Commit
•
ed1991b
1
Parent(s):
fc3ff59
Upload folder using huggingface_hub
Browse files- README.md +59 -0
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- all_results.json +7 -0
- checkpoint-100/README.md +204 -0
- checkpoint-100/adapter_config.json +28 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/added_tokens.json +5 -0
- checkpoint-100/merges.txt +0 -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 +20 -0
- checkpoint-100/tokenizer_config.json +44 -0
- checkpoint-100/trainer_state.json +161 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-100/vocab.json +0 -0
- merges.txt +0 -0
- runs/Mar15_07-08-08_90f17ba55fb1/events.out.tfevents.1710486607.90f17ba55fb1.355.1 +3 -0
- special_tokens_map.json +20 -0
- tokenizer_config.json +44 -0
- train_results.json +7 -0
- trainer_log.jsonl +35 -0
- trainer_state.json +268 -0
- training_args.bin +3 -0
- vocab.json +0 -0
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: Qwen/Qwen1.5-1.8B
|
9 |
+
model-index:
|
10 |
+
- name: train_2024-03-15-07-07-32
|
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_2024-03-15-07-07-32
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on the PIPPA 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 0.9.0
|
56 |
+
- Transformers 4.38.2
|
57 |
+
- Pytorch 2.2.1+cu121
|
58 |
+
- Datasets 2.18.0
|
59 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-1.8B",
|
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": 0.1,
|
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_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e7dd411ac97ecb46eafa6df766860678e727a2c1a568c09165d5307bf734fb3
|
3 |
+
size 6304096
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.99,
|
3 |
+
"train_loss": 2.5343901483636153,
|
4 |
+
"train_runtime": 1859.0377,
|
5 |
+
"train_samples_per_second": 1.477,
|
6 |
+
"train_steps_per_second": 0.092
|
7 |
+
}
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Qwen/Qwen1.5-1.8B
|
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 0.9.0
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-1.8B",
|
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": 0.1,
|
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_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fed755aa35222569f766075cdf782e00aa1396f5753fb9e965ba174e58aea705
|
3 |
+
size 6304096
|
checkpoint-100/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-100/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c690edbe4210abcf2cc0511fed257b7445eeea1cbbdaa37c6c7c3627728059ed
|
3 |
+
size 12663802
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc88650b952bfd5edc596d2f98355841769785e4797c356a63440dc1ce193f5e
|
3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:630b9f8550a654817bb7ab3c8125fd769893207abe6bf080ff46903cff3db713
|
3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
checkpoint-100/tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|endoftext|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"padding_side": "right",
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
+
"unk_token": null
|
44 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.7467248908296944,
|
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": 0.09,
|
13 |
+
"grad_norm": 0.6939600110054016,
|
14 |
+
"learning_rate": 4.9894597202472696e-05,
|
15 |
+
"loss": 2.9255,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.17,
|
20 |
+
"grad_norm": 0.8492265343666077,
|
21 |
+
"learning_rate": 4.957927758986888e-05,
|
22 |
+
"loss": 2.8178,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.26,
|
27 |
+
"grad_norm": 0.8294272422790527,
|
28 |
+
"learning_rate": 4.905670000773126e-05,
|
29 |
+
"loss": 2.7191,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.35,
|
34 |
+
"grad_norm": 0.6167703866958618,
|
35 |
+
"learning_rate": 4.833127094718643e-05,
|
36 |
+
