Hugging Face's logo

wf8888884
/
backup

Safetensors
Model card Files
xet
Community
wf8888884 commited on
Commit
dfafc69
·
verified ·
1 Parent(s): 3627eef

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. Power_Area_Time_SFT/checkpoint-100/README.md +202 -0
  2. Power_Area_Time_SFT/checkpoint-100/adapter_config.json +34 -0
  3. Power_Area_Time_SFT/checkpoint-100/adapter_model.safetensors +3 -0
  4. Power_Area_Time_SFT/checkpoint-100/added_tokens.json +3 -0
  5. Power_Area_Time_SFT/checkpoint-100/rng_state_0.pth +3 -0
  6. Power_Area_Time_SFT/checkpoint-100/rng_state_1.pth +3 -0
  7. Power_Area_Time_SFT/checkpoint-100/rng_state_4.pth +3 -0
  8. Power_Area_Time_SFT/checkpoint-100/rng_state_7.pth +3 -0
  9. Power_Area_Time_SFT/checkpoint-100/scheduler.pt +3 -0
  10. Power_Area_Time_SFT/checkpoint-100/special_tokens_map.json +36 -0
  11. Power_Area_Time_SFT/checkpoint-100/tokenizer.json +0 -0
  12. Power_Area_Time_SFT/checkpoint-100/tokenizer.model +3 -0
  13. Power_Area_Time_SFT/checkpoint-100/tokenizer_config.json +59 -0
  14. Power_Area_Time_SFT/checkpoint-100/trainer_state.json +183 -0
  15. Power_Area_Time_SFT/checkpoint-100/training_args.bin +3 -0
  16. Power_Area_Time_SFT/checkpoint-200/README.md +202 -0
  17. Power_Area_Time_SFT/checkpoint-200/adapter_config.json +34 -0
  18. Power_Area_Time_SFT/checkpoint-200/added_tokens.json +3 -0
  19. Power_Area_Time_SFT/checkpoint-200/rng_state_0.pth +3 -0
  20. Power_Area_Time_SFT/checkpoint-200/rng_state_1.pth +3 -0
  21. Power_Area_Time_SFT/checkpoint-200/rng_state_2.pth +3 -0
  22. Power_Area_Time_SFT/checkpoint-200/rng_state_3.pth +3 -0
  23. Power_Area_Time_SFT/checkpoint-200/rng_state_4.pth +3 -0
  24. Power_Area_Time_SFT/checkpoint-200/rng_state_5.pth +3 -0
  25. Power_Area_Time_SFT/checkpoint-200/rng_state_6.pth +3 -0
  26. Power_Area_Time_SFT/checkpoint-200/rng_state_7.pth +3 -0
  27. Power_Area_Time_SFT/checkpoint-200/scheduler.pt +3 -0
  28. Power_Area_Time_SFT/checkpoint-200/special_tokens_map.json +36 -0
  29. Power_Area_Time_SFT/checkpoint-200/tokenizer.json +0 -0
  30. Power_Area_Time_SFT/checkpoint-200/tokenizer.model +3 -0
  31. Power_Area_Time_SFT/checkpoint-200/tokenizer_config.json +59 -0
  32. Power_Area_Time_SFT/checkpoint-200/trainer_state.json +333 -0
  33. Power_Area_Time_SFT/checkpoint-200/training_args.bin +3 -0
  34. Power_Area_Time_SFT/checkpoint-300/README.md +202 -0
  35. Power_Area_Time_SFT/checkpoint-300/adapter_config.json +34 -0
  36. Power_Area_Time_SFT/checkpoint-300/added_tokens.json +3 -0
  37. Power_Area_Time_SFT/checkpoint-300/rng_state_0.pth +3 -0
  38. Power_Area_Time_SFT/checkpoint-300/rng_state_1.pth +3 -0
  39. Power_Area_Time_SFT/checkpoint-300/rng_state_2.pth +3 -0
  40. Power_Area_Time_SFT/checkpoint-300/rng_state_3.pth +3 -0
  41. Power_Area_Time_SFT/checkpoint-300/rng_state_4.pth +3 -0
  42. Power_Area_Time_SFT/checkpoint-300/rng_state_5.pth +3 -0
  43. Power_Area_Time_SFT/checkpoint-300/rng_state_6.pth +3 -0
  44. Power_Area_Time_SFT/checkpoint-300/rng_state_7.pth +3 -0
  45. Power_Area_Time_SFT/checkpoint-300/scheduler.pt +3 -0
  46. Power_Area_Time_SFT/checkpoint-300/special_tokens_map.json +36 -0
  47. Power_Area_Time_SFT/checkpoint-300/tokenizer.json +0 -0
  48. Power_Area_Time_SFT/checkpoint-300/tokenizer.model +3 -0
  49. Power_Area_Time_SFT/checkpoint-300/tokenizer_config.json +59 -0
  50. Power_Area_Time_SFT/checkpoint-300/trainer_state.json +483 -0
Power_Area_Time_SFT/checkpoint-100/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ishorn5/RTLCoder-v1.1
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
Power_Area_Time_SFT/checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
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": 16,
14
+ "lora_dropout": 0.0,
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
+ "o_proj",
24
+ "q_proj",
25
+ "down_proj",
26
+ "v_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
Power_Area_Time_SFT/checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6fba87471b97a0d83146431b9d698bc311c7fd44f96a6aad2d7696cbcbe3364
3
+ size 83945296
Power_Area_Time_SFT/checkpoint-100/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
Power_Area_Time_SFT/checkpoint-100/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d2a2034ebb05cb71c510897f2795b31164e50f17b270bc25d2be3ad9a17b22
3
+ size 15984
Power_Area_Time_SFT/checkpoint-100/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060dfdb1c49102cbdc8868a6031e68787601b4ccd782f3fb9b137e20c1fd2c7a
3
+ size 15984
Power_Area_Time_SFT/checkpoint-100/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69353c629541c690c5471f8ec05fdab2bfecf3d37afaa436bc45939da6db68f
3
+ size 15984
Power_Area_Time_SFT/checkpoint-100/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e19618bee7c6ef43256fea25abe19bca88535eb1e7dc213cde8929ae4e8180
3
+ size 15984
Power_Area_Time_SFT/checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f649359458cb157292d9a86520c59e16f4c3ef05dbb0c452b05d500dad26a76
3
+ size 1064
Power_Area_Time_SFT/checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "[PAD]"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "[PAD]",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
Power_Area_Time_SFT/checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Power_Area_Time_SFT/checkpoint-100/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
Power_Area_Time_SFT/checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
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
+ "32000": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "additional_special_tokens": [
40
+ "<unk>",
41
+ "<s>",
42
+ "</s>",
43
+ "[PAD]"
44
+ ],
45
+ "bos_token": "<s>",
46
+ "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
47
+ "clean_up_tokenization_spaces": false,
48
+ "eos_token": "</s>",
49
+ "legacy": true,
50
+ "model_max_length": 2048,
51
