Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +16 -0
- chat_template.json +3 -0
- checkpoint-3694/README.md +202 -0
- checkpoint-3694/adapter_config.json +26 -0
- checkpoint-3694/adapter_model.safetensors +3 -0
- checkpoint-3694/optimizer.pt +3 -0
- checkpoint-3694/rng_state.pth +3 -0
- checkpoint-3694/scheduler.pt +3 -0
- checkpoint-3694/trainer_state.json +2904 -0
- checkpoint-3694/training_args.bin +3 -0
- git_hash.txt +1 -0
- merges.txt +0 -0
- preprocessor_config.json +29 -0
- results.json +1 -0
- special_tokens_map.json +31 -0
- tokenizer.json +0 -0
- tokenizer_config.json +144 -0
- training_config.yml +43 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: vidore/colqwen2-base
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "vidore/colqwen2-base",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": "gaussian",
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
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": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
23 |
+
"task_type": "FEATURE_EXTRACTION",
|
24 |
+
"use_dora": false,
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f26000fd1fbd64be94a32e99012afde7b375f8342bb54b7a7dd0c1dd0d57066
|
3 |
+
size 74018232
|
added_tokens.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|box_end|>": 151649,
|
3 |
+
"<|box_start|>": 151648,
|
4 |
+
"<|endoftext|>": 151643,
|
5 |
+
"<|im_end|>": 151645,
|
6 |
+
"<|im_start|>": 151644,
|
7 |
+
"<|image_pad|>": 151655,
|
8 |
+
"<|object_ref_end|>": 151647,
|
9 |
+
"<|object_ref_start|>": 151646,
|
10 |
+
"<|quad_end|>": 151651,
|
11 |
+
"<|quad_start|>": 151650,
|
12 |
+
"<|video_pad|>": 151656,
|
13 |
+
"<|vision_end|>": 151653,
|
14 |
+
"<|vision_pad|>": 151654,
|
15 |
+
"<|vision_start|>": 151652
|
16 |
+
}
|
chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
3 |
+
}
|
checkpoint-3694/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: ./models/colqwen2_base
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
checkpoint-3694/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "./models/colqwen2_base",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": "gaussian",
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
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": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
23 |
+
"task_type": "FEATURE_EXTRACTION",
|
24 |
+
"use_dora": false,
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
checkpoint-3694/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f26000fd1fbd64be94a32e99012afde7b375f8342bb54b7a7dd0c1dd0d57066
|
3 |
+
size 74018232
|
checkpoint-3694/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94dfe0075ec4f21387ac18e77c648bfc5db314e088bdcdb8d4fdf6e30532496b
|
3 |
+
size 148262384
|
checkpoint-3694/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75e9665951c5d547a5de8ed05c5981901bf7eeb728786a0acc4cf999aa58e092
|
3 |
+
size 14244
|
checkpoint-3694/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0c4c047aa3abb1bc366c2fb0e6a4fd601029da0338c37929023a3ff5f04bef3
|
3 |
+
size 1064
|
checkpoint-3694/trainer_state.json
ADDED
@@ -0,0 +1,2904 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 3694,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0027070925825663237,
|
13 |
+
"grad_norm": 5.65625,
|
14 |
+
"learning_rate": 1.0000000000000002e-06,
|
15 |
+
"loss": 0.7343,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.005414185165132647,
|
20 |
+
"grad_norm": 8.9375,
|
21 |
+
"learning_rate": 2.0000000000000003e-06,
|
22 |
+
"loss": 0.864,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.008121277747698972,
|
27 |
+
"grad_norm": 9.0625,
|
28 |
+
"learning_rate": 3e-06,
|
29 |
+
"loss": 0.7618,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.010828370330265295,
|
34 |
+
"grad_norm": 7.375,
|
35 |
+
"learning_rate": 4.000000000000001e-06,
|
36 |
+
"loss": 0.749,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.01353546291283162,
|
41 |
+
"grad_norm": 5.4375,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 0.7434,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.016242555495397944,
|
48 |
+
"grad_norm": 5.34375,
|
49 |
+
"learning_rate": 6e-06,
|
50 |
+
"loss": 0.7079,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.018949648077964266,
|
55 |
+
"grad_norm": 4.25,
|
56 |
+
"learning_rate": 7.000000000000001e-06,
|
57 |
+
"loss": 0.7368,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.02165674066053059,
|
62 |
+
"grad_norm": 3.828125,
|
63 |
+
"learning_rate": 8.000000000000001e-06,
|
64 |
+
"loss": 0.682,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.024363833243096916,
|
69 |
+
"grad_norm": 2.875,
|
70 |
+
"learning_rate": 9e-06,
|
71 |
+
"loss": 0.6489,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.02707092582566324,
|
76 |
+
"grad_norm": 2.453125,
|
77 |
+
"learning_rate": 1e-05,
|
78 |
+
"loss": 0.589,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.02707092582566324,
|
83 |
+
"eval_loss": 0.6064066290855408,
|
84 |
+
"eval_runtime": 155.4734,
|
85 |
+
"eval_samples_per_second": 3.293,
|
86 |
+
"eval_steps_per_second": 0.103,
|
87 |
+
"step": 100
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.02977801840822956,
|
91 |
+
"grad_norm": 2.1875,
|
92 |
+
"learning_rate": 1.1000000000000001e-05,
|
93 |
+
"loss": 0.5723,
|
94 |
+
"step": 110
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.03248511099079589,
|
98 |
+
"grad_norm": 3.640625,
|
99 |
+
"learning_rate": 1.2e-05,
|
100 |
+
"loss": 0.5525,
|
101 |
+
"step": 120
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.03519220357336221,
|
105 |
+
"grad_norm": 2.34375,
|
106 |
+
"learning_rate": 1.3000000000000001e-05,
|
107 |
+
"loss": 0.5503,
|
108 |
+
"step": 130
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.03789929615592853,
|
112 |
+
"grad_norm": 2.3125,
|
113 |
+
"learning_rate": 1.4000000000000001e-05,
|
114 |
+
"loss": 0.4926,
|
115 |
+
"step": 140
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.040606388738494856,
|
119 |
+
"grad_norm": 2.578125,
|
120 |
+
"learning_rate": 1.5e-05,
|
121 |
+
"loss": 0.4831,
|
122 |
+
"step": 150
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.04331348132106118,
|
126 |
+
"grad_norm": 2.109375,
|
127 |
+
"learning_rate": 1.6000000000000003e-05,
|
128 |
+
"loss": 0.4413,
|
129 |
+
"step": 160
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.0460205739036275,
|
133 |
+
"grad_norm": 2.671875,
|
134 |
+
"learning_rate": 1.7000000000000003e-05,
|
135 |
+
"loss": 0.4562,
|
136 |
+
"step": 170
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.04872766648619383,
|
140 |
+
"grad_norm": 2.203125,
|
141 |
+
"learning_rate": 1.8e-05,
|
142 |
+
"loss": 0.4348,
|
143 |
+
"step": 180
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.051434759068760154,
|
147 |
+
"grad_norm": 2.015625,
|
148 |
+
"learning_rate": 1.9e-05,
|
149 |
+
"loss": 0.4386,
|
150 |
+
"step": 190
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.05414185165132648,
|
154 |
+
"grad_norm": 2.09375,
|
155 |
+
"learning_rate": 2e-05,
|
156 |
+
"loss": 0.4009,
|
157 |
+
"step": 200
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.05414185165132648,
|
161 |
+
"eval_loss": 0.4071368873119354,
|
162 |
+
"eval_runtime": 104.5667,
|
163 |
+
"eval_samples_per_second": 4.896,
|
164 |
+
"eval_steps_per_second": 0.153,
|
165 |
+
"step": 200
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.0568489442338928,
|
169 |
+
"grad_norm": 2.25,
|
170 |
+
"learning_rate": 2.1e-05,
|
171 |
+
"loss": 0.4026,
|
172 |
+
"step": 210
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.05955603681645912,
|
176 |
+
"grad_norm": 1.90625,
|
177 |
+
"learning_rate": 2.2000000000000003e-05,
|
178 |
+
"loss": 0.3774,
|
179 |
+
"step": 220
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.062263129399025445,
|
183 |
+
"grad_norm": 1.8828125,
|
184 |
+
"learning_rate": 2.3000000000000003e-05,
|
185 |
+
"loss": 0.3734,
|
186 |
+
"step": 230
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.06497022198159177,
|
190 |
+
"grad_norm": 1.5703125,
|
191 |
+
"learning_rate": 2.4e-05,
|
192 |
+
"loss": 0.331,
|
193 |
+
"step": 240
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.0676773145641581,
|
197 |
+
"grad_norm": 1.671875,
|
198 |
+
"learning_rate": 2.5e-05,
|
199 |
+
"loss": 0.3381,
|
200 |
+
"step": 250
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.07038440714672442,
|
204 |
+
"grad_norm": 1.8515625,
|
205 |
+
"learning_rate": 2.6000000000000002e-05,
|
206 |
+
"loss": 0.3392,
|
207 |
+
"step": 260
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.07309149972929074,
|
211 |
+
"grad_norm": 1.625,
|
212 |
+
"learning_rate": 2.7000000000000002e-05,
|
213 |
+
"loss": 0.3165,
|
214 |
+
"step": 270
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.07579859231185707,
|
218 |
+
"grad_norm": 1.671875,
|
219 |
+
"learning_rate": 2.8000000000000003e-05,
|
220 |
+
"loss": 0.3162,
|
221 |
+
"step": 280
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.07850568489442339,
|
225 |
+
"grad_norm": 1.953125,
|
226 |
+
"learning_rate": 2.9e-05,
|
227 |
+
"loss": 0.2844,
|
228 |
+
"step": 290
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.08121277747698971,
|
232 |
+
"grad_norm": 2.28125,
|
233 |
+
"learning_rate": 3e-05,
|
234 |
+
"loss": 0.3093,
|
235 |
+
"step": 300
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.08121277747698971,
|
239 |
+
"eval_loss": 0.2839646637439728,
|
240 |
+
"eval_runtime": 103.4698,
|
241 |
+
"eval_samples_per_second": 4.948,
|
242 |
+
"eval_steps_per_second": 0.155,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.08391987005955603,