"loss": 2.6713,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.44,
|
41 |
+
"grad_norm": 0.49007371068000793,
|
42 |
+
"learning_rate": 4.7409107388425504e-05,
|
43 |
+
"loss": 2.6395,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.52,
|
48 |
+
"grad_norm": 0.4197269678115845,
|
49 |
+
"learning_rate": 4.629798522095818e-05,
|
50 |
+
"loss": 2.5998,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.61,
|
55 |
+
"grad_norm": 0.35962584614753723,
|
56 |
+
"learning_rate": 4.5007273675572104e-05,
|
57 |
+
"loss": 2.5696,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.7,
|
62 |
+
"grad_norm": 0.31397658586502075,
|
63 |
+
"learning_rate": 4.3547856320882044e-05,
|
64 |
+
"loss": 2.5568,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.79,
|
69 |
+
"grad_norm": 0.2711264193058014,
|
70 |
+
"learning_rate": 4.193203929064353e-05,
|
71 |
+
"loss": 2.4964,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.87,
|
76 |
+
"grad_norm": 0.29537662863731384,
|
77 |
+
"learning_rate": 4.0173447515678916e-05,
|
78 |
+
"loss": 2.5512,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.96,
|
83 |
+
"grad_norm": 0.28811562061309814,
|
84 |
+
"learning_rate": 3.82869098354114e-05,
|
85 |
+
"loss": 2.5155,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.05,
|
90 |
+
"grad_norm": 0.2557935118675232,
|
91 |
+
"learning_rate": 3.628833395777224e-05,
|
92 |
+
"loss": 2.5253,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.14,
|
97 |
+
"grad_norm": 0.243013396859169,
|
98 |
+
"learning_rate": 3.4194572321847336e-05,
|
99 |
+
"loss": 2.5395,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.22,
|
104 |
+
"grad_norm": 0.26634490489959717,
|
105 |
+
"learning_rate": 3.202327999433924e-05,
|
106 |
+
"loss": 2.4728,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.31,
|
111 |
+
"grad_norm": 0.288352906703949,
|
112 |
+
"learning_rate": 2.9792765798093465e-05,
|
113 |
+
"loss": 2.5059,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.4,
|
118 |
+
"grad_norm": 0.25032252073287964,
|
119 |
+
"learning_rate": 2.752183792800671e-05,
|
120 |
+
"loss": 2.5368,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.48,
|
125 |
+
"grad_norm": 0.24827222526073456,
|
126 |
+
"learning_rate": 2.5229645356118163e-05,
|
127 |
+
"loss": 2.4811,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.57,
|
132 |
+
"grad_norm": 0.2552015781402588,
|
133 |
+
"learning_rate": 2.2935516363191693e-05,
|
134 |
+
"loss": 2.5105,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.66,
|
139 |
+
"grad_norm": 0.2699149549007416,
|
140 |
+
"learning_rate": 2.0658795558326743e-05,
|
141 |
+
"loss": 2.5252,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.75,
|
146 |
+
"grad_norm": 0.2718549966812134,
|
147 |
+
"learning_rate": 1.8418680760885027e-05,
|
148 |
+
"loss": 2.4448,
|
149 |
+
"step": 100
|
150 |
+
}
|
151 |
+
],
|
152 |
+
"logging_steps": 5,
|
153 |
+
"max_steps": 171,
|
154 |
+
"num_input_tokens_seen": 0,
|
155 |
+
"num_train_epochs": 3,
|
156 |
+
"save_steps": 100,
|
157 |
+
"total_flos": 1.5003963409563648e+16,
|
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:d328013ce840d512bfda18c4318f213b0268f9ce834a68420ca42557bbe0c0a8
|
3 |
+
size 5112
|
checkpoint-100/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar15_07-08-08_90f17ba55fb1/events.out.tfevents.1710486607.90f17ba55fb1.355.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39a038c4fe68687bcfe2a93234ae94b375de9cad6eb2bbff99f70c4c04f6934c
|
3 |
+
size 12298
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|endoftext|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"padding_side": "right",
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
+
"unk_token": null
|
44 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.99,
|
3 |
+
"train_loss": 2.5343901483636153,
|
4 |
+
"train_runtime": 1859.0377,
|
5 |
+
"train_samples_per_second": 1.477,