+ "pad_token": "[PAD]",
52
+ "padding_side": "right",
53
+ "sp_model_kwargs": {},
54
+ "spaces_between_special_tokens": false,
55
+ "split_special_tokens": false,
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": true
59
+ }
Power_Area_Time_SFT/checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.4482758620689653,
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": 0.3448275862068966,
13
+ "grad_norm": 3.9107234477996826,
14
+ "learning_rate": 8.620689655172415e-07,
15
+ "logits/chosen": -2.363854169845581,
16
+ "logits/rejected": -2.338671922683716,
17
+ "logps/chosen": -76.8819351196289,
18
+ "logps/rejected": -75.86869049072266,
19
+ "loss": 0.6942,
20
+ "rewards/accuracies": 0.375,
21
+ "rewards/chosen": -0.003996999468654394,
22
+ "rewards/margins": -0.004145228303968906,
23
+ "rewards/rejected": 0.00014822949015069753,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.6896551724137931,
28
+ "grad_norm": 4.328212738037109,
29
+ "learning_rate": 1.724137931034483e-06,
30
+ "logits/chosen": -2.3617663383483887,
31
+ "logits/rejected": -2.3477540016174316,
32
+ "logps/chosen": -93.76543426513672,
33
+ "logps/rejected": -75.16656494140625,
34
+ "loss": 0.6931,
35
+ "rewards/accuracies": 0.48750001192092896,
36
+ "rewards/chosen": 0.002653368515893817,
37
+ "rewards/margins": 0.006352785974740982,
38
+ "rewards/rejected": -0.003699416993185878,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 1.0344827586206897,
43
+ "grad_norm": 3.473827838897705,
44
+ "learning_rate": 2.5862068965517246e-06,
45
+ "logits/chosen": -2.3354058265686035,
46
+ "logits/rejected": -2.3330740928649902,
47
+ "logps/chosen": -138.9960479736328,
48
+ "logps/rejected": -67.00438690185547,
49
+ "loss": 0.6927,
50
+ "rewards/accuracies": 0.44999998807907104,
51
+ "rewards/chosen": 0.01745142787694931,
52
+ "rewards/margins": 0.013760591857135296,
53
+ "rewards/rejected": 0.0036908381152898073,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 1.3793103448275863,
58
+ "grad_norm": 3.9458820819854736,
59
+ "learning_rate": 3.448275862068966e-06,
60
+ "logits/chosen": -2.3478751182556152,
61
+ "logits/rejected": -2.3700289726257324,
62
+ "logps/chosen": -75.59983825683594,
63
+ "logps/rejected": -67.20357513427734,
64
+ "loss": 0.69,
65
+ "rewards/accuracies": 0.5,
66
+ "rewards/chosen": 0.00024204826331697404,
67
+ "rewards/margins": 0.005866119172424078,
68
+ "rewards/rejected": -0.005624071694910526,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 1.7241379310344827,
73
+ "grad_norm": 4.299890041351318,
74
+ "learning_rate": 4.310344827586207e-06,
75
+ "logits/chosen": -2.338815212249756,
76
+ "logits/rejected": -2.3532769680023193,
77
+ "logps/chosen": -72.74342346191406,
78
+ "logps/rejected": -87.63409423828125,
79
+ "loss": 0.6899,
80
+ "rewards/accuracies": 0.574999988079071,
81
+ "rewards/chosen": -0.003249581903219223,
82
+ "rewards/margins": 0.006888723932206631,
83
+ "rewards/rejected": -0.010138307698071003,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 2.0689655172413794,
88
+ "grad_norm": 4.957555294036865,
89
+ "learning_rate": 4.999818897894192e-06,
90
+ "logits/chosen": -2.344572067260742,
91
+ "logits/rejected": -2.345888614654541,
92
+ "logps/chosen": -80.16046142578125,
93
+ "logps/rejected": -73.05986022949219,
94
+ "loss": 0.6802,
95
+ "rewards/accuracies": 0.637499988079071,
96
+ "rewards/chosen": -0.013288321904838085,
97
+ "rewards/margins": 0.020968889817595482,
98
+ "rewards/rejected": -0.03425721079111099,
99
+ "step": 60
100
+ },
101
+ {
102
+ "epoch": 2.413793103448276,
103
+ "grad_norm": 4.212078094482422,
104
+ "learning_rate": 4.9934830787948756e-06,
105
+ "logits/chosen": -2.3330090045928955,
106
+ "logits/rejected": -2.328575372695923,
107
+ "logps/chosen": -73.63365173339844,
108
+ "logps/rejected": -74.45356750488281,
109
+ "loss": 0.6693,
110
+ "rewards/accuracies": 0.7124999761581421,
111
+ "rewards/chosen": -0.009874681942164898,
112
+ "rewards/margins": 0.04785541445016861,
113
+ "rewards/rejected": -0.05773010104894638,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 2.7586206896551726,
118
+ "grad_norm": 4.446742534637451,
119
+ "learning_rate": 4.978118375700895e-06,
120
+ "logits/chosen": -2.3472495079040527,
121
+ "logits/rejected": -2.3697409629821777,
122
+ "logps/chosen": -73.44490814208984,
123
+ "logps/rejected": -89.69837951660156,
124
+ "loss": 0.6553,
125
+ "rewards/accuracies": 0.8500000238418579,
126
+ "rewards/chosen": -0.022817375138401985,
127
+ "rewards/margins": 0.09045850485563278,
128
+ "rewards/rejected": -0.11327588558197021,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 3.103448275862069,
133
+ "grad_norm": 4.435715198516846,
134
+ "learning_rate": 4.953780424089803e-06,
135
+ "logits/chosen": -2.346717596054077,
136
+ "logits/rejected": -2.3626608848571777,
137
+ "logps/chosen": -85.64796447753906,
138
+ "logps/rejected": -80.06268310546875,
139
+ "loss": 0.6432,
140
+ "rewards/accuracies": 0.737500011920929,
141
+ "rewards/chosen": -0.0543200746178627,
142
+ "rewards/margins": 0.1085677295923233,
143
+ "rewards/rejected": -0.1628878116607666,
144
+ "step": 90
145
+ },
146
+ {
147
+ "epoch": 3.4482758620689653,
148
+ "grad_norm": 4.5200910568237305,
149
+ "learning_rate": 4.920557351506409e-06,
150
+ "logits/chosen": -2.358900547027588,
151
+ "logits/rejected": -2.3591980934143066,
152
+ "logps/chosen": -82.83473205566406,
153
+ "logps/rejected": -80.66204071044922,
154
+ "loss": 0.5996,
155
+ "rewards/accuracies": 0.875,
156
+ "rewards/chosen": -0.046993009746074677,
157
+ "rewards/margins": 0.20401433110237122,
158
+ "rewards/rejected": -0.2510073184967041,
159
+ "step": 100
160
+ }
161
+ ],
162
+ "logging_steps": 10,
163
+ "max_steps": 580,
164
+ "num_input_tokens_seen": 0,
165
+ "num_train_epochs": 20,
166
+ "save_steps": 100,
167
+ "stateful_callbacks": {
