Hugging Face's logo

Infernaught
/
phi_countdown_n100_mcl_256_pretrained

PEFT
Safetensors
Model card Files
xet
Community
Infernaught commited on
Commit
b3d99cd
·
verified ·
1 Parent(s): b255fc2

Upload folder using huggingface_hub

Browse files
Files changed (39) hide show
  1. checkpoint-30/README.md +202 -0
  2. checkpoint-30/adapter_config.json +36 -0
  3. checkpoint-30/adapter_model.safetensors +3 -0
  4. checkpoint-30/added_tokens.json +13 -0
  5. checkpoint-30/optimizer.pt +3 -0
  6. checkpoint-30/rng_state.pth +3 -0
  7. checkpoint-30/scheduler.pt +3 -0
  8. checkpoint-30/special_tokens_map.json +30 -0
  9. checkpoint-30/tokenizer.json +0 -0
  10. checkpoint-30/tokenizer.model +3 -0
  11. checkpoint-30/tokenizer_config.json +132 -0
  12. checkpoint-30/trainer_state.json +172 -0
  13. checkpoint-30/training_args.bin +3 -0
  14. checkpoint-70/README.md +202 -0
  15. checkpoint-70/adapter_config.json +36 -0
  16. checkpoint-70/adapter_model.safetensors +3 -0
  17. checkpoint-70/added_tokens.json +13 -0
  18. checkpoint-70/optimizer.pt +3 -0
  19. checkpoint-70/rng_state.pth +3 -0
  20. checkpoint-70/scheduler.pt +3 -0
  21. checkpoint-70/special_tokens_map.json +30 -0
  22. checkpoint-70/tokenizer.json +0 -0
  23. checkpoint-70/tokenizer.model +3 -0
  24. checkpoint-70/tokenizer_config.json +132 -0
  25. checkpoint-70/trainer_state.json +356 -0
  26. checkpoint-70/training_args.bin +3 -0
  27. checkpoint-75/README.md +202 -0
  28. checkpoint-75/adapter_config.json +36 -0
  29. checkpoint-75/adapter_model.safetensors +3 -0
  30. checkpoint-75/added_tokens.json +13 -0
  31. checkpoint-75/optimizer.pt +3 -0
  32. checkpoint-75/rng_state.pth +3 -0
  33. checkpoint-75/scheduler.pt +3 -0
  34. checkpoint-75/special_tokens_map.json +30 -0
  35. checkpoint-75/tokenizer.json +0 -0
  36. checkpoint-75/tokenizer.model +3 -0
  37. checkpoint-75/tokenizer_config.json +132 -0
  38. checkpoint-75/trainer_state.json +379 -0
  39. checkpoint-75/training_args.bin +3 -0
checkpoint-30/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3.5-mini-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 0.15.2
checkpoint-30/adapter_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "k_proj",
29
+ "v_proj",
30
+ "o_proj"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_rslora": false
36
+ }
checkpoint-30/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd8b0daf68665b236b93e59cfaa95fc6d0f65cf83364d01bc131c704113855c
3
+ size 12591456
checkpoint-30/added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
checkpoint-30/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31453548b34f41d4da189933539cfafc6f7aae1fc11da00865542ec48196cfe
3
+ size 25219898
checkpoint-30/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ba934eab7b5cf9a3ad552636acec5077cd8a2463383fbefc848e3ace92e309
3
+ size 14244
checkpoint-30/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a182d680dfa7f02ea21519bddd3045c86ea7f82b23e71dbabc25767b08cb2c
3
+ size 1064
checkpoint-30/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-30/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-30/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-30/tokenizer_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "extra_special_tokens": {},
124
+ "legacy": false,
125
+ "model_max_length": 131072,
126
+ "pad_token": "<|endoftext|>",
127
+ "padding_side": "left",
128
+ "sp_model_kwargs": {},
129
+ "tokenizer_class": "LlamaTokenizer",
130
+ "unk_token": "<unk>",
131
+ "use_default_system_prompt": false
132
+ }
checkpoint-30/trainer_state.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 30,
3
+ "best_metric": 0.009350189939141273,
4
+ "best_model_checkpoint": "outputs/microsoft/Phi-3.5-mini-instruct/countdown_n100_mcl_256_pretrained/checkpoint-30",
5
+ "epoch": 1.2,
6
+ "eval_steps": 5,
7
+ "global_step": 30,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2,
14
+ "grad_norm": 0.04710305854678154,
15
+ "learning_rate": 9.466666666666666e-07,
16
+ "loss": 0.0581,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.2,
21
+ "eval_clip_ratio": 0.0,
22
+ "eval_completion_length": 249.7375,
23
+ "eval_kl": 2.7620792388916014e-05,