|
6 |
+
"train_steps_per_second": 0.092
|
7 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 5, "total_steps": 171, "loss": 2.9255, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9894597202472696e-05, "epoch": 0.09, "percentage": 2.92, "elapsed_time": "0:00:51", "remaining_time": "0:28:34"}
|
2 |
+
{"current_steps": 10, "total_steps": 171, "loss": 2.8178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.957927758986888e-05, "epoch": 0.17, "percentage": 5.85, "elapsed_time": "0:01:46", "remaining_time": "0:28:31"}
|
3 |
+
{"current_steps": 15, "total_steps": 171, "loss": 2.7191, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.905670000773126e-05, "epoch": 0.26, "percentage": 8.77, "elapsed_time": "0:02:40", "remaining_time": "0:27:47"}
|
4 |
+
{"current_steps": 20, "total_steps": 171, "loss": 2.6713, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.833127094718643e-05, "epoch": 0.35, "percentage": 11.7, "elapsed_time": "0:03:34", "remaining_time": "0:27:02"}
|
5 |
+
{"current_steps": 25, "total_steps": 171, "loss": 2.6395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7409107388425504e-05, "epoch": 0.44, "percentage": 14.62, "elapsed_time": "0:04:29", "remaining_time": "0:26:12"}
|
6 |
+
{"current_steps": 30, "total_steps": 171, "loss": 2.5998, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.629798522095818e-05, "epoch": 0.52, "percentage": 17.54, "elapsed_time": "0:05:23", "remaining_time": "0:25:21"}
|
7 |
+
{"current_steps": 35, "total_steps": 171, "loss": 2.5696, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5007273675572104e-05, "epoch": 0.61, "percentage": 20.47, "elapsed_time": "0:06:18", "remaining_time": "0:24:29"}
|
8 |
+
{"current_steps": 40, "total_steps": 171, "loss": 2.5568, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3547856320882044e-05, "epoch": 0.7, "percentage": 23.39, "elapsed_time": "0:07:12", "remaining_time": "0:23:35"}
|
9 |
+
{"current_steps": 45, "total_steps": 171, "loss": 2.4964, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.193203929064353e-05, "epoch": 0.79, "percentage": 26.32, "elapsed_time": "0:08:06", "remaining_time": "0:22:43"}
|
10 |
+
{"current_steps": 50, "total_steps": 171, "loss": 2.5512, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0173447515678916e-05, "epoch": 0.87, "percentage": 29.24, "elapsed_time": "0:09:01", "remaining_time": "0:21:49"}
|
11 |
+
{"current_steps": 55, "total_steps": 171, "loss": 2.5155, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.82869098354114e-05, "epoch": 0.96, "percentage": 32.16, "elapsed_time": "0:09:55", "remaining_time": "0:20:56"}
|
12 |
+
{"current_steps": 60, "total_steps": 171, "loss": 2.5253, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.628833395777224e-05, "epoch": 1.05, "percentage": 35.09, "elapsed_time": "0:10:49", "remaining_time": "0:20:01"}
|
13 |
+
{"current_steps": 65, "total_steps": 171, "loss": 2.5395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4194572321847336e-05, "epoch": 1.14, "percentage": 38.01, "elapsed_time": "0:11:43", "remaining_time": "0:19:07"}
|
14 |
+
{"current_steps": 70, "total_steps": 171, "loss": 2.4728, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.202327999433924e-05, "epoch": 1.22, "percentage": 40.94, "elapsed_time": "0:12:38", "remaining_time": "0:18:13"}
|
15 |
+
{"current_steps": 75, "total_steps": 171, "loss": 2.5059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9792765798093465e-05, "epoch": 1.31, "percentage": 43.86, "elapsed_time": "0:13:32", "remaining_time": "0:17:20"}
|
16 |
+
{"current_steps": 80, "total_steps": 171, "loss": 2.5368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.752183792800671e-05, "epoch": 1.4, "percentage": 46.78, "elapsed_time": "0:14:27", "remaining_time": "0:16:26"}
|
17 |
+