168
+ "TrainerControl": {
169
+ "args": {
170
+ "should_epoch_stop": false,
171
+ "should_evaluate": false,
172
+ "should_log": false,
173
+ "should_save": true,
174
+ "should_training_stop": false
175
+ },
176
+ "attributes": {}
177
+ }
178
+ },
179
+ "total_flos": 3.6446446725523046e+17,
180
+ "train_batch_size": 1,
181
+ "trial_name": null,
182
+ "trial_params": null
183
+ }
Power_Area_Time_SFT/checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c39dc276b60c853563692d82de2d090f18d93ee1b30c25c0c44a65f41d370ad6
3
+ size 5368
Power_Area_Time_SFT/checkpoint-200/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ishorn5/RTLCoder-v1.1
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
Power_Area_Time_SFT/checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
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": 16,
14
+ "lora_dropout": 0.0,
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
+ "o_proj",
24
+ "q_proj",
25
+ "down_proj",
26
+ "v_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
Power_Area_Time_SFT/checkpoint-200/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
Power_Area_Time_SFT/checkpoint-200/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d7e02ffb4d440dce7ab4ce0b5617578ec9ce3672acee7434ed6f1153f1ae0c
3
+ size 15984
Power_Area_Time_SFT/checkpoint-200/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b40ca759e432b2688f021b81291d74a40f56a205e9842119f7e772275eebd3
3
+ size 15984
Power_Area_Time_SFT/checkpoint-200/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdaef955ddd36d6bc1c40584113dd6205483e2aa85b02439b8b27e82e02a8359
3
+ size 15984
Power_Area_Time_SFT/checkpoint-200/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b14ae5db356e6512538751d6b386c190754e307cc99cd652d5c6dd891e1f82
3
+ size 15984
Power_Area_Time_SFT/checkpoint-200/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26e28be26826eeeed244b77185c67b443ac185175f8d4bf5ba94caa8b271bc5
3
+ size 15984
Power_Area_Time_SFT/checkpoint-200/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847cedc1d6ca26f299a132c2ade9754887374acb9d98f26594a85d4c7742d474
3
+ size 15984
Power_Area_Time_SFT/checkpoint-200/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd043d1690ae0ff6991b03322799a0b28f021427b15fd9f1e5ed8b9905d9307
3
+ size 15984
Power_Area_Time_SFT/checkpoint-200/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772190f7e6667c865d25fc72da7bdd1b5d39f46fe03bb5c2d754aee1ad3c99c7
3
+ size 15984
Power_Area_Time_SFT/checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91779d753597df7ad790f335f05cf7bab32a28e97a578a59e5c83fea8efecb66
3
+ size 1064
Power_Area_Time_SFT/checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "[PAD]"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "[PAD]",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
Power_Area_Time_SFT/checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Power_Area_Time_SFT/checkpoint-200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
Power_Area_Time_SFT/checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
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
+ "32000": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "additional_special_tokens": [
40
+ "<unk>",
41
+ "<s>",
42
+ "</s>",
43
+ "[PAD]"
44
+ ],
45
+ "bos_token": "<s>",
46
+ "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
47
+ "clean_up_tokenization_spaces": false,
48
+ "eos_token": "</s>",
49
+ "legacy": true,
50
+ "model_max_length": 2048,
51
+ "pad_token": "[PAD]",
52
+ "padding_side": "right",
53
+ "sp_model_kwargs": {},
54
+ "spaces_between_special_tokens": false,
55
+ "split_special_tokens": false,
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": true
59
+ }
Power_Area_Time_SFT/checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,333 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.896551724137931,
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": 0.3448275862068966,
13
+ "grad_norm": 3.9107234477996826,
14
+ "learning_rate": 8.620689655172415e-07,
15
+ "logits/chosen": -2.363854169845581,
16
+ "logits/rejected": -2.338671922683716,
17
+ "logps/chosen": -76.8819351196289,
18
+ "logps/rejected": -75.86869049072266,
19
+ "loss": 0.6942,
20
+ "rewards/accuracies": 0.375,
21
+ "rewards/chosen": -0.003996999468654394,
22
+ "rewards/margins": -0.004145228303968906,
23
+ "rewards/rejected": 0.00014822949015069753,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.6896551724137931,
28
+ "grad_norm": 4.328212738037109,
29
+ "learning_rate": 1.724137931034483e-06,
30
+ "logits/chosen": -2.3617663383483887,
31
+ "logits/rejected": -2.3477540016174316,
32
+ "logps/chosen": -93.76543426513672,
33
+ "logps/rejected": -75.16656494140625,
34
+ "loss": 0.6931,
35
+ "rewards/accuracies": 0.48750001192092896,
36
+ "rewards/chosen": 0.002653368515893817,
37
+ "rewards/margins": 0.006352785974740982,
38
+ "rewards/rejected": -0.003699416993185878,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 1.0344827586206897,
43
+ "grad_norm": 3.473827838897705,
44
+ "learning_rate": 2.5862068965517246e-06,
45
+ "logits/chosen": -2.3354058265686035,
46
+ "logits/rejected": -2.3330740928649902,
47
+ "logps/chosen": -138.9960479736328,
48
+ "logps/rejected": -67.00438690185547,
49
+ "loss": 0.6927,
50
+ "rewards/accuracies": 0.44999998807907104,
51
+ "rewards/chosen": 0.01745142787694931,
52
+ "rewards/margins": 0.013760591857135296,
53
+ "rewards/rejected": 0.0036908381152898073,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 1.3793103448275863,
58
+ "grad_norm": 3.9458820819854736,
59
+ "learning_rate": 3.448275862068966e-06,
60
+ "logits/chosen": -2.3478751182556152,
61
+ "logits/rejected": -2.3700289726257324,
62
+ "logps/chosen": -75.59983825683594,
63
+ "logps/rejected": -67.20357513427734,
64
+ "loss": 0.69,
65
+ "rewards/accuracies": 0.5,
66
