-1500/adapter_model.safetensors +3 -0
  18. checkpoint-1500/optimizer.pt +3 -0
  19. checkpoint-1500/rng_state.pth +3 -0
  20. checkpoint-1500/scheduler.pt +3 -0
  21. checkpoint-1500/special_tokens_map.json +28 -0
  22. checkpoint-1500/tokenizer.json +0 -0
  23. checkpoint-1500/tokenizer_config.json +151 -0
  24. checkpoint-1500/trainer_state.json +558 -0
  25. checkpoint-1500/training_args.bin +3 -0
  26. checkpoint-2000/README.md +202 -0
  27. checkpoint-2000/adapter_config.json +31 -0
  28. checkpoint-2000/adapter_model.safetensors +3 -0
  29. checkpoint-2000/optimizer.pt +3 -0
  30. checkpoint-2000/rng_state.pth +3 -0
  31. checkpoint-2000/scheduler.pt +3 -0
  32. checkpoint-2000/special_tokens_map.json +28 -0
  33. checkpoint-2000/tokenizer.json +0 -0
  34. checkpoint-2000/tokenizer_config.json +151 -0
  35. checkpoint-2000/trainer_state.json +733 -0
  36. checkpoint-2000/training_args.bin +3 -0
  37. checkpoint-2013/README.md +202 -0
  38. checkpoint-2013/adapter_config.json +31 -0
  39. checkpoint-2013/adapter_model.safetensors +3 -0
  40. checkpoint-2013/optimizer.pt +3 -0
  41. checkpoint-2013/rng_state.pth +3 -0
  42. checkpoint-2013/scheduler.pt +3 -0
  43. checkpoint-2013/special_tokens_map.json +28 -0
  44. checkpoint-2013/tokenizer.json +0 -0
  45. checkpoint-2013/tokenizer_config.json +151 -0
  46. checkpoint-2013/trainer_state.json +733 -0
  47. checkpoint-2013/training_args.bin +3 -0
  48. checkpoint-500/README.md +202 -0
  49. checkpoint-500/adapter_config.json +31 -0
  50. checkpoint-500/adapter_model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-128k-instruct
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 0.12.0
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj",
25
+ "k_proj",
26
+ "o_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057b0d140ca2511f2d0bce76c880c577156186db5a7890c907ac56a24653246f
3
+ size 494047976
checkpoint-1000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-128k-instruct
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 0.12.0
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "o_proj",
24
+ "q_proj",
25
+ "k_proj",
26
+ "v_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
checkpoint-1000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb86452cbcb0b3415b4a41eba2ed957f9ac10205733eb3de5f12d68b26a513c
3
+ size 494047976
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d76bba8459bff77e2c96989f34ab035ac39303bfa80174072ee2b40a329ddf5a
3
+ size 201381818
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d49d139fef32458a00eaedbb02c8599e6e6dc78c9afc4da68ddad845f86726
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f239cab3977550af51dae77533320c0c157e084a6c2f322886a7cd5c5c058151
3
+ size 1064
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
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 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32011": {
119
+ "content": "<|im_start|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|im_end|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ }
134
+ },
135
+ "additional_special_tokens": [
136
+ "<|im_start|>",
137
+ "<|im_end|>"
138
+ ],
139
+ "bos_token": "<|im_start|>",
140
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
141
+ "clean_up_tokenization_spaces": false,
142
+ "eos_token": "<|im_end|>",
143
+ "legacy": false,
144
+ "model_max_length": 131072,
145
+ "pad_token": "<|im_end|>",
146
+ "padding_side": "right",
147
+ "sp_model_kwargs": {},
148
+ "tokenizer_class": "LlamaTokenizer",
149
+ "unk_token": "<unk>",
150
+ "use_default_system_prompt": false
151
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,383 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.4903129657228018,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.029806259314456036,
13
+ "grad_norm": 0.22671940922737122,
14
+ "learning_rate": 8e-05,
15
+ "loss": 1.3506,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.05961251862891207,
20
+ "grad_norm": 0.05189573019742966,
21
+ "learning_rate": 0.00016,
22
+ "loss": 0.8372,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.08941877794336811,
27
+ "grad_norm": 0.049646440893411636,
28
+ "learning_rate": 0.0001999871938117722,
29
+ "loss": 0.7053,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.11922503725782414,
34
+ "grad_norm": 0.04605806618928909,
35
+ "learning_rate": 0.0001998847639849245,
36
+ "loss": 0.5957,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.14903129657228018,
41
+ "grad_norm": 0.04606040194630623,
42
+ "learning_rate": 0.0001996800092633612,
43
+ "loss": 0.5457,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.17883755588673622,
48
+ "grad_norm": 0.03791499882936478,
49
+ "learning_rate": 0.0001993731394038509,
50
+ "loss": 0.5301,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.20864381520119224,
55
+ "grad_norm": 0.047940950840711594,
56
+ "learning_rate": 0.0001989644687729177,
57
+ "loss": 0.5223,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.23845007451564829,
62
+ "grad_norm": 0.0519738644361496,
63
+ "learning_rate": 0.0001984544160247949,
64
+ "loss": 0.5117,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.26825633383010433,
69
+ "grad_norm": 0.04569224268198013,
70
+ "learning_rate": 0.00019784350367254322,
71
+ "loss": 0.5181,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.29806259314456035,
76
+ "grad_norm": 0.045780543237924576,
77
+ "learning_rate": 0.0001971323575527731,
78
+ "loss": 0.5168,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.32786885245901637,
83
+ "grad_norm": 0.046496499329805374,
84
+ "learning_rate": 0.0001963217061845192,
85
+ "loss": 0.5051,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.35767511177347244,
90
+ "grad_norm": 0.04850991442799568,
91
+ "learning_rate": 0.00019541238002292394,
92
+ "loss": 0.5083,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.38748137108792846,
97
+ "grad_norm": 0.046593230217695236,
98
+ "learning_rate": 0.00019440531060849504,
99
+ "loss": 0.5066,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.4172876304023845,
104
+ "grad_norm": 0.050816215574741364,
105
+ "learning_rate": 0.00019330152961280765,
106
+ "loss": 0.5021,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.44709388971684055,
111
+ "grad_norm": 0.0533340722322464,
112
+ "learning_rate": 0.00019210216778162994,
113
+ "loss": 0.5017,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.47690014903129657,
118
+ "grad_norm": 0.10607749223709106,
119
+ "learning_rate": 0.00019080845377655352,
120
+ "loss": 0.4996,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.5067064083457526,
125
+ "grad_norm": 0.054169464856386185,
126
+ "learning_rate": 0.00018942171291631653,
127
+ "loss": 0.5014,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.5365126676602087,
132
+ "grad_norm": 0.047340892255306244,
133
+ "learning_rate": 0.000187943365819108,
134
+ "loss": 0.4988,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.5663189269746647,
139
+ "grad_norm": 0.04948943480849266,
140
+ "learning_rate": 0.00018637492694724466,
141
+ "loss": 0.4975,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.5961251862891207,
146
+ "grad_norm": 0.04684118553996086,
147
+ "learning_rate": 0.00018471800305571129,
148
+ "loss": 0.4961,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.6259314456035767,
153
+ "grad_norm": 0.04512176662683487,
154
+ "learning_rate": 0.00018297429154615338,
155
+ "loss": 0.4956,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.6557377049180327,
160
+ "grad_norm": 0.05711393430829048,
161
+ "learning_rate": 0.00018114557872800905,
162
+ "loss": 0.4944,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.6855439642324889,
167
+ "grad_norm": 0.05339927598834038,
168
+ "learning_rate": 0.000179233737988561,
169
+ "loss": 0.4922,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.7153502235469449,
174
+ "grad_norm": 0.04622140899300575,
175
+ "learning_rate": 0.00017724072787378333,
176
+ "loss": 0.4846,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.7451564828614009,
181
+ "grad_norm": 0.0447109080851078,
182
+ "learning_rate": 0.00017516859008194938,
183
+ "loss": 0.4855,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.7749627421758569,
188
+ "grad_norm": 0.0435018390417099,
189
+ "learning_rate": 0.00017301944737205588,
190
+ "loss": 0.486,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.8047690014903129,
195
+ "grad_norm": 0.04844864085316658,
196
+ "learning_rate": 0.0001707955013892061,
197
+ "loss": 0.4911,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 0.834575260804769,
202
+ "grad_norm": 0.05155207961797714,
203
+ "learning_rate": 0.00016849903040917975,
204
+ "loss": 0.4861,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 0.8643815201192251,
209
+ "grad_norm": 0.04522501304745674,
210
+ "learning_rate": 0.00016613238700450013,
