ig16 commited on
Commit
82b7345
·
verified ·
1 Parent(s): c7fef32

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-100/README.md +202 -0
  2. checkpoint-100/adapter_config.json +34 -0
  3. checkpoint-100/special_tokens_map.json +30 -0
  4. checkpoint-100/tokenizer.json +0 -0
  5. checkpoint-100/tokenizer_config.json +46 -0
  6. checkpoint-100/trainer_state.json +104 -0
  7. checkpoint-1000/README.md +202 -0
  8. checkpoint-1000/adapter_config.json +34 -0
  9. checkpoint-1000/special_tokens_map.json +30 -0
  10. checkpoint-1000/tokenizer.json +0 -0
  11. checkpoint-1000/tokenizer_config.json +46 -0
  12. checkpoint-1000/trainer_state.json +734 -0
  13. checkpoint-1200/README.md +202 -0
  14. checkpoint-1200/adapter_config.json +34 -0
  15. checkpoint-1200/optimizer.pt +3 -0
  16. checkpoint-1200/rng_state.pth +3 -0
  17. checkpoint-1200/scheduler.pt +3 -0
  18. checkpoint-1200/special_tokens_map.json +30 -0
  19. checkpoint-1200/tokenizer.json +0 -0
  20. checkpoint-1200/tokenizer.model +3 -0
  21. checkpoint-1200/tokenizer_config.json +46 -0
  22. checkpoint-1200/trainer_state.json +874 -0
  23. checkpoint-1200/training_args.bin +3 -0
  24. checkpoint-1300/adapter_model.safetensors +3 -0
  25. checkpoint-1300/optimizer.pt +3 -0
  26. checkpoint-1300/rng_state.pth +3 -0
  27. checkpoint-1300/scheduler.pt +3 -0
  28. checkpoint-1300/tokenizer.model +3 -0
  29. checkpoint-1300/training_args.bin +3 -0
  30. checkpoint-1400/adapter_model.safetensors +3 -0
  31. checkpoint-1400/optimizer.pt +3 -0
  32. checkpoint-1400/rng_state.pth +3 -0
  33. checkpoint-1400/scheduler.pt +3 -0
  34. checkpoint-1400/tokenizer.model +3 -0
  35. checkpoint-1400/training_args.bin +3 -0
  36. checkpoint-1500/adapter_model.safetensors +3 -0
  37. checkpoint-1500/optimizer.pt +3 -0
  38. checkpoint-1500/rng_state.pth +3 -0
  39. checkpoint-1500/scheduler.pt +3 -0
  40. checkpoint-1500/special_tokens_map.json +30 -0
  41. checkpoint-1500/tokenizer.model +3 -0
  42. checkpoint-1500/tokenizer_config.json +46 -0
  43. checkpoint-1500/training_args.bin +3 -0
  44. checkpoint-1600/adapter_model.safetensors +3 -0
  45. checkpoint-1600/optimizer.pt +3 -0
  46. checkpoint-1600/rng_state.pth +3 -0
  47. checkpoint-1600/scheduler.pt +3 -0
  48. checkpoint-1600/tokenizer.model +3 -0
  49. checkpoint-1600/training_args.bin +3 -0
  50. checkpoint-1700/README.md +202 -0
checkpoint-100/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "trainable_token_indices": null,
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "extra_special_tokens": {},
37
+ "legacy": false,
38
+ "model_max_length": 32768,
39
+ "pad_token": "<unk>",
40
+ "padding_side": "right",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": false
46
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.15491866769945778,
6
+ "eval_steps": 500,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015491866769945779,
14
+ "grad_norm": 0.40339195728302,
15
+ "learning_rate": 9.278350515463919e-07,
16
+ "loss": 1.8526,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.030983733539891558,
21
+ "grad_norm": 0.3715074062347412,
22
+ "learning_rate": 1.9587628865979384e-06,
23
+ "loss": 1.8835,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.046475600309837335,
28
+ "grad_norm": 0.3445941209793091,
29
+ "learning_rate": 2.9896907216494846e-06,
30
+ "loss": 1.8733,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.061967467079783116,
35
+ "grad_norm": 0.3444959223270416,
36
+ "learning_rate": 4.020618556701032e-06,
37
+ "loss": 1.8952,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.07745933384972889,
42
+ "grad_norm": 0.3230769634246826,
43
+ "learning_rate": 5.051546391752578e-06,
44
+ "loss": 1.8588,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.09295120061967467,
49
+ "grad_norm": 0.33751699328422546,
50
+ "learning_rate": 6.082474226804124e-06,
51
+ "loss": 1.8307,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.10844306738962045,
56
+ "grad_norm": 0.2963869869709015,
57
+ "learning_rate": 7.113402061855671e-06,
58
+ "loss": 1.8419,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.12393493415956623,
63
+ "grad_norm": 0.2550879716873169,
64
+ "learning_rate": 8.144329896907216e-06,
65
+ "loss": 1.8281,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.139426800929512,
70
+ "grad_norm": 0.22610870003700256,
71
+ "learning_rate": 9.175257731958764e-06,
72
+ "loss": 1.8005,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.15491866769945778,
77
+ "grad_norm": 0.1930716335773468,
78
+ "learning_rate": 1.0206185567010309e-05,
79
+ "loss": 1.7897,
80
+ "step": 100
81
+ }
82
+ ],
83
+ "logging_steps": 10,
84
+ "max_steps": 1935,
85
+ "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 3,
87
+ "save_steps": 100,
88
+ "stateful_callbacks": {
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": false
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 7.123007667948749e+16,
101
+ "train_batch_size": 4,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
checkpoint-1000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "trainable_token_indices": null,
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "extra_special_tokens": {},
37
+ "legacy": false,
38
+ "model_max_length": 32768,
39
+ "pad_token": "<unk>",
40
+ "padding_side": "right",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": false
46
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.5484120836560806,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015491866769945779,
14
+ "grad_norm": 0.40339195728302,
15
+ "learning_rate": 9.278350515463919e-07,
16
+ "loss": 1.8526,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.030983733539891558,
21
+ "grad_norm": 0.3715074062347412,
22
+ "learning_rate": 1.9587628865979384e-06,
23
+ "loss": 1.8835,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.046475600309837335,
28
+ "grad_norm": 0.3445941209793091,
29
+ "learning_rate": 2.9896907216494846e-06,
30
+ "loss": 1.8733,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.061967467079783116,
35
+ "grad_norm": 0.3444959223270416,
36
+ "learning_rate": 4.020618556701032e-06,
37
+ "loss": 1.8952,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.07745933384972889,
42
+ "grad_norm": 0.3230769634246826,
43
+ "learning_rate": 5.051546391752578e-06,
44