24
+ "eval_loss": 0.011466369964182377,
25
+ "eval_num_tokens": 30743.0,
26
+ "eval_reward": 0.0875,
27
+ "eval_reward_std": 0.14787135720252992,
28
+ "eval_rewards/equation_reward_func": 0.0375,
29
+ "eval_rewards/format_reward_func": 0.05,
30
+ "eval_runtime": 283.5242,
31
+ "eval_samples_per_second": 0.071,
32
+ "eval_steps_per_second": 0.018,
33
+ "step": 5
34
+ },
35
+ {
36
+ "epoch": 0.4,
37
+ "grad_norm": 0.0248898696154356,
38
+ "learning_rate": 8.799999999999999e-07,
39
+ "loss": 0.0305,
40
+ "step": 10
41
+ },
42
+ {
43
+ "epoch": 0.4,
44
+ "eval_clip_ratio": 0.0,
45
+ "eval_completion_length": 248.3125,
46
+ "eval_kl": 3.051459789276123e-05,
47
+ "eval_loss": 0.010714234784245491,
48
+ "eval_num_tokens": 61654.0,
49
+ "eval_reward": 0.1,
50
+ "eval_reward_std": 0.11969234347343445,
51
+ "eval_rewards/equation_reward_func": 0.075,
52
+ "eval_rewards/format_reward_func": 0.025,
53
+ "eval_runtime": 279.7789,
54
+ "eval_samples_per_second": 0.071,
55
+ "eval_steps_per_second": 0.018,
56
+ "step": 10
57
+ },
58
+ {
59
+ "epoch": 0.6,
60
+ "grad_norm": 0.03560088202357292,
61
+ "learning_rate": 8.133333333333333e-07,
62
+ "loss": 0.0333,
63
+ "step": 15
64
+ },
65
+ {
66
+ "epoch": 0.6,
67
+ "eval_clip_ratio": 0.0,
68
+ "eval_completion_length": 248.8125,
69
+ "eval_kl": 3.6323070526123046e-05,
70
+ "eval_loss": 0.016332309693098068,
71
+ "eval_num_tokens": 92513.0,
72
+ "eval_reward": 0.1,
73
+ "eval_reward_std": 0.15773502588272095,
74
+ "eval_rewards/equation_reward_func": 0.0375,
75
+ "eval_rewards/format_reward_func": 0.0625,
76
+ "eval_runtime": 282.7334,
77
+ "eval_samples_per_second": 0.071,
78
+ "eval_steps_per_second": 0.018,
79
+ "step": 15
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "grad_norm": 0.02903689257800579,
84
+ "learning_rate": 7.466666666666667e-07,
85
+ "loss": 0.0363,
86
+ "step": 20
87
+ },
88
+ {
89
+ "epoch": 0.8,
90
+ "eval_clip_ratio": 0.0,
91
+ "eval_completion_length": 241.4375,
92
+ "eval_kl": 3.466010093688965e-05,
93
+ "eval_loss": 0.03578554838895798,
94
+ "eval_num_tokens": 123451.0,
95
+ "eval_reward": 0.1125,
96
+ "eval_reward_std": 0.1978713572025299,
97
+ "eval_rewards/equation_reward_func": 0.0625,
98
+ "eval_rewards/format_reward_func": 0.05,
99
+ "eval_runtime": 282.549,
100
+ "eval_samples_per_second": 0.071,
101
+ "eval_steps_per_second": 0.018,
102
+ "step": 20
103
+ },
104
+ {
105
+ "epoch": 1.0,
106
+ "grad_norm": 5.04811282553419e-07,
107
+ "learning_rate": 6.800000000000001e-07,
108
+ "loss": 0.0011,
109
+ "step": 25
110
+ },
111
+ {
112
+ "epoch": 1.0,
113
+ "eval_clip_ratio": 0.0,
114
+ "eval_completion_length": 247.55,
115
+ "eval_kl": 3.0243396759033202e-05,
116
+ "eval_loss": 0.023990554735064507,
117
+ "eval_num_tokens": 154568.0,
118
+ "eval_reward": 0.1,
119
+ "eval_reward_std": 0.17886751294136047,
120
+ "eval_rewards/equation_reward_func": 0.05,
121
+ "eval_rewards/format_reward_func": 0.05,
122
+ "eval_runtime": 282.4574,
123
+ "eval_samples_per_second": 0.071,
124
+ "eval_steps_per_second": 0.018,
125
+ "step": 25
126
+ },
127
+ {
128
+ "epoch": 1.2,
129
+ "grad_norm": 0.0,
130
+ "learning_rate": 6.133333333333332e-07,
131
+ "loss": 0.0337,
132
+ "step": 30
133
+ },
134
+ {
135
+ "epoch": 1.2,
136
+ "eval_clip_ratio": 0.0,
137
+ "eval_completion_length": 249.3875,
138
+ "eval_kl": 2.872645854949951e-05,
139
+ "eval_loss": 0.009350189939141273,
140
+ "eval_num_tokens": 185750.0,
141
+ "eval_reward": 0.1,
142
+ "eval_reward_std": 0.15,
143
+ "eval_rewards/equation_reward_func": 0.0625,
144
+ "eval_rewards/format_reward_func": 0.0375,
145
+ "eval_runtime": 283.2443,
146
+ "eval_samples_per_second": 0.071,
147
+ "eval_steps_per_second": 0.018,
148
+ "step": 30
149
+ }
150
+ ],
151
+ "logging_steps": 5,
152
+ "max_steps": 75,
153
+ "num_input_tokens_seen": 0,
154
+ "num_train_epochs": 3,
155
+ "save_steps": 5,
156
+ "stateful_callbacks": {
157
+ "TrainerControl": {
158
+ "args": {
159
+ "should_epoch_stop": false,
160
+ "should_evaluate": false,
161
+ "should_log": false,
162
+ "should_save": true,
163
+ "should_training_stop": false
164
+ },
165
+ "attributes": {}
166
+ }
167
+ },
168
+ "total_flos": 0.0,