211
+ "loss": 0.4852,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 0.8941877794336811,
216
+ "grad_norm": 0.047208670526742935,
217
+ "learning_rate": 0.00016369799563438958,
218
+ "loss": 0.4844,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 0.9239940387481371,
223
+ "grad_norm": 0.054809391498565674,
224
+ "learning_rate": 0.00016119835016108197,
225
+ "loss": 0.4815,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 0.9538002980625931,
230
+ "grad_norm": 0.04929815232753754,
231
+ "learning_rate": 0.00015863601129503688,
232
+ "loss": 0.4823,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 0.9836065573770492,
237
+ "grad_norm": 0.05650775134563446,
238
+ "learning_rate": 0.00015601360397167214,
239
+ "loss": 0.481,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 1.0134128166915053,
244
+ "grad_norm": 0.04741150885820389,
245
+ "learning_rate": 0.00015333381466230294,
246
+ "loss": 0.488,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 1.0432190760059612,
251
+ "grad_norm": 0.057174187153577805,
252
+ "learning_rate": 0.00015059938862204127,
253
+ "loss": 0.4821,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 1.0730253353204173,
258
+ "grad_norm": 0.054773855954408646,
259
+ "learning_rate": 0.0001478131270774758,
260
+ "loss": 0.4776,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 1.1028315946348732,
265
+ "grad_norm": 0.05249800160527229,
266
+ "learning_rate": 0.0001449778843570128,
267
+ "loss": 0.4782,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 1.1326378539493294,
272
+ "grad_norm": 0.049587223678827286,
273
+ "learning_rate": 0.00014209656496681812,
274
+ "loss": 0.4819,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 1.1624441132637853,
279
+ "grad_norm": 0.048591841012239456,
280
+ "learning_rate": 0.0001391721206153554,
281
+ "loss": 0.4796,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 1.1922503725782414,
286
+ "grad_norm": 0.05344521254301071,
287
+ "learning_rate": 0.000136207547189569,
288
+ "loss": 0.472,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 1.2220566318926975,
293
+ "grad_norm": 0.052742790430784225,
294
+ "learning_rate": 0.0001332058816858092,
295
+ "loss": 0.476,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 1.2518628912071534,
300
+ "grad_norm": 0.05483981594443321,
301
+ "learning_rate": 0.00013017019909864364,
302
+ "loss": 0.4755,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 1.2816691505216096,
307
+ "grad_norm": 0.050890855491161346,
308
+ "learning_rate": 0.00012710360927074233,
309
+ "loss": 0.4719,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 1.3114754098360657,
314
+ "grad_norm": 0.05531829223036766,
315
+ "learning_rate": 0.0001240092537070631,
316
+ "loss": 0.4745,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 1.3412816691505216,
321
+ "grad_norm": 0.05655696988105774,
322
+ "learning_rate": 0.00012089030235660155,
323
+ "loss": 0.475,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 1.3710879284649775,
328
+ "grad_norm": 0.059185780584812164,
329
+ "learning_rate": 0.00011774995036500181,
330
+ "loss": 0.4714,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 1.4008941877794336,
335
+ "grad_norm": 0.05000292509794235,
336
+ "learning_rate": 0.00011459141480135518,
337
+ "loss": 0.4774,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 1.4307004470938898,
342
+ "grad_norm": 0.05054055526852608,
343
+ "learning_rate": 0.00011141793136253986,
344
+ "loss": 0.4666,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 1.4605067064083457,
349
+ "grad_norm": 0.04777640849351883,
350
+ "learning_rate": 0.00010823275105847772,
351
+ "loss": 0.4711,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 1.4903129657228018,
356
+ "grad_norm": 0.05582300201058388,
357
+ "learning_rate": 0.00010503913688170396,
358
+ "loss": 0.4668,
359
+ "step": 1000
360
+ }
361
+ ],
362
+ "logging_steps": 20,
363
+ "max_steps": 2013,
364
+ "num_input_tokens_seen": 0,
365
+ "num_train_epochs": 3,
366
+ "save_steps": 500,
367
+ "stateful_callbacks": {
368
+ "TrainerControl": {
369
+ "args": {
370
+ "should_epoch_stop": false,
371
+ "should_evaluate": false,
372
+ "should_log": false,
373
+ "should_save": true,
374
+ "should_training_stop": false
375
+ },
376
+ "attributes": {}
377
+ }
378
+ },
379
+ "total_flos": 3.6835684982666035e+17,
380
+ "train_batch_size": 2,
381
+ "trial_name": null,
382
+ "trial_params": null
383
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab60b993eb78303de2a30db3031386bd91b13bdd08654df9622f01f73e805192
3
+ size 5560
checkpoint-1500/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-128k-instruct
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 0.12.0
checkpoint-1500/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj",
25
+ "k_proj",
26
+ "o_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
checkpoint-1500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13216de8a4e88ce61bf2b0e4010065f8d768fdc3cdea39f020a0983e18ebb3d
3
+ size 494047976
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c369b7c11bc8bc721f398efd4619ae84a9b374de939139b80710c7199504f2d1
3
+ size 201381818
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399288a49f4624f59f563783a35d2a4efa0ab3314be93c1c9306738db7939ebe
3
+ size 14244
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64b8be4b9a11f6efe9c86bd69cc8238e2dc9edb844aceec84e7b89f574abf8b6
3
+ size 1064
checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32011": {
119
+ "content": "<|im_start|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|im_end|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ }
134
+ },
135
+ "additional_special_tokens": [
136
+ "<|im_start|>",
137
+ "<|im_end|>"
138
+ ],
139
+ "bos_token": "<|im_start|>",
140
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
141
+ "clean_up_tokenization_spaces": false,
142
+ "eos_token": "<|im_end|>",
143
+ "legacy": false,
144
+ "model_max_length": 131072,
145
+ "pad_token": "<|im_end|>",
146
+ "padding_side": "right",
147
+ "sp_model_kwargs": {},
148
+ "tokenizer_class": "LlamaTokenizer",
149
+ "unk_token": "<unk>",
150
+ "use_default_system_prompt": false
151
+ }
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,558 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.235469448584203,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.029806259314456036,
13
+ "grad_norm": 0.22671940922737122,
14
+ "learning_rate": 8e-05,
15
+ "loss": 1.3506,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.05961251862891207,
20
+ "grad_norm": 0.05189573019742966,
21
+ "learning_rate": 0.00016,
22
+ "loss": 0.8372,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.08941877794336811,
27
+ "grad_norm": 0.049646440893411636,
28
+ "learning_rate": 0.0001999871938117722,
29
+ "loss": 0.7053,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.11922503725782414,
34
+ "grad_norm": 0.04605806618928909,
35
+ "learning_rate": 0.0001998847639849245,
36
+ "loss": 0.5957,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.14903129657228018,
41
+ "grad_norm": 0.04606040194630623,
42
+ "learning_rate": 0.0001996800092633612,
43
+ "loss": 0.5457,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.17883755588673622,
48
+ "grad_norm": 0.03791499882936478,
49
+ "learning_rate": 0.0001993731394038509,
50
+ "loss": 0.5301,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.20864381520119224,
55
+ "grad_norm": 0.047940950840711594,
56
+ "learning_rate": 0.0001989644687729177,
57
+ "loss": 0.5223,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.23845007451564829,
62
+ "grad_norm": 0.0519738644361496,
63
+ "learning_rate": 0.0001984544160247949,
64
+ "loss": 0.5117,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.26825633383010433,
69
+ "grad_norm": 0.04569224268198013,
70
+ "learning_rate": 0.00019784350367254322,
71
+ "loss": 0.5181,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.29806259314456035,
76
+ "grad_norm": 0.045780543237924576,
77
+ "learning_rate": 0.0001971323575527731,
78
+ "loss": 0.5168,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.32786885245901637,
83
+ "grad_norm": 0.046496499329805374,
84
+ "learning_rate": 0.0001963217061845192,
85
+ "loss": 0.5051,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.35767511177347244,
90
+ "grad_norm": 0.04850991442799568,
91
+ "learning_rate": 0.00019541238002292394,
92
+ "loss": 0.5083,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.38748137108792846,
97
+ "grad_norm": 0.046593230217695236,
98
+ "learning_rate": 0.00019440531060849504,
99
+ "loss": 0.5066,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.4172876304023845,
104
+ "grad_norm": 0.050816215574741364,
105
+ "learning_rate": 0.00019330152961280765,
106
+ "loss": 0.5021,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.44709388971684055,
111