+ "loss": 1.8588,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.09295120061967467,
49
+ "grad_norm": 0.33751699328422546,
50
+ "learning_rate": 6.082474226804124e-06,
51
+ "loss": 1.8307,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.10844306738962045,
56
+ "grad_norm": 0.2963869869709015,
57
+ "learning_rate": 7.113402061855671e-06,
58
+ "loss": 1.8419,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.12393493415956623,
63
+ "grad_norm": 0.2550879716873169,
64
+ "learning_rate": 8.144329896907216e-06,
65
+ "loss": 1.8281,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.139426800929512,
70
+ "grad_norm": 0.22610870003700256,
71
+ "learning_rate": 9.175257731958764e-06,
72
+ "loss": 1.8005,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.15491866769945778,
77
+ "grad_norm": 0.1930716335773468,
78
+ "learning_rate": 1.0206185567010309e-05,
79
+ "loss": 1.7897,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.17041053446940357,
84
+ "grad_norm": 0.18139410018920898,
85
+ "learning_rate": 1.1237113402061856e-05,
86
+ "loss": 1.7181,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.18590240123934934,
91
+ "grad_norm": 0.1586223542690277,
92
+ "learning_rate": 1.2268041237113405e-05,
93
+ "loss": 1.7328,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.2013942680092951,
98
+ "grad_norm": 0.2047862708568573,
99
+ "learning_rate": 1.3298969072164948e-05,
100
+ "loss": 1.7268,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.2168861347792409,
105
+ "grad_norm": 0.16858699917793274,
106
+ "learning_rate": 1.4329896907216495e-05,
107
+ "loss": 1.7029,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.23237800154918667,
112
+ "grad_norm": 0.15446807444095612,
113
+ "learning_rate": 1.5360824742268042e-05,
114
+ "loss": 1.7114,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.24786986831913246,
119
+ "grad_norm": 0.1550971418619156,
120
+ "learning_rate": 1.6391752577319588e-05,
121
+ "loss": 1.7054,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.26336173508907823,
126
+ "grad_norm": 0.13774091005325317,
127
+ "learning_rate": 1.7422680412371137e-05,
128
+ "loss": 1.685,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.278853601859024,
133
+ "grad_norm": 0.13972033560276031,
134
+ "learning_rate": 1.8453608247422682e-05,
135
+ "loss": 1.6774,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.29434546862896976,
140
+ "grad_norm": 0.14723576605319977,
141
+ "learning_rate": 1.9484536082474227e-05,
142
+ "loss": 1.63,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.30983733539891556,
147
+ "grad_norm": 0.1486756056547165,
148
+ "learning_rate": 1.9999592986072886e-05,
149
+ "loss": 1.6429,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.32532920216886135,
154
+ "grad_norm": 0.1460903435945511,
155
+ "learning_rate": 1.9996337073445673e-05,
156
+ "loss": 1.669,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.34082106893880715,
161
+ "grad_norm": 0.16247884929180145,
162
+ "learning_rate": 1.9989826308331103e-05,
163
+ "loss": 1.6572,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.3563129357087529,
168
+ "grad_norm": 0.16369281709194183,
169
+ "learning_rate": 1.998006281066369e-05,
170
+ "loss": 1.6545,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.3718048024786987,
175
+ "grad_norm": 0.1450214833021164,
176
+ "learning_rate": 1.996704975948236e-05,
177
+ "loss": 1.6762,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.3872966692486445,
182
+ "grad_norm": 0.17881567776203156,
183
+ "learning_rate": 1.9950791391895335e-05,
184
+ "loss": 1.6397,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.4027885360185902,
189
+ "grad_norm": 0.15863952040672302,
190
+ "learning_rate": 1.9931293001700518e-05,
191
+ "loss": 1.6597,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.418280402788536,
196
+ "grad_norm": 0.1730642467737198,
197
+ "learning_rate": 1.990856093766179e-05,
198
+ "loss": 1.6586,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.4337722695584818,
203
+ "grad_norm": 0.14790953695774078,
204
+ "learning_rate": 1.988260260144185e-05,
205
+ "loss": 1.6416,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.4492641363284276,
210
+ "grad_norm": 0.14577385783195496,
211
+ "learning_rate": 1.9853426445192175e-05,
212
+ "loss": 1.659,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.46475600309837334,
217
+ "grad_norm": 0.13978034257888794,
218
+ "learning_rate": 1.9821041968800982e-05,
219
+ "loss": 1.6362,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.48024786986831913,
224
+ "grad_norm": 0.17719446122646332,
225
+ "learning_rate": 1.9785459716800005e-05,
226
+ "loss": 1.6648,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.4957397366382649,
231
+ "grad_norm": 0.1415952891111374,
232
+ "learning_rate": 1.9746691274931168e-05,
233
+ "loss": 1.6518,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.5112316034082107,
238
+ "grad_norm": 0.1455707997083664,
239
+ "learning_rate": 1.970474926637418e-05,
240
+ "loss": 1.6445,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.5267234701781565,
245
+ "grad_norm": 0.19560855627059937,
246
+ "learning_rate": 1.9659647347636422e-05,
247
+ "loss": 1.6557,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.5422153369481022,
252
+ "grad_norm": 0.15447896718978882,
253
+ "learning_rate": 1.961140020410627e-05,
254
+ "loss": 1.6361,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.557707203718048,
259
+ "grad_norm": 0.17043063044548035,
260
+ "learning_rate": 1.9560023545271512e-05,
261
+ "loss": 1.6289,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.5731990704879938,
266
+ "grad_norm": 0.16939246654510498,
267
+ "learning_rate": 1.9505534099604245e-05,
268
+ "loss": 1.6318,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.5886909372579395,
273
+ "grad_norm": 0.1785915642976761,
274
+ "learning_rate": 1.9447949609114018e-05,
275
+ "loss": 1.6321,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.6041828040278854,
280
+ "grad_norm": 0.16734299063682556,
281
+ "learning_rate": 1.938728882357093e-05,
282
+ "loss": 1.6443,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.6196746707978311,
287
+ "grad_norm": 0.18670211732387543,
288
+ "learning_rate": 1.932357149440067e-05,
289
+ "loss": 1.6683,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.635166537567777,
294