|
247 |
+
"grad_norm": 1.4296875,
|
248 |
+
"learning_rate": 3.1e-05,
|
249 |
+
"loss": 0.2753,
|
250 |
+
"step": 310
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.08662696264212236,
|
254 |
+
"grad_norm": 1.4609375,
|
255 |
+
"learning_rate": 3.2000000000000005e-05,
|
256 |
+
"loss": 0.2625,
|
257 |
+
"step": 320
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.08933405522468868,
|
261 |
+
"grad_norm": 1.5390625,
|
262 |
+
"learning_rate": 3.3e-05,
|
263 |
+
"loss": 0.2525,
|
264 |
+
"step": 330
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.092041147807255,
|
268 |
+
"grad_norm": 1.9453125,
|
269 |
+
"learning_rate": 3.4000000000000007e-05,
|
270 |
+
"loss": 0.2897,
|
271 |
+
"step": 340
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.09474824038982133,
|
275 |
+
"grad_norm": 1.4453125,
|
276 |
+
"learning_rate": 3.5e-05,
|
277 |
+
"loss": 0.243,
|
278 |
+
"step": 350
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.09745533297238766,
|
282 |
+
"grad_norm": 1.6484375,
|
283 |
+
"learning_rate": 3.6e-05,
|
284 |
+
"loss": 0.2442,
|
285 |
+
"step": 360
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.10016242555495398,
|
289 |
+
"grad_norm": 1.15625,
|
290 |
+
"learning_rate": 3.7e-05,
|
291 |
+
"loss": 0.2139,
|
292 |
+
"step": 370
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.10286951813752031,
|
296 |
+
"grad_norm": 1.3203125,
|
297 |
+
"learning_rate": 3.8e-05,
|
298 |
+
"loss": 0.2312,
|
299 |
+
"step": 380
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.10557661072008663,
|
303 |
+
"grad_norm": 2.703125,
|
304 |
+
"learning_rate": 3.9000000000000006e-05,
|
305 |
+
"loss": 0.2202,
|
306 |
+
"step": 390
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.10828370330265295,
|
310 |
+
"grad_norm": 1.078125,
|
311 |
+
"learning_rate": 4e-05,
|
312 |
+
"loss": 0.2115,
|
313 |
+
"step": 400
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.10828370330265295,
|
317 |
+
"eval_loss": 0.23121848702430725,
|
318 |
+
"eval_runtime": 134.1955,
|
319 |
+
"eval_samples_per_second": 3.815,
|
320 |
+
"eval_steps_per_second": 0.119,
|
321 |
+
"step": 400
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.11099079588521928,
|
325 |
+
"grad_norm": 1.828125,
|
326 |
+
"learning_rate": 4.1e-05,
|
327 |
+
"loss": 0.1976,
|
328 |
+
"step": 410
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.1136978884677856,
|
332 |
+
"grad_norm": 1.0546875,
|
333 |
+
"learning_rate": 4.2e-05,
|
334 |
+
"loss": 0.2182,
|
335 |
+
"step": 420
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.11640498105035192,
|
339 |
+
"grad_norm": 1.1015625,
|
340 |
+
"learning_rate": 4.3e-05,
|
341 |
+
"loss": 0.1767,
|
342 |
+
"step": 430
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.11911207363291824,
|
346 |
+
"grad_norm": 3.078125,
|
347 |
+
"learning_rate": 4.4000000000000006e-05,
|
348 |
+
"loss": 0.2058,
|
349 |
+
"step": 440
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.12181916621548457,
|
353 |
+
"grad_norm": 2.25,
|
354 |
+
"learning_rate": 4.5e-05,
|
355 |
+
"loss": 0.168,
|
356 |
+
"step": 450
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.12452625879805089,
|
360 |
+
"grad_norm": 2.5625,
|
361 |
+
"learning_rate": 4.600000000000001e-05,
|
362 |
+
"loss": 0.1728,
|
363 |
+
"step": 460
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.12723335138061723,
|
367 |
+
"grad_norm": 2.109375,
|
368 |
+
"learning_rate": 4.7e-05,
|
369 |
+
"loss": 0.1927,
|
370 |
+
"step": 470
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 0.12994044396318355,
|
374 |
+
"grad_norm": 2.140625,
|
375 |
+
"learning_rate": 4.8e-05,
|
376 |
+
"loss": 0.1433,
|
377 |
+
"step": 480
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.13264753654574987,
|
381 |
+
"grad_norm": 1.6640625,
|
382 |
+
"learning_rate": 4.9e-05,
|
383 |
+
"loss": 0.1728,
|
384 |
+
"step": 490
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.1353546291283162,
|
388 |
+
"grad_norm": 2.4375,
|
389 |
+
"learning_rate": 5e-05,
|
390 |
+
"loss": 0.176,
|
391 |
+
"step": 500
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.1353546291283162,
|
395 |
+
"eval_loss": 0.19780531525611877,
|
396 |
+
"eval_runtime": 102.6349,
|
397 |
+
"eval_samples_per_second": 4.989,
|
398 |
+
"eval_steps_per_second": 0.156,
|
399 |
+
"step": 500
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.13806172171088252,
|
403 |
+
"grad_norm": 1.8984375,
|
404 |
+
"learning_rate": 4.984345648090169e-05,
|
405 |
+
"loss": 0.1639,
|
406 |
+
"step": 510
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 0.14076881429344884,
|
410 |
+
"grad_norm": 1.5078125,
|
411 |
+
"learning_rate": 4.9686912961803384e-05,
|
412 |
+
"loss": 0.1598,
|
413 |
+
"step": 520
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.14347590687601516,
|
417 |
+
"grad_norm": 5.625,
|
418 |
+
"learning_rate": 4.9530369442705075e-05,
|
419 |
+
"loss": 0.17,
|
420 |
+
"step": 530
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 0.1461829994585815,
|
424 |
+
"grad_norm": 2.390625,
|
425 |
+
"learning_rate": 4.9373825923606765e-05,
|
426 |
+
"loss": 0.1601,
|
427 |
+
"step": 540
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.1488900920411478,
|
431 |
+
"grad_norm": 2.28125,
|
432 |
+
"learning_rate": 4.9217282404508456e-05,
|
433 |
+
"loss": 0.2067,
|
434 |
+
"step": 550
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.15159718462371413,
|
438 |
+
"grad_norm": 1.296875,
|
439 |
+
"learning_rate": 4.906073888541015e-05,
|
440 |
+
"loss": 0.1396,
|
441 |
+
"step": 560
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.15430427720628045,
|
445 |
+
"grad_norm": 2.3125,
|
446 |
+
"learning_rate": 4.890419536631184e-05,
|
447 |
+
"loss": 0.1379,
|
448 |
+
"step": 570
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 0.15701136978884678,
|
452 |
+
"grad_norm": 1.984375,
|
453 |
+
"learning_rate": 4.874765184721353e-05,
|
454 |
+
"loss": 0.1722,
|
455 |
+
"step": 580
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.1597184623714131,
|
459 |
+
"grad_norm": 2.796875,
|
460 |
+
"learning_rate": 4.859110832811522e-05,
|
461 |
+
"loss": 0.1608,
|
462 |
+
"step": 590
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 0.16242555495397942,
|
466 |
+
"grad_norm": 2.4375,
|
467 |
+
"learning_rate": 4.843456480901691e-05,
|
468 |
+
"loss": 0.1576,
|
469 |
+
"step": 600
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 0.16242555495397942,
|
473 |
+
"eval_loss": 0.1739654242992401,
|
474 |
+
"eval_runtime": 102.4755,
|
475 |
+
"eval_samples_per_second": 4.996,
|
476 |
+
"eval_steps_per_second": 0.156,
|
477 |
+
"step": 600
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.16513264753654575,
|
481 |
+
"grad_norm": 1.78125,
|
482 |
+
"learning_rate": 4.82780212899186e-05,
|
483 |
+
"loss": 0.1292,
|
484 |
+
"step": 610
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.16783974011911207,
|
488 |
+
"grad_norm": 2.296875,
|
489 |
+
"learning_rate": 4.812147777082029e-05,
|
490 |
+
"loss": 0.1421,
|
491 |
+
"step": 620
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.1705468327016784,
|
495 |
+
"grad_norm": 3.53125,
|
496 |
+
"learning_rate": 4.796493425172198e-05,
|
497 |
+
"loss": 0.1473,
|
498 |
+
"step": 630
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 0.17325392528424471,
|
502 |
+
"grad_norm": 1.6015625,
|
503 |
+
"learning_rate": 4.780839073262367e-05,
|
504 |
+
"loss": 0.1313,
|
505 |
+
"step": 640
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 0.17596101786681104,
|
509 |
+
"grad_norm": 2.75,
|
510 |
+
"learning_rate": 4.765184721352536e-05,
|
511 |
+
"loss": 0.0987,
|
512 |
+
"step": 650
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.17866811044937736,
|
516 |
+
"grad_norm": 2.453125,
|
517 |
+
"learning_rate": 4.7495303694427054e-05,
|
518 |
+
"loss": 0.1301,
|
519 |
+
"step": 660
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.18137520303194368,
|
523 |
+
"grad_norm": 1.203125,
|
524 |
+
"learning_rate": 4.7338760175328744e-05,
|
525 |
+
"loss": 0.118,
|
526 |
+
"step": 670
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.18408229561451,
|
530 |
+
"grad_norm": 2.703125,
|
531 |
+
"learning_rate": 4.7182216656230435e-05,
|
532 |
+
"loss": 0.1384,
|
533 |
+
"step": 680
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.18678938819707633,
|
537 |
+
"grad_norm": 0.78515625,
|
538 |
+
"learning_rate": 4.7025673137132126e-05,
|
539 |
+
"loss": 0.0855,
|
540 |
+
"step": 690
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 0.18949648077964265,
|
544 |
+
"grad_norm": 2.34375,
|
545 |
+
"learning_rate": 4.6869129618033816e-05,
|
546 |
+
"loss": 0.148,
|
547 |
+
"step": 700
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 0.18949648077964265,
|
551 |
+
"eval_loss": 0.1687919795513153,
|
552 |
+
"eval_runtime": 102.502,
|
553 |
+
"eval_samples_per_second": 4.995,
|
554 |
+
"eval_steps_per_second": 0.156,
|
555 |
+
"step": 700
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.19220357336220897,
|
559 |
+
"grad_norm": 0.81640625,
|
560 |
+
"learning_rate": 4.671258609893551e-05,
|
561 |
+
"loss": 0.134,
|
562 |
+
"step": 710
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.19491066594477532,
|
566 |
+
"grad_norm": 1.3046875,
|
567 |
+
"learning_rate": 4.65560425798372e-05,
|
568 |
+
"loss": 0.1222,
|
569 |
+
"step": 720
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.19761775852734165,
|
573 |
+
"grad_norm": 2.5625,
|
574 |
+
"learning_rate": 4.639949906073889e-05,
|
575 |
+
"loss": 0.1511,
|
576 |
+
"step": 730