169
+ "train_batch_size": 4,
170
+ "trial_name": null,
171
+ "trial_params": null
172
+ }
checkpoint-30/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e10b521573cac25922d2ee9076e71c9a2aa5ac01265f1f3bac4705ac267a9aa
3
+ size 6264
checkpoint-70/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3.5-mini-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 0.15.2
checkpoint-70/adapter_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "k_proj",
29
+ "v_proj",
30
+ "o_proj"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_rslora": false
36
+ }
checkpoint-70/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca504d2815a41af3c4f0211ff55fc919999419b3ce7da015e35fc6b5795efd0a
3
+ size 12591456
checkpoint-70/added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
checkpoint-70/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd270d3335a97de72a6c9eb4793b29a8ec4f114ae65f584319426f922ec2d5b4
3
+ size 25219898
checkpoint-70/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba0a0a5033a95123a6adcacc6fe04678869343f55e27c5a56d1e8430bfb0ea6
3
+ size 14244
checkpoint-70/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5a60ebe43db4aa534406417e4b42a931def002b03d7d6ffcde200c9b6005ea
3
+ size 1064
checkpoint-70/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-70/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-70/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-70/tokenizer_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "extra_special_tokens": {},
124
+ "legacy": false,
125
+ "model_max_length": 131072,
126
+ "pad_token": "<|endoftext|>",
127
+ "padding_side": "left",
128
+ "sp_model_kwargs": {},
129
+ "tokenizer_class": "LlamaTokenizer",
130
+ "unk_token": "<unk>",
131
+ "use_default_system_prompt": false
132
+ }
checkpoint-70/trainer_state.json ADDED
@@ -0,0 +1,356 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 30,
3
+ "best_metric": 0.009350189939141273,
4
+ "best_model_checkpoint": "outputs/microsoft/Phi-3.5-mini-instruct/countdown_n100_mcl_256_pretrained/checkpoint-30",
5
+ "epoch": 2.8,
6
+ "eval_steps": 5,
7
+ "global_step": 70,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2,
14
+ "grad_norm": 0.04710305854678154,
15
+ "learning_rate": 9.466666666666666e-07,
16
+ "loss": 0.0581,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.2,
21
+ "eval_clip_ratio": 0.0,
22
+ "eval_completion_length": 249.7375,
23
+ "eval_kl": 2.7620792388916014e-05,
24
+ "eval_loss": 0.011466369964182377,
25
+ "eval_num_tokens": 30743.0,
26
+ "eval_reward": 0.0875,
27
+ "eval_reward_std": 0.14787135720252992,
28
+ "eval_rewards/equation_reward_func": 0.0375,
29
+ "eval_rewards/format_reward_func": 0.05,
30
+ "eval_runtime": 283.5242,
31
+ "eval_samples_per_second": 0.071,
32
+ "eval_steps_per_second": 0.018,
33
+ "step": 5
34
+ },
35
+ {
36
+ "epoch": 0.4,
37
+ "grad_norm": 0.0248898696154356,
38
+ "learning_rate": 8.799999999999999e-07,
39
+ "loss": 0.0305,
40
+ "step": 10
41
+ },
42
+ {
43
+ "epoch": 0.4,
44
+ "eval_clip_ratio": 0.0,
45
+ "eval_completion_length": 248.3125,
46
+ "eval_kl": 3.051459789276123e-05,
47
+ "eval_loss": 0.010714234784245491,
48
+ "eval_num_tokens": 61654.0,
49
+ "eval_reward": 0.1,
50
+ "eval_reward_std": 0.11969234347343445,
51
+ "eval_rewards/equation_reward_func": 0.075,
52
+ "eval_rewards/format_reward_func": 0.025,
53
+ "eval_runtime": 279.7789,
54
+ "eval_samples_per_second": 0.071,
55
+ "eval_steps_per_second": 0.018,
56
+ "step": 10
57
+ },
58
+ {
59
+ "epoch": 0.6,
60
+ "grad_norm": 0.03560088202357292,
61
+ "learning_rate": 8.133333333333333e-07,
62
+ "loss": 0.0333,
63
+ "step": 15
64
+ },
65
+ {
66
+ "epoch": 0.6,
67
+ "eval_clip_ratio": 0.0,
68
+ "eval_completion_length": 248.8125,
69
+ "eval_kl": 3.6323070526123046e-05,
70
+ "eval_loss": 0.016332309693098068,
71
+ "eval_num_tokens": 92513.0,
72
+ "eval_reward": 0.1,
73
+ "eval_reward_std": 0.15773502588272095,
74
+ "eval_rewards/equation_reward_func": 0.0375,
75
+ "eval_rewards/format_reward_func": 0.0625,
76
+ "eval_runtime": 282.7334,
77
+ "eval_samples_per_second": 0.071,
78
+ "eval_steps_per_second": 0.018,
79
+ "step": 15
