Hugging Face's logo

Egoli
/
Qwen2-1.5b-Instruct-q4-huanhuan

Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
Model card Files Community
Egoli commited on
Commit
3cd5588
·
verified ·
1 Parent(s): 30df527

Upload 54 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. adapter_config.json +34 -0
  2. checkpoint-100/README.md +202 -0
  3. checkpoint-100/adapter_config.json +34 -0
  4. checkpoint-100/adapter_model.safetensors +3 -0
  5. checkpoint-100/added_tokens.json +5 -0
  6. checkpoint-100/merges.txt +0 -0
  7. checkpoint-100/optimizer.pt +3 -0
  8. checkpoint-100/rng_state.pth +3 -0
  9. checkpoint-100/scheduler.pt +3 -0
  10. checkpoint-100/special_tokens_map.json +20 -0
  11. checkpoint-100/tokenizer.json +0 -0
  12. checkpoint-100/tokenizer_config.json +44 -0
  13. checkpoint-100/trainer_state.json +193 -0
  14. checkpoint-100/training_args.bin +3 -0
  15. checkpoint-100/vocab.json +0 -0
  16. checkpoint-200/README.md +202 -0
  17. checkpoint-200/adapter_config.json +34 -0
  18. checkpoint-200/adapter_model.safetensors +3 -0
  19. checkpoint-200/added_tokens.json +5 -0
  20. checkpoint-200/merges.txt +0 -0
  21. checkpoint-200/optimizer.pt +3 -0
  22. checkpoint-200/rng_state.pth +3 -0
  23. checkpoint-200/scheduler.pt +3 -0
  24. checkpoint-200/special_tokens_map.json +20 -0
  25. checkpoint-200/tokenizer.json +0 -0
  26. checkpoint-200/tokenizer_config.json +44 -0
  27. checkpoint-200/trainer_state.json +353 -0
  28. checkpoint-200/training_args.bin +3 -0
  29. checkpoint-200/vocab.json +0 -0
  30. checkpoint-240/README.md +202 -0
  31. checkpoint-240/adapter_config.json +34 -0
  32. checkpoint-240/adapter_model.safetensors +3 -0
  33. checkpoint-240/added_tokens.json +5 -0
  34. checkpoint-240/merges.txt +0 -0
  35. checkpoint-240/optimizer.pt +3 -0
  36. checkpoint-240/rng_state.pth +3 -0
  37. checkpoint-240/scheduler.pt +3 -0
  38. checkpoint-240/special_tokens_map.json +20 -0
  39. checkpoint-240/tokenizer.json +0 -0
  40. checkpoint-240/tokenizer_config.json +44 -0
  41. checkpoint-240/trainer_state.json +417 -0
  42. checkpoint-240/training_args.bin +3 -0
  43. checkpoint-240/vocab.json +0 -0
  44. config.json +28 -0
  45. generation_config.json +14 -0
  46. merges.txt +0 -0
  47. model-00001-of-00004.safetensors +3 -0
  48. model-00002-of-00004.safetensors +3 -0
  49. model-00003-of-00004.safetensors +3 -0
  50. model-00004-of-00004.safetensors +3 -0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 8,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "up_proj",
25
+ "q_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": true,
33
+ "use_rslora": false
34
+ }
checkpoint-100/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2-1.5B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 8,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "up_proj",
25
+ "q_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": true,
33
+ "use_rslora": false
34
+ }
checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af6eb31e3f5681f5ddcb0a97e13730261601fa70d74d493da03663b07d2243d0
3
+ size 39588464
checkpoint-100/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
checkpoint-100/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebcb99312f2db4690364c5b92a6f8a7594054a6239968d34260d41676b2fd1eb
3
+ size 79513462
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff39c56748cc5e85691d62bfd6a79e60ab92c1f59b698543eba03446c493cd5c
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8210c3e296732d9d03b85e895008ef852933ca6cd6840952b6a81f4a6dc65e17
3
+ size 1064
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4,
13
+ "grad_norm": 1.758865475654602,
14
+ "learning_rate": 4.994647308096509e-05,
15
+ "loss": 4.3569,
16
+ "num_input_tokens_seen": 5888,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 1.4234931468963623,
