chenhugging commited on
Commit
ea729a8
1 Parent(s): 1cbf6bc

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - llama-factory
6
+ - lora
7
+ - generated_from_trainer
8
+ base_model: CausalLM/34b-beta
9
+ model-index:
10
+ - name: model-update
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # model-update
18
+
19
+ This model is a fine-tuned version of [CausalLM/34b-beta](https://huggingface.co/CausalLM/34b-beta) on the oncc_medqa_instruct dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0005
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_steps: 20
47
+ - num_epochs: 1.0
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.8.2
56
+ - Transformers 4.37.2
57
+ - Pytorch 2.0.1+cu118
58
+ - Datasets 2.17.0
59
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "CausalLM/34b-beta",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6a5dffa2d76e79bd0e4084fffe053ca02ac81ddc1fec84f2618c0fbe2178bb
3
+ size 43285800
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.13428134460167346,
4
+ "train_runtime": 2902.8069,
5
+ "train_samples_per_second": 1.121,
6
+ "train_steps_per_second": 0.07
7
+ }
checkpoint-100/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: /workspace/model
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/workspace/model",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9959cd49f63d4f21008757383fa51c2ac4c7cdbec507e31522adb2d191467f
3
+ size 43285800
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01347d3944528623732064846c30392666535bb71a18de4033a169c5e5d86705
3
+ size 86708485
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa4851eee620994c0ba92e523ba18a1dee79c89af4477f681e6d9dbb50c8f61
3
+ size 14575
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eea28048b2b2c95c10ff2d17df0799ff3a4e498d5d4bd7187083a67fbae901d6
3
+ size 627
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|im_sep|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
checkpoint-100/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "6": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "7": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "8": {
46
+ "content": "<|im_sep|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|im_start|>",
56
+ "<|im_end|>",
57
+ "<|im_sep|>"
58
+ ],
59
+ "bos_token": "<s>",
60
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
61
+ "clean_up_tokenization_spaces": false,
62
+ "eos_token": "</s>",
63
+ "legacy": true,
64
+ "model_max_length": 200000,
65
+ "pad_token": "<unk>",
66
+ "padding_side": "right",
67
+ "sp_model_kwargs": {},
68
+ "spaces_between_special_tokens": false,
69
+ "split_special_tokens": false,
70
+ "tokenizer_class": "LlamaTokenizer",
71
+ "unk_token": "<unk>",
72
+ "use_default_system_prompt": false
73
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.4914004914004914,
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": 0.05,
13
+ "learning_rate": 0.00025,
14
+ "loss": 0.4995,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.1,
19
+ "learning_rate": 0.0005,
20
+ "loss": 0.1621,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.15,
25
+ "learning_rate": 0.0004963251406715272,
26
+ "loss": 0.134,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.2,
31
+ "learning_rate": 0.0004854085994147815,
32
+ "loss": 0.1341,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.25,
37
+ "learning_rate": 0.00046757131025753886,
38
+ "loss": 0.1183,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.29,
43
+ "learning_rate": 0.00044333766942743246,
44
+ "loss": 0.1224,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.34,
49
+ "learning_rate": 0.0004134201186930015,
50
+ "loss": 0.0917,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.39,
55
+ "learning_rate": 0.00037869820037745775,
56
+ "loss": 0.1262,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.44,
61
+ "learning_rate": 0.0003401926998041959,
62
+ "loss": 0.1079,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.49,
67
+ "learning_rate": 0.00029903563535704927,
68
+ "loss": 0.0997,
69
+ "step": 100
70
+ }
71
+ ],
72
+ "logging_steps": 10,
73
+ "max_steps": 203,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 1,
76
+ "save_steps": 100,
77
+ "total_flos": 1.594758970469253e+17,
78
+ "train_batch_size": 4,
79
+ "trial_name": null,
80
+ "trial_params": null
81
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4403575a2e8535a4a7a185feac62d0faf03b6c2bfd40b3e21cec044f8ab6591a
3
+ size 4411
checkpoint-200/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: /workspace/model