+ "grad_norm": 0.0533340722322464,
112
+ "learning_rate": 0.00019210216778162994,
113
+ "loss": 0.5017,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.47690014903129657,
118
+ "grad_norm": 0.10607749223709106,
119
+ "learning_rate": 0.00019080845377655352,
120
+ "loss": 0.4996,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.5067064083457526,
125
+ "grad_norm": 0.054169464856386185,
126
+ "learning_rate": 0.00018942171291631653,
127
+ "loss": 0.5014,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.5365126676602087,
132
+ "grad_norm": 0.047340892255306244,
133
+ "learning_rate": 0.000187943365819108,
134
+ "loss": 0.4988,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.5663189269746647,
139
+ "grad_norm": 0.04948943480849266,
140
+ "learning_rate": 0.00018637492694724466,
141
+ "loss": 0.4975,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.5961251862891207,
146
+ "grad_norm": 0.04684118553996086,
147
+ "learning_rate": 0.00018471800305571129,
148
+ "loss": 0.4961,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.6259314456035767,
153
+ "grad_norm": 0.04512176662683487,
154
+ "learning_rate": 0.00018297429154615338,
155
+ "loss": 0.4956,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.6557377049180327,
160
+ "grad_norm": 0.05711393430829048,
161
+ "learning_rate": 0.00018114557872800905,
162
+ "loss": 0.4944,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.6855439642324889,
167
+ "grad_norm": 0.05339927598834038,
168
+ "learning_rate": 0.000179233737988561,
169
+ "loss": 0.4922,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.7153502235469449,
174
+ "grad_norm": 0.04622140899300575,
175
+ "learning_rate": 0.00017724072787378333,
176
+ "loss": 0.4846,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.7451564828614009,
181
+ "grad_norm": 0.0447109080851078,
182
+ "learning_rate": 0.00017516859008194938,
183
+ "loss": 0.4855,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.7749627421758569,
188
+ "grad_norm": 0.0435018390417099,
189
+ "learning_rate": 0.00017301944737205588,
190
+ "loss": 0.486,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.8047690014903129,
195
+ "grad_norm": 0.04844864085316658,
196
+ "learning_rate": 0.0001707955013892061,
197
+ "loss": 0.4911,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 0.834575260804769,
202
+ "grad_norm": 0.05155207961797714,
203
+ "learning_rate": 0.00016849903040917975,
204
+ "loss": 0.4861,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 0.8643815201192251,
209
+ "grad_norm": 0.04522501304745674,
210
+ "learning_rate": 0.00016613238700450013,
211
+ "loss": 0.4852,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 0.8941877794336811,
216
+ "grad_norm": 0.047208670526742935,
217
+ "learning_rate": 0.00016369799563438958,
218
+ "loss": 0.4844,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 0.9239940387481371,
223
+ "grad_norm": 0.054809391498565674,
224
+ "learning_rate": 0.00016119835016108197,
225
+ "loss": 0.4815,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 0.9538002980625931,
230
+ "grad_norm": 0.04929815232753754,
231
+ "learning_rate": 0.00015863601129503688,
232
+ "loss": 0.4823,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 0.9836065573770492,
237
+ "grad_norm": 0.05650775134563446,
238
+ "learning_rate": 0.00015601360397167214,
239
+ "loss": 0.481,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 1.0134128166915053,
244
+ "grad_norm": 0.04741150885820389,
245
+ "learning_rate": 0.00015333381466230294,
246
+ "loss": 0.488,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 1.0432190760059612,
251
+ "grad_norm": 0.057174187153577805,
252
+ "learning_rate": 0.00015059938862204127,
253
+ "loss": 0.4821,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 1.0730253353204173,
258
+ "grad_norm": 0.054773855954408646,
259
+ "learning_rate": 0.0001478131270774758,
260
+ "loss": 0.4776,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 1.1028315946348732,
265
+ "grad_norm": 0.05249800160527229,
266
+ "learning_rate": 0.0001449778843570128,
267
+ "loss": 0.4782,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 1.1326378539493294,
272
+ "grad_norm": 0.049587223678827286,
273
+ "learning_rate": 0.00014209656496681812,
274
+ "loss": 0.4819,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 1.1624441132637853,
279
+ "grad_norm": 0.048591841012239456,
280
+ "learning_rate": 0.0001391721206153554,
281
+ "loss": 0.4796,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 1.1922503725782414,
286
+ "grad_norm": 0.05344521254301071,
287
+ "learning_rate": 0.000136207547189569,
288
+ "loss": 0.472,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 1.2220566318926975,
293
+ "grad_norm": 0.052742790430784225,
294
+ "learning_rate": 0.0001332058816858092,
295
+ "loss": 0.476,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 1.2518628912071534,
300
+ "grad_norm": 0.05483981594443321,
301
+ "learning_rate": 0.00013017019909864364,
302
+ "loss": 0.4755,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 1.2816691505216096,
307
+ "grad_norm": 0.050890855491161346,
308
+ "learning_rate": 0.00012710360927074233,
309
+ "loss": 0.4719,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 1.3114754098360657,
314
+ "grad_norm": 0.05531829223036766,
315
+ "learning_rate": 0.0001240092537070631,
316
+ "loss": 0.4745,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 1.3412816691505216,
321
+ "grad_norm": 0.05655696988105774,
322
+ "learning_rate": 0.00012089030235660155,
323
+ "loss": 0.475,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 1.3710879284649775,
328
+ "grad_norm": 0.059185780584812164,
329
+ "learning_rate": 0.00011774995036500181,
330
+ "loss": 0.4714,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 1.4008941877794336,
335
+ "grad_norm": 0.05000292509794235,
336
+ "learning_rate": 0.00011459141480135518,
337
+ "loss": 0.4774,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 1.4307004470938898,
342
+ "grad_norm": 0.05054055526852608,
343
+ "learning_rate": 0.00011141793136253986,
344
+ "loss": 0.4666,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 1.4605067064083457,
349
+ "grad_norm": 0.04777640849351883,
350
+ "learning_rate": 0.00010823275105847772,
351
+ "loss": 0.4711,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 1.4903129657228018,
356
+ "grad_norm": 0.05582300201058388,
357
+ "learning_rate": 0.00010503913688170396,
358
+ "loss": 0.4668,
359
+ "step": 1000
360
+ },
361
+ {
362
+ "epoch": 1.520119225037258,
363
+ "grad_norm": 0.059767983853816986,
364
+ "learning_rate": 0.00010184036046466143,
365
+ "loss": 0.4683,
366
+ "step": 1020
367
+ },
368
+ {
369
+ "epoch": 1.5499254843517138,
370
+ "grad_norm": 0.0632881224155426,
371
+ "learning_rate": 9.863969872814403e-05,
372
+ "loss": 0.4695,
373
+ "step": 1040
374
+ },
375
+ {
376
+ "epoch": 1.5797317436661698,
377
+ "grad_norm": 0.05366360396146774,
378
+ "learning_rate": 9.544043052432244e-05,
379
+ "loss": 0.4672,
380
+ "step": 1060
381
+ },
382
+ {
383
+ "epoch": 1.6095380029806259,
384
+ "grad_norm": 0.049754392355680466,
385
+ "learning_rate": 9.224583327779134e-05,
386
+ "loss": 0.4655,
387
+ "step": 1080
388
+ },
389
+ {
390
+ "epoch": 1.639344262295082,
391
+ "grad_norm": 0.055744487792253494,
392
+ "learning_rate": 8.905917962807927e-05,
393
+ "loss": 0.4714,
394
+ "step": 1100
395
+ },
396
+ {
397
+ "epoch": 1.669150521609538,
398
+ "grad_norm": 0.05113043636083603,
399
+ "learning_rate": 8.588373407706007e-05,
400
+ "loss": 0.4626,
401
+ "step": 1120
402
+ },
403
+ {
404
+ "epoch": 1.698956780923994,
405
+ "grad_norm": 0.05468016862869263,
406
+ "learning_rate": 8.272274964470118e-05,
407
+ "loss": 0.4681,
408
+ "step": 1140
409
+ },
410
+ {
411
+ "epoch": 1.7287630402384502,
412
+ "grad_norm": 0.05420814827084541,
413
+ "learning_rate": 7.957946453657403e-05,
414
+ "loss": 0.4684,
415
+ "step": 1160
416
+ },
417
+ {
418
+ "epoch": 1.758569299552906,
419
+ "grad_norm": 0.06343657523393631,
420
+ "learning_rate": 7.645709882654093e-05,
421
+ "loss": 0.4659,
422
+ "step": 1180
423
+ },
424
+ {
425
+ "epoch": 1.788375558867362,
426
+ "grad_norm": 0.05385758727788925,
427
+ "learning_rate": 7.335885115801656e-05,
428
+ "loss": 0.4659,
429
+ "step": 1200
430
+ },
431
+ {
432
+ "epoch": 1.8181818181818183,
433
+ "grad_norm": 0.05174577608704567,
434
+ "learning_rate": 7.028789546718326e-05,
435
+ "loss": 0.4646,
436
+ "step": 1220
437
+ },
438
+ {
439
+ "epoch": 1.8479880774962743,
440
+ "grad_norm": 0.05492328852415085,
441
+ "learning_rate": 6.72473777315176e-05,
442
+ "loss": 0.4657,
443
+ "step": 1240
444
+ },
445
+ {
446
+ "epoch": 1.8777943368107302,
447
+ "grad_norm": 0.060056205838918686,
448
+ "learning_rate": 6.424041274695804e-05,
449
+ "loss": 0.4677,
450
+ "step": 1260
451
+ },
452
+ {
453
+ "epoch": 1.9076005961251863,