22
+ "learning_rate": 4.9786121534345265e-05,
23
+ "loss": 4.043,
24
+ "num_input_tokens_seen": 11872,
25
+ "step": 10
26
+ },
27
+ {
28
+ "epoch": 1.2,
29
+ "grad_norm": 1.5642849206924438,
30
+ "learning_rate": 4.951963201008076e-05,
31
+ "loss": 3.7996,
32
+ "num_input_tokens_seen": 17616,
33
+ "step": 15
34
+ },
35
+ {
36
+ "epoch": 1.6,
37
+ "grad_norm": 1.0812954902648926,
38
+ "learning_rate": 4.914814565722671e-05,
39
+ "loss": 3.7366,
40
+ "num_input_tokens_seen": 23584,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "grad_norm": 1.3543965816497803,
46
+ "learning_rate": 4.867325323737765e-05,
47
+ "loss": 3.6712,
48
+ "num_input_tokens_seen": 29600,
49
+ "step": 25
50
+ },
51
+ {
52
+ "epoch": 2.4,
53
+ "grad_norm": 1.436577558517456,
54
+ "learning_rate": 4.8096988312782174e-05,
55
+ "loss": 3.6046,
56
+ "num_input_tokens_seen": 35184,
57
+ "step": 30
58
+ },
59
+ {
60
+ "epoch": 2.8,
61
+ "grad_norm": 1.079750657081604,
62
+ "learning_rate": 4.742181853831721e-05,
63
+ "loss": 3.4873,
64
+ "num_input_tokens_seen": 41056,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 3.2,
69
+ "grad_norm": 1.5652551651000977,
70
+ "learning_rate": 4.665063509461097e-05,
71
+ "loss": 3.3525,
72
+ "num_input_tokens_seen": 47040,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 3.6,
77
+ "grad_norm": 1.6999948024749756,
78
+ "learning_rate": 4.5786740307563636e-05,
79
+ "loss": 3.2724,
80
+ "num_input_tokens_seen": 53072,
81
+ "step": 45
82
+ },
83
+ {
84
+ "epoch": 4.0,
85
+ "grad_norm": 1.4872270822525024,
86
+ "learning_rate": 4.4833833507280884e-05,
87
+ "loss": 3.3493,
88
+ "num_input_tokens_seen": 59360,
89
+ "step": 50
90
+ },
91
+ {
92
+ "epoch": 4.4,
93
+ "grad_norm": 1.450323462486267,
94
+ "learning_rate": 4.379599518697444e-05,
95
+ "loss": 3.2383,
96
+ "num_input_tokens_seen": 64928,
97
+ "step": 55
98
+ },
99
+ {
100
+ "epoch": 4.8,
101
+ "grad_norm": 1.70930016040802,
102
+ "learning_rate": 4.267766952966369e-05,
103
+ "loss": 3.1941,
104
+ "num_input_tokens_seen": 70752,
105
+ "step": 60
106
+ },
107
+ {
108
+ "epoch": 5.2,
109
+ "grad_norm": 1.9510873556137085,
110
+ "learning_rate": 4.148364537750172e-05,
111
+ "loss": 3.1134,
112
+ "num_input_tokens_seen": 76544,
113
+ "step": 65
114
+ },
115
+ {
116
+ "epoch": 5.6,
117
+ "grad_norm": 1.781402826309204,
118
+ "learning_rate": 4.021903572521802e-05,
119
+ "loss": 3.0551,
120
+ "num_input_tokens_seen": 82736,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 6.0,
125
+ "grad_norm": 1.4807748794555664,
126
+ "learning_rate": 3.888925582549006e-05,
127
+ "loss": 3.0148,
128
+ "num_input_tokens_seen": 88464,
129
+ "step": 75
130
+ },
131
+ {
132
+ "epoch": 6.4,
133
+ "grad_norm": 1.936543345451355,
134
+ "learning_rate": 3.7500000000000003e-05,
135
+ "loss": 2.9215,
136
+ "num_input_tokens_seen": 94496,
137
+ "step": 80
138
+ },
139
+ {
140
+ "epoch": 6.8,
141
+ "grad_norm": 2.542340040206909,
142
+ "learning_rate": 3.6057217255475034e-05,
143
+ "loss": 2.8317,
144
+ "num_input_tokens_seen": 100192,
145
+ "step": 85
146
+ },
147
+ {
148
+ "epoch": 7.2,
149
+ "grad_norm": 2.17262864112854,
150
+ "learning_rate": 3.456708580912725e-05,
151
+ "loss": 2.8665,
152
+ "num_input_tokens_seen": 105904,
153
+ "step": 90
154
+ },
155
+ {
156
+ "epoch": 7.6,
157
+ "grad_norm": 1.919408917427063,
158
+ "learning_rate": 3.303598663257904e-05,
159
+ "loss": 2.8028,
160
+ "num_input_tokens_seen": 111856,
161
+ "step": 95
162
+ },
163
+ {
164
+ "epoch": 8.0,
165
+ "grad_norm": 2.5374443531036377,
166
+ "learning_rate": 3.147047612756302e-05,
167
+ "loss": 2.9059,
168
+ "num_input_tokens_seen": 118064,
169
+ "step": 100
170
+ }
171
+ ],
172
+ "logging_steps": 5,
173
+ "max_steps": 240,
174
+ "num_input_tokens_seen": 118064,