+ "grad_norm": 0.15596874058246613,
295
+ "learning_rate": 1.925681836825331e-05,
296
+ "loss": 1.6336,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.6506584043377227,
301
+ "grad_norm": 0.18547730147838593,
302
+ "learning_rate": 1.9187051180248134e-05,
303
+ "loss": 1.6374,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.6661502711076684,
308
+ "grad_norm": 0.15439730882644653,
309
+ "learning_rate": 1.9114292646896574e-05,
310
+ "loss": 1.6298,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.6816421378776143,
315
+ "grad_norm": 0.15702180564403534,
316
+ "learning_rate": 1.9038566458705615e-05,
317
+ "loss": 1.6235,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.69713400464756,
322
+ "grad_norm": 0.20213943719863892,
323
+ "learning_rate": 1.895989727246405e-05,
324
+ "loss": 1.6511,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.7126258714175058,
329
+ "grad_norm": 0.17505770921707153,
330
+ "learning_rate": 1.8878310703214148e-05,
331
+ "loss": 1.6385,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.7281177381874516,
336
+ "grad_norm": 0.29876482486724854,
337
+ "learning_rate": 1.879383331591123e-05,
338
+ "loss": 1.6508,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.7436096049573974,
343
+ "grad_norm": 0.16168834269046783,
344
+ "learning_rate": 1.8706492616774043e-05,
345
+ "loss": 1.6424,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.7591014717273431,
350
+ "grad_norm": 0.1786322444677353,
351
+ "learning_rate": 1.86163170443286e-05,
352
+ "loss": 1.6699,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.774593338497289,
357
+ "grad_norm": 0.16993215680122375,
358
+ "learning_rate": 1.8523335960148446e-05,
359
+ "loss": 1.6499,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.7900852052672347,
364
+ "grad_norm": 0.15823154151439667,
365
+ "learning_rate": 1.8427579639294436e-05,
366
+ "loss": 1.6227,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.8055770720371804,
371
+ "grad_norm": 0.1717902421951294,
372
+ "learning_rate": 1.8329079260457e-05,
373
+ "loss": 1.6216,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.8210689388071263,
378
+ "grad_norm": 0.17375893890857697,
379
+ "learning_rate": 1.822786689580425e-05,
380
+ "loss": 1.6264,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.836560805577072,
385
+ "grad_norm": 0.18277738988399506,
386
+ "learning_rate": 1.8123975500539114e-05,
387
+ "loss": 1.6314,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.8520526723470179,
392
+ "grad_norm": 0.16117972135543823,
393
+ "learning_rate": 1.8017438902168987e-05,
394
+ "loss": 1.6274,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.8675445391169636,
399
+ "grad_norm": 0.1836647391319275,
400
+ "learning_rate": 1.7908291789491348e-05,
401
+ "loss": 1.6163,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.8830364058869093,
406
+ "grad_norm": 0.1835409700870514,
407
+ "learning_rate": 1.7796569701298906e-05,
408
+ "loss": 1.624,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.8985282726568552,
413
+ "grad_norm": 0.20427103340625763,
414
+ "learning_rate": 1.7682309014808043e-05,
415
+ "loss": 1.6575,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.9140201394268009,
420
+ "grad_norm": 0.18505772948265076,
421
+ "learning_rate": 1.756554693381419e-05,
422
+ "loss": 1.6478,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.9295120061967467,
427
+ "grad_norm": 0.16430599987506866,
428
+ "learning_rate": 1.7446321476578138e-05,
429
+ "loss": 1.6358,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.9450038729666925,
434
+ "grad_norm": 0.1757052093744278,
435
+ "learning_rate": 1.7324671463447092e-05,
436
+ "loss": 1.6383,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.9604957397366383,
441
+ "grad_norm": 0.1813608705997467,
442
+ "learning_rate": 1.7200636504214618e-05,
443
+ "loss": 1.6394,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.975987606506584,
448
+ "grad_norm": 0.16642023622989655,
449
+ "learning_rate": 1.7074256985223496e-05,
450
+ "loss": 1.6293,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.9914794732765299,
455
+ "grad_norm": 0.16024267673492432,
456
+ "learning_rate": 1.6945574056215742e-05,
457
+ "loss": 1.6186,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.0061967467079782,
462
+ "grad_norm": 0.1785087138414383,
463
+ "learning_rate": 1.6814629616934078e-05,
464
+ "loss": 1.6575,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.0216886134779242,
469
+ "grad_norm": 0.15702630579471588,
470
+ "learning_rate": 1.6681466303479196e-05,
471
+ "loss": 1.6431,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.03718048024787,
476
+ "grad_norm": 0.18289993703365326,
477
+ "learning_rate": 1.6546127474427217e-05,
478
+ "loss": 1.6231,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.0526723470178156,
483
+ "grad_norm": 0.18264566361904144,
484
+ "learning_rate": 1.6408657196711977e-05,
485
+ "loss": 1.6293,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.0681642137877614,
490
+ "grad_norm": 0.1770721971988678,
491
+ "learning_rate": 1.6269100231276617e-05,
492
+ "loss": 1.6123,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.0836560805577071,
497
+ "grad_norm": 0.18177859485149384,
498
+ "learning_rate": 1.6127502018499216e-05,
499
+ "loss": 1.6367,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.099147947327653,
504
+ "grad_norm": 0.17744611203670502,
505
+ "learning_rate": 1.598390866339721e-05,
506
+ "loss": 1.6037,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.1146398140975988,
511
+ "grad_norm": 0.17207013070583344,
512
+ "learning_rate": 1.5838366920615395e-05,
513
+ "loss": 1.6184,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.1301316808675446,
518
+ "grad_norm": 0.19843930006027222,
519
+ "learning_rate": 1.5690924179202375e-05,
520
+ "loss": 1.649,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.1456235476374903,
525
+ "grad_norm": 0.1967499703168869,
526
+ "learning_rate": 1.5541628447180494e-05,
527
+ "loss": 1.644,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.161115414407436,
532
+ "grad_norm": 0.2497672736644745,
533
+ "learning_rate": 1.5390528335914216e-05,
534
+ "loss": 1.6452,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.1766072811773818,
539
+ "grad_norm": 0.22346507012844086,
540
+ "learning_rate": 1.5237673044282028e-05,