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "grad_norm": 0.02903689257800579,
84
+ "learning_rate": 7.466666666666667e-07,
85
+ "loss": 0.0363,
86
+ "step": 20
87
+ },
88
+ {
89
+ "epoch": 0.8,
90
+ "eval_clip_ratio": 0.0,
91
+ "eval_completion_length": 241.4375,
92
+ "eval_kl": 3.466010093688965e-05,
93
+ "eval_loss": 0.03578554838895798,
94
+ "eval_num_tokens": 123451.0,
95
+ "eval_reward": 0.1125,
96
+ "eval_reward_std": 0.1978713572025299,
97
+ "eval_rewards/equation_reward_func": 0.0625,
98
+ "eval_rewards/format_reward_func": 0.05,
99
+ "eval_runtime": 282.549,
100
+ "eval_samples_per_second": 0.071,
101
+ "eval_steps_per_second": 0.018,
102
+ "step": 20
103
+ },
104
+ {
105
+ "epoch": 1.0,
106
+ "grad_norm": 5.04811282553419e-07,
107
+ "learning_rate": 6.800000000000001e-07,
108
+ "loss": 0.0011,
109
+ "step": 25
110
+ },
111
+ {
112
+ "epoch": 1.0,
113
+ "eval_clip_ratio": 0.0,
114
+ "eval_completion_length": 247.55,
115
+ "eval_kl": 3.0243396759033202e-05,
116
+ "eval_loss": 0.023990554735064507,
117
+ "eval_num_tokens": 154568.0,
118
+ "eval_reward": 0.1,
119
+ "eval_reward_std": 0.17886751294136047,
120
+ "eval_rewards/equation_reward_func": 0.05,
121
+ "eval_rewards/format_reward_func": 0.05,
122
+ "eval_runtime": 282.4574,
123
+ "eval_samples_per_second": 0.071,
124
+ "eval_steps_per_second": 0.018,
125
+ "step": 25
126
+ },
127
+ {
128
+ "epoch": 1.2,
129
+ "grad_norm": 0.0,
130
+ "learning_rate": 6.133333333333332e-07,
131
+ "loss": 0.0337,
132
+ "step": 30
133
+ },
134
+ {
135
+ "epoch": 1.2,
136
+ "eval_clip_ratio": 0.0,
137
+ "eval_completion_length": 249.3875,
138
+ "eval_kl": 2.872645854949951e-05,
139
+ "eval_loss": 0.009350189939141273,
140
+ "eval_num_tokens": 185750.0,
141
+ "eval_reward": 0.1,
142
+ "eval_reward_std": 0.15,
143
+ "eval_rewards/equation_reward_func": 0.0625,
144
+ "eval_rewards/format_reward_func": 0.0375,
145
+ "eval_runtime": 283.2443,
146
+ "eval_samples_per_second": 0.071,
147
+ "eval_steps_per_second": 0.018,
148
+ "step": 30
149
+ },
150
+ {
151
+ "epoch": 1.4,
152
+ "grad_norm": 0.025708282366394997,
153
+ "learning_rate": 5.466666666666666e-07,
154
+ "loss": 0.0273,
155
+ "step": 35
156
+ },
157
+ {
158
+ "epoch": 1.4,
159
+ "eval_clip_ratio": 0.0,
160
+ "eval_completion_length": 242.05,
161
+ "eval_kl": 3.2845139503479e-05,
162
+ "eval_loss": 0.038312580436468124,
163
+ "eval_num_tokens": 217087.0,
164
+ "eval_reward": 0.1375,
165
+ "eval_reward_std": 0.1978713572025299,
166
+ "eval_rewards/equation_reward_func": 0.0625,
167
+ "eval_rewards/format_reward_func": 0.075,
168
+ "eval_runtime": 283.9676,
169
+ "eval_samples_per_second": 0.07,
170
+ "eval_steps_per_second": 0.018,
171
+ "step": 35
172
+ },
173
+ {
174
+ "epoch": 1.6,
175
+ "grad_norm": 0.04088641330599785,
176
+ "learning_rate": 4.8e-07,
177
+ "loss": 0.0318,
178
+ "step": 40
179
+ },
180
+ {
181
+ "epoch": 1.6,
182
+ "eval_clip_ratio": 0.0,
183
+ "eval_completion_length": 247.9375,
184
+ "eval_kl": 3.358125686645508e-05,
185
+ "eval_loss": 0.028362590819597244,
186
+ "eval_num_tokens": 247949.0,
187
+ "eval_reward": 0.1375,
188
+ "eval_reward_std": 0.1886961877346039,
189
+ "eval_rewards/equation_reward_func": 0.0875,
190
+ "eval_rewards/format_reward_func": 0.05,
191
+ "eval_runtime": 285.356,
192
+ "eval_samples_per_second": 0.07,
193
+ "eval_steps_per_second": 0.018,
194
+ "step": 40
195
+ },
196
+ {
197
+ "epoch": 1.8,
198
+ "grad_norm": 0.024730732664465904,
199
+ "learning_rate": 4.1333333333333333e-07,
200
+ "loss": 0.0578,
201
+ "step": 45
202
+ },
203
+ {
204
+ "epoch": 1.8,
205
+ "eval_clip_ratio": 0.0,
206
+ "eval_completion_length": 246.9625,
207
+ "eval_kl": 2.7140974998474122e-05,
208
+ "eval_loss": 0.043169133365154266,
209
+ "eval_num_tokens": 278710.0,
210
+ "eval_reward": 0.125,
211
+ "eval_reward_std": 0.2,
212
+ "eval_rewards/equation_reward_func": 0.075,
213
+ "eval_rewards/format_reward_func": 0.05,
214
+ "eval_runtime": 285.2657,
215
+ "eval_samples_per_second": 0.07,
216
+ "eval_steps_per_second": 0.018,
217
+ "step": 45
218
+ },
219
+ {
220
+ "epoch": 2.0,
221
+ "grad_norm": 0.03765915334224701,
222
+ "learning_rate": 3.4666666666666665e-07,
223
+ "loss": 0.0234,