175
+ "num_train_epochs": 20,
176
+ "save_steps": 100,
177
+ "stateful_callbacks": {
178
+ "TrainerControl": {
179
+ "args": {
180
+ "should_epoch_stop": false,
181
+ "should_evaluate": false,
182
+ "should_log": false,
183
+ "should_save": true,
184
+ "should_training_stop": false
185
+ },
186
+ "attributes": {}
187
+ }
188
+ },
189
+ "total_flos": 935221387051008.0,
190
+ "train_batch_size": 2,
191
+ "trial_name": null,
192
+ "trial_params": null
193
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88861ed737b91798f2b18542cf81036f47fb195cc2283a0f86fbef9f5c7d5c56
3
+ size 5304
checkpoint-100/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2-1.5B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 8,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "up_proj",
25
+ "q_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": true,
33
+ "use_rslora": false
34
+ }
checkpoint-200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a1ab856bf07f021b2dd2bdb096a19a1afd852d467dd5510be76e8768d15564
3
+ size 39588464
checkpoint-200/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
checkpoint-200/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f356a0679178142786859e1fa31514d14477e6ac628b118ef9663ac9907ab813
3
+ size 79513462
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d44a53784733ae7dcb55555ed75e1fea306bd7427001380dc0f3854a19687855
3
+ size 14244
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3133cb56fc46e3d814a06b3f520019ad72b705f2bc8fd0dd898390bb36dcd1da
3
+ size 1064
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,353 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 16.0,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4,
13
+ "grad_norm": 1.758865475654602,
14
+ "learning_rate": 4.994647308096509e-05,
15
+ "loss": 4.3569,
16
+ "num_input_tokens_seen": 5888,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 1.4234931468963623,
22
+ "learning_rate": 4.9786121534345265e-05,
23
+ "loss": 4.043,
24
+ "num_input_tokens_seen": 11872,
25
+ "step": 10
26
+ },
27
+ {
28
+ "epoch": 1.2,
29
+ "grad_norm": 1.5642849206924438,
30
+ "learning_rate": 4.951963201008076e-05,
31
+ "loss": 3.7996,
32
+ "num_input_tokens_seen": 17616,
33
+ "step": 15
34
+ },
35
+ {
36
+ "epoch": 1.6,
37
+ "grad_norm": 1.0812954902648926,
38
+ "learning_rate": 4.914814565722671e-05,
39
+ "loss": 3.7366,
40
+ "num_input_tokens_seen": 23584,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "grad_norm": 1.3543965816497803,
46
+ "learning_rate": 4.867325323737765e-05,
47
+ "loss": 3.6712,
48
+ "num_input_tokens_seen": 29600,
49
+ "step": 25
50
+ },
51
+ {
52
+ "epoch": 2.4,
53
+ "grad_norm": 1.436577558517456,
54
+ "learning_rate": 4.8096988312782174e-05,
55
+ "loss": 3.6046,
56
+ "num_input_tokens_seen": 35184,
57
+ "step": 30
58
+ },
59
+ {
60
+ "epoch": 2.8,
61
+ "grad_norm": 1.079750657081604,
62
+ "learning_rate": 4.742181853831721e-05,
63
+ "loss": 3.4873,
64
+ "num_input_tokens_seen": 41056,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 3.2,
69
+ "grad_norm": 1.5652551651000977,
70
+ "learning_rate": 4.665063509461097e-05,
71
+ "loss": 3.3525,
72
+ "num_input_tokens_seen": 47040,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 3.6,
77
+ "grad_norm": 1.6999948024749756,
78
+ "learning_rate": 4.5786740307563636e-05,
79
+ "loss": 3.2724,
80
+ "num_input_tokens_seen": 53072,
81
+ "step": 45
82
+ },
83
+ {
84
+ "epoch": 4.0,
85
+ "grad_norm": 1.4872270822525024,
86
+ "learning_rate": 4.4833833507280884e-05,
87
+ "loss": 3.3493,
88
+ "num_input_tokens_seen": 59360,
89
+ "step": 50
90
+ },
91
+ {
92
+ "epoch": 4.4,
93
+ "grad_norm": 1.450323462486267,
94
+ "learning_rate": 4.379599518697444e-05,
95
+ "loss": 3.2383,
96
+ "num_input_tokens_seen": 64928,
97
+ "step": 55
98
+ },
99
+ {
100