541
+ "loss": 1.5909,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.1920991479473277,
546
+ "grad_norm": 0.1980983465909958,
547
+ "learning_rate": 1.5083112342657071e-05,
548
+ "loss": 1.6415,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.2075910147172735,
553
+ "grad_norm": 0.22096283733844757,
554
+ "learning_rate": 1.4926896556701676e-05,
555
+ "loss": 1.6281,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 1.2230828814872192,
560
+ "grad_norm": 0.20375041663646698,
561
+ "learning_rate": 1.4769076550981107e-05,
562
+ "loss": 1.6327,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 1.238574748257165,
567
+ "grad_norm": 0.1991424262523651,
568
+ "learning_rate": 1.4609703712401832e-05,
569
+ "loss": 1.628,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.2540666150271107,
574
+ "grad_norm": 0.1924315243959427,
575
+ "learning_rate": 1.44488299334797e-05,
576
+ "loss": 1.6228,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.2695584817970564,
581
+ "grad_norm": 0.200628861784935,
582
+ "learning_rate": 1.4286507595443527e-05,
583
+ "loss": 1.6252,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 1.2850503485670024,
588
+ "grad_norm": 0.18464049696922302,
589
+ "learning_rate": 1.4122789551179495e-05,
590
+ "loss": 1.6521,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 1.3005422153369481,
595
+ "grad_norm": 0.19593623280525208,
596
+ "learning_rate": 1.3957729108022057e-05,
597
+ "loss": 1.6357,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 1.3160340821068939,
602
+ "grad_norm": 0.1850130409002304,
603
+ "learning_rate": 1.37913800103968e-05,
604
+ "loss": 1.6214,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 1.3315259488768396,
609
+ "grad_norm": 0.19042982161045074,
610
+ "learning_rate": 1.3623796422321018e-05,
611
+ "loss": 1.6258,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 1.3470178156467854,
616
+ "grad_norm": 0.16621778905391693,
617
+ "learning_rate": 1.345503290976768e-05,
618
+ "loss": 1.5954,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 1.3625096824167313,
623
+ "grad_norm": 0.22534021735191345,
624
+ "learning_rate": 1.3285144422898486e-05,
625
+ "loss": 1.63,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 1.378001549186677,
630
+ "grad_norm": 0.20389960706233978,
631
+ "learning_rate": 1.3114186278171855e-05,
632
+ "loss": 1.6105,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 1.3934934159566228,
637
+ "grad_norm": 0.19341149926185608,
638
+ "learning_rate": 1.294221414033163e-05,
639
+ "loss": 1.6311,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 1.4089852827265685,
644
+ "grad_norm": 0.18202827870845795,
645
+ "learning_rate": 1.2769284004282398e-05,
646
+ "loss": 1.6071,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 1.4244771494965143,
651
+ "grad_norm": 0.24331383407115936,
652
+ "learning_rate": 1.2595452176857283e-05,
653
+ "loss": 1.6308,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 1.4399690162664602,
658
+ "grad_norm": 0.19823439419269562,
659
+ "learning_rate": 1.2420775258484194e-05,
660
+ "loss": 1.6338,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 1.4554608830364058,
665
+ "grad_norm": 0.20651289820671082,
666
+ "learning_rate": 1.224531012475647e-05,
667
+ "loss": 1.6289,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.4709527498063517,
672
+ "grad_norm": 0.19937390089035034,
673
+ "learning_rate": 1.2069113907913921e-05,
674
+ "loss": 1.6251,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.4864446165762975,
679
+ "grad_norm": 0.2028992474079132,
680
+ "learning_rate": 1.1892243978240332e-05,
681
+ "loss": 1.6032,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.5019364833462432,
686
+ "grad_norm": 0.19516679644584656,
687
+ "learning_rate": 1.1714757925383418e-05,
688
+ "loss": 1.658,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.5174283501161892,
693
+ "grad_norm": 0.19880403578281403,
694
+ "learning_rate": 1.1536713539603392e-05,
695
+ "loss": 1.6286,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 1.5329202168861347,
700
+ "grad_norm": 0.20677272975444794,
701
+ "learning_rate": 1.1358168792956178e-05,
702
+ "loss": 1.6366,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 1.5484120836560806,
707
+ "grad_norm": 0.19314983487129211,
708
+ "learning_rate": 1.1179181820417469e-05,
709
+ "loss": 1.6277,
710
+ "step": 1000
711
+ }
712
+ ],
713
+ "logging_steps": 10,
714
+ "max_steps": 1935,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 3,
717
+ "save_steps": 100,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": false
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 7.139866728452506e+17,
731
+ "train_batch_size": 4,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
checkpoint-1200/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-1200/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "trainable_token_indices": null,
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-1200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5e77dd80678af258449173891f789d807e56bc45e2fb70732cba03bbe287ef
3
+ size 55533067
checkpoint-1200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ab8031f73a76df28714a3c29dcbfd04b74934009c9d6b9787709b15999a05e
3
+ size 14645
checkpoint-1200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac31bee2d895b360d9ca35ae7d13c37cd73bb9f7bc022c2bcf4670cf7b88d5f
3
+ size 1465
checkpoint-1200/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-1200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-1200/tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "extra_special_tokens": {},
37
+ "legacy": false,
38
+ "model_max_length": 32768,
39
+ "pad_token": "<unk>",
40
+ "padding_side": "right",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": false
46
+ }
checkpoint-1200/trainer_state.json ADDED
@@ -0,0 +1,874 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.858249419054996,
6
+ "eval_steps": 500,
7
+ "global_step": 1200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015491866769945779,
14
+ "grad_norm": 0.40339195728302,
15
+ "learning_rate": 9.278350515463919e-07,
16
+ "loss": 1.8526,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.030983733539891558,
21
+ "grad_norm": 0.3715074062347412,
22
+ "learning_rate": 1.9587628865979384e-06,
23
+ "loss": 1.8835,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.046475600309837335,