454
+ "grad_norm": 0.061595309525728226,
455
+ "learning_rate": 6.127008093701658e-05,
456
+ "loss": 0.4661,
457
+ "step": 1280
458
+ },
459
+ {
460
+ "epoch": 1.9374068554396424,
461
+ "grad_norm": 0.05786813423037529,
462
+ "learning_rate": 5.833942519710177e-05,
463
+ "loss": 0.4641,
464
+ "step": 1300
465
+ },
466
+ {
467
+ "epoch": 1.9672131147540983,
468
+ "grad_norm": 0.05672052502632141,
469
+ "learning_rate": 5.5451447777287324e-05,
470
+ "loss": 0.4653,
471
+ "step": 1320
472
+ },
473
+ {
474
+ "epoch": 1.9970193740685542,
475
+ "grad_norm": 0.06217477470636368,
476
+ "learning_rate": 5.260910720671858e-05,
477
+ "loss": 0.4658,
478
+ "step": 1340
479
+ },
480
+ {
481
+ "epoch": 2.0268256333830106,
482
+ "grad_norm": 0.05346861109137535,
483
+ "learning_rate": 4.981531526280807e-05,
484
+ "loss": 0.4665,
485
+ "step": 1360
486
+ },
487
+ {
488
+ "epoch": 2.0566318926974665,
489
+ "grad_norm": 0.05857508257031441,
490
+ "learning_rate": 4.707293398832504e-05,
491
+ "loss": 0.4676,
492
+ "step": 1380
493
+ },
494
+ {
495
+ "epoch": 2.0864381520119224,
496
+ "grad_norm": 0.05544683709740639,
497
+ "learning_rate": 4.4384772759434425e-05,
498
+ "loss": 0.4678,
499
+ "step": 1400
500
+ },
501
+ {
502
+ "epoch": 2.1162444113263787,
503
+ "grad_norm": 0.05981365218758583,
504
+ "learning_rate": 4.175358540768922e-05,
505
+ "loss": 0.4684,
506
+ "step": 1420
507
+ },
508
+ {
509
+ "epoch": 2.1460506706408347,
510
+ "grad_norm": 0.05496670678257942,
511
+ "learning_rate": 3.9182067398924324e-05,
512
+ "loss": 0.4646,
513
+ "step": 1440
514
+ },
515
+ {
516
+ "epoch": 2.1758569299552906,
517
+ "grad_norm": 0.05577287822961807,
518
+ "learning_rate": 3.667285307194176e-05,
519
+ "loss": 0.4696,
520
+ "step": 1460
521
+ },
522
+ {
523
+ "epoch": 2.2056631892697465,
524
+ "grad_norm": 0.054632559418678284,
525
+ "learning_rate": 3.422851293981676e-05,
526
+ "loss": 0.4686,
527
+ "step": 1480
528
+ },
529
+ {
530
+ "epoch": 2.235469448584203,
531
+ "grad_norm": 0.05347989872097969,
532
+ "learning_rate": 3.185155105658798e-05,
533
+ "loss": 0.4593,
534
+ "step": 1500
535
+ }
536
+ ],
537
+ "logging_steps": 20,
538
+ "max_steps": 2013,
539
+ "num_input_tokens_seen": 0,
540
+ "num_train_epochs": 3,
541
+ "save_steps": 500,
542
+ "stateful_callbacks": {
543
+ "TrainerControl": {
544
+ "args": {
545
+ "should_epoch_stop": false,
546
+ "should_evaluate": false,
547
+ "should_log": false,
548
+ "should_save": true,
549
+ "should_training_stop": false
550
+ },
551
+ "attributes": {}
552
+ }
553
+ },
554
+ "total_flos": 5.5407796188453274e+17,
555
+ "train_batch_size": 2,
556
+ "trial_name": null,
557
+ "trial_params": null
558
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432db7d0354841679f4dbd7551902fa9fde7eb28f12df94fbae067a1e3f5b770
3
+ size 5624
checkpoint-2000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-128k-instruct
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 0.12.0
checkpoint-2000/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj",
25
+ "k_proj",
26
+ "o_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
checkpoint-2000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19261e5251be0e7399c5b81505ceab61d97e5820684ec4b2eddc3eb77aa55b3
3
+ size 494047976
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfb507220787c1b0c4a1c46ed5961da4149dba4618154283932b4b67f0262d3
3
+ size 201381818
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831b553317dc18a71340041751ee40d2dd3693fd60d6a76294dfad47fd240956
3
+ size 14244
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b606b7072d6735cf89a7f009a62b050762f6ff828130da49f78ca563d025ae62
3
+ size 1064
checkpoint-2000/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32011": {
119
+ "content": "<|im_start|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|im_end|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ }
134
+ },
135
+ "additional_special_tokens": [
136
+ "<|im_start|>",
137
+ "<|im_end|>"
138
+ ],
139
+ "bos_token": "<|im_start|>",
140
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
141
+ "clean_up_tokenization_spaces": false,
142
+ "eos_token": "<|im_end|>",
143
+ "legacy": false,
144
+ "model_max_length": 131072,
145
+ "pad_token": "<|im_end|>",
146
+ "padding_side": "right",
147
+ "sp_model_kwargs": {},
148
+ "tokenizer_class": "LlamaTokenizer",
149
+ "unk_token": "<unk>",
150
+ "use_default_system_prompt": false
151
+ }
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9806259314456036,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.029806259314456036,
13
+ "grad_norm": 0.22671940922737122,
14
+ "learning_rate": 8e-05,
15
+ "loss": 1.3506,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.05961251862891207,
20
+ "grad_norm": 0.05189573019742966,
21
+ "learning_rate": 0.00016,
22
+ "loss": 0.8372,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.08941877794336811,
27
+ "grad_norm": 0.049646440893411636,
28
+ "learning_rate": 0.0001999871938117722,
29
+ "loss": 0.7053,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.11922503725782414,
34
+ "grad_norm": 0.04605806618928909,
35
+ "learning_rate": 0.0001998847639849245,
36
+ "loss": 0.5957,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.14903129657228018,
41
+ "grad_norm": 0.04606040194630623,
42
+ "learning_rate": 0.0001996800092633612,
43
+ "loss": 0.5457,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.17883755588673622,
48
+ "grad_norm": 0.03791499882936478,
49
+ "learning_rate": 0.0001993731394038509,
50
+ "loss": 0.5301,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.20864381520119224,
55
+ "grad_norm": 0.047940950840711594,
56
+ "learning_rate": 0.0001989644687729177,
57
+ "loss": 0.5223,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.23845007451564829,
62
+ "grad_norm": 0.0519738644361496,
63
+ "learning_rate": 0.0001984544160247949,
64
+ "loss": 0.5117,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.26825633383010433,
69
+ "grad_norm": 0.04569224268198013,
70
+ "learning_rate": 0.00019784350367254322,
71
+ "loss": 0.5181,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.29806259314456035,
76
+ "grad_norm": 0.045780543237924576,
77
+ "learning_rate": 0.0001971323575527731,
78
+ "loss": 0.5168,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.32786885245901637,
83
+ "grad_norm": 0.046496499329805374,
84
+ "learning_rate": 0.0001963217061845192,
85
+ "loss": 0.5051,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.35767511177347244,
90
+ "grad_norm": 0.04850991442799568,
91
+ "learning_rate": 0.00019541238002292394,
92
+ "loss": 0.5083,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.38748137108792846,
97
+ "grad_norm": 0.046593230217695236,
98
+ "learning_rate": 0.00019440531060849504,
99
+ "loss": 0.5066,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.4172876304023845,
104
+ "grad_norm": 0.050816215574741364,
105
+ "learning_rate": 0.00019330152961280765,
106
+ "loss": 0.5021,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.44709388971684055,
111
+ "grad_norm": 0.0533340722322464,
112
+ "learning_rate": 0.00019210216778162994,
113
+ "loss": 0.5017,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.47690014903129657,
118
+ "grad_norm": 0.10607749223709106,
119
+ "learning_rate": 0.00019080845377655352,
120
+ "loss": 0.4996,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.5067064083457526,
125
+ "grad_norm": 0.054169464856386185,
126
+ "learning_rate": 0.00018942171291631653,
127
+ "loss": 0.5014,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.5365126676602087,
132
+ "grad_norm": 0.047340892255306244,
133
+ "learning_rate": 0.000187943365819108,
134
+ "loss": 0.4988,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.5663189269746647,
139
+ "grad_norm": 0.04948943480849266,
140
+ "learning_rate": 0.00018637492694724466,
141
+ "loss": 0.4975,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.5961251862891207,
146
+ "grad_norm": 0.04684118553996086,
147
+ "learning_rate": 0.00018471800305571129,
148
+ "loss": 0.4961,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.6259314456035767,
153
+ "grad_norm": 0.04512176662683487,
154
+ "learning_rate": 0.00018297429154615338,
155
+ "loss": 0.4956,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.6557377049180327,
160
+ "grad_norm": 0.05711393430829048,
161
+ "learning_rate": 0.00018114557872800905,
162
+ "loss": 0.4944,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.6855439642324889,
167
+ "grad_norm": 0.05339927598834038,
168
+ "learning_rate": 0.000179233737988561,
169
+ "loss": 0.4922,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.7153502235469449,
174
+ "grad_norm": 0.04622140899300575,
175
+ "learning_rate": 0.00017724072787378333,
176
+ "loss": 0.4846,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.7451564828614009,
181
+ "grad_norm": 0.0447109080851078,