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/workspace/model",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
checkpoint-200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c78e415a017c63f30bd358b78fbd47830d15eaff372289e9d9da53e3329d3cc
3
+ size 43285800
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13455327860a5cd758bc1a03e509a0f9d6178db855a040bd9981b05b90d13a5c
3
+ size 86708485
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1158a2d0a5160b25e5e56d91400d6234b8802dfb077d53ca5daadd78ec49e76e
3
+ size 14575
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0acb3b8d508c274423278e116dc4ae36967c330f90ba70aa5db2466effebe8
3
+ size 627
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|im_sep|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
checkpoint-200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "6": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "7": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "8": {
46
+ "content": "<|im_sep|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|im_start|>",
56
+ "<|im_end|>",
57
+ "<|im_sep|>"
58
+ ],
59
+ "bos_token": "<s>",
60
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
61
+ "clean_up_tokenization_spaces": false,
62
+ "eos_token": "</s>",
63
+ "legacy": true,
64
+ "model_max_length": 200000,
65
+ "pad_token": "<unk>",
66
+ "padding_side": "right",
67
+ "sp_model_kwargs": {},
68
+ "spaces_between_special_tokens": false,
69
+ "split_special_tokens": false,
70
+ "tokenizer_class": "LlamaTokenizer",
71
+ "unk_token": "<unk>",
72
+ "use_default_system_prompt": false
73
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9828009828009828,
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": 0.05,
13
+ "learning_rate": 0.00025,
14
+ "loss": 0.4995,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.1,
19
+ "learning_rate": 0.0005,
20
+ "loss": 0.1621,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.15,
25
+ "learning_rate": 0.0004963251406715272,
26
+ "loss": 0.134,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.2,
31
+ "learning_rate": 0.0004854085994147815,
32
+ "loss": 0.1341,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.25,
37
+ "learning_rate": 0.00046757131025753886,
38
+ "loss": 0.1183,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.29,
43
+ "learning_rate": 0.00044333766942743246,
44
+ "loss": 0.1224,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.34,
49
+ "learning_rate": 0.0004134201186930015,
50
+ "loss": 0.0917,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.39,
55
+ "learning_rate": 0.00037869820037745775,
56
+ "loss": 0.1262,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.44,
61
+ "learning_rate": 0.0003401926998041959,
62
+ "loss": 0.1079,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.49,
67
+ "learning_rate": 0.00029903563535704927,
68
+ "loss": 0.0997,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.54,
73
+ "learning_rate": 0.0002564369784137472,
74
+ "loss": 0.106,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.59,
79
+ "learning_rate": 0.00021364908154907752,
80
+ "loss": 0.1139,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.64,
85
+ "learning_rate": 0.00017192986077855136,
86
+ "loss": 0.1102,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.69,
91
+ "learning_rate": 0.0001325058142431701,
92
+ "loss": 0.119,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.74,
97
+ "learning_rate": 9.653596454434699e-05,
98
+ "loss": 0.1091,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.79,
103
+ "learning_rate": 6.507778478375834e-05,
104
+ "loss": 0.1065,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.84,
109
+ "learning_rate": 3.905611004420359e-05,
110
+ "loss": 0.1032,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.88,
115
+ "learning_rate": 1.9235948278956e-05,
116
+ "loss": 0.1177,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.93,
121
+ "learning_rate": 6.199989938854372e-06,
122
+ "loss": 0.1115,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.98,
127
+ "learning_rate": 3.314775287923677e-07,
128
+ "loss": 0.1014,
129
+ "step": 200
130
+ }
131
+ ],
132
+ "logging_steps": 10,
133
+ "max_steps": 203,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 1,
136
+ "save_steps": 100,
137
+ "total_flos": 3.2162362793617e+17,
138
+ "train_batch_size": 4,
139
+ "trial_name": null,
140
+ "trial_params": null
141
