Upload folder using huggingface_hub
Browse files- README.md +57 -1
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- all_results.json +7 -0
- checkpoint-100/README.md +202 -0
- checkpoint-100/adapter_config.json +29 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +24 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +45 -0
- checkpoint-100/trainer_state.json +161 -0
- checkpoint-100/training_args.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
- train_results.json +7 -0
- trainer_log.jsonl +37 -0
- trainer_state.json +282 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,59 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- llama-factory
|
6 |
+
- lora
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
9 |
+
model-index:
|
10 |
+
- name: train_2024-04-24-00-09-45
|
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 |
+
# train_2024-04-24-00-09-45
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the ali_dataset 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: 5e-05
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 8
|
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 |
+
- num_epochs: 3.0
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- PEFT 0.10.0
|
56 |
+
- Transformers 4.40.0
|
57 |
+
- Pytorch 2.2.2+cu121
|
58 |
+
- Datasets 2.19.0
|
59 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9da2ab2aa2a59462bd61ead8ff3aba18be8fe22c3f8d6513edd6c50548c41a2
|
3 |
+
size 13648432
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 2.231679132075909,
|
4 |
+
"train_runtime": 350.7334,
|
5 |
+
"train_samples_per_second": 8.348,
|
6 |
+
"train_steps_per_second": 0.522
|
7 |
+
}
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
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 0.10.0
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83a8bfae52530819b8bb2071a658a754db3cabe2d7ba5b2e616b3a79b7476890
|
3 |
+
size 13648432
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b199e54f79009e17cdf48d6002dd66e94c8bbad3efab5bc2c6dd54a58cb42cd4
|
3 |
+
size 27370618
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba16586a11ebfa21ae23496377c3154236bee12f9bb313d291874d0fa40f0032
|
3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69e4cf7a20bf78cbea223e9dfef76ad97627a9c398a2d7226880ba66d61fba48
|
3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-100/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-100/tokenizer_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
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 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.639344262295082,
|
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": 0.08196721311475409,
|
13 |
+
"grad_norm": 8.290995597839355,
|
14 |
+
"learning_rate": 4.990795908619189e-05,
|
15 |
+
"loss": 6.3211,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.16393442622950818,
|
20 |
+
"grad_norm": 10.25100040435791,
|
21 |
+
"learning_rate": 4.9632514067152726e-05,
|
22 |
+
"loss": 5.8414,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.2459016393442623,
|
27 |
+
"grad_norm": 9.911712646484375,
|
28 |
+
"learning_rate": 4.928142498664579e-05,
|
29 |
+
"loss": 6.2669,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.32786885245901637,
|
34 |
+
"grad_norm": 12.882040977478027,
|
35 |
+
"learning_rate": 4.868186180746792e-05,
|
36 |
+
"loss": 4.3475,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.4098360655737705,
|
41 |
+
"grad_norm": 9.486019134521484,
|
42 |
+
"learning_rate": 4.790792261217512e-05,
|
43 |
+
"loss": 3.6657,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.4918032786885246,
|
48 |
+
"grad_norm": 4.90289306640625,
|
49 |
+
"learning_rate": 4.696530612642871e-05,
|
50 |
+
"loss": 2.6512,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.5737704918032787,
|
55 |
+
"grad_norm": 2.928373336791992,
|
56 |
+
"learning_rate": 4.586095309284618e-05,
|
57 |
+
"loss": 2.1788,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6557377049180327,
|
62 |
+
"grad_norm": 5.331892967224121,
|
63 |
+