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.20032485110990797,
|
580 |
+
"grad_norm": 0.55078125,
|
581 |
+
"learning_rate": 4.624295554164057e-05,
|
582 |
+
"loss": 0.1661,
|
583 |
+
"step": 740
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.2030319436924743,
|
587 |
+
"grad_norm": 1.9140625,
|
588 |
+
"learning_rate": 4.608641202254227e-05,
|
589 |
+
"loss": 0.1381,
|
590 |
+
"step": 750
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.20573903627504062,
|
594 |
+
"grad_norm": 2.015625,
|
595 |
+
"learning_rate": 4.5929868503443954e-05,
|
596 |
+
"loss": 0.1499,
|
597 |
+
"step": 760
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.20844612885760694,
|
601 |
+
"grad_norm": 2.265625,
|
602 |
+
"learning_rate": 4.577332498434565e-05,
|
603 |
+
"loss": 0.1692,
|
604 |
+
"step": 770
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.21115322144017326,
|
608 |
+
"grad_norm": 2.40625,
|
609 |
+
"learning_rate": 4.561678146524734e-05,
|
610 |
+
"loss": 0.1226,
|
611 |
+
"step": 780
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.21386031402273958,
|
615 |
+
"grad_norm": 2.484375,
|
616 |
+
"learning_rate": 4.546023794614903e-05,
|
617 |
+
"loss": 0.1594,
|
618 |
+
"step": 790
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.2165674066053059,
|
622 |
+
"grad_norm": 0.76171875,
|
623 |
+
"learning_rate": 4.5303694427050724e-05,
|
624 |
+
"loss": 0.0962,
|
625 |
+
"step": 800
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.2165674066053059,
|
629 |
+
"eval_loss": 0.15033257007598877,
|
630 |
+
"eval_runtime": 102.8567,
|
631 |
+
"eval_samples_per_second": 4.978,
|
632 |
+
"eval_steps_per_second": 0.156,
|
633 |
+
"step": 800
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.21927449918787223,
|
637 |
+
"grad_norm": 1.4453125,
|
638 |
+
"learning_rate": 4.5147150907952414e-05,
|
639 |
+
"loss": 0.1581,
|
640 |
+
"step": 810
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.22198159177043855,
|
644 |
+
"grad_norm": 2.078125,
|
645 |
+
"learning_rate": 4.4990607388854105e-05,
|
646 |
+
"loss": 0.155,
|
647 |
+
"step": 820
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.22468868435300487,
|
651 |
+
"grad_norm": 0.921875,
|
652 |
+
"learning_rate": 4.4834063869755796e-05,
|
653 |
+
"loss": 0.1103,
|
654 |
+
"step": 830
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.2273957769355712,
|
658 |
+
"grad_norm": 0.90234375,
|
659 |
+
"learning_rate": 4.4677520350657486e-05,
|
660 |
+
"loss": 0.1323,
|
661 |
+
"step": 840
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.23010286951813752,
|
665 |
+
"grad_norm": 0.953125,
|
666 |
+
"learning_rate": 4.452097683155918e-05,
|
667 |
+
"loss": 0.1073,
|
668 |
+
"step": 850
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.23280996210070384,
|
672 |
+
"grad_norm": 0.69921875,
|
673 |
+
"learning_rate": 4.436443331246087e-05,
|
674 |
+
"loss": 0.1333,
|
675 |
+
"step": 860
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.23551705468327017,
|
679 |
+
"grad_norm": 4.34375,
|
680 |
+
"learning_rate": 4.420788979336256e-05,
|
681 |
+
"loss": 0.1429,
|
682 |
+
"step": 870
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.2382241472658365,
|
686 |
+
"grad_norm": 0.5859375,
|
687 |
+
"learning_rate": 4.405134627426425e-05,
|
688 |
+
"loss": 0.0988,
|
689 |
+
"step": 880
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.2409312398484028,
|
693 |
+
"grad_norm": 1.3046875,
|
694 |
+
"learning_rate": 4.389480275516594e-05,
|
695 |
+
"loss": 0.1184,
|
696 |
+
"step": 890
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.24363833243096913,
|
700 |
+
"grad_norm": 1.0234375,
|
701 |
+
"learning_rate": 4.373825923606763e-05,
|
702 |
+
"loss": 0.118,
|
703 |
+
"step": 900
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.24363833243096913,
|
707 |
+
"eval_loss": 0.14425741136074066,
|
708 |
+
"eval_runtime": 115.407,
|
709 |
+
"eval_samples_per_second": 4.436,
|
710 |
+
"eval_steps_per_second": 0.139,
|
711 |
+
"step": 900
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.24634542501353546,
|
715 |
+
"grad_norm": 1.34375,
|
716 |
+
"learning_rate": 4.358171571696932e-05,
|
717 |
+
"loss": 0.1032,
|
718 |
+
"step": 910
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.24905251759610178,
|
722 |
+
"grad_norm": 1.78125,
|
723 |
+
"learning_rate": 4.342517219787101e-05,
|
724 |
+
"loss": 0.1242,
|
725 |
+
"step": 920
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.2517596101786681,
|
729 |
+
"grad_norm": 1.296875,
|
730 |
+
"learning_rate": 4.3268628678772696e-05,
|
731 |
+
"loss": 0.131,
|
732 |
+
"step": 930
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.25446670276123445,
|
736 |
+
"grad_norm": 1.90625,
|
737 |
+
"learning_rate": 4.3112085159674393e-05,
|
738 |
+
"loss": 0.1058,
|
739 |
+
"step": 940
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.25717379534380075,
|
743 |
+
"grad_norm": 1.1015625,
|
744 |
+
"learning_rate": 4.295554164057608e-05,
|
745 |
+
"loss": 0.155,
|
746 |
+
"step": 950
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.2598808879263671,
|
750 |
+
"grad_norm": 1.2734375,
|
751 |
+
"learning_rate": 4.2798998121477775e-05,
|
752 |
+
"loss": 0.1103,
|
753 |
+
"step": 960
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.2625879805089334,
|
757 |
+
"grad_norm": 4.59375,
|
758 |
+
"learning_rate": 4.264245460237946e-05,
|
759 |
+
"loss": 0.1288,
|
760 |
+
"step": 970
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.26529507309149974,
|
764 |
+
"grad_norm": 0.90234375,
|
765 |
+
"learning_rate": 4.2485911083281156e-05,
|
766 |
+
"loss": 0.0967,
|
767 |
+
"step": 980
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.26800216567406604,
|
771 |
+
"grad_norm": 1.734375,
|
772 |
+
"learning_rate": 4.232936756418284e-05,
|
773 |
+
"loss": 0.1523,
|
774 |
+
"step": 990
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.2707092582566324,
|
778 |
+
"grad_norm": 2.90625,
|
779 |
+
"learning_rate": 4.217282404508454e-05,
|
780 |
+
"loss": 0.1364,
|
781 |
+
"step": 1000
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.2707092582566324,
|
785 |
+
"eval_loss": 0.14593610167503357,
|
786 |
+
"eval_runtime": 104.6862,
|
787 |
+
"eval_samples_per_second": 4.891,
|
788 |
+
"eval_steps_per_second": 0.153,
|
789 |
+
"step": 1000
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.2734163508391987,
|
793 |
+
"grad_norm": 2.125,
|
794 |
+
"learning_rate": 4.201628052598622e-05,
|
795 |
+
"loss": 0.1228,
|
796 |
+
"step": 1010
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 0.27612344342176504,
|
800 |
+
"grad_norm": 1.7265625,
|
801 |
+
"learning_rate": 4.185973700688792e-05,
|
802 |
+
"loss": 0.1114,
|
803 |
+
"step": 1020
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 0.27883053600433133,
|
807 |
+
"grad_norm": 1.0859375,
|
808 |
+
"learning_rate": 4.170319348778961e-05,
|
809 |
+
"loss": 0.1016,
|
810 |
+
"step": 1030
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.2815376285868977,
|
814 |
+
"grad_norm": 0.69921875,
|
815 |
+
"learning_rate": 4.15466499686913e-05,
|
816 |
+
"loss": 0.1023,
|
817 |
+
"step": 1040
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.284244721169464,
|
821 |
+
"grad_norm": 1.5859375,
|
822 |
+
"learning_rate": 4.139010644959299e-05,
|
823 |
+
"loss": 0.1097,
|
824 |
+
"step": 1050
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.2869518137520303,
|
828 |
+
"grad_norm": 0.5859375,
|
829 |
+
"learning_rate": 4.123356293049468e-05,
|
830 |
+
"loss": 0.1522,
|
831 |
+
"step": 1060
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.2896589063345966,
|
835 |
+
"grad_norm": 1.296875,
|
836 |
+
"learning_rate": 4.107701941139637e-05,
|
837 |
+
"loss": 0.1218,
|
838 |
+
"step": 1070
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 0.292365998917163,
|
842 |
+
"grad_norm": 1.9765625,
|
843 |
+
"learning_rate": 4.092047589229806e-05,
|
844 |
+
"loss": 0.1491,
|
845 |
+
"step": 1080
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 0.29507309149972927,
|
849 |
+
"grad_norm": 0.82421875,
|
850 |
+
"learning_rate": 4.0763932373199754e-05,
|
851 |
+
"loss": 0.1103,
|
852 |
+
"step": 1090
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 0.2977801840822956,
|
856 |
+
"grad_norm": 1.96875,
|
857 |
+
"learning_rate": 4.0607388854101445e-05,
|
858 |
+
"loss": 0.1419,
|
859 |
+
"step": 1100
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.2977801840822956,
|
863 |
+
"eval_loss": 0.14324142038822174,
|
864 |
+
"eval_runtime": 105.9997,
|
865 |
+
"eval_samples_per_second": 4.83,
|
866 |
+
"eval_steps_per_second": 0.151,
|
867 |
+
"step": 1100
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.3004872766648619,
|
871 |
+
"grad_norm": 0.8984375,
|
872 |
+
"learning_rate": 4.0450845335003135e-05,
|
873 |
+
"loss": 0.0784,
|
874 |
+
"step": 1110
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 0.30319436924742826,
|
878 |
+
"grad_norm": 0.9296875,
|
879 |
+
"learning_rate": 4.029430181590482e-05,
|
880 |
+
"loss": 0.0869,
|
881 |
+
"step": 1120
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 0.30590146182999456,
|
885 |
+
"grad_norm": 0.6015625,
|
886 |
+
"learning_rate": 4.013775829680652e-05,
|
887 |
+
"loss": 0.1135,
|
888 |
+
"step": 1130
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.3086085544125609,
|
892 |
+
"grad_norm": 1.4453125,
|
893 |
+
"learning_rate": 3.99812147777082e-05,
|
894 |
+
"loss": 0.1296,
|
895 |
+
"step": 1140
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.31131564699512726,
|
899 |
+
"grad_norm": 0.8203125,
|
900 |
+
"learning_rate": 3.98246712586099e-05,
