Adding checkpoint-1400
Browse files- README.md +202 -0
- adapter_config.json +43 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- trainer_state.json +252 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: llava-hf/llava-1.5-7b-hf
|
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 0.11.1
|
adapter_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlavaForConditionalGeneration",
|
5 |
+
"parent_library": "transformers.models.llava.modeling_llava"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
+
"lora_dropout": 0.0,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 64,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"fc1",
|
27 |
+
"o_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_proj",
|
30 |
+
"v_proj",
|
31 |
+
"linear_1",
|
32 |
+
"linear_2",
|
33 |
+
"down_proj",
|
34 |
+
"fc2",
|
35 |
+
"up_proj",
|
36 |
+
"out_proj",
|
37 |
+
"lm_head",
|
38 |
+
"gate_proj"
|
39 |
+
],
|
40 |
+
"task_type": null,
|
41 |
+
"use_dora": false,
|
42 |
+
"use_rslora": false
|
43 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f6bf990dae510db8cc5a17fadcdf064f64d6c3390d4e3b529e683e11fbadbcc
|
3 |
+
size 1290994752
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:011c78853f7a913e1e497f203d1ea072c33a3041ba09ad875d09b9ba1ee57caa
|
3 |
+
size 1304976932
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc1cf56ce761ebab86f7df792d3a7d8b83237a2da76cf63dd0d935a7df8b4a3f
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da74d39e496cbc025182a0edf86ff5273273157ae4111643bd1e629f825ea149
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"32000": {
|
30 |
+
"content": "<image>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<pad>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"bos_token": "<s>",
|
47 |
+
"clean_up_tokenization_spaces": false,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"legacy": false,
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"pad_token": "<pad>",
|
52 |
+
"padding_side": "left",
|
53 |
+
"processor_class": "LlavaProcessor",
|
54 |
+
"sp_model_kwargs": {},
|
55 |
+
"tokenizer_class": "LlamaTokenizer",
|
56 |
+
"trust_remote_code": false,
|
57 |
+
"unk_token": "<unk>",
|
58 |
+
"use_default_system_prompt": false
|
59 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,252 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 4.576775972964242e-05,
|
3 |
+
"best_model_checkpoint": "llava-1.5-7b-sroie/checkpoint-1400",
|
4 |
+
"epoch": 11.2,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 1400,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.8,
|
13 |
+
"grad_norm": 0.2929452955722809,
|
14 |
+
"learning_rate": 1.3776e-05,
|
15 |
+
"loss": 0.572,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.8,
|
20 |
+
"eval_loss": 0.03328470513224602,
|
21 |
+
"eval_runtime": 60.4001,
|
22 |
+
"eval_samples_per_second": 2.086,
|
23 |
+
"eval_steps_per_second": 2.086,
|
24 |
+
"step": 100
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.6,
|
28 |
+
"grad_norm": 0.01092437468469143,
|
29 |
+
"learning_rate": 1.3552e-05,
|
30 |
+
"loss": 0.0046,
|
31 |
+
"step": 200
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 1.6,
|
35 |
+
"eval_loss": 0.0008874661289155483,
|
36 |
+
"eval_runtime": 61.352,
|
37 |
+
"eval_samples_per_second": 2.054,
|
38 |
+
"eval_steps_per_second": 2.054,
|
39 |
+
"step": 200
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.4,
|
43 |
+
"grad_norm": 0.005791354924440384,
|
44 |
+
"learning_rate": 1.3327999999999998e-05,
|
45 |
+
"loss": 0.0007,
|
46 |
+
"step": 300
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 2.4,
|
50 |
+
"eval_loss": 0.0004409343237057328,
|
51 |
+
"eval_runtime": 61.1557,
|
52 |
+
"eval_samples_per_second": 2.06,
|
53 |
+
"eval_steps_per_second": 2.06,
|
54 |
+
"step": 300
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.2,
|
58 |
+
"grad_norm": 0.002793485065922141,
|
59 |
+
"learning_rate": 1.3104e-05,
|
60 |
+
"loss": 0.0004,
|
61 |
+
"step": 400
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 3.2,
|
65 |
+
"eval_loss": 0.00029093530611135066,
|
66 |
+
"eval_runtime": 60.6893,
|
67 |
+
"eval_samples_per_second": 2.076,
|
68 |
+
"eval_steps_per_second": 2.076,
|
69 |
+
"step": 400
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.0,
|
73 |
+
"grad_norm": 0.0015204106457531452,
|
74 |
+
"learning_rate": 1.288e-05,
|
75 |
+
"loss": 0.0002,
|
76 |
+
"step": 500
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.0,
|
80 |
+
"eval_loss": 0.0002039903192780912,
|
81 |
+
"eval_runtime": 61.3698,
|
82 |
+
"eval_samples_per_second": 2.053,
|
83 |
+
"eval_steps_per_second": 2.053,
|
84 |
+
"step": 500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 4.8,
|
88 |
+
"grad_norm": 0.0009014272363856435,
|
89 |
+
"learning_rate": 1.2656e-05,
|
90 |
+
"loss": 0.0002,
|
91 |
+
"step": 600