"learning_rate": 4.460299516441777e-05,
|
64 |
+
"loss": 2.0556,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.7377049180327869,
|
69 |
+
"grad_norm": 3.0905227661132812,
|
70 |
+
"learning_rate": 4.320069502892462e-05,
|
71 |
+
"loss": 2.0827,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.819672131147541,
|
76 |
+
"grad_norm": 3.840454339981079,
|
77 |
+
"learning_rate": 4.1664378205239085e-05,
|
78 |
+
"loss": 1.9863,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.9016393442622951,
|
83 |
+
"grad_norm": 2.925448179244995,
|
84 |
+
"learning_rate": 4.000535701370921e-05,
|
85 |
+
"loss": 2.0797,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.9836065573770492,
|
90 |
+
"grad_norm": 4.124454498291016,
|
91 |
+
"learning_rate": 3.823584728045463e-05,
|
92 |
+
"loss": 1.9855,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.0655737704918034,
|
97 |
+
"grad_norm": 2.905304431915283,
|
98 |
+
"learning_rate": 3.636887838890265e-05,
|
99 |
+
"loss": 1.8565,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.1475409836065573,
|
104 |
+
"grad_norm": 2.937238931655884,
|
105 |
+
"learning_rate": 3.4418197340879635e-05,
|
106 |
+
"loss": 1.7846,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.2295081967213115,
|
111 |
+
"grad_norm": 2.9058425426483154,
|
112 |
+
"learning_rate": 3.239816753368223e-05,
|
113 |
+
"loss": 1.8977,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.3114754098360657,
|
118 |
+
"grad_norm": 3.247345447540283,
|
119 |
+
"learning_rate": 3.0323662998460393e-05,
|
120 |
+
"loss": 1.6528,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.3934426229508197,
|
125 |
+
"grad_norm": 3.5700137615203857,
|
126 |
+
"learning_rate": 2.8209958878663778e-05,
|
127 |
+
"loss": 1.7865,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.4754098360655736,
|
132 |
+
"grad_norm": 3.3404250144958496,
|
133 |
+
"learning_rate": 2.6072618954988866e-05,
|
134 |
+
"loss": 1.6595,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.5573770491803278,
|
139 |
+
"grad_norm": 2.9976389408111572,
|
140 |
+
"learning_rate": 2.3927381045011136e-05,
|
141 |
+
"loss": 1.795,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.639344262295082,
|
146 |
+
"grad_norm": 2.907928943634033,
|
147 |
+
"learning_rate": 2.1790041121336225e-05,
|
148 |
+
"loss": 1.6754,
|
149 |
+
"step": 100
|
150 |
+
}
|
151 |
+
],
|
152 |
+
"logging_steps": 5,
|
153 |
+
"max_steps": 183,
|
154 |
+
"num_input_tokens_seen": 0,
|
155 |
+
"num_train_epochs": 3,
|
156 |
+
"save_steps": 100,
|
157 |
+
"total_flos": 5218424960974848.0,
|
158 |
+
"train_batch_size": 2,
|
159 |
+
"trial_name": null,
|
160 |
+
"trial_params": null
|
161 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:451ea05a0196edc64a345b0220cd5e4f39763b61e221cb2fb962fe82628ca593
|
3 |
+
size 5176
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
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 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 2.231679132075909,
|
4 |
+
"train_runtime": 350.7334,
|
5 |
+
"train_samples_per_second": 8.348,
|
6 |
+
"train_steps_per_second": 0.522
|
7 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 5, "total_steps": 183, "loss": 6.3211, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.990795908619189e-05, "epoch": 0.08196721311475409, "percentage": 2.73, "elapsed_time": "0:00:09", "remaining_time": "0:05:44"}
|
2 |
+
{"current_steps": 10, "total_steps": 183, "loss": 5.8414, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9632514067152726e-05, "epoch": 0.16393442622950818, "percentage": 5.46, "elapsed_time": "0:00:18", "remaining_time": "0:05:13"}
|
3 |
+
{"current_steps": 15, "total_steps": 183, "loss": 6.2669, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.928142498664579e-05, "epoch": 0.2459016393442623, "percentage": 8.2, "elapsed_time": "0:00:26", "remaining_time": "0:04:58"}
|
4 |
+
{"current_steps": 20, "total_steps": 183, "loss": 4.3475, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.868186180746792e-05, "epoch": 0.32786885245901637, "percentage": 10.93, "elapsed_time": "0:00:35", "remaining_time": "0:04:47"}