+ "epoch": 4.8,
101
+ "grad_norm": 1.70930016040802,
102
+ "learning_rate": 4.267766952966369e-05,
103
+ "loss": 3.1941,
104
+ "num_input_tokens_seen": 70752,
105
+ "step": 60
106
+ },
107
+ {
108
+ "epoch": 5.2,
109
+ "grad_norm": 1.9510873556137085,
110
+ "learning_rate": 4.148364537750172e-05,
111
+ "loss": 3.1134,
112
+ "num_input_tokens_seen": 76544,
113
+ "step": 65
114
+ },
115
+ {
116
+ "epoch": 5.6,
117
+ "grad_norm": 1.781402826309204,
118
+ "learning_rate": 4.021903572521802e-05,
119
+ "loss": 3.0551,
120
+ "num_input_tokens_seen": 82736,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 6.0,
125
+ "grad_norm": 1.4807748794555664,
126
+ "learning_rate": 3.888925582549006e-05,
127
+ "loss": 3.0148,
128
+ "num_input_tokens_seen": 88464,
129
+ "step": 75
130
+ },
131
+ {
132
+ "epoch": 6.4,
133
+ "grad_norm": 1.936543345451355,
134
+ "learning_rate": 3.7500000000000003e-05,
135
+ "loss": 2.9215,
136
+ "num_input_tokens_seen": 94496,
137
+ "step": 80
138
+ },
139
+ {
140
+ "epoch": 6.8,
141
+ "grad_norm": 2.542340040206909,
142
+ "learning_rate": 3.6057217255475034e-05,
143
+ "loss": 2.8317,
144
+ "num_input_tokens_seen": 100192,
145
+ "step": 85
146
+ },
147
+ {
148
+ "epoch": 7.2,
149
+ "grad_norm": 2.17262864112854,
150
+ "learning_rate": 3.456708580912725e-05,
151
+ "loss": 2.8665,
152
+ "num_input_tokens_seen": 105904,
153
+ "step": 90
154
+ },
155
+ {
156
+ "epoch": 7.6,
157
+ "grad_norm": 1.919408917427063,
158
+ "learning_rate": 3.303598663257904e-05,
159
+ "loss": 2.8028,
160
+ "num_input_tokens_seen": 111856,
161
+ "step": 95
162
+ },
163
+ {
164
+ "epoch": 8.0,
165
+ "grad_norm": 2.5374443531036377,
166
+ "learning_rate": 3.147047612756302e-05,
167
+ "loss": 2.9059,
168
+ "num_input_tokens_seen": 118064,
169
+ "step": 100
170
+ },
171
+ {
172
+ "epoch": 8.4,
173
+ "grad_norm": 1.868935465812683,
174
+ "learning_rate": 2.9877258050403212e-05,
175
+ "loss": 2.6716,
176
+ "num_input_tokens_seen": 124192,
177
+ "step": 105
178
+ },
179
+ {
180
+ "epoch": 8.8,
181
+ "grad_norm": 1.9682857990264893,
182
+ "learning_rate": 2.8263154805501297e-05,
183
+ "loss": 2.7336,
184
+ "num_input_tokens_seen": 129856,
185
+ "step": 110
186
+ },
187
+ {
188
+ "epoch": 9.2,
189
+ "grad_norm": 2.1156065464019775,
190
+ "learning_rate": 2.663507823075358e-05,
191
+ "loss": 2.6835,
192
+ "num_input_tokens_seen": 135760,
193
+ "step": 115
194
+ },
195
+ {
196
+ "epoch": 9.6,
197
+ "grad_norm": 2.3779890537261963,
198
+ "learning_rate": 2.5e-05,
199
+ "loss": 2.5898,
200
+ "num_input_tokens_seen": 141760,
201
+ "step": 120
202
+ },
203
+ {
204
+ "epoch": 10.0,
205
+ "grad_norm": 2.671842336654663,
206
+ "learning_rate": 2.3364921769246423e-05,
207
+ "loss": 2.5017,
208
+ "num_input_tokens_seen": 147664,
209
+ "step": 125
210
+ },
211
+ {
212
+ "epoch": 10.4,
213
+ "grad_norm": 2.809380292892456,
214
+ "learning_rate": 2.173684519449872e-05,
215
+ "loss": 2.4384,
216
+ "num_input_tokens_seen": 153312,
217
+ "step": 130
218
+ },
219
+ {
220
+ "epoch": 10.8,
221
+ "grad_norm": 3.9723222255706787,
222
+ "learning_rate": 2.0122741949596797e-05,
223
+ "loss": 2.5169,
224
+ "num_input_tokens_seen": 159584,
225
+ "step": 135
226
+ },
227
+ {
228
+ "epoch": 11.2,
229
+ "grad_norm": 2.3110992908477783,
230
+ "learning_rate": 1.852952387243698e-05,
231
+ "loss": 2.3124,
232
+ "num_input_tokens_seen": 165040,
233
+ "step": 140
234
+ },
235
+ {
236
+ "epoch": 11.6,
237
+ "grad_norm": 2.2998690605163574,
238
+ "learning_rate": 1.6964013367420966e-05,
239
+ "loss": 2.4734,
240
+ "num_input_tokens_seen": 170944,
241
+ "step": 145
242
+ },
243
+ {
244
+ "epoch": 12.0,
245
+ "grad_norm": 3.0829477310180664,
246
+ "learning_rate": 1.5432914190872757e-05,
247
+ "loss": 2.3957,
248
+ "num_input_tokens_seen": 177168,
249
+ "step": 150
250
+ },