|
901 |
+
"loss": 0.122,
|
902 |
+
"step": 1150
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.31402273957769355,
|
906 |
+
"grad_norm": 1.3203125,
|
907 |
+
"learning_rate": 3.966812773951158e-05,
|
908 |
+
"loss": 0.1102,
|
909 |
+
"step": 1160
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.3167298321602599,
|
913 |
+
"grad_norm": 0.98046875,
|
914 |
+
"learning_rate": 3.951158422041328e-05,
|
915 |
+
"loss": 0.1284,
|
916 |
+
"step": 1170
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.3194369247428262,
|
920 |
+
"grad_norm": 2.390625,
|
921 |
+
"learning_rate": 3.9355040701314964e-05,
|
922 |
+
"loss": 0.139,
|
923 |
+
"step": 1180
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 0.32214401732539255,
|
927 |
+
"grad_norm": 1.03125,
|
928 |
+
"learning_rate": 3.919849718221666e-05,
|
929 |
+
"loss": 0.1405,
|
930 |
+
"step": 1190
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.32485110990795885,
|
934 |
+
"grad_norm": 0.75390625,
|
935 |
+
"learning_rate": 3.9041953663118345e-05,
|
936 |
+
"loss": 0.1359,
|
937 |
+
"step": 1200
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 0.32485110990795885,
|
941 |
+
"eval_loss": 0.13801878690719604,
|
942 |
+
"eval_runtime": 105.4772,
|
943 |
+
"eval_samples_per_second": 4.854,
|
944 |
+
"eval_steps_per_second": 0.152,
|
945 |
+
"step": 1200
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.3275582024905252,
|
949 |
+
"grad_norm": 0.9609375,
|
950 |
+
"learning_rate": 3.888541014402004e-05,
|
951 |
+
"loss": 0.0934,
|
952 |
+
"step": 1210
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.3302652950730915,
|
956 |
+
"grad_norm": 1.9921875,
|
957 |
+
"learning_rate": 3.8728866624921726e-05,
|
958 |
+
"loss": 0.1272,
|
959 |
+
"step": 1220
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 0.33297238765565784,
|
963 |
+
"grad_norm": 2.734375,
|
964 |
+
"learning_rate": 3.8572323105823424e-05,
|
965 |
+
"loss": 0.1099,
|
966 |
+
"step": 1230
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 0.33567948023822414,
|
970 |
+
"grad_norm": 1.1171875,
|
971 |
+
"learning_rate": 3.841577958672511e-05,
|
972 |
+
"loss": 0.1019,
|
973 |
+
"step": 1240
|
974 |
+
},
|
975 |
+
{
|
976 |
+
"epoch": 0.3383865728207905,
|
977 |
+
"grad_norm": 1.1171875,
|
978 |
+
"learning_rate": 3.8259236067626805e-05,
|
979 |
+
"loss": 0.1503,
|
980 |
+
"step": 1250
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.3410936654033568,
|
984 |
+
"grad_norm": 0.490234375,
|
985 |
+
"learning_rate": 3.810269254852849e-05,
|
986 |
+
"loss": 0.0857,
|
987 |
+
"step": 1260
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.34380075798592313,
|
991 |
+
"grad_norm": 0.69140625,
|
992 |
+
"learning_rate": 3.794614902943019e-05,
|
993 |
+
"loss": 0.0949,
|
994 |
+
"step": 1270
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.34650785056848943,
|
998 |
+
"grad_norm": 2.015625,
|
999 |
+
"learning_rate": 3.778960551033187e-05,
|
1000 |
+
"loss": 0.1242,
|
1001 |
+
"step": 1280
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 0.3492149431510558,
|
1005 |
+
"grad_norm": 0.5546875,
|
1006 |
+
"learning_rate": 3.763306199123356e-05,
|
1007 |
+
"loss": 0.1041,
|
1008 |
+
"step": 1290
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 0.3519220357336221,
|
1012 |
+
"grad_norm": 1.5234375,
|
1013 |
+
"learning_rate": 3.747651847213526e-05,
|
1014 |
+
"loss": 0.0727,
|
1015 |
+
"step": 1300
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 0.3519220357336221,
|
1019 |
+
"eval_loss": 0.13924407958984375,
|
1020 |
+
"eval_runtime": 103.9612,
|
1021 |
+
"eval_samples_per_second": 4.925,
|
1022 |
+
"eval_steps_per_second": 0.154,
|
1023 |
+
"step": 1300
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.3546291283161884,
|
1027 |
+
"grad_norm": 1.0625,
|
1028 |
+
"learning_rate": 3.731997495303694e-05,
|
1029 |
+
"loss": 0.0898,
|
1030 |
+
"step": 1310
|
1031 |
+
},
|
1032 |
+
{
|
1033 |
+
"epoch": 0.3573362208987547,
|
1034 |
+
"grad_norm": 2.609375,
|
1035 |
+
"learning_rate": 3.716343143393864e-05,
|
1036 |
+
"loss": 0.1697,
|
1037 |
+
"step": 1320
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 0.36004331348132107,
|
1041 |
+
"grad_norm": 1.1015625,
|
1042 |
+
"learning_rate": 3.7006887914840324e-05,
|
1043 |
+
"loss": 0.1111,
|
1044 |
+
"step": 1330
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.36275040606388737,
|
1048 |
+
"grad_norm": 0.44921875,
|
1049 |
+
"learning_rate": 3.685034439574202e-05,
|
1050 |
+
"loss": 0.1194,
|
1051 |
+
"step": 1340
|
1052 |
+
},
|
1053 |
+
{
|
1054 |
+
"epoch": 0.3654574986464537,
|
1055 |
+
"grad_norm": 1.421875,
|
1056 |
+
"learning_rate": 3.6693800876643706e-05,
|
1057 |
+
"loss": 0.1019,
|
1058 |
+
"step": 1350
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.36816459122902,
|
1062 |
+
"grad_norm": 1.25,
|
1063 |
+
"learning_rate": 3.65372573575454e-05,
|
1064 |
+
"loss": 0.0984,
|
1065 |
+
"step": 1360
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.37087168381158636,
|
1069 |
+
"grad_norm": 0.86328125,
|
1070 |
+
"learning_rate": 3.638071383844709e-05,
|
1071 |
+
"loss": 0.1298,
|
1072 |
+
"step": 1370
|
1073 |
+
},
|
1074 |
+
{
|
1075 |
+
"epoch": 0.37357877639415266,
|
1076 |
+
"grad_norm": 1.6484375,
|
1077 |
+
"learning_rate": 3.6224170319348784e-05,
|
1078 |
+
"loss": 0.1242,
|
1079 |
+
"step": 1380
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 0.376285868976719,
|
1083 |
+
"grad_norm": 0.72265625,
|
1084 |
+
"learning_rate": 3.606762680025047e-05,
|
1085 |
+
"loss": 0.094,
|
1086 |
+
"step": 1390
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 0.3789929615592853,
|
1090 |
+
"grad_norm": 1.2421875,
|
1091 |
+
"learning_rate": 3.5911083281152166e-05,
|
1092 |
+
"loss": 0.1286,
|
1093 |
+
"step": 1400
|
1094 |
+
},
|
1095 |
+
{
|
1096 |
+
"epoch": 0.3789929615592853,
|
1097 |
+
"eval_loss": 0.13358080387115479,
|
1098 |
+
"eval_runtime": 120.0689,
|
1099 |
+
"eval_samples_per_second": 4.264,
|
1100 |
+
"eval_steps_per_second": 0.133,
|
1101 |
+
"step": 1400
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.38170005414185165,
|
1105 |
+
"grad_norm": 2.703125,
|
1106 |
+
"learning_rate": 3.575453976205385e-05,
|
1107 |
+
"loss": 0.1594,
|
1108 |
+
"step": 1410
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.38440714672441795,
|
1112 |
+
"grad_norm": 2.0,
|
1113 |
+
"learning_rate": 3.559799624295555e-05,
|
1114 |
+
"loss": 0.0771,
|
1115 |
+
"step": 1420
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.3871142393069843,
|
1119 |
+
"grad_norm": 2.328125,
|
1120 |
+
"learning_rate": 3.544145272385723e-05,
|
1121 |
+
"loss": 0.1485,
|
1122 |
+
"step": 1430
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.38982133188955065,
|
1126 |
+
"grad_norm": 0.30859375,
|
1127 |
+
"learning_rate": 3.528490920475893e-05,
|
1128 |
+
"loss": 0.0938,
|
1129 |
+
"step": 1440
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.39252842447211694,
|
1133 |
+
"grad_norm": 0.91015625,
|
1134 |
+
"learning_rate": 3.512836568566061e-05,
|
1135 |
+
"loss": 0.1372,
|
1136 |
+
"step": 1450
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.3952355170546833,
|
1140 |
+
"grad_norm": 0.6953125,
|
1141 |
+
"learning_rate": 3.497182216656231e-05,
|
1142 |
+
"loss": 0.1033,
|
1143 |
+
"step": 1460
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.3979426096372496,
|
1147 |
+
"grad_norm": 1.0546875,
|
1148 |
+
"learning_rate": 3.4815278647463994e-05,
|
1149 |
+
"loss": 0.1345,
|
1150 |
+
"step": 1470
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.40064970221981594,
|
1154 |
+
"grad_norm": 0.91015625,
|
1155 |
+
"learning_rate": 3.4658735128365685e-05,
|
1156 |
+
"loss": 0.103,
|
1157 |
+
"step": 1480
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.40335679480238223,
|
1161 |
+
"grad_norm": 1.125,
|
1162 |
+
"learning_rate": 3.4502191609267375e-05,
|
1163 |
+
"loss": 0.083,
|
1164 |
+
"step": 1490
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.4060638873849486,
|
1168 |
+
"grad_norm": 0.9296875,
|
1169 |
+
"learning_rate": 3.4345648090169066e-05,
|
1170 |
+
"loss": 0.1024,
|
1171 |
+
"step": 1500
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.4060638873849486,
|
1175 |
+
"eval_loss": 0.13767841458320618,
|
1176 |
+
"eval_runtime": 104.1987,
|
1177 |
+
"eval_samples_per_second": 4.914,
|
1178 |
+
"eval_steps_per_second": 0.154,
|
1179 |
+
"step": 1500
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.4087709799675149,
|
1183 |
+
"grad_norm": 1.71875,
|
1184 |
+
"learning_rate": 3.418910457107076e-05,
|
1185 |
+
"loss": 0.1319,
|
1186 |
+
"step": 1510
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.41147807255008123,
|
1190 |
+
"grad_norm": 1.0703125,
|
1191 |
+
"learning_rate": 3.403256105197245e-05,
|
1192 |
+
"loss": 0.1152,
|
1193 |
+
"step": 1520
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.4141851651326475,
|
1197 |
+
"grad_norm": 1.3125,
|
1198 |
+
"learning_rate": 3.387601753287414e-05,
|
1199 |
+
"loss": 0.1072,
|
1200 |
+
"step": 1530
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.4168922577152139,
|
1204 |
+
"grad_norm": 2.171875,
|
1205 |
+
"learning_rate": 3.371947401377583e-05,
|
1206 |
+
"loss": 0.1408,
|
1207 |
+
"step": 1540
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.41959935029778017,
|
1211 |
+
"grad_norm": 1.53125,
|
1212 |
+
"learning_rate": 3.3562930494677526e-05,
|
1213 |
+
"loss": 0.1125,
|
1214 |
+
"step": 1550
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.4223064428803465,
|
1218 |
+
"grad_norm": 1.578125,
|
1219 |
+
"learning_rate": 3.340638697557921e-05,