|
5 |
+
{"current_steps": 25, "total_steps": 183, "loss": 3.6657, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.790792261217512e-05, "epoch": 0.4098360655737705, "percentage": 13.66, "elapsed_time": "0:00:44", "remaining_time": "0:04:38"}
|
6 |
+
{"current_steps": 30, "total_steps": 183, "loss": 2.6512, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.696530612642871e-05, "epoch": 0.4918032786885246, "percentage": 16.39, "elapsed_time": "0:00:52", "remaining_time": "0:04:29"}
|
7 |
+
{"current_steps": 35, "total_steps": 183, "loss": 2.1788, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.586095309284618e-05, "epoch": 0.5737704918032787, "percentage": 19.13, "elapsed_time": "0:01:01", "remaining_time": "0:04:20"}
|
8 |
+
{"current_steps": 40, "total_steps": 183, "loss": 2.0556, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.460299516441777e-05, "epoch": 0.6557377049180327, "percentage": 21.86, "elapsed_time": "0:01:10", "remaining_time": "0:04:11"}
|
9 |
+
{"current_steps": 45, "total_steps": 183, "loss": 2.0827, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.320069502892462e-05, "epoch": 0.7377049180327869, "percentage": 24.59, "elapsed_time": "0:01:19", "remaining_time": "0:04:05"}
|
10 |
+
{"current_steps": 50, "total_steps": 183, "loss": 1.9863, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.1664378205239085e-05, "epoch": 0.819672131147541, "percentage": 27.32, "elapsed_time": "0:01:28", "remaining_time": "0:03:56"}
|
11 |
+
{"current_steps": 55, "total_steps": 183, "loss": 2.0797, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.000535701370921e-05, "epoch": 0.9016393442622951, "percentage": 30.05, "elapsed_time": "0:01:38", "remaining_time": "0:03:48"}
|
12 |
+
{"current_steps": 60, "total_steps": 183, "loss": 1.9855, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.823584728045463e-05, "epoch": 0.9836065573770492, "percentage": 32.79, "elapsed_time": "0:01:47", "remaining_time": "0:03:40"}
|
13 |
+
{"current_steps": 65, "total_steps": 183, "loss": 1.8565, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.636887838890265e-05, "epoch": 1.0655737704918034, "percentage": 35.52, "elapsed_time": "0:01:56", "remaining_time": "0:03:31"}
|
14 |
+
{"current_steps": 70, "total_steps": 183, "loss": 1.7846, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.4418197340879635e-05, "epoch": 1.1475409836065573, "percentage": 38.25, "elapsed_time": "0:02:05", "remaining_time": "0:03:23"}
|
15 |
+
{"current_steps": 75, "total_steps": 183, "loss": 1.8977, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.239816753368223e-05, "epoch": 1.2295081967213115, "percentage": 40.98, "elapsed_time": "0:02:14", "remaining_time": "0:03:14"}
|
16 |
+
{"current_steps": 80, "total_steps": 183, "loss": 1.6528, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0323662998460393e-05, "epoch": 1.3114754098360657, "percentage": 43.72, "elapsed_time": "0:02:24", "remaining_time": "0:03:06"}
|
17 |
+
{"current_steps": 85, "total_steps": 183, "loss": 1.7865, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8209958878663778e-05, "epoch": 1.3934426229508197, "percentage": 46.45, "elapsed_time": "0:02:33", "remaining_time": "0:02:57"}
|
18 |
+
{"current_steps": 90, "total_steps": 183, "loss": 1.6595, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.6072618954988866e-05, "epoch": 1.4754098360655736, "percentage": 49.18, "elapsed_time": "0:02:43", "remaining_time": "0:02:48"}
|
19 |
+
{"current_steps": 95, "total_steps": 183, "loss": 1.795, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3927381045011136e-05, "epoch": 1.5573770491803278, "percentage": 51.91, "elapsed_time": "0:02:52", "remaining_time": "0:02:39"}
|
20 |
+
{"current_steps": 100, "total_steps": 183, "loss": 1.6754, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.1790041121336225e-05, "epoch": 1.639344262295082, "percentage": 54.64, "elapsed_time": "0:03:02", "remaining_time": "0:02:31"}
|