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4403575a2e8535a4a7a185feac62d0faf03b6c2bfd40b3e21cec044f8ab6591a
3
+ size 4411
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|im_sep|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "6": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "7": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "8": {
46
+ "content": "<|im_sep|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|im_start|>",
56
+ "<|im_end|>",
57
+ "<|im_sep|>"
58
+ ],
59
+ "bos_token": "<s>",
60
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
61
+ "clean_up_tokenization_spaces": false,
62
+ "eos_token": "</s>",
63
+ "legacy": true,
64
+ "model_max_length": 200000,
65
+ "pad_token": "<unk>",
66
+ "padding_side": "right",
67
+ "sp_model_kwargs": {},
68
+ "spaces_between_special_tokens": false,
69
+ "split_special_tokens": false,
70
+ "tokenizer_class": "LlamaTokenizer",
71
+ "unk_token": "<unk>",
72
+ "use_default_system_prompt": false
73
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.13428134460167346,
4
+ "train_runtime": 2902.8069,
5
+ "train_samples_per_second": 1.121,
6
+ "train_steps_per_second": 0.07
7
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 203, "loss": 0.4995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 0.05, "percentage": 4.93, "elapsed_time": "0:02:23", "remaining_time": "0:46:02"}
2
+ {"current_steps": 20, "total_steps": 203, "loss": 0.1621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005, "epoch": 0.1, "percentage": 9.85, "elapsed_time": "0:04:44", "remaining_time": "0:43:21"}
3
+ {"current_steps": 30, "total_steps": 203, "loss": 0.134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004963251406715272, "epoch": 0.15, "percentage": 14.78, "elapsed_time": "0:07:04", "remaining_time": "0:40:45"}
4
+ {"current_steps": 40, "total_steps": 203, "loss": 0.1341, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004854085994147815, "epoch": 0.2, "percentage": 19.7, "elapsed_time": "0:09:27", "remaining_time": "0:38:33"}
5
+ {"current_steps": 50, "total_steps": 203, "loss": 0.1183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00046757131025753886, "epoch": 0.25, "percentage": 24.63, "elapsed_time": "0:11:50", "remaining_time": "0:36:12"}
6
+ {"current_steps": 60, "total_steps": 203, "loss": 0.1224, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00044333766942743246, "epoch": 0.29, "percentage": 29.56, "elapsed_time": "0:14:13", "remaining_time": "0:33:55"}
7
+ {"current_steps": 70, "total_steps": 203, "loss": 0.0917, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004134201186930015, "epoch": 0.34, "percentage": 34.48, "elapsed_time": "0:16:37", "remaining_time": "0:31:36"}
8
+ {"current_steps": 80, "total_steps": 203, "loss": 0.1262, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00037869820037745775, "epoch": 0.39, "percentage": 39.41, "elapsed_time": "0:19:01", "remaining_time": "0:29:15"}
9
+ {"current_steps": 90, "total_steps": 203, "loss": 0.1079, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003401926998041959, "epoch": 0.44, "percentage": 44.33, "elapsed_time": "0:21:21", "remaining_time": "0:26:49"}
10
+ {"current_steps": 100, "total_steps": 203, "loss": 0.0997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029903563535704927, "epoch": 0.49, "percentage": 49.26, "elapsed_time": "0:23:38", "remaining_time": "0:24:21"}
11
+ {"current_steps": 110, "total_steps": 203, "loss": 0.106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002564369784137472, "epoch": 0.54, "percentage": 54.19, "elapsed_time": "0:26:00", "remaining_time": "0:21:59"}
12
+ {"current_steps": 120, "total_steps": 203, "loss": 0.1139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021364908154907752, "epoch": 0.59, "percentage": 59.11, "elapsed_time": "0:28:32", "remaining_time": "0:19:44"}
13
+ {"current_steps": 130, "total_steps": 203, "loss": 0.1102, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017192986077855136, "epoch": 0.64, "percentage": 64.04, "elapsed_time": "0:30:54", "remaining_time": "0:17:21"}
14
+ {"current_steps": 140, "total_steps": 203, "loss": 0.119, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001325058142431701, "epoch": 0.69, "percentage": 68.97, "elapsed_time": "0:33:19", "remaining_time": "0:14:59"}
15
+ {"current_steps": 150, "total_steps": 203, "loss": 0.1091, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.653596454434699e-05, "epoch": 0.74, "percentage": 73.89, "elapsed_time": "0:35:42", "remaining_time": "0:12:37"}