|
1220 |
+
"loss": 0.1144,
|
1221 |
+
"step": 1560
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.4250135354629128,
|
1225 |
+
"grad_norm": 1.6015625,
|
1226 |
+
"learning_rate": 3.324984345648091e-05,
|
1227 |
+
"loss": 0.1092,
|
1228 |
+
"step": 1570
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.42772062804547917,
|
1232 |
+
"grad_norm": 0.408203125,
|
1233 |
+
"learning_rate": 3.309329993738259e-05,
|
1234 |
+
"loss": 0.1271,
|
1235 |
+
"step": 1580
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.43042772062804546,
|
1239 |
+
"grad_norm": 0.72265625,
|
1240 |
+
"learning_rate": 3.293675641828429e-05,
|
1241 |
+
"loss": 0.0882,
|
1242 |
+
"step": 1590
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.4331348132106118,
|
1246 |
+
"grad_norm": 0.296875,
|
1247 |
+
"learning_rate": 3.278021289918597e-05,
|
1248 |
+
"loss": 0.1141,
|
1249 |
+
"step": 1600
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.4331348132106118,
|
1253 |
+
"eval_loss": 0.13831546902656555,
|
1254 |
+
"eval_runtime": 104.916,
|
1255 |
+
"eval_samples_per_second": 4.88,
|
1256 |
+
"eval_steps_per_second": 0.153,
|
1257 |
+
"step": 1600
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.4358419057931781,
|
1261 |
+
"grad_norm": 0.462890625,
|
1262 |
+
"learning_rate": 3.262366938008767e-05,
|
1263 |
+
"loss": 0.0874,
|
1264 |
+
"step": 1610
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 0.43854899837574446,
|
1268 |
+
"grad_norm": 1.921875,
|
1269 |
+
"learning_rate": 3.2467125860989355e-05,
|
1270 |
+
"loss": 0.1288,
|
1271 |
+
"step": 1620
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.44125609095831075,
|
1275 |
+
"grad_norm": 1.3359375,
|
1276 |
+
"learning_rate": 3.231058234189105e-05,
|
1277 |
+
"loss": 0.1171,
|
1278 |
+
"step": 1630
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"epoch": 0.4439631835408771,
|
1282 |
+
"grad_norm": 0.447265625,
|
1283 |
+
"learning_rate": 3.2154038822792736e-05,
|
1284 |
+
"loss": 0.0845,
|
1285 |
+
"step": 1640
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.4466702761234434,
|
1289 |
+
"grad_norm": 1.703125,
|
1290 |
+
"learning_rate": 3.1997495303694433e-05,
|
1291 |
+
"loss": 0.1052,
|
1292 |
+
"step": 1650
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.44937736870600975,
|
1296 |
+
"grad_norm": 1.484375,
|
1297 |
+
"learning_rate": 3.184095178459612e-05,
|
1298 |
+
"loss": 0.1187,
|
1299 |
+
"step": 1660
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.45208446128857604,
|
1303 |
+
"grad_norm": 2.8125,
|
1304 |
+
"learning_rate": 3.168440826549781e-05,
|
1305 |
+
"loss": 0.1051,
|
1306 |
+
"step": 1670
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.4547915538711424,
|
1310 |
+
"grad_norm": 1.9765625,
|
1311 |
+
"learning_rate": 3.15278647463995e-05,
|
1312 |
+
"loss": 0.1415,
|
1313 |
+
"step": 1680
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.4574986464537087,
|
1317 |
+
"grad_norm": 1.3828125,
|
1318 |
+
"learning_rate": 3.137132122730119e-05,
|
1319 |
+
"loss": 0.1313,
|
1320 |
+
"step": 1690
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 0.46020573903627504,
|
1324 |
+
"grad_norm": 0.8359375,
|
1325 |
+
"learning_rate": 3.121477770820288e-05,
|
1326 |
+
"loss": 0.1129,
|
1327 |
+
"step": 1700
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 0.46020573903627504,
|
1331 |
+
"eval_loss": 0.13771241903305054,
|
1332 |
+
"eval_runtime": 104.8503,
|
1333 |
+
"eval_samples_per_second": 4.883,
|
1334 |
+
"eval_steps_per_second": 0.153,
|
1335 |
+
"step": 1700
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 0.4629128316188414,
|
1339 |
+
"grad_norm": 1.8359375,
|
1340 |
+
"learning_rate": 3.105823418910457e-05,
|
1341 |
+
"loss": 0.1618,
|
1342 |
+
"step": 1710
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 0.4656199242014077,
|
1346 |
+
"grad_norm": 0.53515625,
|
1347 |
+
"learning_rate": 3.090169067000626e-05,
|
1348 |
+
"loss": 0.1025,
|
1349 |
+
"step": 1720
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 0.46832701678397404,
|
1353 |
+
"grad_norm": 4.0625,
|
1354 |
+
"learning_rate": 3.074514715090795e-05,
|
1355 |
+
"loss": 0.1253,
|
1356 |
+
"step": 1730
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 0.47103410936654033,
|
1360 |
+
"grad_norm": 2.25,
|
1361 |
+
"learning_rate": 3.058860363180964e-05,
|
1362 |
+
"loss": 0.1098,
|
1363 |
+
"step": 1740
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 0.4737412019491067,
|
1367 |
+
"grad_norm": 1.484375,
|
1368 |
+
"learning_rate": 3.0432060112711337e-05,
|
1369 |
+
"loss": 0.0868,
|
1370 |
+
"step": 1750
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 0.476448294531673,
|
1374 |
+
"grad_norm": 1.9375,
|
1375 |
+
"learning_rate": 3.0275516593613024e-05,
|
1376 |
+
"loss": 0.1427,
|
1377 |
+
"step": 1760
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 0.47915538711423933,
|
1381 |
+
"grad_norm": 2.546875,
|
1382 |
+
"learning_rate": 3.011897307451472e-05,
|
1383 |
+
"loss": 0.1272,
|
1384 |
+
"step": 1770
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 0.4818624796968056,
|
1388 |
+
"grad_norm": 2.703125,
|
1389 |
+
"learning_rate": 2.9962429555416406e-05,
|
1390 |
+
"loss": 0.16,
|
1391 |
+
"step": 1780
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 0.484569572279372,
|
1395 |
+
"grad_norm": 1.2578125,
|
1396 |
+
"learning_rate": 2.9805886036318097e-05,
|
1397 |
+
"loss": 0.1079,
|
1398 |
+
"step": 1790
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 0.48727666486193827,
|
1402 |
+
"grad_norm": 0.75,
|
1403 |
+
"learning_rate": 2.9649342517219787e-05,
|
1404 |
+
"loss": 0.0907,
|
1405 |
+
"step": 1800
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 0.48727666486193827,
|
1409 |
+
"eval_loss": 0.14291706681251526,
|
1410 |
+
"eval_runtime": 105.4966,
|
1411 |
+
"eval_samples_per_second": 4.853,
|
1412 |
+
"eval_steps_per_second": 0.152,
|
1413 |
+
"step": 1800
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.4899837574445046,
|
1417 |
+
"grad_norm": 0.94140625,
|
1418 |
+
"learning_rate": 2.9492798998121478e-05,
|
1419 |
+
"loss": 0.1137,
|
1420 |
+
"step": 1810
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.4926908500270709,
|
1424 |
+
"grad_norm": 1.796875,
|
1425 |
+
"learning_rate": 2.9336255479023172e-05,
|
1426 |
+
"loss": 0.114,
|
1427 |
+
"step": 1820
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 0.49539794260963727,
|
1431 |
+
"grad_norm": 1.4296875,
|
1432 |
+
"learning_rate": 2.917971195992486e-05,
|
1433 |
+
"loss": 0.1263,
|
1434 |
+
"step": 1830
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.49810503519220356,
|
1438 |
+
"grad_norm": 2.171875,
|
1439 |
+
"learning_rate": 2.9023168440826553e-05,
|
1440 |
+
"loss": 0.1095,
|
1441 |
+
"step": 1840
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 0.5008121277747699,
|
1445 |
+
"grad_norm": 1.2734375,
|
1446 |
+
"learning_rate": 2.886662492172824e-05,
|
1447 |
+
"loss": 0.1609,
|
1448 |
+
"step": 1850
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 0.5035192203573362,
|
1452 |
+
"grad_norm": 1.84375,
|
1453 |
+
"learning_rate": 2.8710081402629935e-05,
|
1454 |
+
"loss": 0.1079,
|
1455 |
+
"step": 1860
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 0.5062263129399025,
|
1459 |
+
"grad_norm": 0.328125,
|
1460 |
+
"learning_rate": 2.8553537883531622e-05,
|
1461 |
+
"loss": 0.1114,
|
1462 |
+
"step": 1870
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"epoch": 0.5089334055224689,
|
1466 |
+
"grad_norm": 1.9140625,
|
1467 |
+
"learning_rate": 2.8396994364433316e-05,
|
1468 |
+
"loss": 0.1163,
|
1469 |
+
"step": 1880
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 0.5116404981050352,
|
1473 |
+
"grad_norm": 0.68359375,
|
1474 |
+
"learning_rate": 2.8240450845335004e-05,
|
1475 |
+
"loss": 0.105,
|
1476 |
+
"step": 1890
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 0.5143475906876015,
|
1480 |
+
"grad_norm": 0.76171875,
|
1481 |
+
"learning_rate": 2.8083907326236698e-05,
|
1482 |
+
"loss": 0.0931,
|
1483 |
+
"step": 1900
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 0.5143475906876015,
|
1487 |
+
"eval_loss": 0.1378411054611206,
|
1488 |
+
"eval_runtime": 122.4527,
|
1489 |
+
"eval_samples_per_second": 4.181,
|
1490 |
+
"eval_steps_per_second": 0.131,
|
1491 |
+
"step": 1900
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 0.5170546832701678,
|
1495 |
+
"grad_norm": 2.125,
|
1496 |
+
"learning_rate": 2.7927363807138385e-05,
|
1497 |
+
"loss": 0.1137,
|
1498 |
+
"step": 1910
|
1499 |
+
},
|
1500 |
+
{
|
1501 |
+
"epoch": 0.5197617758527342,
|
1502 |
+
"grad_norm": 1.265625,
|
1503 |
+
"learning_rate": 2.777082028804008e-05,
|
1504 |
+
"loss": 0.1127,
|
1505 |
+
"step": 1920
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 0.5224688684353005,
|
1509 |
+
"grad_norm": 1.7734375,
|
1510 |
+
"learning_rate": 2.7614276768941766e-05,
|
1511 |
+
"loss": 0.1082,
|
1512 |
+
"step": 1930
|
1513 |
+
},
|
1514 |
+
{
|
1515 |
+
"epoch": 0.5251759610178668,
|
1516 |
+
"grad_norm": 1.6640625,
|
1517 |
+
"learning_rate": 2.745773324984346e-05,
|
1518 |
+
"loss": 0.1147,
|
1519 |
+
"step": 1940
|
1520 |
+
},
|
1521 |
+
{
|
1522 |
+
"epoch": 0.5278830536004331,
|
1523 |
+
"grad_norm": 1.84375,
|
1524 |
+
"learning_rate": 2.7301189730745148e-05,
|
1525 |
+
"loss": 0.1027,
|
1526 |
+
"step": 1950
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 0.5305901461829995,
|
1530 |
+
"grad_norm": 0.86328125,
|
1531 |
+
"learning_rate": 2.7144646211646842e-05,
|
1532 |
+
"loss": 0.108,
|
1533 |
+
"step": 1960
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 0.5332972387655658,