224
+ "step": 50
225
+ },
226
+ {
227
+ "epoch": 2.0,
228
+ "eval_clip_ratio": 0.0,
229
+ "eval_completion_length": 247.05,
230
+ "eval_kl": 3.2660365104675296e-05,
231
+ "eval_loss": 0.026807209476828575,
232
+ "eval_num_tokens": 309954.0,
233
+ "eval_reward": 0.125,
234
+ "eval_reward_std": 0.20773502588272094,
235
+ "eval_rewards/equation_reward_func": 0.0875,
236
+ "eval_rewards/format_reward_func": 0.0375,
237
+ "eval_runtime": 284.404,
238
+ "eval_samples_per_second": 0.07,
239
+ "eval_steps_per_second": 0.018,
240
+ "step": 50
241
+ },
242
+ {
243
+ "epoch": 2.2,
244
+ "grad_norm": 0.01991177722811699,
245
+ "learning_rate": 2.8e-07,
246
+ "loss": 0.0691,
247
+ "step": 55
248
+ },
249
+ {
250
+ "epoch": 2.2,
251
+ "eval_clip_ratio": 0.0,
252
+ "eval_completion_length": 242.6375,
253
+ "eval_kl": 3.68952751159668e-05,
254
+ "eval_loss": 0.04483898729085922,
255
+ "eval_num_tokens": 340605.0,
256
+ "eval_reward": 0.1625,
257
+ "eval_reward_std": 0.25560638308525085,
258
+ "eval_rewards/equation_reward_func": 0.1,
259
+ "eval_rewards/format_reward_func": 0.0625,
260
+ "eval_runtime": 283.6459,
261
+ "eval_samples_per_second": 0.071,
262
+ "eval_steps_per_second": 0.018,
263
+ "step": 55
264
+ },
265
+ {
266
+ "epoch": 2.4,
267
+ "grad_norm": 0.0200728178024292,
268
+ "learning_rate": 2.1333333333333334e-07,
269
+ "loss": 0.0518,
270
+ "step": 60
271
+ },
272
+ {
273
+ "epoch": 2.4,
274
+ "eval_clip_ratio": 0.0,
275
+ "eval_completion_length": 250.45,
276
+ "eval_kl": 3.1629204750061034e-05,
277
+ "eval_loss": 0.009741068817675114,
278
+ "eval_num_tokens": 371457.0,
279
+ "eval_reward": 0.075,
280
+ "eval_reward_std": 0.12886751294136048,
281
+ "eval_rewards/equation_reward_func": 0.05,
282
+ "eval_rewards/format_reward_func": 0.025,
283
+ "eval_runtime": 283.7186,
284
+ "eval_samples_per_second": 0.07,
285
+ "eval_steps_per_second": 0.018,
286
+ "step": 60
287
+ },
288
+ {
289
+ "epoch": 2.6,
290
+ "grad_norm": 0.021919438615441322,
291
+ "learning_rate": 1.4666666666666666e-07,
292
+ "loss": 0.0167,
293
+ "step": 65
294
+ },
295
+ {
296
+ "epoch": 2.6,
297
+ "eval_clip_ratio": 0.0,
298
+ "eval_completion_length": 250.35,
299
+ "eval_kl": 2.8392672538757326e-05,
300
+ "eval_loss": 0.016574550420045853,
301
+ "eval_num_tokens": 402684.0,
302
+ "eval_reward": 0.1125,
303
+ "eval_reward_std": 0.14469234347343446,
304
+ "eval_rewards/equation_reward_func": 0.075,
305
+ "eval_rewards/format_reward_func": 0.0375,
306
+ "eval_runtime": 283.4564,
307
+ "eval_samples_per_second": 0.071,
308
+ "eval_steps_per_second": 0.018,
309
+ "step": 65
310
+ },
311
+ {
312
+ "epoch": 2.8,
313
+ "grad_norm": 0.03317731246352196,
314
+ "learning_rate": 8e-08,
315
+ "loss": 0.0358,
316
+ "step": 70
317
+ },
318
+ {
319
+ "epoch": 2.8,
320
+ "eval_clip_ratio": 0.0,
321
+ "eval_completion_length": 246.825,
322
+ "eval_kl": 3.1587481498718264e-05,
323
+ "eval_loss": 0.04395188018679619,
324
+ "eval_num_tokens": 433755.0,
325
+ "eval_reward": 0.2,
326
+ "eval_reward_std": 0.3154700517654419,
327
+ "eval_rewards/equation_reward_func": 0.0625,
328
+ "eval_rewards/format_reward_func": 0.1375,
329
+ "eval_runtime": 284.1288,
330
+ "eval_samples_per_second": 0.07,
331
+ "eval_steps_per_second": 0.018,
332
+ "step": 70
333
+ }
334
+ ],
335
+ "logging_steps": 5,
336
+ "max_steps": 75,
337
+ "num_input_tokens_seen": 0,
338
+ "num_train_epochs": 3,
339
+ "save_steps": 5,
340
+ "stateful_callbacks": {
341
+ "TrainerControl": {
342
+ "args": {
343
+ "should_epoch_stop": false,
344
+ "should_evaluate": false,
345
+ "should_log": false,
346
+ "should_save": true,
347
+ "should_training_stop": false
348
+ },
349
+ "attributes": {}
350
+ }
351
+ },
352
+ "total_flos": 0.0,
353
+ "train_batch_size": 4,
354
+ "trial_name": null,
355
+ "trial_params": null
356
+ }
checkpoint-70/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e10b521573cac25922d2ee9076e71c9a2aa5ac01265f1f3bac4705ac267a9aa
3
+ size 6264
checkpoint-75/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3.5-mini-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 0.15.2
checkpoint-75/adapter_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "k_proj",