{"current_steps": 85, "total_steps": 171, "loss": 2.4811, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5229645356118163e-05, "epoch": 1.48, "percentage": 49.71, "elapsed_time": "0:15:21", "remaining_time": "0:15:32"}
|
18 |
+
{"current_steps": 90, "total_steps": 171, "loss": 2.5105, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2935516363191693e-05, "epoch": 1.57, "percentage": 52.63, "elapsed_time": "0:16:15", "remaining_time": "0:14:38"}
|
19 |
+
{"current_steps": 95, "total_steps": 171, "loss": 2.5252, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0658795558326743e-05, "epoch": 1.66, "percentage": 55.56, "elapsed_time": "0:17:10", "remaining_time": "0:13:44"}
|
20 |
+
{"current_steps": 100, "total_steps": 171, "loss": 2.4448, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8418680760885027e-05, "epoch": 1.75, "percentage": 58.48, "elapsed_time": "0:18:04", "remaining_time": "0:12:50"}
|
21 |
+
{"current_steps": 105, "total_steps": 171, "loss": 2.438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6234061120181142e-05, "epoch": 1.83, "percentage": 61.4, "elapsed_time": "0:19:00", "remaining_time": "0:11:56"}
|
22 |
+
{"current_steps": 110, "total_steps": 171, "loss": 2.49, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4123357837948175e-05, "epoch": 1.92, "percentage": 64.33, "elapsed_time": "0:19:54", "remaining_time": "0:11:02"}
|
23 |
+
{"current_steps": 115, "total_steps": 171, "loss": 2.4363, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2104368836641908e-05, "epoch": 2.01, "percentage": 67.25, "elapsed_time": "0:20:48", "remaining_time": "0:10:08"}
|
24 |
+
{"current_steps": 120, "total_steps": 171, "loss": 2.4613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0194118683375503e-05, "epoch": 2.1, "percentage": 70.18, "elapsed_time": "0:21:43", "remaining_time": "0:09:13"}
|
25 |
+
{"current_steps": 125, "total_steps": 171, "loss": 2.4758, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.40871503495947e-06, "epoch": 2.18, "percentage": 73.1, "elapsed_time": "0:22:37", "remaining_time": "0:08:19"}
|
26 |
+
{"current_steps": 130, "total_steps": 171, "loss": 2.4591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.763212814534484e-06, "epoch": 2.27, "percentage": 76.02, "elapsed_time": "0:23:32", "remaining_time": "0:07:25"}
|
27 |
+
{"current_steps": 135, "total_steps": 171, "loss": 2.4655, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.271487265090163e-06, "epoch": 2.36, "percentage": 78.95, "elapsed_time": "0:24:26", "remaining_time": "0:06:31"}
|
28 |
+
{"current_steps": 140, "total_steps": 171, "loss": 2.4813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.94611695031086e-06, "epoch": 2.45, "percentage": 81.87, "elapsed_time": "0:25:21", "remaining_time": "0:05:36"}
|
29 |
+
{"current_steps": 145, "total_steps": 171, "loss": 2.4453, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7982776893115627e-06, "epoch": 2.53, "percentage": 84.8, "elapsed_time": "0:26:15", "remaining_time": "0:04:42"}
|
30 |
+
{"current_steps": 150, "total_steps": 171, "loss": 2.4941, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.837648319629956e-06, "epoch": 2.62, "percentage": 87.72, "elapsed_time": "0:27:09", "remaining_time": "0:03:48"}
|
31 |
+
{"current_steps": 155, "total_steps": 171, "loss": 2.4701, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0723290831021471e-06, "epoch": 2.71, "percentage": 90.64, "elapsed_time": "0:28:04", "remaining_time": "0:02:53"}
|
32 |
+
{"current_steps": 160, "total_steps": 171, "loss": 2.4543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.087733228106517e-07, "epoch": 2.79, "percentage": 93.57, "elapsed_time": "0:28:59", "remaining_time": "0:01:59"}
|
33 |
+
{"current_steps": 165, "total_steps": 171, "loss": 2.5142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.517330670512629e-07, "epoch": 2.88, "percentage": 96.49, "elapsed_time": "0:29:53", "remaining_time": "0:01:05"}