182
+ "learning_rate": 0.00017516859008194938,
183
+ "loss": 0.4855,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.7749627421758569,
188
+ "grad_norm": 0.0435018390417099,
189
+ "learning_rate": 0.00017301944737205588,
190
+ "loss": 0.486,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.8047690014903129,
195
+ "grad_norm": 0.04844864085316658,
196
+ "learning_rate": 0.0001707955013892061,
197
+ "loss": 0.4911,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 0.834575260804769,
202
+ "grad_norm": 0.05155207961797714,
203
+ "learning_rate": 0.00016849903040917975,
204
+ "loss": 0.4861,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 0.8643815201192251,
209
+ "grad_norm": 0.04522501304745674,
210
+ "learning_rate": 0.00016613238700450013,
211
+ "loss": 0.4852,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 0.8941877794336811,
216
+ "grad_norm": 0.047208670526742935,
217
+ "learning_rate": 0.00016369799563438958,
218
+ "loss": 0.4844,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 0.9239940387481371,
223
+ "grad_norm": 0.054809391498565674,
224
+ "learning_rate": 0.00016119835016108197,
225
+ "loss": 0.4815,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 0.9538002980625931,
230
+ "grad_norm": 0.04929815232753754,
231
+ "learning_rate": 0.00015863601129503688,
232
+ "loss": 0.4823,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 0.9836065573770492,
237
+ "grad_norm": 0.05650775134563446,
238
+ "learning_rate": 0.00015601360397167214,
239
+ "loss": 0.481,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 1.0134128166915053,
244
+ "grad_norm": 0.04741150885820389,
245
+ "learning_rate": 0.00015333381466230294,
246
+ "loss": 0.488,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 1.0432190760059612,
251
+ "grad_norm": 0.057174187153577805,
252
+ "learning_rate": 0.00015059938862204127,
253
+ "loss": 0.4821,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 1.0730253353204173,
258
+ "grad_norm": 0.054773855954408646,
259
+ "learning_rate": 0.0001478131270774758,
260
+ "loss": 0.4776,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 1.1028315946348732,
265
+ "grad_norm": 0.05249800160527229,
266
+ "learning_rate": 0.0001449778843570128,
267
+ "loss": 0.4782,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 1.1326378539493294,
272
+ "grad_norm": 0.049587223678827286,
273
+ "learning_rate": 0.00014209656496681812,
274
+ "loss": 0.4819,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 1.1624441132637853,
279
+ "grad_norm": 0.048591841012239456,
280
+ "learning_rate": 0.0001391721206153554,
281
+ "loss": 0.4796,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 1.1922503725782414,
286
+ "grad_norm": 0.05344521254301071,
287
+ "learning_rate": 0.000136207547189569,
288
+ "loss": 0.472,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 1.2220566318926975,
293
+ "grad_norm": 0.052742790430784225,
294
+ "learning_rate": 0.0001332058816858092,
295
+ "loss": 0.476,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 1.2518628912071534,
300
+ "grad_norm": 0.05483981594443321,
301
+ "learning_rate": 0.00013017019909864364,
302
+ "loss": 0.4755,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 1.2816691505216096,
307
+ "grad_norm": 0.050890855491161346,
308
+ "learning_rate": 0.00012710360927074233,
309
+ "loss": 0.4719,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 1.3114754098360657,
314
+ "grad_norm": 0.05531829223036766,
315
+ "learning_rate": 0.0001240092537070631,
316
+ "loss": 0.4745,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 1.3412816691505216,
321
+ "grad_norm": 0.05655696988105774,
322
+ "learning_rate": 0.00012089030235660155,
323
+ "loss": 0.475,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 1.3710879284649775,
328
+ "grad_norm": 0.059185780584812164,
329
+ "learning_rate": 0.00011774995036500181,
330
+ "loss": 0.4714,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 1.4008941877794336,
335
+ "grad_norm": 0.05000292509794235,
336
+ "learning_rate": 0.00011459141480135518,
337
+ "loss": 0.4774,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 1.4307004470938898,
342
+ "grad_norm": 0.05054055526852608,
343
+ "learning_rate": 0.00011141793136253986,
344
+ "loss": 0.4666,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 1.4605067064083457,
349
+ "grad_norm": 0.04777640849351883,
350
+ "learning_rate": 0.00010823275105847772,
351
+ "loss": 0.4711,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 1.4903129657228018,
356
+ "grad_norm": 0.05582300201058388,
357
+ "learning_rate": 0.00010503913688170396,
358
+ "loss": 0.4668,
359
+ "step": 1000
360
+ },
361
+ {
362
+ "epoch": 1.520119225037258,
363
+ "grad_norm": 0.059767983853816986,
364
+ "learning_rate": 0.00010184036046466143,
365
+ "loss": 0.4683,
366
+ "step": 1020
367
+ },
368
+ {
369
+ "epoch": 1.5499254843517138,
370
+ "grad_norm": 0.0632881224155426,
371
+ "learning_rate": 9.863969872814403e-05,
372
+ "loss": 0.4695,
373
+ "step": 1040
374
+ },
375
+ {
376
+ "epoch": 1.5797317436661698,
377
+ "grad_norm": 0.05366360396146774,
378
+ "learning_rate": 9.544043052432244e-05,
379
+ "loss": 0.4672,
380
+ "step": 1060
381
+ },
382
+ {
383
+ "epoch": 1.6095380029806259,
384
+ "grad_norm": 0.049754392355680466,
385
+ "learning_rate": 9.224583327779134e-05,
386
+ "loss": 0.4655,
387
+ "step": 1080
388
+ },
389
+ {
390
+ "epoch": 1.639344262295082,
391
+ "grad_norm": 0.055744487792253494,
392
+ "learning_rate": 8.905917962807927e-05,
393
+ "loss": 0.4714,
394
+ "step": 1100
395
+ },
396
+ {
397
+ "epoch": 1.669150521609538,
398
+ "grad_norm": 0.05113043636083603,
399
+ "learning_rate": 8.588373407706007e-05,
400
+ "loss": 0.4626,
401
+ "step": 1120
402
+ },
403
+ {
404
+ "epoch": 1.698956780923994,
405
+ "grad_norm": 0.05468016862869263,
406
+ "learning_rate": 8.272274964470118e-05,
407
+ "loss": 0.4681,
408
+ "step": 1140
409
+ },
410
+ {
411
+ "epoch": 1.7287630402384502,
412
+ "grad_norm": 0.05420814827084541,
413
+ "learning_rate": 7.957946453657403e-05,
414
+ "loss": 0.4684,
415
+ "step": 1160
416
+ },
417
+ {
418
+ "epoch": 1.758569299552906,
419
+ "grad_norm": 0.06343657523393631,
420
+ "learning_rate": 7.645709882654093e-05,
421
+ "loss": 0.4659,
422
+ "step": 1180
423
+ },
424
+ {
425
+ "epoch": 1.788375558867362,
426
+ "grad_norm": 0.05385758727788925,
427
+ "learning_rate": 7.335885115801656e-05,
428
+ "loss": 0.4659,
429
+ "step": 1200
430
+ },
431
+ {
432
+ "epoch": 1.8181818181818183,
433
+ "grad_norm": 0.05174577608704567,
434
+ "learning_rate": 7.028789546718326e-05,
435
+ "loss": 0.4646,
436
+ "step": 1220
437
+ },
438
+ {
439
+ "epoch": 1.8479880774962743,
440
+ "grad_norm": 0.05492328852415085,
441
+ "learning_rate": 6.72473777315176e-05,
442
+ "loss": 0.4657,
443
+ "step": 1240
444
+ },
445
+ {
446
+ "epoch": 1.8777943368107302,
447
+ "grad_norm": 0.060056205838918686,
448
+ "learning_rate": 6.424041274695804e-05,
449
+ "loss": 0.4677,
450
+ "step": 1260
451
+ },
452
+ {
453
+ "epoch": 1.9076005961251863,
454
+ "grad_norm": 0.061595309525728226,
455
+ "learning_rate": 6.127008093701658e-05,
456
+ "loss": 0.4661,
457
+ "step": 1280
458
+ },
459
+ {
460
+ "epoch": 1.9374068554396424,
461
+ "grad_norm": 0.05786813423037529,
462
+ "learning_rate": 5.833942519710177e-05,
463
+ "loss": 0.4641,
464
+ "step": 1300
465
+ },
466
+ {
467
+ "epoch": 1.9672131147540983,
468
+ "grad_norm": 0.05672052502632141,
469
+ "learning_rate": 5.5451447777287324e-05,
470
+ "loss": 0.4653,
471
+ "step": 1320
472
+ },
473
+ {
474
+ "epoch": 1.9970193740685542,
475
+ "grad_norm": 0.06217477470636368,
476
+ "learning_rate": 5.260910720671858e-05,
477
+ "loss": 0.4658,
478
+ "step": 1340
479
+ },
480
+ {
481
+ "epoch": 2.0268256333830106,
482
+ "grad_norm": 0.05346861109137535,
483
+ "learning_rate": 4.981531526280807e-05,
484
+ "loss": 0.4665,
485
+ "step": 1360
486
+ },
487
+ {
488
+ "epoch": 2.0566318926974665,
489
+ "grad_norm": 0.05857508257031441,
490
+ "learning_rate": 4.707293398832504e-05,
491
+ "loss": 0.4676,
492
+ "step": 1380
493
+ },
494
+ {
495
+ "epoch": 2.0864381520119224,
496
+ "grad_norm": 0.05544683709740639,
497
+ "learning_rate": 4.4384772759434425e-05,
498
+ "loss": 0.4678,
499
+ "step": 1400
500
+ },
501
+ {
502
+ "epoch": 2.1162444113263787,
503
+ "grad_norm": 0.05981365218758583,
504
+ "learning_rate": 4.175358540768922e-05,
505
+ "loss": 0.4684,
506
+ "step": 1420
507
+ },
508
+ {
509
+ "epoch": 2.1460506706408347,
510
+ "grad_norm": 0.05496670678257942,
511
+ "learning_rate": 3.9182067398924324e-05,
512
+ "loss": 0.4646,
513
+ "step": 1440
514
+ },
515
+ {
516
+ "epoch": 2.1758569299552906,
517
+ "grad_norm": 0.05577287822961807,
518
+ "learning_rate": 3.667285307194176e-05,
519
+ "loss": 0.4696,
520
+ "step": 1460
521
+ },
522
+ {
523
+ "epoch": 2.2056631892697465,
524