29
+ "v_proj",
30
+ "o_proj"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_rslora": false
36
+ }
checkpoint-75/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc085ca55181132e4e631578112d3022be2801a6172ecd0a1200c6119b1c011
3
+ size 12591456
checkpoint-75/added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
checkpoint-75/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e1eda41d1c581fa2206543d71ebe88eaa51fac4149f55cb2adc88b7131c770
3
+ size 25219898
checkpoint-75/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0393816af5e506720af7a25500bfd823405c1f828d9e947cee94a8ab4c238a
3
+ size 14244
checkpoint-75/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157488aabe3e3a3d69331e12ad906e4041818e78393c1fdcb2cb7857a7689d9e
3
+ size 1064
checkpoint-75/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-75/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-75/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-75/tokenizer_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "extra_special_tokens": {},
124
+ "legacy": false,
125
+ "model_max_length": 131072,
126
+ "pad_token": "<|endoftext|>",
127
+ "padding_side": "left",
128
+ "sp_model_kwargs": {},
129
+ "tokenizer_class": "LlamaTokenizer",
130
+ "unk_token": "<unk>",
131
+ "use_default_system_prompt": false
132
+ }
checkpoint-75/trainer_state.json ADDED
@@ -0,0 +1,379 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 30,
3
+ "best_metric": 0.009350189939141273,
4
+ "best_model_checkpoint": "outputs/microsoft/Phi-3.5-mini-instruct/countdown_n100_mcl_256_pretrained/checkpoint-30",
5
+ "epoch": 3.0,
6
+ "eval_steps": 5,
7
+ "global_step": 75,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2,
14
+ "grad_norm": 0.04710305854678154,
15
+ "learning_rate": 9.466666666666666e-07,
16
+ "loss": 0.0581,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.2,
21
+ "eval_clip_ratio": 0.0,
22
+ "eval_completion_length": 249.7375,
23
+ "eval_kl": 2.7620792388916014e-05,
24
+ "eval_loss": 0.011466369964182377,
25
+ "eval_num_tokens": 30743.0,
26
+ "eval_reward": 0.0875,
27
+ "eval_reward_std": 0.14787135720252992,
28
+ "eval_rewards/equation_reward_func": 0.0375,
29
+ "eval_rewards/format_reward_func": 0.05,
30
+ "eval_runtime": 283.5242,
31
+ "eval_samples_per_second": 0.071,
32
+ "eval_steps_per_second": 0.018,
33
+ "step": 5
34
+ },
35
+ {
36
+ "epoch": 0.4,
37
+ "grad_norm": 0.0248898696154356,
38
+ "learning_rate": 8.799999999999999e-07,
39
+ "loss": 0.0305,
40
+ "step": 10
41
+ },
42
+ {
43
+ "epoch": 0.4,
44
+ "eval_clip_ratio": 0.0,
45
+ "eval_completion_length": 248.3125,
46
+ "eval_kl": 3.051459789276123e-05,
47
+ "eval_loss": 0.010714234784245491,
48
+ "eval_num_tokens": 61654.0,
49
+ "eval_reward": 0.1,
50
+ "eval_reward_std": 0.11969234347343445,
51
+ "eval_rewards/equation_reward_func": 0.075,
52
+ "eval_rewards/format_reward_func": 0.025,
53
+ "eval_runtime": 279.7789,
54
+ "eval_samples_per_second": 0.071,
55
+ "eval_steps_per_second": 0.018,
56
+ "step": 10
57
+ },
58
+ {
59
+ "epoch": 0.6,
60
+ "grad_norm": 0.03560088202357292,
61
+ "learning_rate": 8.133333333333333e-07,
62
+ "loss": 0.0333,
63
+ "step": 15
64
+ },
65
+ {
66
+ "epoch": 0.6,
67
+ "eval_clip_ratio": 0.0,
68
+ "eval_completion_length": 248.8125,
69
+ "eval_kl": 3.6323070526123046e-05,
70
+ "eval_loss": 0.016332309693098068,
71
+ "eval_num_tokens": 92513.0,
72
+ "eval_reward": 0.1,
73
+ "eval_reward_std": 0.15773502588272095,
74
+ "eval_rewards/equation_reward_func": 0.0375,
75
+ "eval_rewards/format_reward_func": 0.0625,
76
+ "eval_runtime": 282.7334,
77
+ "eval_samples_per_second": 0.071,
78
+ "eval_steps_per_second": 0.018,
79
+ "step": 15
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "grad_norm": 0.02903689257800579,
84
+ "learning_rate": 7.466666666666667e-07,
85
+ "loss": 0.0363,
86
+ "step": 20
87
+ },
88
+ {
89
+ "epoch": 0.8,
90
+ "eval_clip_ratio": 0.0,
91
+ "eval_completion_length": 241.4375,
92
+ "eval_kl": 3.466010093688965e-05,
93
+ "eval_loss": 0.03578554838895798,
94
+ "eval_num_tokens": 123451.0,
95
+ "eval_reward": 0.1125,
96
+ "eval_reward_std": 0.1978713572025299,
97
+ "eval_rewards/equation_reward_func": 0.0625,