+ "rewards/chosen": 0.00024204826331697404,
67
+ "rewards/margins": 0.005866119172424078,
68
+ "rewards/rejected": -0.005624071694910526,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 1.7241379310344827,
73
+ "grad_norm": 4.299890041351318,
74
+ "learning_rate": 4.310344827586207e-06,
75
+ "logits/chosen": -2.338815212249756,
76
+ "logits/rejected": -2.3532769680023193,
77
+ "logps/chosen": -72.74342346191406,
78
+ "logps/rejected": -87.63409423828125,
79
+ "loss": 0.6899,
80
+ "rewards/accuracies": 0.574999988079071,
81
+ "rewards/chosen": -0.003249581903219223,
82
+ "rewards/margins": 0.006888723932206631,
83
+ "rewards/rejected": -0.010138307698071003,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 2.0689655172413794,
88
+ "grad_norm": 4.957555294036865,
89
+ "learning_rate": 4.999818897894192e-06,
90
+ "logits/chosen": -2.344572067260742,
91
+ "logits/rejected": -2.345888614654541,
92
+ "logps/chosen": -80.16046142578125,
93
+ "logps/rejected": -73.05986022949219,
94
+ "loss": 0.6802,
95
+ "rewards/accuracies": 0.637499988079071,
96
+ "rewards/chosen": -0.013288321904838085,
97
+ "rewards/margins": 0.020968889817595482,
98
+ "rewards/rejected": -0.03425721079111099,
99
+ "step": 60
100
+ },
101
+ {
102
+ "epoch": 2.413793103448276,
103
+ "grad_norm": 4.212078094482422,
104
+ "learning_rate": 4.9934830787948756e-06,
105
+ "logits/chosen": -2.3330090045928955,
106
+ "logits/rejected": -2.328575372695923,
107
+ "logps/chosen": -73.63365173339844,
108
+ "logps/rejected": -74.45356750488281,
109
+ "loss": 0.6693,
110
+ "rewards/accuracies": 0.7124999761581421,
111
+ "rewards/chosen": -0.009874681942164898,
112
+ "rewards/margins": 0.04785541445016861,
113
+ "rewards/rejected": -0.05773010104894638,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 2.7586206896551726,
118
+ "grad_norm": 4.446742534637451,
119
+ "learning_rate": 4.978118375700895e-06,
120
+ "logits/chosen": -2.3472495079040527,
121
+ "logits/rejected": -2.3697409629821777,
122
+ "logps/chosen": -73.44490814208984,
123
+ "logps/rejected": -89.69837951660156,
124
+ "loss": 0.6553,
125
+ "rewards/accuracies": 0.8500000238418579,
126
+ "rewards/chosen": -0.022817375138401985,
127
+ "rewards/margins": 0.09045850485563278,
128
+ "rewards/rejected": -0.11327588558197021,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 3.103448275862069,
133
+ "grad_norm": 4.435715198516846,
134
+ "learning_rate": 4.953780424089803e-06,
135
+ "logits/chosen": -2.346717596054077,
136
+ "logits/rejected": -2.3626608848571777,
137
+ "logps/chosen": -85.64796447753906,
138
+ "logps/rejected": -80.06268310546875,
139
+ "loss": 0.6432,
140
+ "rewards/accuracies": 0.737500011920929,
141
+ "rewards/chosen": -0.0543200746178627,
142
+ "rewards/margins": 0.1085677295923233,
143
+ "rewards/rejected": -0.1628878116607666,
144
+ "step": 90
145
+ },
146
+ {
147
+ "epoch": 3.4482758620689653,
148
+ "grad_norm": 4.5200910568237305,
149
+ "learning_rate": 4.920557351506409e-06,
150
+ "logits/chosen": -2.358900547027588,
151
+ "logits/rejected": -2.3591980934143066,
152
+ "logps/chosen": -82.83473205566406,
153
+ "logps/rejected": -80.66204071044922,
154
+ "loss": 0.5996,
155
+ "rewards/accuracies": 0.875,
156
+ "rewards/chosen": -0.046993009746074677,
157
+ "rewards/margins": 0.20401433110237122,
158
+ "rewards/rejected": -0.2510073184967041,
159
+ "step": 100
160
+ },
161
+ {
162
+ "epoch": 3.793103448275862,
163
+ "grad_norm": 4.106562614440918,
164
+ "learning_rate": 4.878569458453592e-06,
165
+ "logits/chosen": -2.347762107849121,
166
+ "logits/rejected": -2.33540415763855,
167
+ "logps/chosen": -72.23506164550781,
168
+ "logps/rejected": -85.77088928222656,
169
+ "loss": 0.6003,
170
+ "rewards/accuracies": 0.824999988079071,
171
+ "rewards/chosen": -0.051100969314575195,
172
+ "rewards/margins": 0.24443332850933075,
173
+ "rewards/rejected": -0.29553431272506714,
174
+ "step": 110
175
+ },
176
+ {
177
+ "epoch": 4.137931034482759,
178
+ "grad_norm": 4.67632532119751,
179
+ "learning_rate": 4.827968782785062e-06,
180
+ "logits/chosen": -2.353370428085327,
181
+ "logits/rejected": -2.378964900970459,
182
+ "logps/chosen": -67.91919708251953,
183
+ "logps/rejected": -86.26390838623047,
184
+ "loss": 0.5716,
185
+ "rewards/accuracies": 0.7875000238418579,
186
+ "rewards/chosen": -0.11952020972967148,
187
+ "rewards/margins": 0.30119410157203674,
188
+ "rewards/rejected": -0.42071428894996643,
189
+ "step": 120
190
+ },
191
+ {
192
+ "epoch": 4.482758620689655,
193
+ "grad_norm": 4.5131025314331055,
194
+ "learning_rate": 4.7689385491773934e-06,
195
+ "logits/chosen": -2.3820648193359375,
196
+ "logits/rejected": -2.403965473175049,
197
+ "logps/chosen": -71.66841125488281,
198
+ "logps/rejected": -77.90869140625,
199
+ "loss": 0.5362,
200
+ "rewards/accuracies": 0.875,
201
+ "rewards/chosen": -0.0694696456193924,
202
+ "rewards/margins": 0.47986412048339844,
203
+ "rewards/rejected": -0.5493337512016296,
204
+ "step": 130
205
+ },
206
+ {
207
+ "epoch": 4.827586206896552,
208
+ "grad_norm": 4.446605205535889,
209
+ "learning_rate": 4.70169250567482e-06,
210
+ "logits/chosen": -2.372788906097412,
211
+ "logits/rejected": -2.379612684249878,
212
+ "logps/chosen": -69.44779968261719,
213
+ "logps/rejected": -80.1120376586914,
214
+ "loss": 0.5186,
215
+ "rewards/accuracies": 0.862500011920929,
216
+ "rewards/chosen": -0.12896183133125305,
217
+ "rewards/margins": 0.5137210488319397,
218
+ "rewards/rejected": -0.6426829099655151,
219
+ "step": 140
220
+ },
221
+ {
222
+ "epoch": 5.172413793103448,
223
+ "grad_norm": 4.605374813079834,
224
+ "learning_rate": 4.626474149709127e-06,
225
+ "logits/chosen": -2.3140041828155518,
226
+ "logits/rejected": -2.336975574493408,
227
+ "logps/chosen": -87.05641174316406,
228
+ "logps/rejected": -94.53668212890625,
229
+ "loss": 0.4794,
230
+ "rewards/accuracies": 0.8374999761581421,