+ "grad_norm": 0.054632559418678284,
525
+ "learning_rate": 3.422851293981676e-05,
526
+ "loss": 0.4686,
527
+ "step": 1480
528
+ },
529
+ {
530
+ "epoch": 2.235469448584203,
531
+ "grad_norm": 0.05347989872097969,
532
+ "learning_rate": 3.185155105658798e-05,
533
+ "loss": 0.4593,
534
+ "step": 1500
535
+ },
536
+ {
537
+ "epoch": 2.2652757078986587,
538
+ "grad_norm": 0.055116716772317886,
539
+ "learning_rate": 2.9544402452031228e-05,
540
+ "loss": 0.4624,
541
+ "step": 1520
542
+ },
543
+ {
544
+ "epoch": 2.2950819672131146,
545
+ "grad_norm": 0.06154646724462509,
546
+ "learning_rate": 2.7309430637142908e-05,
547
+ "loss": 0.4594,
548
+ "step": 1540
549
+ },
550
+ {
551
+ "epoch": 2.3248882265275705,
552
+ "grad_norm": 0.05557813495397568,
553
+ "learning_rate": 2.514892518288988e-05,
554
+ "loss": 0.465,
555
+ "step": 1560
556
+ },
557
+ {
558
+ "epoch": 2.354694485842027,
559
+ "grad_norm": 0.059582650661468506,
560
+ "learning_rate": 2.30650993747055e-05,
561
+ "loss": 0.4676,
562
+ "step": 1580
563
+ },
564
+ {
565
+ "epoch": 2.384500745156483,
566
+ "grad_norm": 0.05283711850643158,
567
+ "learning_rate": 2.1060087945134677e-05,
568
+ "loss": 0.4606,
569
+ "step": 1600
570
+ },
571
+ {
572
+ "epoch": 2.4143070044709387,
573
+ "grad_norm": 0.052977778017520905,
574
+ "learning_rate": 1.9135944886951297e-05,
575
+ "loss": 0.4555,
576
+ "step": 1620
577
+ },
578
+ {
579
+ "epoch": 2.444113263785395,
580
+ "grad_norm": 0.05678584426641464,
581
+ "learning_rate": 1.7294641348987062e-05,
582
+ "loss": 0.4594,
583
+ "step": 1640
584
+ },
585
+ {
586
+ "epoch": 2.473919523099851,
587
+ "grad_norm": 0.05940232425928116,
588
+ "learning_rate": 1.5538063616829045e-05,
589
+ "loss": 0.4646,
590
+ "step": 1660
591
+ },
592
+ {
593
+ "epoch": 2.503725782414307,
594
+ "grad_norm": 0.05490659549832344,
595
+ "learning_rate": 1.3868011180452723e-05,
596
+ "loss": 0.4623,
597
+ "step": 1680
598
+ },
599
+ {
600
+ "epoch": 2.533532041728763,
601
+ "grad_norm": 0.06109332665801048,
602
+ "learning_rate": 1.2286194890771819e-05,
603
+ "loss": 0.4578,
604
+ "step": 1700
605
+ },
606
+ {
607
+ "epoch": 2.563338301043219,
608
+ "grad_norm": 0.1325128823518753,
609
+ "learning_rate": 1.0794235206991854e-05,
610
+ "loss": 0.4596,
611
+ "step": 1720
612
+ },
613
+ {
614
+ "epoch": 2.593144560357675,
615
+ "grad_norm": 0.058020610362291336,
616
+ "learning_rate": 9.393660536564408e-06,
617
+ "loss": 0.4557,
618
+ "step": 1740
619
+ },
620
+ {
621
+ "epoch": 2.6229508196721314,
622
+ "grad_norm": 0.05302806943655014,
623
+ "learning_rate": 8.085905669441096e-06,
624
+ "loss": 0.4579,
625
+ "step": 1760
626
+ },
627
+ {
628
+ "epoch": 2.6527570789865873,
629
+ "grad_norm": 0.06191584840416908,
630
+ "learning_rate": 6.8723103082327655e-06,
631
+ "loss": 0.4573,
632
+ "step": 1780
633
+ },
634
+ {
635
+ "epoch": 2.682563338301043,
636
+ "grad_norm": 0.05629570782184601,
637
+ "learning_rate": 5.7541176957785605e-06,
638
+ "loss": 0.4546,
639
+ "step": 1800
640
+ },
641
+ {
642
+ "epoch": 2.712369597615499,
643
+ "grad_norm": 0.05981377512216568,
644
+ "learning_rate": 4.732473341531307e-06,
645
+ "loss": 0.4604,
646
+ "step": 1820
647
+ },
648
+ {
649
+ "epoch": 2.742175856929955,
650
+ "grad_norm": 0.05614262446761131,
651
+ "learning_rate": 3.808423848064013e-06,
652
+ "loss": 0.4586,
653
+ "step": 1840
654
+ },
655
+ {
656
+ "epoch": 2.7719821162444114,
657
+ "grad_norm": 0.05837514251470566,
658
+ "learning_rate": 2.9829158388991584e-06,
659
+ "loss": 0.4563,
660
+ "step": 1860
661
+ },
662
+ {
663
+ "epoch": 2.8017883755588673,
664
+ "grad_norm": 0.05666237697005272,
665
+ "learning_rate": 2.2567949887598806e-06,
666
+ "loss": 0.4567,
667
+ "step": 1880
668
+ },
669
+ {
670
+ "epoch": 2.8315946348733236,
671
+ "grad_norm": 0.05505252629518509,
672
+ "learning_rate": 1.6308051572357152e-06,
673
+ "loss": 0.4565,
674
+ "step": 1900
675
+ },
676
+ {
677
+ "epoch": 2.8614008941877795,
678
+ "grad_norm": 0.05452287942171097,
679
+ "learning_rate": 1.1055876267510256e-06,
680
+ "loss": 0.4599,
681
+ "step": 1920
682
+ },
683
+ {
684
+ "epoch": 2.8912071535022354,
685
+ "grad_norm": 0.05594036355614662,
686
+ "learning_rate": 6.816804456163284e-07,
687
+ "loss": 0.4599,
688
+ "step": 1940
689
+ },
690
+ {
691
+ "epoch": 2.9210134128166914,
692
+ "grad_norm": 0.05466296523809433,
693
+ "learning_rate": 3.595178768358021e-07,
694
+ "loss": 0.4591,
695
+ "step": 1960
696
+ },
697
+ {
698
+ "epoch": 2.9508196721311473,
699
+ "grad_norm": 0.05625637248158455,
700
+ "learning_rate": 1.3942995323543706e-07,
701
+ "loss": 0.4571,
702
+ "step": 1980
703
+ },
704
+ {
705
+ "epoch": 2.9806259314456036,
706
+ "grad_norm": 0.05620352923870087,
707
+ "learning_rate": 2.164213936770576e-08,
708
+ "loss": 0.4596,
709
+ "step": 2000
710
+ }
711
+ ],
712
+ "logging_steps": 20,
713
+ "max_steps": 2013,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 3,
716
+ "save_steps": 500,
717
+ "stateful_callbacks": {
718
+ "TrainerControl": {
719
+ "args": {
720
+ "should_epoch_stop": false,
721
+ "should_evaluate": false,
722
+ "should_log": false,
723
+ "should_save": true,
724
+ "should_training_stop": false
725
+ },
726
+ "attributes": {}
727
+ }
728
+ },
729
+ "total_flos": 7.382794119791247e+17,
730
+ "train_batch_size": 2,
731
+ "trial_name": null,
732
+ "trial_params": null
733
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432db7d0354841679f4dbd7551902fa9fde7eb28f12df94fbae067a1e3f5b770
3
+ size 5624
checkpoint-2013/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-128k-instruct
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 0.12.0
checkpoint-2013/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj",
25
+ "k_proj",
26
+ "o_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
checkpoint-2013/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057b0d140ca2511f2d0bce76c880c577156186db5a7890c907ac56a24653246f
3
+ size 494047976
checkpoint-2013/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ebc3d749cdc0f244445e33bc45ed0b48a8ed5cd07836296667494e1a571d28d
3
+ size 201381818
checkpoint-2013/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f8c363649c4e46cef97745088a8e4c36cdff05c43dc550f376762915602996
3
+ size 14244
checkpoint-2013/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a454c9b3f6121f7efbfdd8d1c962a1e2e6d47501ab60156b3fbbf82701fda2c5
3
+ size 1064
checkpoint-2013/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
checkpoint-2013/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2013/tokenizer_config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32011": {
119
+ "content": "<|im_start|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|im_end|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ }
134
+ },
135
+ "additional_special_tokens": [
136
+ "<|im_start|>",
137
+ "<|im_end|>"
138
+ ],
139
+ "bos_token": "<|im_start|>",
140
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
141
+ "clean_up_tokenization_spaces": false,
142
+ "eos_token": "<|im_end|>",
143
+ "legacy": false,
144
+ "model_max_length": 131072,
145
+ "pad_token": "<|im_end|>",
146
+ "padding_side": "right",
147
+ "sp_model_kwargs": {},
148
+ "tokenizer_class": "LlamaTokenizer",
149
+ "unk_token": "<unk>",
150
+ "use_default_system_prompt": false
151
+ }
checkpoint-2013/trainer_state.json ADDED
@@ -0,0 +1,733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2013,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.029806259314456036,
13
+ "grad_norm": 0.22671940922737122,
14
+ "learning_rate": 8e-05,
15
+ "loss": 1.3506,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.05961251862891207,
20
+ "grad_norm": 0.05189573019742966,
21
+ "learning_rate": 0.00016,
22
+ "loss": 0.8372,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.08941877794336811,
27
+ "grad_norm": 0.049646440893411636,
28
+ "learning_rate": 0.0001999871938117722,
29
+ "loss": 0.7053,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.11922503725782414,
34
+ "grad_norm": 0.04605806618928909,
35
+ "learning_rate": 0.0001998847639849245,
36
+ "loss": 0.5957,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.14903129657228018,
41
+ "grad_norm": 0.04606040194630623,
42
+ "learning_rate": 0.0001996800092633612,
43
+ "loss": 0.5457,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.17883755588673622,
48
+ "grad_norm": 0.03791499882936478,
49
+ "learning_rate": 0.0001993731394038509,
50
+ "loss": 0.5301,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.20864381520119224,
55
+ "grad_norm": 0.047940950840711594,
56
+ "learning_rate": 0.0001989644687729177,
57
+ "loss": 0.5223,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.23845007451564829,
62
+ "grad_norm": 0.0519738644361496,
63
+ "learning_rate": 0.0001984544160247949,
64
+ "loss": 0.5117,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.26825633383010433,