28
+ "grad_norm": 0.3445941209793091,
29
+ "learning_rate": 2.9896907216494846e-06,
30
+ "loss": 1.8733,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.061967467079783116,
35
+ "grad_norm": 0.3444959223270416,
36
+ "learning_rate": 4.020618556701032e-06,
37
+ "loss": 1.8952,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.07745933384972889,
42
+ "grad_norm": 0.3230769634246826,
43
+ "learning_rate": 5.051546391752578e-06,
44
+ "loss": 1.8588,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.09295120061967467,
49
+ "grad_norm": 0.33751699328422546,
50
+ "learning_rate": 6.082474226804124e-06,
51
+ "loss": 1.8307,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.10844306738962045,
56
+ "grad_norm": 0.2963869869709015,
57
+ "learning_rate": 7.113402061855671e-06,
58
+ "loss": 1.8419,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.12393493415956623,
63
+ "grad_norm": 0.2550879716873169,
64
+ "learning_rate": 8.144329896907216e-06,
65
+ "loss": 1.8281,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.139426800929512,
70
+ "grad_norm": 0.22610870003700256,
71
+ "learning_rate": 9.175257731958764e-06,
72
+ "loss": 1.8005,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.15491866769945778,
77
+ "grad_norm": 0.1930716335773468,
78
+ "learning_rate": 1.0206185567010309e-05,
79
+ "loss": 1.7897,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.17041053446940357,
84
+ "grad_norm": 0.18139410018920898,
85
+ "learning_rate": 1.1237113402061856e-05,
86
+ "loss": 1.7181,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.18590240123934934,
91
+ "grad_norm": 0.1586223542690277,
92
+ "learning_rate": 1.2268041237113405e-05,
93
+ "loss": 1.7328,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.2013942680092951,
98
+ "grad_norm": 0.2047862708568573,
99
+ "learning_rate": 1.3298969072164948e-05,
100
+ "loss": 1.7268,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.2168861347792409,
105
+ "grad_norm": 0.16858699917793274,
106
+ "learning_rate": 1.4329896907216495e-05,
107
+ "loss": 1.7029,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.23237800154918667,
112
+ "grad_norm": 0.15446807444095612,
113
+ "learning_rate": 1.5360824742268042e-05,
114
+ "loss": 1.7114,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.24786986831913246,
119
+ "grad_norm": 0.1550971418619156,
120
+ "learning_rate": 1.6391752577319588e-05,
121
+ "loss": 1.7054,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.26336173508907823,
126
+ "grad_norm": 0.13774091005325317,
127
+ "learning_rate": 1.7422680412371137e-05,
128
+ "loss": 1.685,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.278853601859024,
133
+ "grad_norm": 0.13972033560276031,
134
+ "learning_rate": 1.8453608247422682e-05,
135
+ "loss": 1.6774,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.29434546862896976,
140
+ "grad_norm": 0.14723576605319977,
141
+ "learning_rate": 1.9484536082474227e-05,
142
+ "loss": 1.63,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.30983733539891556,
147
+ "grad_norm": 0.1486756056547165,
148
+ "learning_rate": 1.9999592986072886e-05,
149
+ "loss": 1.6429,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.32532920216886135,
154
+ "grad_norm": 0.1460903435945511,
155
+ "learning_rate": 1.9996337073445673e-05,
156
+ "loss": 1.669,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.34082106893880715,
161
+ "grad_norm": 0.16247884929180145,
162
+ "learning_rate": 1.9989826308331103e-05,
163
+ "loss": 1.6572,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.3563129357087529,
168
+ "grad_norm": 0.16369281709194183,
169
+ "learning_rate": 1.998006281066369e-05,
170
+ "loss": 1.6545,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.3718048024786987,
175
+ "grad_norm": 0.1450214833021164,
176
+ "learning_rate": 1.996704975948236e-05,
177
+ "loss": 1.6762,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.3872966692486445,
182
+ "grad_norm": 0.17881567776203156,
183
+ "learning_rate": 1.9950791391895335e-05,
184
+ "loss": 1.6397,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.4027885360185902,
189
+ "grad_norm": 0.15863952040672302,
190
+ "learning_rate": 1.9931293001700518e-05,
191
+ "loss": 1.6597,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.418280402788536,
196
+ "grad_norm": 0.1730642467737198,
197
+ "learning_rate": 1.990856093766179e-05,
198
+ "loss": 1.6586,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.4337722695584818,
203
+ "grad_norm": 0.14790953695774078,
204
+ "learning_rate": 1.988260260144185e-05,
205
+ "loss": 1.6416,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.4492641363284276,
210
+ "grad_norm": 0.14577385783195496,
211
+ "learning_rate": 1.9853426445192175e-05,
212
+ "loss": 1.659,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.46475600309837334,
217
+ "grad_norm": 0.13978034257888794,
218
+ "learning_rate": 1.9821041968800982e-05,
219
+ "loss": 1.6362,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.48024786986831913,
224
+ "grad_norm": 0.17719446122646332,
225
+ "learning_rate": 1.9785459716800005e-05,
226
+ "loss": 1.6648,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.4957397366382649,
231
+ "grad_norm": 0.1415952891111374,
232
+ "learning_rate": 1.9746691274931168e-05,
233
+ "loss": 1.6518,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.5112316034082107,
238
+ "grad_norm": 0.1455707997083664,
239
+ "learning_rate": 1.970474926637418e-05,
240
+ "loss": 1.6445,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.5267234701781565,
245
+ "grad_norm": 0.19560855627059937,
246
+ "learning_rate": 1.9659647347636422e-05,
247
+ "loss": 1.6557,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.5422153369481022,
252
+ "grad_norm": 0.15447896718978882,
253
+ "learning_rate": 1.961140020410627e-05,
254
+ "loss": 1.6361,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.557707203718048,
259
+ "grad_norm": 0.17043063044548035,
260
+ "learning_rate": 1.9560023545271512e-05,
261
+ "loss": 1.6289,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.5731990704879938,
266
+ "grad_norm": 0.16939246654510498,
267
+ "learning_rate": 1.9505534099604245e-05,
268
+ "loss": 1.6318,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.5886909372579395,
273
+ "grad_norm": 0.1785915642976761,