|
34 |
+
{"current_steps": 170, "total_steps": 171, "loss": 2.4938, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.218959166932268e-09, "epoch": 2.97, "percentage": 99.42, "elapsed_time": "0:30:48", "remaining_time": "0:00:10"}
|
35 |
+
{"current_steps": 171, "total_steps": 171, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.99, "percentage": 100.0, "elapsed_time": "0:30:58", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
@@ -0,0 +1,268 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.986899563318777,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 171,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.09,
|
13 |
+
"grad_norm": 0.6939600110054016,
|
14 |
+
"learning_rate": 4.9894597202472696e-05,
|
15 |
+
"loss": 2.9255,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.17,
|
20 |
+
"grad_norm": 0.8492265343666077,
|
21 |
+
"learning_rate": 4.957927758986888e-05,
|
22 |
+
"loss": 2.8178,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.26,
|
27 |
+
"grad_norm": 0.8294272422790527,
|
28 |
+
"learning_rate": 4.905670000773126e-05,
|
29 |
+
"loss": 2.7191,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.35,
|
34 |
+
"grad_norm": 0.6167703866958618,
|
35 |
+
"learning_rate": 4.833127094718643e-05,
|
36 |
+
"loss": 2.6713,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.44,
|
41 |
+
"grad_norm": 0.49007371068000793,
|
42 |
+
"learning_rate": 4.7409107388425504e-05,
|
43 |
+
"loss": 2.6395,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.52,
|
48 |
+
"grad_norm": 0.4197269678115845,
|
49 |
+
"learning_rate": 4.629798522095818e-05,
|
50 |
+
"loss": 2.5998,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.61,
|
55 |
+
"grad_norm": 0.35962584614753723,
|
56 |
+
"learning_rate": 4.5007273675572104e-05,
|
57 |
+
"loss": 2.5696,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.7,
|
62 |
+
"grad_norm": 0.31397658586502075,
|
63 |
+
"learning_rate": 4.3547856320882044e-05,
|
64 |
+
"loss": 2.5568,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.79,
|
69 |
+
"grad_norm": 0.2711264193058014,
|
70 |
+
"learning_rate": 4.193203929064353e-05,
|
71 |
+
"loss": 2.4964,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.87,
|
76 |
+
"grad_norm": 0.29537662863731384,
|
77 |
+
"learning_rate": 4.0173447515678916e-05,
|
78 |
+
"loss": 2.5512,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.96,
|
83 |
+
"grad_norm": 0.28811562061309814,
|
84 |
+
"learning_rate": 3.82869098354114e-05,
|
85 |
+
"loss": 2.5155,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.05,
|
90 |
+
"grad_norm": 0.2557935118675232,
|
91 |
+
"learning_rate": 3.628833395777224e-05,
|
92 |
+
"loss": 2.5253,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.14,
|
97 |
+
"grad_norm": 0.243013396859169,
|
98 |
+
"learning_rate": 3.4194572321847336e-05,
|
99 |
+
"loss": 2.5395,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.22,
|
104 |
+
"grad_norm": 0.26634490489959717,
|
105 |
+
"learning_rate": 3.202327999433924e-05,
|
106 |
+
"loss": 2.4728,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.31,
|
111 |
+
"grad_norm": 0.288352906703949,
|
112 |
+
"learning_rate": 2.9792765798093465e-05,
|
113 |
+
"loss": 2.5059,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.4,
|
118 |
+
"grad_norm": 0.25032252073287964,
|
119 |
+
"learning_rate": 2.752183792800671e-05,
|
120 |
+
"loss": 2.5368,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.48,
|
125 |
+
"grad_norm": 0.24827222526073456,
|
126 |
+
"learning_rate": 2.5229645356118163e-05,
|
127 |
+
"loss": 2.4811,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.57,
|
132 |
+
"grad_norm": 0.2552015781402588,
|
133 |
+
"learning_rate": 2.2935516363191693e-05,
|
134 |
+
"loss": 2.5105,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.66,
|
139 |
+
"grad_norm": 0.2699149549007416,
|
140 |