69
+ "grad_norm": 0.04569224268198013,
70
+ "learning_rate": 0.00019784350367254322,
71
+ "loss": 0.5181,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.29806259314456035,
76
+ "grad_norm": 0.045780543237924576,
77
+ "learning_rate": 0.0001971323575527731,
78
+ "loss": 0.5168,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.32786885245901637,
83
+ "grad_norm": 0.046496499329805374,
84
+ "learning_rate": 0.0001963217061845192,
85
+ "loss": 0.5051,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.35767511177347244,
90
+ "grad_norm": 0.04850991442799568,
91
+ "learning_rate": 0.00019541238002292394,
92
+ "loss": 0.5083,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.38748137108792846,
97
+ "grad_norm": 0.046593230217695236,
98
+ "learning_rate": 0.00019440531060849504,
99
+ "loss": 0.5066,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.4172876304023845,
104
+ "grad_norm": 0.050816215574741364,
105
+ "learning_rate": 0.00019330152961280765,
106
+ "loss": 0.5021,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.44709388971684055,
111
+ "grad_norm": 0.0533340722322464,
112
+ "learning_rate": 0.00019210216778162994,
113
+ "loss": 0.5017,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.47690014903129657,
118
+ "grad_norm": 0.10607749223709106,
119
+ "learning_rate": 0.00019080845377655352,
120
+ "loss": 0.4996,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.5067064083457526,
125
+ "grad_norm": 0.054169464856386185,
126
+ "learning_rate": 0.00018942171291631653,
127
+ "loss": 0.5014,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.5365126676602087,
132
+ "grad_norm": 0.047340892255306244,
133
+ "learning_rate": 0.000187943365819108,
134
+ "loss": 0.4988,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.5663189269746647,
139
+ "grad_norm": 0.04948943480849266,
140
+ "learning_rate": 0.00018637492694724466,
141
+ "loss": 0.4975,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.5961251862891207,
146
+ "grad_norm": 0.04684118553996086,
147
+ "learning_rate": 0.00018471800305571129,
148
+ "loss": 0.4961,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.6259314456035767,
153
+ "grad_norm": 0.04512176662683487,
154
+ "learning_rate": 0.00018297429154615338,
155
+ "loss": 0.4956,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.6557377049180327,
160
+ "grad_norm": 0.05711393430829048,
161
+ "learning_rate": 0.00018114557872800905,
162
+ "loss": 0.4944,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.6855439642324889,
167
+ "grad_norm": 0.05339927598834038,
168
+ "learning_rate": 0.000179233737988561,
169
+ "loss": 0.4922,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.7153502235469449,
174
+ "grad_norm": 0.04622140899300575,
175
+ "learning_rate": 0.00017724072787378333,
176
+ "loss": 0.4846,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.7451564828614009,
181
+ "grad_norm": 0.0447109080851078,
182
+ "learning_rate": 0.00017516859008194938,
183
+ "loss": 0.4855,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.7749627421758569,
188
+ "grad_norm": 0.0435018390417099,
189
+ "learning_rate": 0.00017301944737205588,
190
+ "loss": 0.486,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.8047690014903129,
195
+ "grad_norm": 0.04844864085316658,
196
+ "learning_rate": 0.0001707955013892061,
197
+ "loss": 0.4911,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 0.834575260804769,
202
+ "grad_norm": 0.05155207961797714,
203
+ "learning_rate": 0.00016849903040917975,
204
+ "loss": 0.4861,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 0.8643815201192251,
209
+ "grad_norm": 0.04522501304745674,
210
+ "learning_rate": 0.00016613238700450013,
211
+ "loss": 0.4852,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 0.8941877794336811,
216
+ "grad_norm": 0.047208670526742935,
217
+ "learning_rate": 0.00016369799563438958,
218
+ "loss": 0.4844,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 0.9239940387481371,
223
+ "grad_norm": 0.054809391498565674,
224
+ "learning_rate": 0.00016119835016108197,
225
+ "loss": 0.4815,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 0.9538002980625931,
230
+ "grad_norm": 0.04929815232753754,
231
+ "learning_rate": 0.00015863601129503688,
232
+ "loss": 0.4823,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 0.9836065573770492,
237
+ "grad_norm": 0.05650775134563446,
238
+ "learning_rate": 0.00015601360397167214,
239
+ "loss": 0.481,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 1.0134128166915053,
244
+ "grad_norm": 0.04741150885820389,
245
+ "learning_rate": 0.00015333381466230294,
246
+ "loss": 0.488,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 1.0432190760059612,
251
+ "grad_norm": 0.057174187153577805,
252
+ "learning_rate": 0.00015059938862204127,
253
+ "loss": 0.4821,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 1.0730253353204173,
258
+ "grad_norm": 0.054773855954408646,
259
+ "learning_rate": 0.0001478131270774758,
260
+ "loss": 0.4776,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 1.1028315946348732,
265
+ "grad_norm": 0.05249800160527229,
266
+ "learning_rate": 0.0001449778843570128,
267
+ "loss": 0.4782,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 1.1326378539493294,
272
+ "grad_norm": 0.049587223678827286,
273
+ "learning_rate": 0.00014209656496681812,
274
+ "loss": 0.4819,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 1.1624441132637853,
279
+ "grad_norm": 0.048591841012239456,
280
+ "learning_rate": 0.0001391721206153554,
281
+ "loss": 0.4796,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 1.1922503725782414,
286
+ "grad_norm": 0.05344521254301071,
287
+ "learning_rate": 0.000136207547189569,
288
+ "loss": 0.472,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 1.2220566318926975,
293
+ "grad_norm": 0.052742790430784225,
294
+ "learning_rate": 0.0001332058816858092,
295
+ "loss": 0.476,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 1.2518628912071534,
300
+ "grad_norm": 0.05483981594443321,
301
+ "learning_rate": 0.00013017019909864364,
302
+ "loss": 0.4755,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 1.2816691505216096,
307
+ "grad_norm": 0.050890855491161346,
308
+ "learning_rate": 0.00012710360927074233,
309
+ "loss": 0.4719,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 1.3114754098360657,
314
+ "grad_norm": 0.05531829223036766,
315
+ "learning_rate": 0.0001240092537070631,
316
+ "loss": 0.4745,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 1.3412816691505216,
321
+ "grad_norm": 0.05655696988105774,
322
+ "learning_rate": 0.00012089030235660155,
323
+ "loss": 0.475,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 1.3710879284649775,
328
+ "grad_norm": 0.059185780584812164,
329
+ "learning_rate": 0.00011774995036500181,
330
+ "loss": 0.4714,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 1.4008941877794336,
335
+ "grad_norm": 0.05000292509794235,
336
+ "learning_rate": 0.00011459141480135518,
337
+ "loss": 0.4774,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 1.4307004470938898,
342
+ "grad_norm": 0.05054055526852608,
343
+ "learning_rate": 0.00011141793136253986,
344
+ "loss": 0.4666,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 1.4605067064083457,
349
+ "grad_norm": 0.04777640849351883,
350
+ "learning_rate": 0.00010823275105847772,
351
+ "loss": 0.4711,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 1.4903129657228018,
356
+ "grad_norm": 0.05582300201058388,
357
+ "learning_rate": 0.00010503913688170396,
358
+ "loss": 0.4668,
359
+ "step": 1000
360
+ },
361
+ {
362
+ "epoch": 1.520119225037258,
363
+ "grad_norm": 0.059767983853816986,
364
+ "learning_rate": 0.00010184036046466143,
365
+ "loss": 0.4683,
366
+ "step": 1020
367
+ },
368
+ {
369
+ "epoch": 1.5499254843517138,
370
+ "grad_norm": 0.0632881224155426,
371
+ "learning_rate": 9.863969872814403e-05,
372
+ "loss": 0.4695,
373
+ "step": 1040
374
+ },
375
+ {
376
+ "epoch": 1.5797317436661698,
377
+ "grad_norm": 0.05366360396146774,
378
+ "learning_rate": 9.544043052432244e-05,
379
+ "loss": 0.4672,
380
+ "step": 1060
381
+ },
382
+ {
383
+ "epoch": 1.6095380029806259,
384
+ "grad_norm": 0.049754392355680466,
385
+ "learning_rate": 9.224583327779134e-05,
386
+ "loss": 0.4655,
387
+ "step": 1080
388
+ },
389
+ {
390
+ "epoch": 1.639344262295082,
391
+ "grad_norm": 0.055744487792253494,
392
+ "learning_rate": 8.905917962807927e-05,
393
+ "loss": 0.4714,
394
+ "step": 1100
395
+ },
396
+ {
397
+ "epoch": 1.669150521609538,
398
+ "grad_norm": 0.05113043636083603,
399
+ "learning_rate": 8.588373407706007e-05,
400
+ "loss": 0.4626,
401
+ "step": 1120
402
+ },
403
+ {
404
+ "epoch": 1.698956780923994,
405
+ "grad_norm": 0.05468016862869263,
406
+ "learning_rate": 8.272274964470118e-05,
407
+ "loss": 0.4681,
408
+ "step": 1140
409
+ },
410
+ {
411
+ "epoch": 1.7287630402384502,