21 |
+
{"current_steps": 105, "total_steps": 183, "loss": 1.6433, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.9676337001539612e-05, "epoch": 1.721311475409836, "percentage": 57.38, "elapsed_time": "0:03:12", "remaining_time": "0:02:22"}
|
22 |
+
{"current_steps": 110, "total_steps": 183, "loss": 1.5446, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.760183246631777e-05, "epoch": 1.8032786885245902, "percentage": 60.11, "elapsed_time": "0:03:21", "remaining_time": "0:02:13"}
|
23 |
+
{"current_steps": 115, "total_steps": 183, "loss": 1.5668, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.558180265912037e-05, "epoch": 1.8852459016393444, "percentage": 62.84, "elapsed_time": "0:03:31", "remaining_time": "0:02:05"}
|
24 |
+
{"current_steps": 120, "total_steps": 183, "loss": 1.5542, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3631121611097364e-05, "epoch": 1.9672131147540983, "percentage": 65.57, "elapsed_time": "0:03:41", "remaining_time": "0:01:56"}
|
25 |
+
{"current_steps": 125, "total_steps": 183, "loss": 1.4999, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.1764152719545372e-05, "epoch": 2.0491803278688523, "percentage": 68.31, "elapsed_time": "0:03:51", "remaining_time": "0:01:47"}
|
26 |
+
{"current_steps": 130, "total_steps": 183, "loss": 1.6873, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.994642986290797e-06, "epoch": 2.1311475409836067, "percentage": 71.04, "elapsed_time": "0:04:01", "remaining_time": "0:01:38"}
|
27 |
+
{"current_steps": 135, "total_steps": 183, "loss": 1.5267, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 8.33562179476092e-06, "epoch": 2.2131147540983607, "percentage": 73.77, "elapsed_time": "0:04:11", "remaining_time": "0:01:29"}
|
28 |
+
{"current_steps": 140, "total_steps": 183, "loss": 1.6676, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.799304971075382e-06, "epoch": 2.2950819672131146, "percentage": 76.5, "elapsed_time": "0:04:22", "remaining_time": "0:01:20"}
|
29 |
+
{"current_steps": 145, "total_steps": 183, "loss": 1.7066, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.397004835582242e-06, "epoch": 2.3770491803278686, "percentage": 79.23, "elapsed_time": "0:04:32", "remaining_time": "0:01:11"}
|
30 |
+
{"current_steps": 150, "total_steps": 183, "loss": 1.4762, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.139046907153818e-06, "epoch": 2.459016393442623, "percentage": 81.97, "elapsed_time": "0:04:42", "remaining_time": "0:01:02"}
|
31 |
+
{"current_steps": 155, "total_steps": 183, "loss": 1.5355, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0346938735712954e-06, "epoch": 2.540983606557377, "percentage": 84.7, "elapsed_time": "0:04:53", "remaining_time": "0:00:52"}
|
32 |
+
{"current_steps": 160, "total_steps": 183, "loss": 1.708, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.092077387824884e-06, "epoch": 2.6229508196721314, "percentage": 87.43, "elapsed_time": "0:05:03", "remaining_time": "0:00:43"}
|
33 |
+
{"current_steps": 165, "total_steps": 183, "loss": 1.54, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3181381925320785e-06, "epoch": 2.7049180327868854, "percentage": 90.16, "elapsed_time": "0:05:13", "remaining_time": "0:00:34"}
|
34 |
+
{"current_steps": 170, "total_steps": 183, "loss": 1.5244, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.185750133542169e-07, "epoch": 2.7868852459016393, "percentage": 92.9, "elapsed_time": "0:05:24", "remaining_time": "0:00:24"}
|
35 |
+
{"current_steps": 175, "total_steps": 183, "loss": 1.5209, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.978025977230736e-07, "epoch": 2.8688524590163933, "percentage": 95.63, "elapsed_time": "0:05:34", "remaining_time": "0:00:15"}
|
36 |
+
{"current_steps": 180, "total_steps": 183, "loss": 1.5363, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.891920784984184e-08, "epoch": 2.9508196721311473, "percentage": 98.36, "elapsed_time": "0:05:44", "remaining_time": "0:00:05"}
|
37 |
+