251
+ {
252
+ "epoch": 12.4,
253
+ "grad_norm": 2.7017433643341064,
254
+ "learning_rate": 1.3942782744524973e-05,
255
+ "loss": 2.5141,
256
+ "num_input_tokens_seen": 183088,
257
+ "step": 155
258
+ },
259
+ {
260
+ "epoch": 12.8,
261
+ "grad_norm": 3.001948118209839,
262
+ "learning_rate": 1.2500000000000006e-05,
263
+ "loss": 2.2276,
264
+ "num_input_tokens_seen": 188736,
265
+ "step": 160
266
+ },
267
+ {
268
+ "epoch": 13.2,
269
+ "grad_norm": 3.0778212547302246,
270
+ "learning_rate": 1.1110744174509952e-05,
271
+ "loss": 2.1839,
272
+ "num_input_tokens_seen": 194592,
273
+ "step": 165
274
+ },
275
+ {
276
+ "epoch": 13.6,
277
+ "grad_norm": 3.4998250007629395,
278
+ "learning_rate": 9.780964274781984e-06,
279
+ "loss": 2.3212,
280
+ "num_input_tokens_seen": 200528,
281
+ "step": 170
282
+ },
283
+ {
284
+ "epoch": 14.0,
285
+ "grad_norm": 2.9788782596588135,
286
+ "learning_rate": 8.51635462249828e-06,
287
+ "loss": 2.2398,
288
+ "num_input_tokens_seen": 206256,
289
+ "step": 175
290
+ },
291
+ {
292
+ "epoch": 14.4,
293
+ "grad_norm": 3.000025510787964,
294
+ "learning_rate": 7.3223304703363135e-06,
295
+ "loss": 2.2431,
296
+ "num_input_tokens_seen": 212480,
297
+ "step": 180
298
+ },
299
+ {
300
+ "epoch": 14.8,
301
+ "grad_norm": 3.488719940185547,
302
+ "learning_rate": 6.204004813025568e-06,
303
+ "loss": 2.0743,
304
+ "num_input_tokens_seen": 218208,
305
+ "step": 185
306
+ },
307
+ {
308
+ "epoch": 15.2,
309
+ "grad_norm": 3.7175214290618896,
310
+ "learning_rate": 5.166166492719124e-06,
311
+ "loss": 2.1343,
312
+ "num_input_tokens_seen": 223632,
313
+ "step": 190
314
+ },
315
+ {
316
+ "epoch": 15.6,
317
+ "grad_norm": 3.5645270347595215,
318
+ "learning_rate": 4.213259692436367e-06,
319
+ "loss": 2.3751,
320
+ "num_input_tokens_seen": 229776,
321
+ "step": 195
322
+ },
323
+ {
324
+ "epoch": 16.0,
325
+ "grad_norm": 3.673673629760742,
326
+ "learning_rate": 3.3493649053890326e-06,
327
+ "loss": 2.0981,
328
+ "num_input_tokens_seen": 235392,
329
+ "step": 200
330
+ }
331
+ ],
332
+ "logging_steps": 5,
333
+ "max_steps": 240,
334
+ "num_input_tokens_seen": 235392,
335
+ "num_train_epochs": 20,
336
+ "save_steps": 100,
337
+ "stateful_callbacks": {
338
+ "TrainerControl": {
339
+ "args": {
340
+ "should_epoch_stop": false,
341
+ "should_evaluate": false,
342
+ "should_log": false,
343
+ "should_save": true,
344
+ "should_training_stop": false
345
+ },
346
+ "attributes": {}
347
+ }
348
+ },
349
+ "total_flos": 1864612690919424.0,
350
+ "train_batch_size": 2,
351
+ "trial_name": null,
352
+ "trial_params": null
353
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88861ed737b91798f2b18542cf81036f47fb195cc2283a0f86fbef9f5c7d5c56
3
+ size 5304
checkpoint-200/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-240/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2-1.5B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-240/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 8,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "up_proj",
25
+ "q_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": true,
33
+ "use_rslora": false
34
+ }
checkpoint-240/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fda7d6167c440da3e80fdb3580d334fd34dce3b2eea000bf7763b8b38bddf21
3
+ size 39588464
checkpoint-240/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
checkpoint-240/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-240/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6eb8127430096672be9d5f8d2aa0b72c052b68156233fd83e3ec31a6b219fba
3
+ size 79513462
checkpoint-240/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb512edbf725e7c96c3109f7cd79eba5fb2a57850749b080cd81dd106ee0914
3
+ size 14244
checkpoint-240/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573e42e65bdbeb9991d17e7ed690aa2f143f2a22479ade9d84c12c5ef1c9d7ac