412
+ "grad_norm": 0.05420814827084541,
413
+ "learning_rate": 7.957946453657403e-05,
414
+ "loss": 0.4684,
415
+ "step": 1160
416
+ },
417
+ {
418
+ "epoch": 1.758569299552906,
419
+ "grad_norm": 0.06343657523393631,
420
+ "learning_rate": 7.645709882654093e-05,
421
+ "loss": 0.4659,
422
+ "step": 1180
423
+ },
424
+ {
425
+ "epoch": 1.788375558867362,
426
+ "grad_norm": 0.05385758727788925,
427
+ "learning_rate": 7.335885115801656e-05,
428
+ "loss": 0.4659,
429
+ "step": 1200
430
+ },
431
+ {
432
+ "epoch": 1.8181818181818183,
433
+ "grad_norm": 0.05174577608704567,
434
+ "learning_rate": 7.028789546718326e-05,
435
+ "loss": 0.4646,
436
+ "step": 1220
437
+ },
438
+ {
439
+ "epoch": 1.8479880774962743,
440
+ "grad_norm": 0.05492328852415085,
441
+ "learning_rate": 6.72473777315176e-05,
442
+ "loss": 0.4657,
443
+ "step": 1240
444
+ },
445
+ {
446
+ "epoch": 1.8777943368107302,
447
+ "grad_norm": 0.060056205838918686,
448
+ "learning_rate": 6.424041274695804e-05,
449
+ "loss": 0.4677,
450
+ "step": 1260
451
+ },
452
+ {
453
+ "epoch": 1.9076005961251863,
454
+ "grad_norm": 0.061595309525728226,
455
+ "learning_rate": 6.127008093701658e-05,
456
+ "loss": 0.4661,
457
+ "step": 1280
458
+ },
459
+ {
460
+ "epoch": 1.9374068554396424,
461
+ "grad_norm": 0.05786813423037529,
462
+ "learning_rate": 5.833942519710177e-05,
463
+ "loss": 0.4641,
464
+ "step": 1300
465
+ },
466
+ {
467
+ "epoch": 1.9672131147540983,
468
+ "grad_norm": 0.05672052502632141,
469
+ "learning_rate": 5.5451447777287324e-05,
470
+ "loss": 0.4653,
471
+ "step": 1320
472
+ },
473
+ {
474
+ "epoch": 1.9970193740685542,
475
+ "grad_norm": 0.06217477470636368,
476
+ "learning_rate": 5.260910720671858e-05,
477
+ "loss": 0.4658,
478
+ "step": 1340
479
+ },
480
+ {
481
+ "epoch": 2.0268256333830106,
482
+ "grad_norm": 0.05346861109137535,
483
+ "learning_rate": 4.981531526280807e-05,
484
+ "loss": 0.4665,
485
+ "step": 1360
486
+ },
487
+ {
488
+ "epoch": 2.0566318926974665,
489
+ "grad_norm": 0.05857508257031441,
490
+ "learning_rate": 4.707293398832504e-05,
491
+ "loss": 0.4676,
492
+ "step": 1380
493
+ },
494
+ {
495
+ "epoch": 2.0864381520119224,
496
+ "grad_norm": 0.05544683709740639,
497
+ "learning_rate": 4.4384772759434425e-05,
498
+ "loss": 0.4678,
499
+ "step": 1400
500
+ },
501
+ {
502
+ "epoch": 2.1162444113263787,
503
+ "grad_norm": 0.05981365218758583,
504
+ "learning_rate": 4.175358540768922e-05,
505
+ "loss": 0.4684,
506
+ "step": 1420
507
+ },
508
+ {
509
+ "epoch": 2.1460506706408347,
510
+ "grad_norm": 0.05496670678257942,
511
+ "learning_rate": 3.9182067398924324e-05,
512
+ "loss": 0.4646,
513
+ "step": 1440
514
+ },
515
+ {
516
+ "epoch": 2.1758569299552906,
517
+ "grad_norm": 0.05577287822961807,
518
+ "learning_rate": 3.667285307194176e-05,
519
+ "loss": 0.4696,
520
+ "step": 1460
521
+ },
522
+ {
523
+ "epoch": 2.2056631892697465,
524
+ "grad_norm": 0.054632559418678284,
525
+ "learning_rate": 3.422851293981676e-05,
526
+ "loss": 0.4686,
527
+ "step": 1480
528
+ },
529
+ {
530
+ "epoch": 2.235469448584203,
531
+ "grad_norm": 0.05347989872097969,
532
+ "learning_rate": 3.185155105658798e-05,
533
+ "loss": 0.4593,
534
+ "step": 1500
535
+ },
536
+ {
537
+ "epoch": 2.2652757078986587,
538
+ "grad_norm": 0.055116716772317886,
539
+ "learning_rate": 2.9544402452031228e-05,
540
+ "loss": 0.4624,
541
+ "step": 1520
542
+ },
543
+ {
544
+ "epoch": 2.2950819672131146,
545
+ "grad_norm": 0.06154646724462509,
546
+ "learning_rate": 2.7309430637142908e-05,
547
+ "loss": 0.4594,
548
+ "step": 1540
549
+ },
550
+ {
551
+ "epoch": 2.3248882265275705,
552
+ "grad_norm": 0.05557813495397568,
553
+ "learning_rate": 2.514892518288988e-05,
554
+ "loss": 0.465,
555
+ "step": 1560
556
+ },
557
+ {
558
+ "epoch": 2.354694485842027,
559
+ "grad_norm": 0.059582650661468506,
560
+ "learning_rate": 2.30650993747055e-05,
561
+ "loss": 0.4676,
562
+ "step": 1580
563
+ },
564
+ {
565
+ "epoch": 2.384500745156483,
566
+ "grad_norm": 0.05283711850643158,
567
+ "learning_rate": 2.1060087945134677e-05,
568
+ "loss": 0.4606,
569
+ "step": 1600
570
+ },
571
+ {
572
+ "epoch": 2.4143070044709387,
573
+ "grad_norm": 0.052977778017520905,
574
+ "learning_rate": 1.9135944886951297e-05,
575
+ "loss": 0.4555,
576
+ "step": 1620
577
+ },
578
+ {
579
+ "epoch": 2.444113263785395,
580
+ "grad_norm": 0.05678584426641464,
581
+ "learning_rate": 1.7294641348987062e-05,
582
+ "loss": 0.4594,
583
+ "step": 1640
584
+ },
585
+ {
586
+ "epoch": 2.473919523099851,
587
+ "grad_norm": 0.05940232425928116,
588
+ "learning_rate": 1.5538063616829045e-05,
589
+ "loss": 0.4646,
590
+ "step": 1660
591
+ },
592
+ {
593
+ "epoch": 2.503725782414307,
594
+ "grad_norm": 0.05490659549832344,
595
+ "learning_rate": 1.3868011180452723e-05,
596
+ "loss": 0.4623,
597
+ "step": 1680
598
+ },
599
+ {
600
+ "epoch": 2.533532041728763,
601
+ "grad_norm": 0.06109332665801048,
602
+ "learning_rate": 1.2286194890771819e-05,
603
+ "loss": 0.4578,
604
+ "step": 1700
605
+ },
606
+ {
607
+ "epoch": 2.563338301043219,
608
+ "grad_norm": 0.1325128823518753,
609
+ "learning_rate": 1.0794235206991854e-05,
610
+ "loss": 0.4596,
611
+ "step": 1720
612
+ },
613
+ {
614
+ "epoch": 2.593144560357675,
615
+ "grad_norm": 0.058020610362291336,
616
+ "learning_rate": 9.393660536564408e-06,
617
+ "loss": 0.4557,
618
+ "step": 1740
619
+ },
620
+ {
621
+ "epoch": 2.6229508196721314,
622
+ "grad_norm": 0.05302806943655014,
623
+ "learning_rate": 8.085905669441096e-06,
624
+ "loss": 0.4579,
625
+ "step": 1760
626
+ },
627
+ {
628
+ "epoch": 2.6527570789865873,
629
+ "grad_norm": 0.06191584840416908,
630
+ "learning_rate": 6.8723103082327655e-06,
631
+ "loss": 0.4573,
632
+ "step": 1780
633
+ },
634
+ {
635
+ "epoch": 2.682563338301043,
636
+ "grad_norm": 0.05629570782184601,
637
+ "learning_rate": 5.7541176957785605e-06,
638
+ "loss": 0.4546,
639
+ "step": 1800
640
+ },
641
+ {
642
+ "epoch": 2.712369597615499,
643
+ "grad_norm": 0.05981377512216568,
644
+ "learning_rate": 4.732473341531307e-06,
645
+ "loss": 0.4604,
646
+ "step": 1820
647
+ },
648
+ {
649
+ "epoch": 2.742175856929955,
650
+ "grad_norm": 0.05614262446761131,
651
+ "learning_rate": 3.808423848064013e-06,
652
+ "loss": 0.4586,
653
+ "step": 1840
654
+ },
655
+ {
656
+ "epoch": 2.7719821162444114,
657
+ "grad_norm": 0.05837514251470566,
658
+ "learning_rate": 2.9829158388991584e-06,
659
+ "loss": 0.4563,
660
+ "step": 1860
661
+ },
662
+ {
663
+ "epoch": 2.8017883755588673,
664
+ "grad_norm": 0.05666237697005272,
665
+ "learning_rate": 2.2567949887598806e-06,
666
+ "loss": 0.4567,
667
+ "step": 1880
668
+ },
669
+ {
670
+ "epoch": 2.8315946348733236,
671
+ "grad_norm": 0.05505252629518509,
672
+ "learning_rate": 1.6308051572357152e-06,
673
+ "loss": 0.4565,
674
+ "step": 1900
675
+ },
676
+ {
677
+ "epoch": 2.8614008941877795,
678
+ "grad_norm": 0.05452287942171097,
679
+ "learning_rate": 1.1055876267510256e-06,
680
+ "loss": 0.4599,
681
+ "step": 1920
682
+ },
683
+ {
684
+ "epoch": 2.8912071535022354,
685
+ "grad_norm": 0.05594036355614662,
686
+ "learning_rate": 6.816804456163284e-07,
687
+ "loss": 0.4599,
688
+ "step": 1940
689
+ },
690
+ {
691
+ "epoch": 2.9210134128166914,
692
+ "grad_norm": 0.05466296523809433,
693
+ "learning_rate": 3.595178768358021e-07,
694
+ "loss": 0.4591,
695
+ "step": 1960
696
+ },
697
+ {
698
+ "epoch": 2.9508196721311473,
699
+ "grad_norm": 0.05625637248158455,
700
+ "learning_rate": 1.3942995323543706e-07,
701
+ "loss": 0.4571,
702
+ "step": 1980
703
+ },
704
+ {
705
+ "epoch": 2.9806259314456036,
706
+ "grad_norm": 0.05620352923870087,
707
+ "learning_rate": 2.164213936770576e-08,
708
+ "loss": 0.4596,
709
+ "step": 2000
710
+ }
711
+ ],
712
+ "logging_steps": 20,
713
+ "max_steps": 2013,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 3,
716
+ "save_steps": 500,
717
+ "stateful_callbacks": {
718
+ "TrainerControl": {
719
+ "args": {
720
+ "should_epoch_stop": false,
721
+ "should_evaluate": false,
722
+ "should_log": false,
723
+ "should_save": true,
724
+ "should_training_stop": true
725
+ },
726
+ "attributes": {}
727
+ }
728
+ },
729
+ "total_flos": 7.430225993190605e+17,
730
+ "train_batch_size": 2,
731
+ "trial_name": null,
732
+ "trial_params": null
733
+ }
checkpoint-2013/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432db7d0354841679f4dbd7551902fa9fde7eb28f12df94fbae067a1e3f5b770
3
+ size 5624
checkpoint-500/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-128k-instruct
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 0.12.0
checkpoint-500/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "o_proj",
24
+ "q_proj",
25
+ "k_proj",
26
+ "v_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
checkpoint-500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d46eaa31a858db846680d1affd3700056832c2b4da708ad295e0a2de933f43
3
+ size 494047976