274
+ "learning_rate": 1.9447949609114018e-05,
275
+ "loss": 1.6321,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.6041828040278854,
280
+ "grad_norm": 0.16734299063682556,
281
+ "learning_rate": 1.938728882357093e-05,
282
+ "loss": 1.6443,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.6196746707978311,
287
+ "grad_norm": 0.18670211732387543,
288
+ "learning_rate": 1.932357149440067e-05,
289
+ "loss": 1.6683,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.635166537567777,
294
+ "grad_norm": 0.15596874058246613,
295
+ "learning_rate": 1.925681836825331e-05,
296
+ "loss": 1.6336,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.6506584043377227,
301
+ "grad_norm": 0.18547730147838593,
302
+ "learning_rate": 1.9187051180248134e-05,
303
+ "loss": 1.6374,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.6661502711076684,
308
+ "grad_norm": 0.15439730882644653,
309
+ "learning_rate": 1.9114292646896574e-05,
310
+ "loss": 1.6298,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.6816421378776143,
315
+ "grad_norm": 0.15702180564403534,
316
+ "learning_rate": 1.9038566458705615e-05,
317
+ "loss": 1.6235,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.69713400464756,
322
+ "grad_norm": 0.20213943719863892,
323
+ "learning_rate": 1.895989727246405e-05,
324
+ "loss": 1.6511,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.7126258714175058,
329
+ "grad_norm": 0.17505770921707153,
330
+ "learning_rate": 1.8878310703214148e-05,
331
+ "loss": 1.6385,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.7281177381874516,
336
+ "grad_norm": 0.29876482486724854,
337
+ "learning_rate": 1.879383331591123e-05,
338
+ "loss": 1.6508,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.7436096049573974,
343
+ "grad_norm": 0.16168834269046783,
344
+ "learning_rate": 1.8706492616774043e-05,
345
+ "loss": 1.6424,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.7591014717273431,
350
+ "grad_norm": 0.1786322444677353,
351
+ "learning_rate": 1.86163170443286e-05,
352
+ "loss": 1.6699,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.774593338497289,
357
+ "grad_norm": 0.16993215680122375,
358
+ "learning_rate": 1.8523335960148446e-05,
359
+ "loss": 1.6499,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.7900852052672347,
364
+ "grad_norm": 0.15823154151439667,
365
+ "learning_rate": 1.8427579639294436e-05,
366
+ "loss": 1.6227,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.8055770720371804,
371
+ "grad_norm": 0.1717902421951294,
372
+ "learning_rate": 1.8329079260457e-05,
373
+ "loss": 1.6216,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.8210689388071263,
378
+ "grad_norm": 0.17375893890857697,
379
+ "learning_rate": 1.822786689580425e-05,
380
+ "loss": 1.6264,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.836560805577072,
385
+ "grad_norm": 0.18277738988399506,
386
+ "learning_rate": 1.8123975500539114e-05,
387
+ "loss": 1.6314,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.8520526723470179,
392
+ "grad_norm": 0.16117972135543823,
393
+ "learning_rate": 1.8017438902168987e-05,
394
+ "loss": 1.6274,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.8675445391169636,
399
+ "grad_norm": 0.1836647391319275,
400
+ "learning_rate": 1.7908291789491348e-05,
401
+ "loss": 1.6163,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.8830364058869093,
406
+ "grad_norm": 0.1835409700870514,
407
+ "learning_rate": 1.7796569701298906e-05,
408
+ "loss": 1.624,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.8985282726568552,
413
+ "grad_norm": 0.20427103340625763,
414
+ "learning_rate": 1.7682309014808043e-05,
415
+ "loss": 1.6575,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.9140201394268009,
420
+ "grad_norm": 0.18505772948265076,
421
+ "learning_rate": 1.756554693381419e-05,
422
+ "loss": 1.6478,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.9295120061967467,
427
+ "grad_norm": 0.16430599987506866,
428
+ "learning_rate": 1.7446321476578138e-05,
429
+ "loss": 1.6358,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.9450038729666925,
434
+ "grad_norm": 0.1757052093744278,
435
+ "learning_rate": 1.7324671463447092e-05,
436
+ "loss": 1.6383,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.9604957397366383,
441
+ "grad_norm": 0.1813608705997467,
442
+ "learning_rate": 1.7200636504214618e-05,
443
+ "loss": 1.6394,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.975987606506584,
448
+ "grad_norm": 0.16642023622989655,
449
+ "learning_rate": 1.7074256985223496e-05,
450
+ "loss": 1.6293,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.9914794732765299,
455
+ "grad_norm": 0.16024267673492432,
456
+ "learning_rate": 1.6945574056215742e-05,
457
+ "loss": 1.6186,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.0061967467079782,
462
+ "grad_norm": 0.1785087138414383,
463
+ "learning_rate": 1.6814629616934078e-05,
464
+ "loss": 1.6575,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.0216886134779242,
469
+ "grad_norm": 0.15702630579471588,
470
+ "learning_rate": 1.6681466303479196e-05,
471
+ "loss": 1.6431,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.03718048024787,
476
+ "grad_norm": 0.18289993703365326,
477
+ "learning_rate": 1.6546127474427217e-05,
478
+ "loss": 1.6231,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.0526723470178156,
483
+ "grad_norm": 0.18264566361904144,
484
+ "learning_rate": 1.6408657196711977e-05,
485
+ "loss": 1.6293,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.0681642137877614,
490
+ "grad_norm": 0.1770721971988678,
491
+ "learning_rate": 1.6269100231276617e-05,
492
+ "loss": 1.6123,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.0836560805577071,
497
+ "grad_norm": 0.18177859485149384,
498
+ "learning_rate": 1.6127502018499216e-05,
499
+ "loss": 1.6367,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.099147947327653,
504
+ "grad_norm": 0.17744611203670502,
505
+ "learning_rate": 1.598390866339721e-05,
506
+ "loss": 1.6037,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.1146398140975988,
511
+ "grad_norm": 0.17207013070583344,
512
+ "learning_rate": 1.5838366920615395e-05,
513
+ "loss": 1.6184,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.1301316808675446,
518
+ "grad_norm": 0.19843930006027222,
519
+ "learning_rate": 1.5690924179202375e-05,
520