3
+ size 1064
checkpoint-240/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
checkpoint-240/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-240/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
checkpoint-240/trainer_state.json ADDED
@@ -0,0 +1,417 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.2,
5
+ "eval_steps": 500,
6
+ "global_step": 240,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4,
13
+ "grad_norm": 1.758865475654602,
14
+ "learning_rate": 4.994647308096509e-05,
15
+ "loss": 4.3569,
16
+ "num_input_tokens_seen": 5888,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 1.4234931468963623,
22
+ "learning_rate": 4.9786121534345265e-05,
23
+ "loss": 4.043,
24
+ "num_input_tokens_seen": 11872,
25
+ "step": 10
26
+ },
27
+ {
28
+ "epoch": 1.2,
29
+ "grad_norm": 1.5642849206924438,
30
+ "learning_rate": 4.951963201008076e-05,
31
+ "loss": 3.7996,
32
+ "num_input_tokens_seen": 17616,
33
+ "step": 15
34
+ },
35
+ {
36
+ "epoch": 1.6,
37
+ "grad_norm": 1.0812954902648926,
38
+ "learning_rate": 4.914814565722671e-05,
39
+ "loss": 3.7366,
40
+ "num_input_tokens_seen": 23584,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "grad_norm": 1.3543965816497803,
46
+ "learning_rate": 4.867325323737765e-05,
47
+ "loss": 3.6712,
48
+ "num_input_tokens_seen": 29600,
49
+ "step": 25
50
+ },
51
+ {
52
+ "epoch": 2.4,
53
+ "grad_norm": 1.436577558517456,
54
+ "learning_rate": 4.8096988312782174e-05,
55
+ "loss": 3.6046,
56
+ "num_input_tokens_seen": 35184,
57
+ "step": 30
58
+ },
59
+ {
60
+ "epoch": 2.8,
61
+ "grad_norm": 1.079750657081604,
62
+ "learning_rate": 4.742181853831721e-05,
63
+ "loss": 3.4873,
64
+ "num_input_tokens_seen": 41056,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 3.2,
69
+ "grad_norm": 1.5652551651000977,
70
+ "learning_rate": 4.665063509461097e-05,
71
+ "loss": 3.3525,
72
+ "num_input_tokens_seen": 47040,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 3.6,
77
+ "grad_norm": 1.6999948024749756,
78
+ "learning_rate": 4.5786740307563636e-05,
79
+ "loss": 3.2724,
80
+ "num_input_tokens_seen": 53072,
81
+ "step": 45
82
+ },
83
+ {
84
+ "epoch": 4.0,
85
+ "grad_norm": 1.4872270822525024,
86
+ "learning_rate": 4.4833833507280884e-05,
87
+ "loss": 3.3493,
88
+ "num_input_tokens_seen": 59360,
89
+ "step": 50
90
+ },
91
+ {
92
+ "epoch": 4.4,
93
+ "grad_norm": 1.450323462486267,
94
+ "learning_rate": 4.379599518697444e-05,
95
+ "loss": 3.2383,
96
+ "num_input_tokens_seen": 64928,
97
+ "step": 55
98
+ },
99
+ {
100
+ "epoch": 4.8,
101
+ "grad_norm": 1.70930016040802,
102
+ "learning_rate": 4.267766952966369e-05,
103
+ "loss": 3.1941,
104
+ "num_input_tokens_seen": 70752,
105
+ "step": 60
106
+ },
107
+ {
108
+ "epoch": 5.2,
109
+ "grad_norm": 1.9510873556137085,
110
+ "learning_rate": 4.148364537750172e-05,
111
+ "loss": 3.1134,
112
+ "num_input_tokens_seen": 76544,
113
+ "step": 65
114
+ },
115
+ {
116
+ "epoch": 5.6,
117
+ "grad_norm": 1.781402826309204,
118
+ "learning_rate": 4.021903572521802e-05,
119
+ "loss": 3.0551,
120
+ "num_input_tokens_seen": 82736,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 6.0,
125
+ "grad_norm": 1.4807748794555664,
126
+ "learning_rate": 3.888925582549006e-05,
127
+ "loss": 3.0148,
128
+ "num_input_tokens_seen": 88464,
129
+ "step": 75
130
+ },
131
+ {
132
+ "epoch": 6.4,
133
+ "grad_norm": 1.936543345451355,
134
+ "learning_rate": 3.7500000000000003e-05,
135
+ "loss": 2.9215,
136
+ "num_input_tokens_seen": 94496,
137
+ "step": 80
138
+ },
139
+ {
140
+ "epoch": 6.8,
141
+ "grad_norm": 2.542340040206909,
142
+ "learning_rate": 3.6057217255475034e-05,
143
+ "loss": 2.8317,
144
+ "num_input_tokens_seen": 100192,
145
+ "step": 85
146
+ },
147
+ {
148
+ "epoch": 7.2,
149