231
+ "rewards/chosen": -0.15513856709003448,
232
+ "rewards/margins": 0.6417296528816223,
233
+ "rewards/rejected": -0.7968682050704956,
234
+ "step": 150
235
+ },
236
+ {
237
+ "epoch": 5.517241379310345,
238
+ "grad_norm": 6.027809143066406,
239
+ "learning_rate": 4.54355584639723e-06,
240
+ "logits/chosen": -2.365192413330078,
241
+ "logits/rejected": -2.3872745037078857,
242
+ "logps/chosen": -73.7781753540039,
243
+ "logps/rejected": -82.1873550415039,
244
+ "loss": 0.4599,
245
+ "rewards/accuracies": 0.8125,
246
+ "rewards/chosen": -0.25834327936172485,
247
+ "rewards/margins": 0.5800828337669373,
248
+ "rewards/rejected": -0.8384261131286621,
249
+ "step": 160
250
+ },
251
+ {
252
+ "epoch": 5.862068965517241,
253
+ "grad_norm": 5.196141242980957,
254
+ "learning_rate": 4.45323784230908e-06,
255
+ "logits/chosen": -2.391653299331665,
256
+ "logits/rejected": -2.394854784011841,
257
+ "logps/chosen": -72.33963775634766,
258
+ "logps/rejected": -86.77699279785156,
259
+ "loss": 0.4467,
260
+ "rewards/accuracies": 0.8999999761581421,
261
+ "rewards/chosen": -0.2543284595012665,
262
+ "rewards/margins": 0.7806032299995422,
263
+ "rewards/rejected": -1.0349315404891968,
264
+ "step": 170
265
+ },
266
+ {
267
+ "epoch": 6.206896551724138,
268
+ "grad_norm": 5.285089015960693,
269
+ "learning_rate": 4.355847178277025e-06,
270
+ "logits/chosen": -2.3918795585632324,
271
+ "logits/rejected": -2.4050662517547607,
272
+ "logps/chosen": -77.20832061767578,
273
+ "logps/rejected": -98.5592041015625,
274
+ "loss": 0.4052,
275
+ "rewards/accuracies": 0.887499988079071,
276
+ "rewards/chosen": -0.35020238161087036,
277
+ "rewards/margins": 1.0169063806533813,
278
+ "rewards/rejected": -1.367108702659607,
279
+ "step": 180
280
+ },
281
+ {
282
+ "epoch": 6.551724137931035,
283
+ "grad_norm": 5.308840751647949,
284
+ "learning_rate": 4.2517365051833564e-06,
285
+ "logits/chosen": -2.3778843879699707,
286
+ "logits/rejected": -2.3865675926208496,
287
+ "logps/chosen": -69.90904235839844,
288
+ "logps/rejected": -86.66047668457031,
289
+ "loss": 0.3809,
290
+ "rewards/accuracies": 0.9375,
291
+ "rewards/chosen": -0.42647725343704224,
292
+ "rewards/margins": 0.9949015378952026,
293
+ "rewards/rejected": -1.4213788509368896,
294
+ "step": 190
295
+ },
296
+ {
297
+ "epoch": 6.896551724137931,
298
+ "grad_norm": 6.095545768737793,
299
+ "learning_rate": 4.141282807014034e-06,
300
+ "logits/chosen": -2.407437801361084,
301
+ "logits/rejected": -2.4296727180480957,
302
+ "logps/chosen": -82.95701599121094,
303
+ "logps/rejected": -83.4615478515625,
304
+ "loss": 0.3742,
305
+ "rewards/accuracies": 0.875,
306
+ "rewards/chosen": -0.6070786714553833,
307
+ "rewards/margins": 0.968428909778595,
308
+ "rewards/rejected": -1.5755075216293335,
309
+ "step": 200
310
+ }
311
+ ],
312
+ "logging_steps": 10,
313
+ "max_steps": 580,
314
+ "num_input_tokens_seen": 0,
315
+ "num_train_epochs": 20,
316
+ "save_steps": 100,
317
+ "stateful_callbacks": {
318
+ "TrainerControl": {
319
+ "args": {
320
+ "should_epoch_stop": false,
321
+ "should_evaluate": false,
322
+ "should_log": false,
323
+ "should_save": true,
324
+ "should_training_stop": false
325
+ },
326
+ "attributes": {}
327
+ }
328
+ },
329
+ "total_flos": 7.2868315071198e+17,
330
+ "train_batch_size": 1,
331
+ "trial_name": null,
332
+ "trial_params": null
333
+ }
Power_Area_Time_SFT/checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c39dc276b60c853563692d82de2d090f18d93ee1b30c25c0c44a65f41d370ad6
3
+ size 5368
Power_Area_Time_SFT/checkpoint-300/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ishorn5/RTLCoder-v1.1
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
Power_Area_Time_SFT/checkpoint-300/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
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": 16,
14
+ "lora_dropout": 0.0,
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
+ "o_proj",
24
+ "q_proj",
25
+ "down_proj",
26
+ "v_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
Power_Area_Time_SFT/checkpoint-300/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
Power_Area_Time_SFT/checkpoint-300/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba4c26c615bd5830d41566fab54dc69174be292761b34514b27fbe82b45b630b
3
+ size 15984
Power_Area_Time_SFT/checkpoint-300/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60c761d7f9b90c29c2d348a1133fd39be52c65e6bee4c2d179f6a6e564eb3a40
3
+ size 15984
Power_Area_Time_SFT/checkpoint-300/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccab847cc956e055fd3f9dcce06898826d065211e945b83576c8d487f87c5469
3
+ size 15984
Power_Area_Time_SFT/checkpoint-300/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e5f1dbdcf6ec820c22fd1e4258fcd7af2a2bce65c480988d3f111aa574c9c06
3
+ size 15984
Power_Area_Time_SFT/checkpoint-300/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a23184c3e806d2649776427d1da2c0c9137f9b23a84468f3bdd5bbc75f696c9
3
+ size 15984
Power_Area_Time_SFT/checkpoint-300/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382fc01b809542bf6f5e26742e3e19e80a1f189ac5de24cf8cd822e303916b83
3
+ size 15984
Power_Area_Time_SFT/checkpoint-300/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b178265c7d2ae07bff10b7312e5e49b9f5b4914c38969d2f64a6ca006296bca
3
+ size 15984
Power_Area_Time_SFT/checkpoint-300/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668825a859126c4cf32afb883895c91004130b6aee02178736ca2840e5429ad0
3
+ size 15984
Power_Area_Time_SFT/checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b47f004eb04e7696b54e7cc0fbeb90f37c253591ea075c818122b3642c678b6
3
+ size 1064
Power_Area_Time_SFT/checkpoint-300/special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "[PAD]"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "[PAD]",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