+ "loss": 1.649,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.1456235476374903,
525
+ "grad_norm": 0.1967499703168869,
526
+ "learning_rate": 1.5541628447180494e-05,
527
+ "loss": 1.644,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.161115414407436,
532
+ "grad_norm": 0.2497672736644745,
533
+ "learning_rate": 1.5390528335914216e-05,
534
+ "loss": 1.6452,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.1766072811773818,
539
+ "grad_norm": 0.22346507012844086,
540
+ "learning_rate": 1.5237673044282028e-05,
541
+ "loss": 1.5909,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.1920991479473277,
546
+ "grad_norm": 0.1980983465909958,
547
+ "learning_rate": 1.5083112342657071e-05,
548
+ "loss": 1.6415,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.2075910147172735,
553
+ "grad_norm": 0.22096283733844757,
554
+ "learning_rate": 1.4926896556701676e-05,
555
+ "loss": 1.6281,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 1.2230828814872192,
560
+ "grad_norm": 0.20375041663646698,
561
+ "learning_rate": 1.4769076550981107e-05,
562
+ "loss": 1.6327,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 1.238574748257165,
567
+ "grad_norm": 0.1991424262523651,
568
+ "learning_rate": 1.4609703712401832e-05,
569
+ "loss": 1.628,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.2540666150271107,
574
+ "grad_norm": 0.1924315243959427,
575
+ "learning_rate": 1.44488299334797e-05,
576
+ "loss": 1.6228,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.2695584817970564,
581
+ "grad_norm": 0.200628861784935,
582
+ "learning_rate": 1.4286507595443527e-05,
583
+ "loss": 1.6252,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 1.2850503485670024,
588
+ "grad_norm": 0.18464049696922302,
589
+ "learning_rate": 1.4122789551179495e-05,
590
+ "loss": 1.6521,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 1.3005422153369481,
595
+ "grad_norm": 0.19593623280525208,
596
+ "learning_rate": 1.3957729108022057e-05,
597
+ "loss": 1.6357,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 1.3160340821068939,
602
+ "grad_norm": 0.1850130409002304,
603
+ "learning_rate": 1.37913800103968e-05,
604
+ "loss": 1.6214,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 1.3315259488768396,
609
+ "grad_norm": 0.19042982161045074,
610
+ "learning_rate": 1.3623796422321018e-05,
611
+ "loss": 1.6258,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 1.3470178156467854,
616
+ "grad_norm": 0.16621778905391693,
617
+ "learning_rate": 1.345503290976768e-05,
618
+ "loss": 1.5954,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 1.3625096824167313,
623
+ "grad_norm": 0.22534021735191345,
624
+ "learning_rate": 1.3285144422898486e-05,
625
+ "loss": 1.63,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 1.378001549186677,
630
+ "grad_norm": 0.20389960706233978,
631
+ "learning_rate": 1.3114186278171855e-05,
632
+ "loss": 1.6105,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 1.3934934159566228,
637
+ "grad_norm": 0.19341149926185608,
638
+ "learning_rate": 1.294221414033163e-05,
639
+ "loss": 1.6311,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 1.4089852827265685,
644
+ "grad_norm": 0.18202827870845795,
645
+ "learning_rate": 1.2769284004282398e-05,
646
+ "loss": 1.6071,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 1.4244771494965143,
651
+ "grad_norm": 0.24331383407115936,
652
+ "learning_rate": 1.2595452176857283e-05,
653
+ "loss": 1.6308,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 1.4399690162664602,
658
+ "grad_norm": 0.19823439419269562,
659
+ "learning_rate": 1.2420775258484194e-05,
660
+ "loss": 1.6338,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 1.4554608830364058,
665
+ "grad_norm": 0.20651289820671082,
666
+ "learning_rate": 1.224531012475647e-05,
667
+ "loss": 1.6289,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.4709527498063517,
672
+ "grad_norm": 0.19937390089035034,
673
+ "learning_rate": 1.2069113907913921e-05,
674
+ "loss": 1.6251,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.4864446165762975,
679
+ "grad_norm": 0.2028992474079132,
680
+ "learning_rate": 1.1892243978240332e-05,
681
+ "loss": 1.6032,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.5019364833462432,
686
+ "grad_norm": 0.19516679644584656,
687
+ "learning_rate": 1.1714757925383418e-05,
688
+ "loss": 1.658,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.5174283501161892,
693
+ "grad_norm": 0.19880403578281403,
694
+ "learning_rate": 1.1536713539603392e-05,
695
+ "loss": 1.6286,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 1.5329202168861347,
700
+ "grad_norm": 0.20677272975444794,
701
+ "learning_rate": 1.1358168792956178e-05,
702
+ "loss": 1.6366,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 1.5484120836560806,
707
+ "grad_norm": 0.19314983487129211,
708
+ "learning_rate": 1.1179181820417469e-05,
709
+ "loss": 1.6277,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 1.5639039504260264,
714
+ "grad_norm": 0.22714097797870636,
715
+ "learning_rate": 1.0999810900953701e-05,
716
+ "loss": 1.604,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 1.579395817195972,
721
+ "grad_norm": 0.19973160326480865,
722
+ "learning_rate": 1.0820114438546152e-05,
723
+ "loss": 1.6419,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 1.5948876839659178,
728
+ "grad_norm": 0.19317737221717834,
729
+ "learning_rate": 1.0640150943174368e-05,
730
+ "loss": 1.6208,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 1.6103795507358636,
735
+ "grad_norm": 0.19110378623008728,
736
+ "learning_rate": 1.045997901176503e-05,
737
+ "loss": 1.6419,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 1.6258714175058095,
742
+ "grad_norm": 0.19884715974330902,
743
+ "learning_rate": 1.0279657309112526e-05,
744
+ "loss": 1.6374,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 1.641363284275755,
749
+ "grad_norm": 0.2037876695394516,
750
+ "learning_rate": 1.0099244548777444e-05,
751
+ "loss": 1.6226,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 1.656855151045701,
756
+ "grad_norm": 0.19929030537605286,
757
+ "learning_rate": 9.918799473969162e-06,
758
+ "loss": 1.6246,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 1.6723470178156468,
763
+ "grad_norm": 0.2003982663154602,
764
+ "learning_rate": 9.738380838418804e-06,
765