|
1537 |
+
"grad_norm": 0.59375,
|
1538 |
+
"learning_rate": 2.698810269254853e-05,
|
1539 |
+
"loss": 0.0917,
|
1540 |
+
"step": 1970
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 0.5360043313481321,
|
1544 |
+
"grad_norm": 0.515625,
|
1545 |
+
"learning_rate": 2.683155917345022e-05,
|
1546 |
+
"loss": 0.078,
|
1547 |
+
"step": 1980
|
1548 |
+
},
|
1549 |
+
{
|
1550 |
+
"epoch": 0.5387114239306985,
|
1551 |
+
"grad_norm": 1.1796875,
|
1552 |
+
"learning_rate": 2.667501565435191e-05,
|
1553 |
+
"loss": 0.0845,
|
1554 |
+
"step": 1990
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.5414185165132648,
|
1558 |
+
"grad_norm": 1.7890625,
|
1559 |
+
"learning_rate": 2.65184721352536e-05,
|
1560 |
+
"loss": 0.0888,
|
1561 |
+
"step": 2000
|
1562 |
+
},
|
1563 |
+
{
|
1564 |
+
"epoch": 0.5414185165132648,
|
1565 |
+
"eval_loss": 0.14294707775115967,
|
1566 |
+
"eval_runtime": 103.5797,
|
1567 |
+
"eval_samples_per_second": 4.943,
|
1568 |
+
"eval_steps_per_second": 0.154,
|
1569 |
+
"step": 2000
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.5441256090958311,
|
1573 |
+
"grad_norm": 2.234375,
|
1574 |
+
"learning_rate": 2.636192861615529e-05,
|
1575 |
+
"loss": 0.099,
|
1576 |
+
"step": 2010
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"epoch": 0.5468327016783974,
|
1580 |
+
"grad_norm": 1.2421875,
|
1581 |
+
"learning_rate": 2.6205385097056983e-05,
|
1582 |
+
"loss": 0.1048,
|
1583 |
+
"step": 2020
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 0.5495397942609638,
|
1587 |
+
"grad_norm": 1.984375,
|
1588 |
+
"learning_rate": 2.604884157795867e-05,
|
1589 |
+
"loss": 0.1117,
|
1590 |
+
"step": 2030
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 0.5522468868435301,
|
1594 |
+
"grad_norm": 1.6328125,
|
1595 |
+
"learning_rate": 2.5892298058860364e-05,
|
1596 |
+
"loss": 0.1291,
|
1597 |
+
"step": 2040
|
1598 |
+
},
|
1599 |
+
{
|
1600 |
+
"epoch": 0.5549539794260964,
|
1601 |
+
"grad_norm": 1.4765625,
|
1602 |
+
"learning_rate": 2.573575453976205e-05,
|
1603 |
+
"loss": 0.1529,
|
1604 |
+
"step": 2050
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 0.5576610720086627,
|
1608 |
+
"grad_norm": 1.203125,
|
1609 |
+
"learning_rate": 2.5579211020663746e-05,
|
1610 |
+
"loss": 0.0559,
|
1611 |
+
"step": 2060
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 0.5603681645912291,
|
1615 |
+
"grad_norm": 1.40625,
|
1616 |
+
"learning_rate": 2.5422667501565433e-05,
|
1617 |
+
"loss": 0.0992,
|
1618 |
+
"step": 2070
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 0.5630752571737954,
|
1622 |
+
"grad_norm": 0.7578125,
|
1623 |
+
"learning_rate": 2.5266123982467127e-05,
|
1624 |
+
"loss": 0.0876,
|
1625 |
+
"step": 2080
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 0.5657823497563617,
|
1629 |
+
"grad_norm": 1.6328125,
|
1630 |
+
"learning_rate": 2.510958046336882e-05,
|
1631 |
+
"loss": 0.1442,
|
1632 |
+
"step": 2090
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 0.568489442338928,
|
1636 |
+
"grad_norm": 0.734375,
|
1637 |
+
"learning_rate": 2.495303694427051e-05,
|
1638 |
+
"loss": 0.073,
|
1639 |
+
"step": 2100
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"epoch": 0.568489442338928,
|
1643 |
+
"eval_loss": 0.1371915191411972,
|
1644 |
+
"eval_runtime": 102.7955,
|
1645 |
+
"eval_samples_per_second": 4.981,
|
1646 |
+
"eval_steps_per_second": 0.156,
|
1647 |
+
"step": 2100
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.5711965349214944,
|
1651 |
+
"grad_norm": 1.4453125,
|
1652 |
+
"learning_rate": 2.47964934251722e-05,
|
1653 |
+
"loss": 0.0818,
|
1654 |
+
"step": 2110
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.5739036275040607,
|
1658 |
+
"grad_norm": 1.0,
|
1659 |
+
"learning_rate": 2.463994990607389e-05,
|
1660 |
+
"loss": 0.0785,
|
1661 |
+
"step": 2120
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.576610720086627,
|
1665 |
+
"grad_norm": 2.09375,
|
1666 |
+
"learning_rate": 2.448340638697558e-05,
|
1667 |
+
"loss": 0.0966,
|
1668 |
+
"step": 2130
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.5793178126691932,
|
1672 |
+
"grad_norm": 1.3828125,
|
1673 |
+
"learning_rate": 2.432686286787727e-05,
|
1674 |
+
"loss": 0.0805,
|
1675 |
+
"step": 2140
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.5820249052517596,
|
1679 |
+
"grad_norm": 0.9375,
|
1680 |
+
"learning_rate": 2.4170319348778962e-05,
|
1681 |
+
"loss": 0.1032,
|
1682 |
+
"step": 2150
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.584731997834326,
|
1686 |
+
"grad_norm": 1.9765625,
|
1687 |
+
"learning_rate": 2.4013775829680653e-05,
|
1688 |
+
"loss": 0.1314,
|
1689 |
+
"step": 2160
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.5874390904168922,
|
1693 |
+
"grad_norm": 1.5078125,
|
1694 |
+
"learning_rate": 2.3857232310582343e-05,
|
1695 |
+
"loss": 0.1026,
|
1696 |
+
"step": 2170
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.5901461829994585,
|
1700 |
+
"grad_norm": 0.58984375,
|
1701 |
+
"learning_rate": 2.3700688791484034e-05,
|
1702 |
+
"loss": 0.0858,
|
1703 |
+
"step": 2180
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.5928532755820249,
|
1707 |
+
"grad_norm": 0.51171875,
|
1708 |
+
"learning_rate": 2.3544145272385725e-05,
|
1709 |
+
"loss": 0.069,
|
1710 |
+
"step": 2190
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.5955603681645912,
|
1714 |
+
"grad_norm": 0.94140625,
|
1715 |
+
"learning_rate": 2.3387601753287412e-05,
|
1716 |
+
"loss": 0.1238,
|
1717 |
+
"step": 2200
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.5955603681645912,
|
1721 |
+
"eval_loss": 0.1365373730659485,
|
1722 |
+
"eval_runtime": 103.5823,
|
1723 |
+
"eval_samples_per_second": 4.943,
|
1724 |
+
"eval_steps_per_second": 0.154,
|
1725 |
+
"step": 2200
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.5982674607471575,
|
1729 |
+
"grad_norm": 1.0390625,
|
1730 |
+
"learning_rate": 2.3231058234189106e-05,
|
1731 |
+
"loss": 0.1196,
|
1732 |
+
"step": 2210
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 0.6009745533297238,
|
1736 |
+
"grad_norm": 1.1875,
|
1737 |
+
"learning_rate": 2.3074514715090797e-05,
|
1738 |
+
"loss": 0.111,
|
1739 |
+
"step": 2220
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 0.6036816459122902,
|
1743 |
+
"grad_norm": 0.5546875,
|
1744 |
+
"learning_rate": 2.2917971195992488e-05,
|
1745 |
+
"loss": 0.0875,
|
1746 |
+
"step": 2230
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 0.6063887384948565,
|
1750 |
+
"grad_norm": 1.2421875,
|
1751 |
+
"learning_rate": 2.2761427676894178e-05,
|
1752 |
+
"loss": 0.1029,
|
1753 |
+
"step": 2240
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 0.6090958310774228,
|
1757 |
+
"grad_norm": 1.3671875,
|
1758 |
+
"learning_rate": 2.260488415779587e-05,
|
1759 |
+
"loss": 0.0933,
|
1760 |
+
"step": 2250
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 0.6118029236599891,
|
1764 |
+
"grad_norm": 1.140625,
|
1765 |
+
"learning_rate": 2.244834063869756e-05,
|
1766 |
+
"loss": 0.1009,
|
1767 |
+
"step": 2260
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.6145100162425555,
|
1771 |
+
"grad_norm": 2.234375,
|
1772 |
+
"learning_rate": 2.229179711959925e-05,
|
1773 |
+
"loss": 0.135,
|
1774 |
+
"step": 2270
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 0.6172171088251218,
|
1778 |
+
"grad_norm": 1.671875,
|
1779 |
+
"learning_rate": 2.213525360050094e-05,
|
1780 |
+
"loss": 0.0773,
|
1781 |
+
"step": 2280
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 0.6199242014076881,
|
1785 |
+
"grad_norm": 0.9375,
|
1786 |
+
"learning_rate": 2.1978710081402632e-05,
|
1787 |
+
"loss": 0.0732,
|
1788 |
+
"step": 2290
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 0.6226312939902545,
|
1792 |
+
"grad_norm": 2.0625,
|
1793 |
+
"learning_rate": 2.1822166562304323e-05,
|
1794 |
+
"loss": 0.0851,
|
1795 |
+
"step": 2300
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 0.6226312939902545,
|
1799 |
+
"eval_loss": 0.1353287696838379,
|
1800 |
+
"eval_runtime": 102.3815,
|
1801 |
+
"eval_samples_per_second": 5.001,
|
1802 |
+
"eval_steps_per_second": 0.156,
|
1803 |
+
"step": 2300
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.6253383865728208,
|
1807 |
+
"grad_norm": 0.71484375,
|
1808 |
+
"learning_rate": 2.1665623043206013e-05,
|
1809 |
+
"loss": 0.0633,
|
1810 |
+
"step": 2310
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 0.6280454791553871,
|
1814 |
+
"grad_norm": 1.328125,
|
1815 |
+
"learning_rate": 2.1509079524107704e-05,
|
1816 |
+
"loss": 0.0825,
|
1817 |
+
"step": 2320
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 0.6307525717379534,
|
1821 |
+
"grad_norm": 0.515625,
|
1822 |
+
"learning_rate": 2.1352536005009395e-05,
|
1823 |
+
"loss": 0.1016,
|
1824 |
+
"step": 2330
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.6334596643205198,
|
1828 |
+
"grad_norm": 2.40625,
|
1829 |
+
"learning_rate": 2.1195992485911085e-05,
|
1830 |
+
"loss": 0.0942,
|
1831 |
+
"step": 2340
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 0.6361667569030861,
|
1835 |
+
"grad_norm": 1.75,
|
1836 |
+
"learning_rate": 2.1039448966812776e-05,
|
1837 |
+
"loss": 0.086,
|
1838 |
+
"step": 2350
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 0.6388738494856524,
|
1842 |
+
"grad_norm": 1.328125,
|
1843 |
+
"learning_rate": 2.0882905447714467e-05,
|
1844 |
+
"loss": 0.1095,
|
1845 |
+
"step": 2360
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.6415809420682187,
|
1849 |
+
"grad_norm": 0.63671875,
|
1850 |
+
"learning_rate": 2.0726361928616157e-05,
|
1851 |
+
"loss": 0.0711,