{"current_steps": 183, "total_steps": 183, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:05:50", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
@@ -0,0 +1,282 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 183,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.08196721311475409,
|
13 |
+
"grad_norm": 8.290995597839355,
|
14 |
+
"learning_rate": 4.990795908619189e-05,
|
15 |
+
"loss": 6.3211,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.16393442622950818,
|
20 |
+
"grad_norm": 10.25100040435791,
|
21 |
+
"learning_rate": 4.9632514067152726e-05,
|
22 |
+
"loss": 5.8414,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.2459016393442623,
|
27 |
+
"grad_norm": 9.911712646484375,
|
28 |
+
"learning_rate": 4.928142498664579e-05,
|
29 |
+
"loss": 6.2669,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.32786885245901637,
|
34 |
+
"grad_norm": 12.882040977478027,
|
35 |
+
"learning_rate": 4.868186180746792e-05,
|
36 |
+
"loss": 4.3475,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.4098360655737705,
|
41 |
+
"grad_norm": 9.486019134521484,
|
42 |
+
"learning_rate": 4.790792261217512e-05,
|
43 |
+
"loss": 3.6657,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.4918032786885246,
|
48 |
+
"grad_norm": 4.90289306640625,
|
49 |
+
"learning_rate": 4.696530612642871e-05,
|
50 |
+
"loss": 2.6512,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.5737704918032787,
|
55 |
+
"grad_norm": 2.928373336791992,
|
56 |
+
"learning_rate": 4.586095309284618e-05,
|
57 |
+
"loss": 2.1788,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6557377049180327,
|
62 |
+
"grad_norm": 5.331892967224121,
|
63 |
+
"learning_rate": 4.460299516441777e-05,
|
64 |
+
"loss": 2.0556,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.7377049180327869,
|
69 |
+
"grad_norm": 3.0905227661132812,
|
70 |
+
"learning_rate": 4.320069502892462e-05,
|
71 |
+
"loss": 2.0827,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.819672131147541,
|
76 |
+
"grad_norm": 3.840454339981079,
|
77 |
+
"learning_rate": 4.1664378205239085e-05,
|
78 |
+
"loss": 1.9863,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.9016393442622951,
|
83 |
+
"grad_norm": 2.925448179244995,
|
84 |
+
"learning_rate": 4.000535701370921e-05,
|
85 |
+
"loss": 2.0797,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.9836065573770492,
|
90 |
+
"grad_norm": 4.124454498291016,
|
91 |
+
"learning_rate": 3.823584728045463e-05,
|
92 |
+
"loss": 1.9855,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.0655737704918034,
|
97 |
+
"grad_norm": 2.905304431915283,
|
98 |
+
"learning_rate": 3.636887838890265e-05,
|
99 |
+
"loss": 1.8565,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.1475409836065573,
|
104 |
+
"grad_norm": 2.937238931655884,
|
105 |
+
"learning_rate": 3.4418197340879635e-05,
|
106 |
+
"loss": 1.7846,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.2295081967213115,
|
111 |
+
"grad_norm": 2.9058425426483154,
|
112 |
+
"learning_rate": 3.239816753368223e-05,
|
113 |
+
"loss": 1.8977,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.3114754098360657,
|
118 |
+
"grad_norm": 3.247345447540283,
|
119 |
+
"learning_rate": 3.0323662998460393e-05,
|
120 |
+
"loss": 1.6528,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.3934426229508197,
|
125 |
+
"grad_norm": 3.5700137615203857,
|
126 |
+
"learning_rate": 2.8209958878663778e-05,
|
127 |
+
"loss": 1.7865,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.4754098360655736,
|
132 |
+
"grad_norm": 3.3404250144958496,
|
133 |
+
"learning_rate": 2.6072618954988866e-05,
|
134 |
+
"loss": 1.6595,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.5573770491803278,
|
139 |
+
"grad_norm": 2.9976389408111572,
|
140 |
+
"learning_rate": 2.3927381045011136e-05,
|
141 |
+
"loss": 1.795,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.639344262295082,
|
146 |
+
"grad_norm": 2.907928943634033,
|
147 |
+
"learning_rate": 2.1790041121336225e-05,
|
148 |
+
"loss": 1.6754,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.721311475409836,
|
153 |
+
"grad_norm": 2.8854143619537354,
|
154 |