+ "loss": 1.6284,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 1.6878388845855925,
770
+ "grad_norm": 0.19803060591220856,
771
+ "learning_rate": 9.558047387248736e-06,
772
+ "loss": 1.6735,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 1.7033307513555385,
777
+ "grad_norm": 0.1816408932209015,
778
+ "learning_rate": 9.37785783784492e-06,
779
+ "loss": 1.6476,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 1.718822618125484,
784
+ "grad_norm": 0.2075837105512619,
785
+ "learning_rate": 9.197870860738245e-06,
786
+ "loss": 1.6332,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 1.73431448489543,
791
+ "grad_norm": 0.18789494037628174,
792
+ "learning_rate": 9.018145060501152e-06,
793
+ "loss": 1.6261,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 1.7498063516653757,
798
+ "grad_norm": 0.2126590460538864,
799
+ "learning_rate": 8.838738956665709e-06,
800
+ "loss": 1.638,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 1.7652982184353214,
805
+ "grad_norm": 0.19256949424743652,
806
+ "learning_rate": 8.65971096466939e-06,
807
+ "loss": 1.633,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 1.7807900852052674,
812
+ "grad_norm": 0.22011205554008484,
813
+ "learning_rate": 8.481119376834753e-06,
814
+ "loss": 1.6397,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 1.796281951975213,
819
+ "grad_norm": 0.2018994390964508,
820
+ "learning_rate": 8.303022343389188e-06,
821
+ "loss": 1.6424,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 1.8117738187451589,
826
+ "grad_norm": 0.22901326417922974,
827
+ "learning_rate": 8.125477853530944e-06,
828
+ "loss": 1.594,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 1.8272656855151046,
833
+ "grad_norm": 0.20335343480110168,
834
+ "learning_rate": 7.948543716547584e-06,
835
+ "loss": 1.6246,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 1.8427575522850503,
840
+ "grad_norm": 0.19213028252124786,
841
+ "learning_rate": 7.772277542993006e-06,
842
+ "loss": 1.6424,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 1.858249419054996,
847
+ "grad_norm": 0.5027441382408142,
848
+ "learning_rate": 7.596736725929218e-06,
849
+ "loss": 1.618,
850
+ "step": 1200
851
+ }
852
+ ],
853
+ "logging_steps": 10,
854
+ "max_steps": 1935,
855
+ "num_input_tokens_seen": 0,
856
+ "num_train_epochs": 3,
857
+ "save_steps": 100,
858
+ "stateful_callbacks": {
859
+ "TrainerControl": {
860
+ "args": {
861
+ "should_epoch_stop": false,
862
+ "should_evaluate": false,
863
+ "should_log": false,
864
+ "should_save": true,
865
+ "should_training_stop": false
866
+ },
867
+ "attributes": {}
868
+ }
869
+ },
870
+ "total_flos": 8.568761294494679e+17,
871
+ "train_batch_size": 4,
872
+ "trial_name": null,
873
+ "trial_params": null
874
+ }
checkpoint-1200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ffa5d5b04da897e6731be2deb611d6507683c904cfe7504dee49a611b5e681a
3
+ size 6033
checkpoint-1300/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbad298ac45cd910b05ac19a2c1cceeb46f15a7b8ffbd0b6de2c4becd29ea5e1
3
+ size 109069176
checkpoint-1300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46b3531ce6a68b6d2487710b1608358cbc4fb4baf13aae565e2543cd7ff2922
3
+ size 55533067
checkpoint-1300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a033fc3b68e3de44573bcc115e7a8dc36dde45c3dd82bce6315cb5c61de828
3
+ size 14645
checkpoint-1300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8eaa20793a330534292b621fff141f8dd83ae9f148311b96abeae0d9cf405a6
3
+ size 1465
checkpoint-1300/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-1300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ffa5d5b04da897e6731be2deb611d6507683c904cfe7504dee49a611b5e681a
3
+ size 6033
checkpoint-1400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba91ac49c2a5435accfdac9c6287dd3632475927bd42f27ee193f0229e165414
3
+ size 109069176
checkpoint-1400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85f58d4b392f857895bfcbc915f49b85e60ef9b2edc958166212facae4b83a3
3
+ size 55533067
checkpoint-1400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0aa9a3649d0c97877b923733c114c830f3386a660ff9124e1e0ff8507f5bb6
3
+ size 14645
checkpoint-1400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ee3561940de8f05864fb9f1e43c7475badc80ae805bc516ed76bfdd91f271e
3
+ size 1465
checkpoint-1400/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-1400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ffa5d5b04da897e6731be2deb611d6507683c904cfe7504dee49a611b5e681a
3
+ size 6033
checkpoint-1500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dff2f436ad8c0788a3dc2160fe324922695f70ccf377881429fcbb0126eec4b
3
+ size 109069176
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2fea7e015a7875ad4789070592c1da381c57c2b79e0111f3bafbf5616c5d5bb
3
+ size 55533067
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b17692319f50e56fb0d850a7fe529b3c144dcff31c4e298b0cab6cc159f8cdf
3
+ size 14645
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1561a4283900eccd390885fd70766c9a961e814ccf8bb6ad798a9bf7f38c078
3
+ size 1465
checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-1500/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "extra_special_tokens": {},
37
+ "legacy": false,
38
+ "model_max_length": 32768,
39
+ "pad_token": "<unk>",
40
+ "padding_side": "right",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": false
46
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ffa5d5b04da897e6731be2deb611d6507683c904cfe7504dee49a611b5e681a
3
+ size 6033
checkpoint-1600/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae5ff6d40924049b77725a40ab2b9df56c72e91aafde2001e108b500a7a5970
3
+ size 109069176
checkpoint-1600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7ec3a9e3a1f7908acc3b355f30f26c7578ee776960f30894049ce1a149035c
3
+ size 55533067
checkpoint-1600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98068a92c8fe52738688bb5fbcea1c0038f74d9cada7b766e52c91b234903d4c
3
+ size 14645
checkpoint-1600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168489bca68ee7800014d52f722b280e20df99f6b91c2ea80d25c92b12b4d8ab
3
+ size 1465
checkpoint-1600/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-1600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ffa5d5b04da897e6731be2deb611d6507683c904cfe7504dee49a611b5e681a
3
+ size 6033
checkpoint-1700/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2