Power_Area_Time_SFT/checkpoint-300/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Power_Area_Time_SFT/checkpoint-300/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
Power_Area_Time_SFT/checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
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
+ "32000": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "additional_special_tokens": [
40
+ "<unk>",
41
+ "<s>",
42
+ "</s>",
43
+ "[PAD]"
44
+ ],
45
+ "bos_token": "<s>",
46
+ "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
47
+ "clean_up_tokenization_spaces": false,
48
+ "eos_token": "</s>",
49
+ "legacy": true,
50
+ "model_max_length": 2048,
51
+ "pad_token": "[PAD]",
52
+ "padding_side": "right",
53
+ "sp_model_kwargs": {},
54
+ "spaces_between_special_tokens": false,
55
+ "split_special_tokens": false,
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": true
59
+ }
Power_Area_Time_SFT/checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,483 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.344827586206897,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.3448275862068966,
13
+ "grad_norm": 3.9107234477996826,
14
+ "learning_rate": 8.620689655172415e-07,
15
+ "logits/chosen": -2.363854169845581,
16
+ "logits/rejected": -2.338671922683716,
17
+ "logps/chosen": -76.8819351196289,
18
+ "logps/rejected": -75.86869049072266,
19
+ "loss": 0.6942,
20
+ "rewards/accuracies": 0.375,
21
+ "rewards/chosen": -0.003996999468654394,
22
+ "rewards/margins": -0.004145228303968906,
23
+ "rewards/rejected": 0.00014822949015069753,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.6896551724137931,
28
+ "grad_norm": 4.328212738037109,
29
+ "learning_rate": 1.724137931034483e-06,
30
+ "logits/chosen": -2.3617663383483887,
31
+ "logits/rejected": -2.3477540016174316,
32
+ "logps/chosen": -93.76543426513672,
33
+ "logps/rejected": -75.16656494140625,
34
+ "loss": 0.6931,
35
+ "rewards/accuracies": 0.48750001192092896,
36
+ "rewards/chosen": 0.002653368515893817,
37
+ "rewards/margins": 0.006352785974740982,
38
+ "rewards/rejected": -0.003699416993185878,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 1.0344827586206897,
43
+ "grad_norm": 3.473827838897705,
44
+ "learning_rate": 2.5862068965517246e-06,
45
+ "logits/chosen": -2.3354058265686035,
46
+ "logits/rejected": -2.3330740928649902,
47
+ "logps/chosen": -138.9960479736328,
48
+ "logps/rejected": -67.00438690185547,
49
+ "loss": 0.6927,
50
+ "rewards/accuracies": 0.44999998807907104,
51
+ "rewards/chosen": 0.01745142787694931,
52
+ "rewards/margins": 0.013760591857135296,
53
+ "rewards/rejected": 0.0036908381152898073,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 1.3793103448275863,
58
+ "grad_norm": 3.9458820819854736,
59
+ "learning_rate": 3.448275862068966e-06,
60
+ "logits/chosen": -2.3478751182556152,
61
+ "logits/rejected": -2.3700289726257324,
62
+ "logps/chosen": -75.59983825683594,
63
+ "logps/rejected": -67.20357513427734,
64
+ "loss": 0.69,
65
+ "rewards/accuracies": 0.5,
66
+ "rewards/chosen": 0.00024204826331697404,
67
+ "rewards/margins": 0.005866119172424078,
68
+ "rewards/rejected": -0.005624071694910526,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 1.7241379310344827,
73
+ "grad_norm": 4.299890041351318,
74
+ "learning_rate": 4.310344827586207e-06,
75
+ "logits/chosen": -2.338815212249756,
76
+ "logits/rejected": -2.3532769680023193,
77
+ "logps/chosen": -72.74342346191406,
78
+ "logps/rejected": -87.63409423828125,
79
+ "loss": 0.6899,
80
+ "rewards/accuracies": 0.574999988079071,
81
+ "rewards/chosen": -0.003249581903219223,
82
+ "rewards/margins": 0.006888723932206631,
83
+ "rewards/rejected": -0.010138307698071003,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 2.0689655172413794,
88
+ "grad_norm": 4.957555294036865,
89
+ "learning_rate": 4.999818897894192e-06,
90
+ "logits/chosen": -2.344572067260742,
91
+ "logits/rejected": -2.345888614654541,
92
+ "logps/chosen": -80.16046142578125,
93
+ "logps/rejected": -73.05986022949219,
94
+ "loss": 0.6802,
95
+ "rewards/accuracies": 0.637499988079071,
96
+ "rewards/chosen": -0.013288321904838085,
97
+ "rewards/margins": 0.020968889817595482,
98
+ "rewards/rejected": -0.03425721079111099,
99
+ "step": 60
100
+ },
101
+ {
102
+ "epoch": 2.413793103448276,
103
+ "grad_norm": 4.212078094482422,
104
+ "learning_rate": 4.9934830787948756e-06,
105
+ "logits/chosen": -2.3330090045928955,
106
+ "logits/rejected": -2.328575372695923,
107
+ "logps/chosen": -73.63365173339844,
108
+ "logps/rejected": -74.45356750488281,
109
+ "loss": 0.6693,
110
+ "rewards/accuracies": 0.7124999761581421,
111
+ "rewards/chosen": -0.009874681942164898,
112
+ "rewards/margins": 0.04785541445016861,
113
+ "rewards/rejected": -0.05773010104894638,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 2.7586206896551726,
118
+ "grad_norm": 4.446742534637451,
119
+ "learning_rate": 4.978118375700895e-06,
120
+ "logits/chosen": -2.3472495079040527,
121
+ "logits/rejected": -2.3697409629821777,
122
+ "logps/chosen": -73.44490814208984,
123
+ "logps/rejected": -89.69837951660156,
124
+ "loss": 0.6553,
125
+ "rewards/accuracies": 0.8500000238418579,
126
+ "rewards/chosen": -0.022817375138401985,
127
+ "rewards/margins": 0.09045850485563278,
128
+ "rewards/rejected": -0.11327588558197021,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 3.103448275862069,
133
+ "grad_norm": 4.435715198516846,
134
+ "learning_rate": 4.953780424089803e-06,
135
+ "logits/chosen": -2.346717596054077,
136
+ "logits/rejected": -2.3626608848571777,
137
+ "logps/chosen": -85.64796447753906,
138
+ "logps/rejected": -80.06268310546875,
139
+ "loss": 0.6432,
140
+ "rewards/accuracies": 0.737500011920929,
141
+ "rewards/chosen": -0.0543200746178627,
142
+ "rewards/margins": 0.1085677295923233,
143
+ "rewards/rejected": -0.1628878116607666,
144
+ "step": 90
145