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 4.8,
|
95 |
+
"eval_loss": 0.00016169117589015514,
|
96 |
+
"eval_runtime": 60.6043,
|
97 |
+
"eval_samples_per_second": 2.079,
|
98 |
+
"eval_steps_per_second": 2.079,
|
99 |
+
"step": 600
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 5.6,
|
103 |
+
"grad_norm": 0.0006670297589153051,
|
104 |
+
"learning_rate": 1.2432e-05,
|
105 |
+
"loss": 0.0001,
|
106 |
+
"step": 700
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 5.6,
|
110 |
+
"eval_loss": 0.0001274394162464887,
|
111 |
+
"eval_runtime": 60.5564,
|
112 |
+
"eval_samples_per_second": 2.081,
|
113 |
+
"eval_steps_per_second": 2.081,
|
114 |
+
"step": 700
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 6.4,
|
118 |
+
"grad_norm": 0.00041761380271054804,
|
119 |
+
"learning_rate": 1.2207999999999999e-05,
|
120 |
+
"loss": 0.0001,
|
121 |
+
"step": 800
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 6.4,
|
125 |
+
"eval_loss": 0.000104410013591405,
|
126 |
+
"eval_runtime": 60.3212,
|
127 |
+
"eval_samples_per_second": 2.089,
|
128 |
+
"eval_steps_per_second": 2.089,
|
129 |
+
"step": 800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 7.2,
|
133 |
+
"grad_norm": 0.0005114951636642218,
|
134 |
+
"learning_rate": 1.1983999999999999e-05,
|
135 |
+
"loss": 0.0001,
|
136 |
+
"step": 900
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 7.2,
|
140 |
+
"eval_loss": 8.86739362613298e-05,
|
141 |
+
"eval_runtime": 60.7862,
|
142 |
+
"eval_samples_per_second": 2.073,
|
143 |
+
"eval_steps_per_second": 2.073,
|
144 |
+
"step": 900
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 8.0,
|
148 |
+
"grad_norm": 0.00042668674723245203,
|
149 |
+
"learning_rate": 1.176e-05,
|
150 |
+
"loss": 0.0001,
|
151 |
+
"step": 1000
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 8.0,
|
155 |
+
"eval_loss": 7.54967040847987e-05,
|
156 |
+
"eval_runtime": 60.5531,
|
157 |
+
"eval_samples_per_second": 2.081,
|
158 |
+
"eval_steps_per_second": 2.081,
|
159 |
+
"step": 1000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 8.8,
|
163 |
+
"grad_norm": 0.0005093810614198446,
|
164 |
+
"learning_rate": 1.1536e-05,
|
165 |
+
"loss": 0.0001,
|
166 |
+
"step": 1100
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 8.8,
|
170 |
+
"eval_loss": 6.56623815302737e-05,
|
171 |
+
"eval_runtime": 60.7572,
|
172 |
+
"eval_samples_per_second": 2.074,
|
173 |
+
"eval_steps_per_second": 2.074,
|
174 |
+
"step": 1100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 9.6,
|
178 |
+
"grad_norm": 0.00028865510830655694,
|
179 |
+
"learning_rate": 1.1312000000000001e-05,
|
180 |
+
"loss": 0.0001,
|
181 |
+
"step": 1200
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 9.6,
|
185 |
+
"eval_loss": 5.7752622524276376e-05,
|
186 |
+
"eval_runtime": 61.9729,
|
187 |
+
"eval_samples_per_second": 2.033,
|
188 |
+
"eval_steps_per_second": 2.033,
|
189 |
+
"step": 1200
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 10.4,
|
193 |
+
"grad_norm": 0.00028205872513353825,
|
194 |
+
"learning_rate": 1.1088e-05,
|
195 |
+
"loss": 0.0001,
|
196 |
+
"step": 1300
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 10.4,
|
200 |
+
"eval_loss": 5.1226033974671736e-05,
|
201 |
+
"eval_runtime": 60.9193,
|
202 |
+
"eval_samples_per_second": 2.068,
|
203 |
+
"eval_steps_per_second": 2.068,
|
204 |
+
"step": 1300
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 11.2,
|
208 |
+
"grad_norm": 0.00026295348652638495,
|
209 |
+
"learning_rate": 1.0864e-05,
|
210 |
+
"loss": 0.0,
|
211 |
+
"step": 1400
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 11.2,
|
215 |
+
"eval_loss": 4.576775972964242e-05,
|
216 |
+
"eval_runtime": 61.4909,
|
217 |
+
"eval_samples_per_second": 2.049,
|
218 |
+
"eval_steps_per_second": 2.049,
|
219 |
+
"step": 1400
|
220 |
+
}
|
221 |
+
],
|
222 |
+
"logging_steps": 100,
|
223 |
+
"max_steps": 6250,
|
224 |
+
"num_input_tokens_seen": 0,
|
225 |
+
"num_train_epochs": 50,
|
226 |
+
"save_steps": 100,
|
227 |
+
"stateful_callbacks": {
|
228 |
+
"EarlyStoppingCallback": {
|
229 |
+
"args": {
|
230 |
+
"early_stopping_patience": 3,
|
231 |
+
"early_stopping_threshold": 0.0
|
232 |
+
},
|
233 |
+
"attributes": {
|
234 |
+
"early_stopping_patience_counter": 0
|
235 |
+
}
|
236 |
+
},
|
237 |
+
"TrainerControl": {
|
238 |
+
"args": {
|
239 |
+
"should_epoch_stop": false,
|
240 |
+
"should_evaluate": false,
|
241 |
+
"should_log": false,
|
242 |
+
"should_save": true,
|
243 |
+
"should_training_stop": false
|
244 |
+
},
|
245 |
+
"attributes": {}
|
246 |
+
}
|
247 |
+
},
|
248 |
+
"total_flos": 5.025909547008e+16,
|
249 |
+
"train_batch_size": 4,
|
250 |
+
"trial_name": null,
|
251 |
+
"trial_params": null
|
252 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19a104b948ba459fd24d29f8107bfdbf7b70e67be1fbd4d34752e6a54fc81bb6
|
3 |
+
size 5112
|