16
+ {"current_steps": 160, "total_steps": 203, "loss": 0.1065, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.507778478375834e-05, "epoch": 0.79, "percentage": 78.82, "elapsed_time": "0:38:07", "remaining_time": "0:10:14"}
17
+ {"current_steps": 170, "total_steps": 203, "loss": 0.1032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.905611004420359e-05, "epoch": 0.84, "percentage": 83.74, "elapsed_time": "0:40:31", "remaining_time": "0:07:52"}
18
+ {"current_steps": 180, "total_steps": 203, "loss": 0.1177, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9235948278956e-05, "epoch": 0.88, "percentage": 88.67, "elapsed_time": "0:42:56", "remaining_time": "0:05:29"}
19
+ {"current_steps": 190, "total_steps": 203, "loss": 0.1115, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.199989938854372e-06, "epoch": 0.93, "percentage": 93.6, "elapsed_time": "0:45:15", "remaining_time": "0:03:05"}
20
+ {"current_steps": 200, "total_steps": 203, "loss": 0.1014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.314775287923677e-07, "epoch": 0.98, "percentage": 98.52, "elapsed_time": "0:47:38", "remaining_time": "0:00:42"}
21
+ {"current_steps": 203, "total_steps": 203, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:48:22", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9975429975429976,
5
+ "eval_steps": 500,
6
+ "global_step": 203,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "learning_rate": 0.00025,
14
+ "loss": 0.4995,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.1,
19
+ "learning_rate": 0.0005,
20
+ "loss": 0.1621,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.15,
25
+ "learning_rate": 0.0004963251406715272,
26
+ "loss": 0.134,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.2,
31
+ "learning_rate": 0.0004854085994147815,
32
+ "loss": 0.1341,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.25,
37
+ "learning_rate": 0.00046757131025753886,
38
+ "loss": 0.1183,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.29,
43
+ "learning_rate": 0.00044333766942743246,
44
+ "loss": 0.1224,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.34,
49
+ "learning_rate": 0.0004134201186930015,
50
+ "loss": 0.0917,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.39,
55
+ "learning_rate": 0.00037869820037745775,
56
+ "loss": 0.1262,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.44,
61
+ "learning_rate": 0.0003401926998041959,
62
+ "loss": 0.1079,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.49,
67
+ "learning_rate": 0.00029903563535704927,
68
+ "loss": 0.0997,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.54,
73
+ "learning_rate": 0.0002564369784137472,
74
+ "loss": 0.106,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.59,
79
+ "learning_rate": 0.00021364908154907752,
80
+ "loss": 0.1139,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.64,
85
+ "learning_rate": 0.00017192986077855136,
86
+ "loss": 0.1102,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.69,
91
+ "learning_rate": 0.0001325058142431701,
92
+ "loss": 0.119,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.74,
97
+ "learning_rate": 9.653596454434699e-05,
98
+ "loss": 0.1091,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.79,
103
+ "learning_rate": 6.507778478375834e-05,
104
+ "loss": 0.1065,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.84,
109
+ "learning_rate": 3.905611004420359e-05,
110
+ "loss": 0.1032,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.88,
115
+ "learning_rate": 1.9235948278956e-05,
116
+ "loss": 0.1177,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.93,
121
+ "learning_rate": 6.199989938854372e-06,
122
+ "loss": 0.1115,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.98,
127
+ "learning_rate": 3.314775287923677e-07,
128
+ "loss": 0.1014,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 1.0,
133
+ "step": 203,
134
+ "total_flos": 3.266870789007606e+17,
135
+ "train_loss": 0.13428134460167346,
136
+ "train_runtime": 2902.8069,
137
+ "train_samples_per_second": 1.121,
138
+ "train_steps_per_second": 0.07
139
+ }
140
+ ],
141
+ "logging_steps": 10,
142
+ "max_steps": 203,
143
+ "num_input_tokens_seen": 0,
144
+ "num_train_epochs": 1,
145
+ "save_steps": 100,
146
+ "total_flos": 3.266870789007606e+17,
147
+ "train_batch_size": 4,
148
+ "trial_name": null,
149
+ "trial_params": null
150
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4403575a2e8535a4a7a185feac62d0faf03b6c2bfd40b3e21cec044f8ab6591a
3
+ size 4411