+ },
146
+ {
147
+ "epoch": 3.4482758620689653,
148
+ "grad_norm": 4.5200910568237305,
149
+ "learning_rate": 4.920557351506409e-06,
150
+ "logits/chosen": -2.358900547027588,
151
+ "logits/rejected": -2.3591980934143066,
152
+ "logps/chosen": -82.83473205566406,
153
+ "logps/rejected": -80.66204071044922,
154
+ "loss": 0.5996,
155
+ "rewards/accuracies": 0.875,
156
+ "rewards/chosen": -0.046993009746074677,
157
+ "rewards/margins": 0.20401433110237122,
158
+ "rewards/rejected": -0.2510073184967041,
159
+ "step": 100
160
+ },
161
+ {
162
+ "epoch": 3.793103448275862,
163
+ "grad_norm": 4.106562614440918,
164
+ "learning_rate": 4.878569458453592e-06,
165
+ "logits/chosen": -2.347762107849121,
166
+ "logits/rejected": -2.33540415763855,
167
+ "logps/chosen": -72.23506164550781,
168
+ "logps/rejected": -85.77088928222656,
169
+ "loss": 0.6003,
170
+ "rewards/accuracies": 0.824999988079071,
171
+ "rewards/chosen": -0.051100969314575195,
172
+ "rewards/margins": 0.24443332850933075,
173
+ "rewards/rejected": -0.29553431272506714,
174
+ "step": 110
175
+ },
176
+ {
177
+ "epoch": 4.137931034482759,
178
+ "grad_norm": 4.67632532119751,
179
+ "learning_rate": 4.827968782785062e-06,
180
+ "logits/chosen": -2.353370428085327,
181
+ "logits/rejected": -2.378964900970459,
182
+ "logps/chosen": -67.91919708251953,
183
+ "logps/rejected": -86.26390838623047,
184
+ "loss": 0.5716,
185
+ "rewards/accuracies": 0.7875000238418579,
186
+ "rewards/chosen": -0.11952020972967148,
187
+ "rewards/margins": 0.30119410157203674,
188
+ "rewards/rejected": -0.42071428894996643,
189
+ "step": 120
190
+ },
191
+ {
192
+ "epoch": 4.482758620689655,
193
+ "grad_norm": 4.5131025314331055,
194
+ "learning_rate": 4.7689385491773934e-06,
195
+ "logits/chosen": -2.3820648193359375,
196
+ "logits/rejected": -2.403965473175049,
197
+ "logps/chosen": -71.66841125488281,
198
+ "logps/rejected": -77.90869140625,
199
+ "loss": 0.5362,
200
+ "rewards/accuracies": 0.875,
201
+ "rewards/chosen": -0.0694696456193924,
202
+ "rewards/margins": 0.47986412048339844,
203
+ "rewards/rejected": -0.5493337512016296,
204
+ "step": 130
205
+ },
206
+ {
207
+ "epoch": 4.827586206896552,
208
+ "grad_norm": 4.446605205535889,
209
+ "learning_rate": 4.70169250567482e-06,
210
+ "logits/chosen": -2.372788906097412,
211
+ "logits/rejected": -2.379612684249878,
212
+ "logps/chosen": -69.44779968261719,
213
+ "logps/rejected": -80.1120376586914,
214
+ "loss": 0.5186,
215
+ "rewards/accuracies": 0.862500011920929,
216
+ "rewards/chosen": -0.12896183133125305,
217
+ "rewards/margins": 0.5137210488319397,
218
+ "rewards/rejected": -0.6426829099655151,
219
+ "step": 140
220
+ },
221
+ {
222
+ "epoch": 5.172413793103448,
223
+ "grad_norm": 4.605374813079834,
224
+ "learning_rate": 4.626474149709127e-06,
225
+ "logits/chosen": -2.3140041828155518,
226
+ "logits/rejected": -2.336975574493408,
227
+ "logps/chosen": -87.05641174316406,
228
+ "logps/rejected": -94.53668212890625,
229
+ "loss": 0.4794,
230
+ "rewards/accuracies": 0.8374999761581421,
231
+ "rewards/chosen": -0.15513856709003448,
232
+ "rewards/margins": 0.6417296528816223,
233
+ "rewards/rejected": -0.7968682050704956,
234
+ "step": 150
235
+ },
236
+ {
237
+ "epoch": 5.517241379310345,
238
+ "grad_norm": 6.027809143066406,
239
+ "learning_rate": 4.54355584639723e-06,
240
+ "logits/chosen": -2.365192413330078,
241
+ "logits/rejected": -2.3872745037078857,
242
+ "logps/chosen": -73.7781753540039,
243
+ "logps/rejected": -82.1873550415039,
244
+ "loss": 0.4599,
245
+ "rewards/accuracies": 0.8125,
246
+ "rewards/chosen": -0.25834327936172485,
247
+ "rewards/margins": 0.5800828337669373,
248
+ "rewards/rejected": -0.8384261131286621,
249
+ "step": 160
250
+ },
251
+ {
252
+ "epoch": 5.862068965517241,
253
+ "grad_norm": 5.196141242980957,
254
+ "learning_rate": 4.45323784230908e-06,
255
+ "logits/chosen": -2.391653299331665,
256
+ "logits/rejected": -2.394854784011841,
257
+ "logps/chosen": -72.33963775634766,
258
+ "logps/rejected": -86.77699279785156,
259
+ "loss": 0.4467,
260
+ "rewards/accuracies": 0.8999999761581421,
261
+ "rewards/chosen": -0.2543284595012665,
262
+ "rewards/margins": 0.7806032299995422,
263
+ "rewards/rejected": -1.0349315404891968,
264
+ "step": 170
265
+ },
266
+ {
267
+ "epoch": 6.206896551724138,
268
+ "grad_norm": 5.285089015960693,
269
+ "learning_rate": 4.355847178277025e-06,
270
+ "logits/chosen": -2.3918795585632324,
271
+ "logits/rejected": -2.4050662517547607,
272
+ "logps/chosen": -77.20832061767578,
273
+ "logps/rejected": -98.5592041015625,
274
+ "loss": 0.4052,
275
+ "rewards/accuracies": 0.887499988079071,
276
+ "rewards/chosen": -0.35020238161087036,
277
+ "rewards/margins": 1.0169063806533813,
278
+ "rewards/rejected": -1.367108702659607,
279
+ "step": 180
280
+ },
281
+ {
282
+ "epoch": 6.551724137931035,
283
+ "grad_norm": 5.308840751647949,
284
+ "learning_rate": 4.2517365051833564e-06,
285
+ "logits/chosen": -2.3778843879699707,
286
+ "logits/rejected": -2.3865675926208496,
287
+ "logps/chosen": -69.90904235839844,
288
+ "logps/rejected": -86.66047668457031,
289
+ "loss": 0.3809,
290
+ "rewards/accuracies": 0.9375,
291
+ "rewards/chosen": -0.42647725343704224,
292
+ "rewards/margins": 0.9949015378952026,
293
+ "rewards/rejected": -1.4213788509368896,
294
+ "step": 190
295
+ },
296
+ {
297
+ "epoch": 6.896551724137931,
298
+ "grad_norm": 6.095545768737793,
299
+ "learning_rate": 4.141282807014034e-06,
300
+ "logits/chosen": -2.407437801361084,
301
+ "logits/rejected": -2.4296727180480957,
302
+ "logps/chosen": -82.95701599121094,
303
+ "logps/rejected": -83.4615478515625,
304
+ "loss": 0.3742,
305
+ "rewards/accuracies": 0.875,
306
+ "rewards/chosen": -0.6070786714553833,
307
+ "rewards/margins": 0.968428909778595,
308
+ "rewards/rejected": -1.5755075216293335,
309
+ "step": 200
310
+ },
311
+ {
312