|
1852 |
+
"step": 2370
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 0.6442880346507851,
|
1856 |
+
"grad_norm": 1.3515625,
|
1857 |
+
"learning_rate": 2.0569818409517845e-05,
|
1858 |
+
"loss": 0.0677,
|
1859 |
+
"step": 2380
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 0.6469951272333514,
|
1863 |
+
"grad_norm": 2.046875,
|
1864 |
+
"learning_rate": 2.0413274890419535e-05,
|
1865 |
+
"loss": 0.0892,
|
1866 |
+
"step": 2390
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 0.6497022198159177,
|
1870 |
+
"grad_norm": 1.640625,
|
1871 |
+
"learning_rate": 2.0256731371321226e-05,
|
1872 |
+
"loss": 0.0955,
|
1873 |
+
"step": 2400
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 0.6497022198159177,
|
1877 |
+
"eval_loss": 0.13519829511642456,
|
1878 |
+
"eval_runtime": 121.253,
|
1879 |
+
"eval_samples_per_second": 4.223,
|
1880 |
+
"eval_steps_per_second": 0.132,
|
1881 |
+
"step": 2400
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 0.652409312398484,
|
1885 |
+
"grad_norm": 1.265625,
|
1886 |
+
"learning_rate": 2.0100187852222917e-05,
|
1887 |
+
"loss": 0.1012,
|
1888 |
+
"step": 2410
|
1889 |
+
},
|
1890 |
+
{
|
1891 |
+
"epoch": 0.6551164049810504,
|
1892 |
+
"grad_norm": 0.984375,
|
1893 |
+
"learning_rate": 1.9943644333124608e-05,
|
1894 |
+
"loss": 0.1008,
|
1895 |
+
"step": 2420
|
1896 |
+
},
|
1897 |
+
{
|
1898 |
+
"epoch": 0.6578234975636167,
|
1899 |
+
"grad_norm": 0.9453125,
|
1900 |
+
"learning_rate": 1.9787100814026298e-05,
|
1901 |
+
"loss": 0.1026,
|
1902 |
+
"step": 2430
|
1903 |
+
},
|
1904 |
+
{
|
1905 |
+
"epoch": 0.660530590146183,
|
1906 |
+
"grad_norm": 0.95703125,
|
1907 |
+
"learning_rate": 1.963055729492799e-05,
|
1908 |
+
"loss": 0.1021,
|
1909 |
+
"step": 2440
|
1910 |
+
},
|
1911 |
+
{
|
1912 |
+
"epoch": 0.6632376827287493,
|
1913 |
+
"grad_norm": 1.4375,
|
1914 |
+
"learning_rate": 1.947401377582968e-05,
|
1915 |
+
"loss": 0.1098,
|
1916 |
+
"step": 2450
|
1917 |
+
},
|
1918 |
+
{
|
1919 |
+
"epoch": 0.6659447753113157,
|
1920 |
+
"grad_norm": 0.375,
|
1921 |
+
"learning_rate": 1.931747025673137e-05,
|
1922 |
+
"loss": 0.0828,
|
1923 |
+
"step": 2460
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 0.668651867893882,
|
1927 |
+
"grad_norm": 0.94140625,
|
1928 |
+
"learning_rate": 1.9160926737633064e-05,
|
1929 |
+
"loss": 0.0612,
|
1930 |
+
"step": 2470
|
1931 |
+
},
|
1932 |
+
{
|
1933 |
+
"epoch": 0.6713589604764483,
|
1934 |
+
"grad_norm": 3.21875,
|
1935 |
+
"learning_rate": 1.9004383218534755e-05,
|
1936 |
+
"loss": 0.1367,
|
1937 |
+
"step": 2480
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 0.6740660530590146,
|
1941 |
+
"grad_norm": 1.1796875,
|
1942 |
+
"learning_rate": 1.8847839699436446e-05,
|
1943 |
+
"loss": 0.0647,
|
1944 |
+
"step": 2490
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 0.676773145641581,
|
1948 |
+
"grad_norm": 0.5703125,
|
1949 |
+
"learning_rate": 1.8691296180338137e-05,
|
1950 |
+
"loss": 0.0973,
|
1951 |
+
"step": 2500
|
1952 |
+
},
|
1953 |
+
{
|
1954 |
+
"epoch": 0.676773145641581,
|
1955 |
+
"eval_loss": 0.13495835661888123,
|
1956 |
+
"eval_runtime": 105.5301,
|
1957 |
+
"eval_samples_per_second": 4.852,
|
1958 |
+
"eval_steps_per_second": 0.152,
|
1959 |
+
"step": 2500
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.6794802382241473,
|
1963 |
+
"grad_norm": 1.2890625,
|
1964 |
+
"learning_rate": 1.8534752661239827e-05,
|
1965 |
+
"loss": 0.0775,
|
1966 |
+
"step": 2510
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 0.6821873308067136,
|
1970 |
+
"grad_norm": 0.96484375,
|
1971 |
+
"learning_rate": 1.8378209142141518e-05,
|
1972 |
+
"loss": 0.0836,
|
1973 |
+
"step": 2520
|
1974 |
+
},
|
1975 |
+
{
|
1976 |
+
"epoch": 0.6848944233892799,
|
1977 |
+
"grad_norm": 2.5625,
|
1978 |
+
"learning_rate": 1.822166562304321e-05,
|
1979 |
+
"loss": 0.1118,
|
1980 |
+
"step": 2530
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 0.6876015159718463,
|
1984 |
+
"grad_norm": 1.1328125,
|
1985 |
+
"learning_rate": 1.80651221039449e-05,
|
1986 |
+
"loss": 0.0889,
|
1987 |
+
"step": 2540
|
1988 |
+
},
|
1989 |
+
{
|
1990 |
+
"epoch": 0.6903086085544126,
|
1991 |
+
"grad_norm": 0.71484375,
|
1992 |
+
"learning_rate": 1.790857858484659e-05,
|
1993 |
+
"loss": 0.0982,
|
1994 |
+
"step": 2550
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 0.6930157011369789,
|
1998 |
+
"grad_norm": 2.125,
|
1999 |
+
"learning_rate": 1.775203506574828e-05,
|
2000 |
+
"loss": 0.1131,
|
2001 |
+
"step": 2560
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 0.6957227937195453,
|
2005 |
+
"grad_norm": 1.015625,
|
2006 |
+
"learning_rate": 1.7595491546649968e-05,
|
2007 |
+
"loss": 0.1142,
|
2008 |
+
"step": 2570
|
2009 |
+
},
|
2010 |
+
{
|
2011 |
+
"epoch": 0.6984298863021116,
|
2012 |
+
"grad_norm": 0.3671875,
|
2013 |
+
"learning_rate": 1.743894802755166e-05,
|
2014 |
+
"loss": 0.0911,
|
2015 |
+
"step": 2580
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 0.7011369788846779,
|
2019 |
+
"grad_norm": 1.2421875,
|
2020 |
+
"learning_rate": 1.728240450845335e-05,
|
2021 |
+
"loss": 0.0774,
|
2022 |
+
"step": 2590
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 0.7038440714672441,
|
2026 |
+
"grad_norm": 0.9453125,
|
2027 |
+
"learning_rate": 1.712586098935504e-05,
|
2028 |
+
"loss": 0.0933,
|
2029 |
+
"step": 2600
|
2030 |
+
},
|
2031 |
+
{
|
2032 |
+
"epoch": 0.7038440714672441,
|
2033 |
+
"eval_loss": 0.13393962383270264,
|
2034 |
+
"eval_runtime": 103.5576,
|
2035 |
+
"eval_samples_per_second": 4.944,
|
2036 |
+
"eval_steps_per_second": 0.155,
|
2037 |
+
"step": 2600
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 0.7065511640498106,
|
2041 |
+
"grad_norm": 1.234375,
|
2042 |
+
"learning_rate": 1.696931747025673e-05,
|
2043 |
+
"loss": 0.1073,
|
2044 |
+
"step": 2610
|
2045 |
+
},
|
2046 |
+
{
|
2047 |
+
"epoch": 0.7092582566323768,
|
2048 |
+
"grad_norm": 2.203125,
|
2049 |
+
"learning_rate": 1.681277395115842e-05,
|
2050 |
+
"loss": 0.097,
|
2051 |
+
"step": 2620
|
2052 |
+
},
|
2053 |
+
{
|
2054 |
+
"epoch": 0.7119653492149431,
|
2055 |
+
"grad_norm": 0.94140625,
|
2056 |
+
"learning_rate": 1.6656230432060112e-05,
|
2057 |
+
"loss": 0.0772,
|
2058 |
+
"step": 2630
|
2059 |
+
},
|
2060 |
+
{
|
2061 |
+
"epoch": 0.7146724417975094,
|
2062 |
+
"grad_norm": 2.953125,
|
2063 |
+
"learning_rate": 1.6499686912961803e-05,
|
2064 |
+
"loss": 0.0935,
|
2065 |
+
"step": 2640
|
2066 |
+
},
|
2067 |
+
{
|
2068 |
+
"epoch": 0.7173795343800758,
|
2069 |
+
"grad_norm": 0.267578125,
|
2070 |
+
"learning_rate": 1.6343143393863494e-05,
|
2071 |
+
"loss": 0.0924,
|
2072 |
+
"step": 2650
|
2073 |
+
},
|
2074 |
+
{
|
2075 |
+
"epoch": 0.7200866269626421,
|
2076 |
+
"grad_norm": 1.359375,
|
2077 |
+
"learning_rate": 1.6186599874765184e-05,
|
2078 |
+
"loss": 0.1057,
|
2079 |
+
"step": 2660
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 0.7227937195452084,
|
2083 |
+
"grad_norm": 1.4296875,
|
2084 |
+
"learning_rate": 1.6030056355666875e-05,
|
2085 |
+
"loss": 0.0865,
|
2086 |
+
"step": 2670
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"epoch": 0.7255008121277747,
|
2090 |
+
"grad_norm": 1.09375,
|
2091 |
+
"learning_rate": 1.5873512836568566e-05,
|
2092 |
+
"loss": 0.0957,
|
2093 |
+
"step": 2680
|
2094 |
+
},
|
2095 |
+
{
|
2096 |
+
"epoch": 0.7282079047103411,
|
2097 |
+
"grad_norm": 1.09375,
|
2098 |
+
"learning_rate": 1.5716969317470257e-05,
|
2099 |
+
"loss": 0.107,
|
2100 |
+
"step": 2690
|
2101 |
+
},
|
2102 |
+
{
|
2103 |
+
"epoch": 0.7309149972929074,
|
2104 |
+
"grad_norm": 0.734375,
|
2105 |
+
"learning_rate": 1.5560425798371947e-05,
|
2106 |
+
"loss": 0.0976,
|
2107 |
+
"step": 2700
|
2108 |
+
},
|
2109 |
+
{
|
2110 |
+
"epoch": 0.7309149972929074,
|
2111 |
+
"eval_loss": 0.13289867341518402,
|
2112 |
+
"eval_runtime": 104.5232,
|
2113 |
+
"eval_samples_per_second": 4.898,
|
2114 |
+
"eval_steps_per_second": 0.153,
|
2115 |
+
"step": 2700
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 0.7336220898754737,
|
2119 |
+
"grad_norm": 0.34765625,
|
2120 |
+
"learning_rate": 1.5403882279273638e-05,
|
2121 |
+
"loss": 0.0918,
|
2122 |
+
"step": 2710
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 0.73632918245804,
|
2126 |
+
"grad_norm": 1.6875,
|
2127 |
+
"learning_rate": 1.5247338760175329e-05,
|
2128 |
+
"loss": 0.1113,
|
2129 |
+
"step": 2720
|
2130 |
+
},
|
2131 |
+
{
|
2132 |
+
"epoch": 0.7390362750406064,
|
2133 |
+
"grad_norm": 1.328125,
|
2134 |
+
"learning_rate": 1.5090795241077021e-05,
|
2135 |
+
"loss": 0.1221,
|
2136 |
+
"step": 2730
|
2137 |
+
},
|
2138 |
+
{
|
2139 |
+
"epoch": 0.7417433676231727,
|
2140 |
+
"grad_norm": 1.0390625,
|
2141 |
+
"learning_rate": 1.4934251721978712e-05,
|
2142 |
+
"loss": 0.1236,
|
2143 |
+
"step": 2740
|
2144 |
+
},
|
2145 |
+
{
|
2146 |
+
"epoch": 0.744450460205739,
|
2147 |
+
"grad_norm": 0.95703125,
|
2148 |
+
"learning_rate": 1.4777708202880403e-05,
|
2149 |
+
"loss": 0.119,
|
2150 |
+
"step": 2750
|
2151 |
+
},
|
2152 |
+
{
|
2153 |
+
"epoch": 0.7471575527883053,
|
2154 |
+
"grad_norm": 3.125,
|
2155 |
+
"learning_rate": 1.4621164683782093e-05,
|
2156 |
+
"loss": 0.1141,
|
2157 |
+
"step": 2760
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 0.7498646453708717,
|
2161 |
+
"grad_norm": 0.94921875,
|
2162 |
+
"learning_rate": 1.4464621164683784e-05,
|
2163 |
+
"loss": 0.106,
|
2164 |
+
"step": 2770
|
2165 |
+
},
|
2166 |
+
{
|
2167 |
+
"epoch": 0.752571737953438,
|
2168 |
+
"grad_norm": 1.1640625,
|
2169 |
+
"learning_rate": 1.4308077645585475e-05,
|
2170 |
+
"loss": 0.0963,
|
2171 |
+
"step": 2780