98
+ "eval_rewards/format_reward_func": 0.05,
99
+ "eval_runtime": 282.549,
100
+ "eval_samples_per_second": 0.071,
101
+ "eval_steps_per_second": 0.018,
102
+ "step": 20
103
+ },
104
+ {
105
+ "epoch": 1.0,
106
+ "grad_norm": 5.04811282553419e-07,
107
+ "learning_rate": 6.800000000000001e-07,
108
+ "loss": 0.0011,
109
+ "step": 25
110
+ },
111
+ {
112
+ "epoch": 1.0,
113
+ "eval_clip_ratio": 0.0,
114
+ "eval_completion_length": 247.55,
115
+ "eval_kl": 3.0243396759033202e-05,
116
+ "eval_loss": 0.023990554735064507,
117
+ "eval_num_tokens": 154568.0,
118
+ "eval_reward": 0.1,
119
+ "eval_reward_std": 0.17886751294136047,
120
+ "eval_rewards/equation_reward_func": 0.05,
121
+ "eval_rewards/format_reward_func": 0.05,
122
+ "eval_runtime": 282.4574,
123
+ "eval_samples_per_second": 0.071,
124
+ "eval_steps_per_second": 0.018,
125
+ "step": 25
126
+ },
127
+ {
128
+ "epoch": 1.2,
129
+ "grad_norm": 0.0,
130
+ "learning_rate": 6.133333333333332e-07,
131
+ "loss": 0.0337,
132
+ "step": 30
133
+ },
134
+ {
135
+ "epoch": 1.2,
136
+ "eval_clip_ratio": 0.0,
137
+ "eval_completion_length": 249.3875,
138
+ "eval_kl": 2.872645854949951e-05,
139
+ "eval_loss": 0.009350189939141273,
140
+ "eval_num_tokens": 185750.0,
141
+ "eval_reward": 0.1,
142
+ "eval_reward_std": 0.15,
143
+ "eval_rewards/equation_reward_func": 0.0625,
144
+ "eval_rewards/format_reward_func": 0.0375,
145
+ "eval_runtime": 283.2443,
146
+ "eval_samples_per_second": 0.071,
147
+ "eval_steps_per_second": 0.018,
148
+ "step": 30
149
+ },
150
+ {
151
+ "epoch": 1.4,
152
+ "grad_norm": 0.025708282366394997,
153
+ "learning_rate": 5.466666666666666e-07,
154
+ "loss": 0.0273,
155
+ "step": 35
156
+ },
157
+ {
158
+ "epoch": 1.4,
159
+ "eval_clip_ratio": 0.0,
160
+ "eval_completion_length": 242.05,
161
+ "eval_kl": 3.2845139503479e-05,
162
+ "eval_loss": 0.038312580436468124,
163
+ "eval_num_tokens": 217087.0,
164
+ "eval_reward": 0.1375,
165
+ "eval_reward_std": 0.1978713572025299,
166
+ "eval_rewards/equation_reward_func": 0.0625,
167
+ "eval_rewards/format_reward_func": 0.075,
168
+ "eval_runtime": 283.9676,
169
+ "eval_samples_per_second": 0.07,
170
+ "eval_steps_per_second": 0.018,
171
+ "step": 35
172
+ },
173
+ {
174
+ "epoch": 1.6,
175
+ "grad_norm": 0.04088641330599785,
176
+ "learning_rate": 4.8e-07,
177
+ "loss": 0.0318,
178
+ "step": 40
179
+ },
180
+ {
181
+ "epoch": 1.6,
182
+ "eval_clip_ratio": 0.0,
183
+ "eval_completion_length": 247.9375,
184
+ "eval_kl": 3.358125686645508e-05,
185
+ "eval_loss": 0.028362590819597244,
186
+ "eval_num_tokens": 247949.0,
187
+ "eval_reward": 0.1375,
188
+ "eval_reward_std": 0.1886961877346039,
189
+ "eval_rewards/equation_reward_func": 0.0875,
190
+ "eval_rewards/format_reward_func": 0.05,
191
+ "eval_runtime": 285.356,
192
+ "eval_samples_per_second": 0.07,
193
+ "eval_steps_per_second": 0.018,
194
+ "step": 40
195
+ },
196
+ {
197
+ "epoch": 1.8,
198
+ "grad_norm": 0.024730732664465904,
199
+ "learning_rate": 4.1333333333333333e-07,
200
+ "loss": 0.0578,
201
+ "step": 45
202
+ },
203
+ {
204
+ "epoch": 1.8,
205
+ "eval_clip_ratio": 0.0,
206
+ "eval_completion_length": 246.9625,
207
+ "eval_kl": 2.7140974998474122e-05,
208
+ "eval_loss": 0.043169133365154266,
209
+ "eval_num_tokens": 278710.0,
210
+ "eval_reward": 0.125,
211
+ "eval_reward_std": 0.2,
212
+ "eval_rewards/equation_reward_func": 0.075,
213
+ "eval_rewards/format_reward_func": 0.05,
214
+ "eval_runtime": 285.2657,
215
+ "eval_samples_per_second": 0.07,
216
+ "eval_steps_per_second": 0.018,
217
+ "step": 45
218
+ },
219
+ {
220
+ "epoch": 2.0,
221
+ "grad_norm": 0.03765915334224701,
222
+ "learning_rate": 3.4666666666666665e-07,
223
+ "loss": 0.0234,
224
+ "step": 50
225
+ },
226
+ {
227
+ "epoch": 2.0,
228
+ "eval_clip_ratio": 0.0,
229
+ "eval_completion_length": 247.05,
230
+ "eval_kl": 3.2660365104675296e-05,
231
+ "eval_loss": 0.026807209476828575,
232
+ "eval_num_tokens": 309954.0,
233
+ "eval_reward": 0.125,
234
+ "eval_reward_std": 0.20773502588272094,
235
+ "eval_rewards/equation_reward_func": 0.0875,
236
+ "eval_rewards/format_reward_func": 0.0375,
237
+ "eval_runtime": 284.404,
238