+
"learning_rate": 2.0658795558326743e-05,
|
141 |
+
"loss": 2.5252,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.75,
|
146 |
+
"grad_norm": 0.2718549966812134,
|
147 |
+
"learning_rate": 1.8418680760885027e-05,
|
148 |
+
"loss": 2.4448,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.83,
|
153 |
+
"grad_norm": 0.2571737468242645,
|
154 |
+
"learning_rate": 1.6234061120181142e-05,
|
155 |
+
"loss": 2.438,
|
156 |
+
"step": 105
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.92,
|
160 |
+
"grad_norm": 0.25729846954345703,
|
161 |
+
"learning_rate": 1.4123357837948175e-05,
|
162 |
+
"loss": 2.49,
|
163 |
+
"step": 110
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 2.01,
|
167 |
+
"grad_norm": 0.29407253861427307,
|
168 |
+
"learning_rate": 1.2104368836641908e-05,
|
169 |
+
"loss": 2.4363,
|
170 |
+
"step": 115
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.1,
|
174 |
+
"grad_norm": 0.2614673376083374,
|
175 |
+
"learning_rate": 1.0194118683375503e-05,
|
176 |
+
"loss": 2.4613,
|
177 |
+
"step": 120
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2.18,
|
181 |
+
"grad_norm": 0.24367694556713104,
|
182 |
+
"learning_rate": 8.40871503495947e-06,
|
183 |
+
"loss": 2.4758,
|
184 |
+
"step": 125
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.27,
|
188 |
+
"grad_norm": 0.26960763335227966,
|
189 |
+
"learning_rate": 6.763212814534484e-06,
|
190 |
+
"loss": 2.4591,
|
191 |
+
"step": 130
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.36,
|
195 |
+
"grad_norm": 0.24732153117656708,
|
196 |
+
"learning_rate": 5.271487265090163e-06,
|
197 |
+
"loss": 2.4655,
|
198 |
+
"step": 135
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.45,
|
202 |
+
"grad_norm": 0.2650165855884552,
|
203 |
+
"learning_rate": 3.94611695031086e-06,
|
204 |
+
"loss": 2.4813,
|
205 |
+
"step": 140
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.53,
|
209 |
+
"grad_norm": 0.26127758622169495,
|
210 |
+
"learning_rate": 2.7982776893115627e-06,
|
211 |
+
"loss": 2.4453,
|
212 |
+
"step": 145
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.62,
|
216 |
+
"grad_norm": 0.2666429877281189,
|
217 |
+
"learning_rate": 1.837648319629956e-06,
|
218 |
+
"loss": 2.4941,
|
219 |
+
"step": 150
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.71,
|
223 |
+
"grad_norm": 0.25974979996681213,
|
224 |
+
"learning_rate": 1.0723290831021471e-06,
|
225 |
+
"loss": 2.4701,
|
226 |
+
"step": 155
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.79,
|
230 |
+
"grad_norm": 0.2709636092185974,
|
231 |
+
"learning_rate": 5.087733228106517e-07,
|
232 |
+
"loss": 2.4543,
|
233 |
+
"step": 160
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.88,
|
237 |
+
"grad_norm": 0.24128825962543488,
|
238 |
+
"learning_rate": 1.517330670512629e-07,
|
239 |
+
"loss": 2.5142,
|
240 |
+
"step": 165
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.97,
|
244 |
+
"grad_norm": 0.26422107219696045,
|
245 |
+
"learning_rate": 4.218959166932268e-09,
|
246 |
+
"loss": 2.4938,
|
247 |
+
"step": 170
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.99,
|
251 |
+
"step": 171,
|
252 |
+
"total_flos": 2.565405626125517e+16,
|
253 |
+
"train_loss": 2.5343901483636153,
|
254 |
+
"train_runtime": 1859.0377,
|
255 |
+
"train_samples_per_second": 1.477,
|
256 |
+
"train_steps_per_second": 0.092
|
257 |
+
}
|
258 |
+
],
|
259 |
+
"logging_steps": 5,
|
260 |
+
"max_steps": 171,
|
261 |
+
"num_input_tokens_seen": 0,
|
262 |
+
"num_train_epochs": 3,
|
263 |
+
"save_steps": 100,
|
264 |
+
"total_flos": 2.565405626125517e+16,
|
265 |
+
"train_batch_size": 2,
|
266 |
+
"trial_name": null,
|
267 |
+
"trial_params": null
|
268 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d328013ce840d512bfda18c4318f213b0268f9ce834a68420ca42557bbe0c0a8
|
3 |
+
size 5112
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|