+
"learning_rate": 1.9676337001539612e-05,
|
155 |
+
"loss": 1.6433,
|
156 |
+
"step": 105
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.8032786885245902,
|
160 |
+
"grad_norm": 3.0124289989471436,
|
161 |
+
"learning_rate": 1.760183246631777e-05,
|
162 |
+
"loss": 1.5446,
|
163 |
+
"step": 110
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.8852459016393444,
|
167 |
+
"grad_norm": 3.203061819076538,
|
168 |
+
"learning_rate": 1.558180265912037e-05,
|
169 |
+
"loss": 1.5668,
|
170 |
+
"step": 115
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.9672131147540983,
|
174 |
+
"grad_norm": 2.9160172939300537,
|
175 |
+
"learning_rate": 1.3631121611097364e-05,
|
176 |
+
"loss": 1.5542,
|
177 |
+
"step": 120
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2.0491803278688523,
|
181 |
+
"grad_norm": 3.249051570892334,
|
182 |
+
"learning_rate": 1.1764152719545372e-05,
|
183 |
+
"loss": 1.4999,
|
184 |
+
"step": 125
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.1311475409836067,
|
188 |
+
"grad_norm": 3.0132319927215576,
|
189 |
+
"learning_rate": 9.994642986290797e-06,
|
190 |
+
"loss": 1.6873,
|
191 |
+
"step": 130
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.2131147540983607,
|
195 |
+
"grad_norm": 3.1967945098876953,
|
196 |
+
"learning_rate": 8.33562179476092e-06,
|
197 |
+
"loss": 1.5267,
|
198 |
+
"step": 135
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.2950819672131146,
|
202 |
+
"grad_norm": 3.5244369506835938,
|
203 |
+
"learning_rate": 6.799304971075382e-06,
|
204 |
+
"loss": 1.6676,
|
205 |
+
"step": 140
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.3770491803278686,
|
209 |
+
"grad_norm": 3.073401689529419,
|
210 |
+
"learning_rate": 5.397004835582242e-06,
|
211 |
+
"loss": 1.7066,
|
212 |
+
"step": 145
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.459016393442623,
|
216 |
+
"grad_norm": 2.9026217460632324,
|
217 |
+
"learning_rate": 4.139046907153818e-06,
|
218 |
+
"loss": 1.4762,
|
219 |
+
"step": 150
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.540983606557377,
|
223 |
+
"grad_norm": 2.8583261966705322,
|
224 |
+
"learning_rate": 3.0346938735712954e-06,
|
225 |
+
"loss": 1.5355,
|
226 |
+
"step": 155
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.6229508196721314,
|
230 |
+
"grad_norm": 3.106534242630005,
|
231 |
+
"learning_rate": 2.092077387824884e-06,
|
232 |
+
"loss": 1.708,
|
233 |
+
"step": 160
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.7049180327868854,
|
237 |
+
"grad_norm": 3.100788116455078,
|
238 |
+
"learning_rate": 1.3181381925320785e-06,
|
239 |
+
"loss": 1.54,
|
240 |
+
"step": 165
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.7868852459016393,
|
244 |
+
"grad_norm": 3.149162530899048,
|
245 |
+
"learning_rate": 7.185750133542169e-07,
|
246 |
+
"loss": 1.5244,
|
247 |
+
"step": 170
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.8688524590163933,
|
251 |
+
"grad_norm": 3.3356781005859375,
|
252 |
+
"learning_rate": 2.978025977230736e-07,
|
253 |
+
"loss": 1.5209,
|
254 |
+
"step": 175
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.9508196721311473,
|
258 |
+
"grad_norm": 2.8666839599609375,
|
259 |
+
"learning_rate": 5.891920784984184e-08,
|
260 |
+
"loss": 1.5363,
|
261 |
+
"step": 180
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 3.0,
|
265 |
+
"step": 183,
|
266 |
+
"total_flos": 9540135882719232.0,
|
267 |
+
"train_loss": 2.231679132075909,
|
268 |
+
"train_runtime": 350.7334,
|
269 |
+
"train_samples_per_second": 8.348,
|
270 |
+
"train_steps_per_second": 0.522
|
271 |
+
}
|
272 |
+
],
|
273 |
+
"logging_steps": 5,
|
274 |
+
"max_steps": 183,
|
275 |
+
"num_input_tokens_seen": 0,
|
276 |
+
"num_train_epochs": 3,
|
277 |
+
"save_steps": 100,
|
278 |
+
"total_flos": 9540135882719232.0,
|
279 |
+
"train_batch_size": 2,
|
280 |
+
"trial_name": null,
|
281 |
+
"trial_params": null
|
282 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:451ea05a0196edc64a345b0220cd5e4f39763b61e221cb2fb962fe82628ca593
|
3 |
+
size 5176
|