+ "grad_norm": 2.17262864112854,
150
+ "learning_rate": 3.456708580912725e-05,
151
+ "loss": 2.8665,
152
+ "num_input_tokens_seen": 105904,
153
+ "step": 90
154
+ },
155
+ {
156
+ "epoch": 7.6,
157
+ "grad_norm": 1.919408917427063,
158
+ "learning_rate": 3.303598663257904e-05,
159
+ "loss": 2.8028,
160
+ "num_input_tokens_seen": 111856,
161
+ "step": 95
162
+ },
163
+ {
164
+ "epoch": 8.0,
165
+ "grad_norm": 2.5374443531036377,
166
+ "learning_rate": 3.147047612756302e-05,
167
+ "loss": 2.9059,
168
+ "num_input_tokens_seen": 118064,
169
+ "step": 100
170
+ },
171
+ {
172
+ "epoch": 8.4,
173
+ "grad_norm": 1.868935465812683,
174
+ "learning_rate": 2.9877258050403212e-05,
175
+ "loss": 2.6716,
176
+ "num_input_tokens_seen": 124192,
177
+ "step": 105
178
+ },
179
+ {
180
+ "epoch": 8.8,
181
+ "grad_norm": 1.9682857990264893,
182
+ "learning_rate": 2.8263154805501297e-05,
183
+ "loss": 2.7336,
184
+ "num_input_tokens_seen": 129856,
185
+ "step": 110
186
+ },
187
+ {
188
+ "epoch": 9.2,
189
+ "grad_norm": 2.1156065464019775,
190
+ "learning_rate": 2.663507823075358e-05,
191
+ "loss": 2.6835,
192
+ "num_input_tokens_seen": 135760,
193
+ "step": 115
194
+ },
195
+ {
196
+ "epoch": 9.6,
197
+ "grad_norm": 2.3779890537261963,
198
+ "learning_rate": 2.5e-05,
199
+ "loss": 2.5898,
200
+ "num_input_tokens_seen": 141760,
201
+ "step": 120
202
+ },
203
+ {
204
+ "epoch": 10.0,
205
+ "grad_norm": 2.671842336654663,
206
+ "learning_rate": 2.3364921769246423e-05,
207
+ "loss": 2.5017,
208
+ "num_input_tokens_seen": 147664,
209
+ "step": 125
210
+ },
211
+ {
212
+ "epoch": 10.4,
213
+ "grad_norm": 2.809380292892456,
214
+ "learning_rate": 2.173684519449872e-05,
215
+ "loss": 2.4384,
216
+ "num_input_tokens_seen": 153312,
217
+ "step": 130
218
+ },
219
+ {
220
+ "epoch": 10.8,
221
+ "grad_norm": 3.9723222255706787,
222
+ "learning_rate": 2.0122741949596797e-05,
223
+ "loss": 2.5169,
224
+ "num_input_tokens_seen": 159584,
225
+ "step": 135
226
+ },
227
+ {
228
+ "epoch": 11.2,
229
+ "grad_norm": 2.3110992908477783,
230
+ "learning_rate": 1.852952387243698e-05,
231
+ "loss": 2.3124,
232
+ "num_input_tokens_seen": 165040,
233
+ "step": 140
234
+ },
235
+ {
236
+ "epoch": 11.6,
237
+ "grad_norm": 2.2998690605163574,
238
+ "learning_rate": 1.6964013367420966e-05,
239
+ "loss": 2.4734,
240
+ "num_input_tokens_seen": 170944,
241
+ "step": 145
242
+ },
243
+ {
244
+ "epoch": 12.0,
245
+ "grad_norm": 3.0829477310180664,
246
+ "learning_rate": 1.5432914190872757e-05,
247
+ "loss": 2.3957,
248
+ "num_input_tokens_seen": 177168,
249
+ "step": 150
250
+ },
251
+ {
252
+ "epoch": 12.4,
253
+ "grad_norm": 2.7017433643341064,
254
+ "learning_rate": 1.3942782744524973e-05,
255
+ "loss": 2.5141,
256
+ "num_input_tokens_seen": 183088,
257
+ "step": 155
258
+ },
259
+ {
260
+ "epoch": 12.8,
261
+ "grad_norm": 3.001948118209839,
262
+ "learning_rate": 1.2500000000000006e-05,
263
+ "loss": 2.2276,
264
+ "num_input_tokens_seen": 188736,
265
+ "step": 160
266
+ },
267
+ {
268
+ "epoch": 13.2,
269
+ "grad_norm": 3.0778212547302246,
270
+ "learning_rate": 1.1110744174509952e-05,
271
+ "loss": 2.1839,
272
+ "num_input_tokens_seen": 194592,
273
+ "step": 165
274
+ },
275
+ {
276
+ "epoch": 13.6,
277
+ "grad_norm": 3.4998250007629395,
278
+ "learning_rate": 9.780964274781984e-06,
279
+ "loss": 2.3212,
280
+ "num_input_tokens_seen": 200528,
281
+ "step": 170
282
+ },
283
+ {
284
+ "epoch": 14.0,
285
+ "grad_norm": 2.9788782596588135,
286
+ "learning_rate": 8.51635462249828e-06,
287
+ "loss": 2.2398,
288
+ "num_input_tokens_seen": 206256,
289
+ "step": 175
290
+ },
291
+ {
292
+ "epoch": 14.4,
293
+ "grad_norm": 3.000025510787964,
294
+ "learning_rate": 7.3223304703363135e-06,
295
+ "loss": 2.2431,
296
+ "num_input_tokens_seen": 212480,
297
+ "step": 180
298
+ },
299
+ {