+ "eval_samples_per_second": 0.07,
239
+ "eval_steps_per_second": 0.018,
240
+ "step": 50
241
+ },
242
+ {
243
+ "epoch": 2.2,
244
+ "grad_norm": 0.01991177722811699,
245
+ "learning_rate": 2.8e-07,
246
+ "loss": 0.0691,
247
+ "step": 55
248
+ },
249
+ {
250
+ "epoch": 2.2,
251
+ "eval_clip_ratio": 0.0,
252
+ "eval_completion_length": 242.6375,
253
+ "eval_kl": 3.68952751159668e-05,
254
+ "eval_loss": 0.04483898729085922,
255
+ "eval_num_tokens": 340605.0,
256
+ "eval_reward": 0.1625,
257
+ "eval_reward_std": 0.25560638308525085,
258
+ "eval_rewards/equation_reward_func": 0.1,
259
+ "eval_rewards/format_reward_func": 0.0625,
260
+ "eval_runtime": 283.6459,
261
+ "eval_samples_per_second": 0.071,
262
+ "eval_steps_per_second": 0.018,
263
+ "step": 55
264
+ },
265
+ {
266
+ "epoch": 2.4,
267
+ "grad_norm": 0.0200728178024292,
268
+ "learning_rate": 2.1333333333333334e-07,
269
+ "loss": 0.0518,
270
+ "step": 60
271
+ },
272
+ {
273
+ "epoch": 2.4,
274
+ "eval_clip_ratio": 0.0,
275
+ "eval_completion_length": 250.45,
276
+ "eval_kl": 3.1629204750061034e-05,
277
+ "eval_loss": 0.009741068817675114,
278
+ "eval_num_tokens": 371457.0,
279
+ "eval_reward": 0.075,
280
+ "eval_reward_std": 0.12886751294136048,
281
+ "eval_rewards/equation_reward_func": 0.05,
282
+ "eval_rewards/format_reward_func": 0.025,
283
+ "eval_runtime": 283.7186,
284
+ "eval_samples_per_second": 0.07,
285
+ "eval_steps_per_second": 0.018,
286
+ "step": 60
287
+ },
288
+ {
289
+ "epoch": 2.6,
290
+ "grad_norm": 0.021919438615441322,
291
+ "learning_rate": 1.4666666666666666e-07,
292
+ "loss": 0.0167,
293
+ "step": 65
294
+ },
295
+ {
296
+ "epoch": 2.6,
297
+ "eval_clip_ratio": 0.0,
298
+ "eval_completion_length": 250.35,
299
+ "eval_kl": 2.8392672538757326e-05,
300
+ "eval_loss": 0.016574550420045853,
301
+ "eval_num_tokens": 402684.0,
302
+ "eval_reward": 0.1125,
303
+ "eval_reward_std": 0.14469234347343446,
304
+ "eval_rewards/equation_reward_func": 0.075,
305
+ "eval_rewards/format_reward_func": 0.0375,
306
+ "eval_runtime": 283.4564,
307
+ "eval_samples_per_second": 0.071,
308
+ "eval_steps_per_second": 0.018,
309
+ "step": 65
310
+ },
311
+ {
312
+ "epoch": 2.8,
313
+ "grad_norm": 0.03317731246352196,
314
+ "learning_rate": 8e-08,
315
+ "loss": 0.0358,
316
+ "step": 70
317
+ },
318
+ {
319
+ "epoch": 2.8,
320
+ "eval_clip_ratio": 0.0,
321
+ "eval_completion_length": 246.825,
322
+ "eval_kl": 3.1587481498718264e-05,
323
+ "eval_loss": 0.04395188018679619,
324
+ "eval_num_tokens": 433755.0,
325
+ "eval_reward": 0.2,
326
+ "eval_reward_std": 0.3154700517654419,
327
+ "eval_rewards/equation_reward_func": 0.0625,
328
+ "eval_rewards/format_reward_func": 0.1375,
329
+ "eval_runtime": 284.1288,
330
+ "eval_samples_per_second": 0.07,
331
+ "eval_steps_per_second": 0.018,
332
+ "step": 70
333
+ },
334
+ {
335
+ "epoch": 3.0,
336
+ "grad_norm": 0.04194802790880203,
337
+ "learning_rate": 1.3333333333333334e-08,
338
+ "loss": 0.0372,
339
+ "step": 75
340
+ },
341
+ {
342
+ "epoch": 3.0,
343
+ "eval_clip_ratio": 0.0,
344
+ "eval_completion_length": 247.825,
345
+ "eval_kl": 3.3229589462280273e-05,
346
+ "eval_loss": 0.034269753843545914,
347
+ "eval_num_tokens": 464648.0,
348
+ "eval_reward": 0.1,
349
+ "eval_reward_std": 0.15,
350
+ "eval_rewards/equation_reward_func": 0.0625,
351
+ "eval_rewards/format_reward_func": 0.0375,
352
+ "eval_runtime": 283.7321,
353
+ "eval_samples_per_second": 0.07,
354
+ "eval_steps_per_second": 0.018,
355
+ "step": 75
356
+ }
357
+ ],
358
+ "logging_steps": 5,
359
+ "max_steps": 75,
360
+ "num_input_tokens_seen": 0,
361
+ "num_train_epochs": 3,
362
+ "save_steps": 5,
363
+ "stateful_callbacks": {
364
+ "TrainerControl": {
365
+ "args": {
366
+ "should_epoch_stop": false,
367
+ "should_evaluate": false,
368
+ "should_log": false,
369
+ "should_save": true,
370
+ "should_training_stop": true
371
+ },
372
+ "attributes": {}
373
+ }
374
+ },
375
+ "total_flos": 0.0,
376
+ "train_batch_size": 4,
377
+ "trial_name": null,
378
+ "trial_params": null
379
+ }
checkpoint-75/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e10b521573cac25922d2ee9076e71c9a2aa5ac01265f1f3bac4705ac267a9aa
3
+ size 6264