+ "epoch": 7.241379310344827,
313
+ "grad_norm": 5.683840751647949,
314
+ "learning_rate": 4.024886035802432e-06,
315
+ "logits/chosen": -2.411830186843872,
316
+ "logits/rejected": -2.4354729652404785,
317
+ "logps/chosen": -61.66484451293945,
318
+ "logps/rejected": -90.95805358886719,
319
+ "loss": 0.3421,
320
+ "rewards/accuracies": 0.8999999761581421,
321
+ "rewards/chosen": -0.5454065203666687,
322
+ "rewards/margins": 1.2011836767196655,
323
+ "rewards/rejected": -1.7465900182724,
324
+ "step": 210
325
+ },
326
+ {
327
+ "epoch": 7.586206896551724,
328
+ "grad_norm": 5.584890842437744,
329
+ "learning_rate": 3.9029676634059565e-06,
330
+ "logits/chosen": -2.3816287517547607,
331
+ "logits/rejected": -2.37958025932312,
332
+ "logps/chosen": -87.12813568115234,
333
+ "logps/rejected": -92.26463317871094,
334
+ "loss": 0.3138,
335
+ "rewards/accuracies": 0.949999988079071,
336
+ "rewards/chosen": -0.5636588335037231,
337
+ "rewards/margins": 1.3944618701934814,
338
+ "rewards/rejected": -1.9581207036972046,
339
+ "step": 220
340
+ },
341
+ {
342
+ "epoch": 7.931034482758621,
343
+ "grad_norm": 7.526435375213623,
344
+ "learning_rate": 3.7759691553595214e-06,
345
+ "logits/chosen": -2.399634599685669,
346
+ "logits/rejected": -2.407938241958618,
347
+ "logps/chosen": -82.55473327636719,
348
+ "logps/rejected": -89.76951599121094,
349
+ "loss": 0.3046,
350
+ "rewards/accuracies": 0.9750000238418579,
351
+ "rewards/chosen": -0.9372364282608032,
352
+ "rewards/margins": 1.309622049331665,
353
+ "rewards/rejected": -2.246858596801758,
354
+ "step": 230
355
+ },
356
+ {
357
+ "epoch": 8.275862068965518,
358
+ "grad_norm": 5.150575637817383,
359
+ "learning_rate": 3.6443503723320837e-06,
360
+ "logits/chosen": -2.36824893951416,
361
+ "logits/rejected": -2.3758621215820312,
362
+ "logps/chosen": -85.68852996826172,
363
+ "logps/rejected": -102.09485626220703,
364
+ "loss": 0.2638,
365
+ "rewards/accuracies": 0.949999988079071,
366
+ "rewards/chosen": -0.9749407768249512,
367
+ "rewards/margins": 1.6947702169418335,
368
+ "rewards/rejected": -2.669710874557495,
369
+ "step": 240
370
+ },
371
+ {
372
+ "epoch": 8.620689655172415,
373
+ "grad_norm": 6.282366752624512,
374
+ "learning_rate": 3.508587904974522e-06,
375
+ "logits/chosen": -2.3659470081329346,
376
+ "logits/rejected": -2.367462635040283,
377
+ "logps/chosen": -87.00023651123047,
378
+ "logps/rejected": -123.0126953125,
379
+ "loss": 0.2405,
380
+ "rewards/accuracies": 0.9624999761581421,
381
+ "rewards/chosen": -1.026289939880371,
382
+ "rewards/margins": 1.9990599155426025,
383
+ "rewards/rejected": -3.0253496170043945,
384
+ "step": 250
385
+ },
386
+ {
387
+ "epoch": 8.96551724137931,
388
+ "grad_norm": 6.396641731262207,
389
+ "learning_rate": 3.3691733481883693e-06,
390
+ "logits/chosen": -2.3716306686401367,
391
+ "logits/rejected": -2.3546042442321777,
392
+ "logps/chosen": -87.29267883300781,
393
+ "logps/rejected": -98.01856994628906,
394
+ "loss": 0.2546,
395
+ "rewards/accuracies": 0.949999988079071,
396
+ "rewards/chosen": -1.2485218048095703,
397
+ "rewards/margins": 1.980831503868103,
398
+ "rewards/rejected": -3.229353427886963,
399
+ "step": 260
400
+ },
401
+ {
402
+ "epoch": 9.310344827586206,
403
+ "grad_norm": 5.644590377807617,
404
+ "learning_rate": 3.226611521064278e-06,
405
+ "logits/chosen": -2.2916407585144043,
406
+ "logits/rejected": -2.3004841804504395,
407
+ "logps/chosen": -79.30825805664062,
408
+ "logps/rejected": -113.4272689819336,
409
+ "loss": 0.1999,
410
+ "rewards/accuracies": 0.9750000238418579,
411
+ "rewards/chosen": -1.1944876909255981,
412
+ "rewards/margins": 2.365144729614258,
413
+ "rewards/rejected": -3.5596320629119873,
414
+ "step": 270
415
+ },
416
+ {
417
+ "epoch": 9.655172413793103,
418
+ "grad_norm": 6.177416801452637,
419
+ "learning_rate": 3.0814186389357765e-06,
420
+ "logits/chosen": -2.346484661102295,
421
+ "logits/rejected": -2.346285581588745,
422
+ "logps/chosen": -77.01927947998047,
423
+ "logps/rejected": -105.2061538696289,
424
+ "loss": 0.1875,
425
+ "rewards/accuracies": 0.987500011920929,
426
+ "rewards/chosen": -1.260752558708191,
427
+ "rewards/margins": 2.249293565750122,
428
+ "rewards/rejected": -3.5100464820861816,
429
+ "step": 280
430
+ },
431
+ {
432
+ "epoch": 10.0,
433
+ "grad_norm": 6.281085014343262,
434
+ "learning_rate": 2.9341204441673267e-06,
435
+ "logits/chosen": -2.3005917072296143,
436
+ "logits/rejected": -2.3319716453552246,
437
+ "logps/chosen": -92.97987365722656,
438
+ "logps/rejected": -112.0716552734375,
439
+ "loss": 0.2036,
440
+ "rewards/accuracies": 0.949999988079071,
441
+ "rewards/chosen": -1.6851022243499756,
442
+ "rewards/margins": 2.1508073806762695,
443
+ "rewards/rejected": -3.835909605026245,
444
+ "step": 290
445
+ },
446
+ {
447
+ "epoch": 10.344827586206897,
448
+ "grad_norm": 5.364060401916504,
449
+ "learning_rate": 2.785250302445062e-06,
450
+ "logits/chosen": -2.3305928707122803,
451
+ "logits/rejected": -2.3451201915740967,
452
+ "logps/chosen": -85.11759185791016,
453
+ "logps/rejected": -115.65193176269531,
454
+ "loss": 0.1664,
455
+ "rewards/accuracies": 1.0,
456
+ "rewards/chosen": -1.5494135618209839,
457
+ "rewards/margins": 2.6376235485076904,
458
+ "rewards/rejected": -4.187037467956543,
459
+ "step": 300
460
+ }
461
+ ],
462
+ "logging_steps": 10,
463
+ "max_steps": 580,
464
+ "num_input_tokens_seen": 0,
465
+ "num_train_epochs": 20,
466
+ "save_steps": 100,
467
+ "stateful_callbacks": {
468
+ "TrainerControl": {
469
+ "args": {
470
+ "should_epoch_stop": false,
471
+ "should_evaluate": false,
472
+ "should_log": false,
473
+ "should_save": true,
474
+ "should_training_stop": false
475
+ },
476
+ "attributes": {}
477
+ }
478
+ },
479
+ "total_flos": 1.0937569428300104e+18,
480
+ "train_batch_size": 1,
481
+ "trial_name": null,
482
+ "trial_params": null
483
+ }