300
+ "epoch": 14.8,
301
+ "grad_norm": 3.488719940185547,
302
+ "learning_rate": 6.204004813025568e-06,
303
+ "loss": 2.0743,
304
+ "num_input_tokens_seen": 218208,
305
+ "step": 185
306
+ },
307
+ {
308
+ "epoch": 15.2,
309
+ "grad_norm": 3.7175214290618896,
310
+ "learning_rate": 5.166166492719124e-06,
311
+ "loss": 2.1343,
312
+ "num_input_tokens_seen": 223632,
313
+ "step": 190
314
+ },
315
+ {
316
+ "epoch": 15.6,
317
+ "grad_norm": 3.5645270347595215,
318
+ "learning_rate": 4.213259692436367e-06,
319
+ "loss": 2.3751,
320
+ "num_input_tokens_seen": 229776,
321
+ "step": 195
322
+ },
323
+ {
324
+ "epoch": 16.0,
325
+ "grad_norm": 3.673673629760742,
326
+ "learning_rate": 3.3493649053890326e-06,
327
+ "loss": 2.0981,
328
+ "num_input_tokens_seen": 235392,
329
+ "step": 200
330
+ },
331
+ {
332
+ "epoch": 16.4,
333
+ "grad_norm": 3.5783541202545166,
334
+ "learning_rate": 2.578181461682794e-06,
335
+ "loss": 2.151,
336
+ "num_input_tokens_seen": 241168,
337
+ "step": 205
338
+ },
339
+ {
340
+ "epoch": 16.8,
341
+ "grad_norm": 3.5505430698394775,
342
+ "learning_rate": 1.9030116872178316e-06,
343
+ "loss": 2.1801,
344
+ "num_input_tokens_seen": 247200,
345
+ "step": 210
346
+ },
347
+ {
348
+ "epoch": 17.2,
349
+ "grad_norm": 3.7030887603759766,
350
+ "learning_rate": 1.3267467626223606e-06,
351
+ "loss": 2.3428,
352
+ "num_input_tokens_seen": 253536,
353
+ "step": 215
354
+ },
355
+ {
356
+ "epoch": 17.6,
357
+ "grad_norm": 3.326767921447754,
358
+ "learning_rate": 8.51854342773295e-07,
359
+ "loss": 2.1907,
360
+ "num_input_tokens_seen": 259568,
361
+ "step": 220
362
+ },
363
+ {
364
+ "epoch": 18.0,
365
+ "grad_norm": 3.3685076236724854,
366
+ "learning_rate": 4.803679899192392e-07,
367
+ "loss": 2.0246,
368
+ "num_input_tokens_seen": 265056,
369
+ "step": 225
370
+ },
371
+ {
372
+ "epoch": 18.4,
373
+ "grad_norm": 3.4106569290161133,
374
+ "learning_rate": 2.1387846565474045e-07,
375
+ "loss": 2.1411,
376
+ "num_input_tokens_seen": 271312,
377
+ "step": 230
378
+ },
379
+ {
380
+ "epoch": 18.8,
381
+ "grad_norm": 3.188873529434204,
382
+ "learning_rate": 5.352691903491303e-08,
383
+ "loss": 2.0321,
384
+ "num_input_tokens_seen": 277008,
385
+ "step": 235
386
+ },
387
+ {
388
+ "epoch": 19.2,
389
+ "grad_norm": 3.023102045059204,
390
+ "learning_rate": 0.0,
391
+ "loss": 2.2785,
392
+ "num_input_tokens_seen": 282848,
393
+ "step": 240
394
+ }
395
+ ],
396
+ "logging_steps": 5,
397
+ "max_steps": 240,
398
+ "num_input_tokens_seen": 282848,
399
+ "num_train_epochs": 20,
400
+ "save_steps": 100,
401
+ "stateful_callbacks": {
402
+ "TrainerControl": {
403
+ "args": {
404
+ "should_epoch_stop": false,
405
+ "should_evaluate": false,
406
+ "should_log": false,
407
+ "should_save": true,
408
+ "should_training_stop": true
409
+ },
410
+ "attributes": {}
411
+ }
412
+ },
413
+ "total_flos": 2240526315257856.0,
414
+ "train_batch_size": 2,
415
+ "trial_name": null,
416
+ "trial_params": null
417
+ }
checkpoint-240/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88861ed737b91798f2b18542cf81036f47fb195cc2283a0f86fbef9f5c7d5c56
3
+ size 5304
checkpoint-240/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.42.3",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.42.3"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99ed3114e8d6550597464904b2bc7db3fdf52bd0f2a0f9428b826e8b4207979
3
+ size 973272632
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0edffcc6d7000d32fe3e61f6b2ebae6ce326866a22ad68a0e868c10bd36453b7
3
+ size 997323016
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729e998c8a54d367da5dd56df489fd603d9cdd64a0cb3cb7e7839af40abda79a
3
+ size 995739192
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9952fd5b5b99009d05da9bfda19e410762fd03e489f8a041fdd282428a4f949e
3
+ size 121131784