|
2172 |
+
},
|
2173 |
+
{
|
2174 |
+
"epoch": 0.7552788305360043,
|
2175 |
+
"grad_norm": 1.234375,
|
2176 |
+
"learning_rate": 1.4151534126487165e-05,
|
2177 |
+
"loss": 0.0946,
|
2178 |
+
"step": 2790
|
2179 |
+
},
|
2180 |
+
{
|
2181 |
+
"epoch": 0.7579859231185706,
|
2182 |
+
"grad_norm": 1.71875,
|
2183 |
+
"learning_rate": 1.3994990607388856e-05,
|
2184 |
+
"loss": 0.0985,
|
2185 |
+
"step": 2800
|
2186 |
+
},
|
2187 |
+
{
|
2188 |
+
"epoch": 0.7579859231185706,
|
2189 |
+
"eval_loss": 0.13054493069648743,
|
2190 |
+
"eval_runtime": 102.656,
|
2191 |
+
"eval_samples_per_second": 4.988,
|
2192 |
+
"eval_steps_per_second": 0.156,
|
2193 |
+
"step": 2800
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.760693015701137,
|
2197 |
+
"grad_norm": 1.1875,
|
2198 |
+
"learning_rate": 1.3838447088290547e-05,
|
2199 |
+
"loss": 0.1329,
|
2200 |
+
"step": 2810
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 0.7634001082837033,
|
2204 |
+
"grad_norm": 2.21875,
|
2205 |
+
"learning_rate": 1.3681903569192236e-05,
|
2206 |
+
"loss": 0.1072,
|
2207 |
+
"step": 2820
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 0.7661072008662696,
|
2211 |
+
"grad_norm": 1.390625,
|
2212 |
+
"learning_rate": 1.3525360050093926e-05,
|
2213 |
+
"loss": 0.0953,
|
2214 |
+
"step": 2830
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.7688142934488359,
|
2218 |
+
"grad_norm": 1.046875,
|
2219 |
+
"learning_rate": 1.3368816530995617e-05,
|
2220 |
+
"loss": 0.0912,
|
2221 |
+
"step": 2840
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 0.7715213860314023,
|
2225 |
+
"grad_norm": 0.984375,
|
2226 |
+
"learning_rate": 1.3212273011897308e-05,
|
2227 |
+
"loss": 0.1132,
|
2228 |
+
"step": 2850
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.7742284786139686,
|
2232 |
+
"grad_norm": 0.5234375,
|
2233 |
+
"learning_rate": 1.3055729492798999e-05,
|
2234 |
+
"loss": 0.1059,
|
2235 |
+
"step": 2860
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.7769355711965349,
|
2239 |
+
"grad_norm": 0.99609375,
|
2240 |
+
"learning_rate": 1.289918597370069e-05,
|
2241 |
+
"loss": 0.1182,
|
2242 |
+
"step": 2870
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 0.7796426637791013,
|
2246 |
+
"grad_norm": 0.921875,
|
2247 |
+
"learning_rate": 1.274264245460238e-05,
|
2248 |
+
"loss": 0.0647,
|
2249 |
+
"step": 2880
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 0.7823497563616676,
|
2253 |
+
"grad_norm": 1.609375,
|
2254 |
+
"learning_rate": 1.258609893550407e-05,
|
2255 |
+
"loss": 0.1049,
|
2256 |
+
"step": 2890
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 0.7850568489442339,
|
2260 |
+
"grad_norm": 2.53125,
|
2261 |
+
"learning_rate": 1.2429555416405761e-05,
|
2262 |
+
"loss": 0.1223,
|
2263 |
+
"step": 2900
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 0.7850568489442339,
|
2267 |
+
"eval_loss": 0.13052764534950256,
|
2268 |
+
"eval_runtime": 114.8255,
|
2269 |
+
"eval_samples_per_second": 4.459,
|
2270 |
+
"eval_steps_per_second": 0.139,
|
2271 |
+
"step": 2900
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 0.7877639415268002,
|
2275 |
+
"grad_norm": 1.59375,
|
2276 |
+
"learning_rate": 1.2273011897307452e-05,
|
2277 |
+
"loss": 0.0768,
|
2278 |
+
"step": 2910
|
2279 |
+
},
|
2280 |
+
{
|
2281 |
+
"epoch": 0.7904710341093666,
|
2282 |
+
"grad_norm": 1.0,
|
2283 |
+
"learning_rate": 1.2116468378209143e-05,
|
2284 |
+
"loss": 0.0902,
|
2285 |
+
"step": 2920
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 0.7931781266919329,
|
2289 |
+
"grad_norm": 1.0546875,
|
2290 |
+
"learning_rate": 1.1959924859110834e-05,
|
2291 |
+
"loss": 0.1059,
|
2292 |
+
"step": 2930
|
2293 |
+
},
|
2294 |
+
{
|
2295 |
+
"epoch": 0.7958852192744992,
|
2296 |
+
"grad_norm": 0.66796875,
|
2297 |
+
"learning_rate": 1.1803381340012524e-05,
|
2298 |
+
"loss": 0.0919,
|
2299 |
+
"step": 2940
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 0.7985923118570655,
|
2303 |
+
"grad_norm": 1.859375,
|
2304 |
+
"learning_rate": 1.1646837820914215e-05,
|
2305 |
+
"loss": 0.0779,
|
2306 |
+
"step": 2950
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 0.8012994044396319,
|
2310 |
+
"grad_norm": 1.1328125,
|
2311 |
+
"learning_rate": 1.1490294301815906e-05,
|
2312 |
+
"loss": 0.1019,
|
2313 |
+
"step": 2960
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.8040064970221982,
|
2317 |
+
"grad_norm": 0.8671875,
|
2318 |
+
"learning_rate": 1.1333750782717596e-05,
|
2319 |
+
"loss": 0.0909,
|
2320 |
+
"step": 2970
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 0.8067135896047645,
|
2324 |
+
"grad_norm": 0.435546875,
|
2325 |
+
"learning_rate": 1.1177207263619287e-05,
|
2326 |
+
"loss": 0.0973,
|
2327 |
+
"step": 2980
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 0.8094206821873308,
|
2331 |
+
"grad_norm": 1.453125,
|
2332 |
+
"learning_rate": 1.1020663744520978e-05,
|
2333 |
+
"loss": 0.0875,
|
2334 |
+
"step": 2990
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 0.8121277747698972,
|
2338 |
+
"grad_norm": 0.71484375,
|
2339 |
+
"learning_rate": 1.0864120225422668e-05,
|
2340 |
+
"loss": 0.1053,
|
2341 |
+
"step": 3000
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 0.8121277747698972,
|
2345 |
+
"eval_loss": 0.13060268759727478,
|
2346 |
+
"eval_runtime": 108.9657,
|
2347 |
+
"eval_samples_per_second": 4.699,
|
2348 |
+
"eval_steps_per_second": 0.147,
|
2349 |
+
"step": 3000
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 0.8148348673524635,
|
2353 |
+
"grad_norm": 1.140625,
|
2354 |
+
"learning_rate": 1.070757670632436e-05,
|
2355 |
+
"loss": 0.0808,
|
2356 |
+
"step": 3010
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 0.8175419599350298,
|
2360 |
+
"grad_norm": 2.140625,
|
2361 |
+
"learning_rate": 1.0551033187226048e-05,
|
2362 |
+
"loss": 0.0766,
|
2363 |
+
"step": 3020
|
2364 |
+
},
|
2365 |
+
{
|
2366 |
+
"epoch": 0.8202490525175961,
|
2367 |
+
"grad_norm": 1.0546875,
|
2368 |
+
"learning_rate": 1.0394489668127739e-05,
|
2369 |
+
"loss": 0.073,
|
2370 |
+
"step": 3030
|
2371 |
+
},
|
2372 |
+
{
|
2373 |
+
"epoch": 0.8229561451001625,
|
2374 |
+
"grad_norm": 1.859375,
|
2375 |
+
"learning_rate": 1.023794614902943e-05,
|
2376 |
+
"loss": 0.108,
|
2377 |
+
"step": 3040
|
2378 |
+
},
|
2379 |
+
{
|
2380 |
+
"epoch": 0.8256632376827288,
|
2381 |
+
"grad_norm": 0.69140625,
|
2382 |
+
"learning_rate": 1.008140262993112e-05,
|
2383 |
+
"loss": 0.0815,
|
2384 |
+
"step": 3050
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 0.828370330265295,
|
2388 |
+
"grad_norm": 0.80859375,
|
2389 |
+
"learning_rate": 9.924859110832813e-06,
|
2390 |
+
"loss": 0.0965,
|
2391 |
+
"step": 3060
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 0.8310774228478613,
|
2395 |
+
"grad_norm": 1.953125,
|
2396 |
+
"learning_rate": 9.768315591734503e-06,
|
2397 |
+
"loss": 0.1145,
|
2398 |
+
"step": 3070
|
2399 |
+
},
|
2400 |
+
{
|
2401 |
+
"epoch": 0.8337845154304278,
|
2402 |
+
"grad_norm": 0.734375,
|
2403 |
+
"learning_rate": 9.611772072636194e-06,
|
2404 |
+
"loss": 0.1319,
|
2405 |
+
"step": 3080
|
2406 |
+
},
|
2407 |
+
{
|
2408 |
+
"epoch": 0.836491608012994,
|
2409 |
+
"grad_norm": 1.671875,
|
2410 |
+
"learning_rate": 9.455228553537885e-06,
|
2411 |
+
"loss": 0.0871,
|
2412 |
+
"step": 3090
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 0.8391987005955603,
|
2416 |
+
"grad_norm": 1.515625,
|
2417 |
+
"learning_rate": 9.298685034439576e-06,
|
2418 |
+
"loss": 0.1207,
|
2419 |
+
"step": 3100
|
2420 |
+
},
|
2421 |
+
{
|
2422 |
+
"epoch": 0.8391987005955603,
|
2423 |
+
"eval_loss": 0.1296384036540985,
|
2424 |
+
"eval_runtime": 103.7944,
|
2425 |
+
"eval_samples_per_second": 4.933,
|
2426 |
+
"eval_steps_per_second": 0.154,
|
2427 |
+
"step": 3100
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"epoch": 0.8419057931781266,
|
2431 |
+
"grad_norm": 2.203125,
|
2432 |
+
"learning_rate": 9.142141515341266e-06,
|
2433 |
+
"loss": 0.1177,
|
2434 |
+
"step": 3110
|
2435 |
+
},
|
2436 |
+
{
|
2437 |
+
"epoch": 0.844612885760693,
|
2438 |
+
"grad_norm": 1.1171875,
|
2439 |
+
"learning_rate": 8.985597996242955e-06,
|
2440 |
+
"loss": 0.1111,
|
2441 |
+
"step": 3120
|
2442 |
+
},
|
2443 |
+
{
|
2444 |
+
"epoch": 0.8473199783432593,
|
2445 |
+
"grad_norm": 0.384765625,
|
2446 |
+
"learning_rate": 8.829054477144646e-06,
|
2447 |
+
"loss": 0.0774,
|
2448 |
+
"step": 3130
|
2449 |
+
},
|
2450 |
+
{
|
2451 |
+
"epoch": 0.8500270709258256,
|
2452 |
+
"grad_norm": 1.3984375,
|
2453 |
+
"learning_rate": 8.672510958046337e-06,
|
2454 |
+
"loss": 0.0864,
|
2455 |
+
"step": 3140
|
2456 |
+
},
|
2457 |
+
{
|
2458 |
+
"epoch": 0.852734163508392,
|
2459 |
+
"grad_norm": 0.42578125,
|
2460 |
+
"learning_rate": 8.515967438948027e-06,
|
2461 |
+
"loss": 0.0914,
|
2462 |
+
"step": 3150
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 0.8554412560909583,
|
2466 |
+
"grad_norm": 0.453125,
|
2467 |
+
"learning_rate": 8.359423919849718e-06,
|
2468 |
+
"loss": 0.0947,
|
2469 |
+
"step": 3160
|
2470 |
+
},
|
2471 |
+
{
|
2472 |
+
"epoch": 0.8581483486735246,
|
2473 |
+
"grad_norm": 1.265625,
|
2474 |
+
"learning_rate": 8.202880400751409e-06,
|
2475 |
+
"loss": 0.0812,
|
2476 |
+
"step": 3170
|
2477 |
+
},
|
2478 |
+
{
|
2479 |
+
"epoch": 0.8608554412560909,
|
2480 |
+
"grad_norm": 1.296875,
|
2481 |
+
"learning_rate": 8.0463368816531e-06,
|
2482 |
+
"loss": 0.0924,
|
2483 |
+
"step": 3180
|
2484 |
+
},
|
2485 |
+
{
|
2486 |
+
"epoch": 0.8635625338386573,
|
2487 |
+
"grad_norm": 0.69921875,
|
2488 |
+
"learning_rate": 7.889793362554792e-06,
|
2489 |
+
"loss": 0.1047,
|
2490 |
+
"step": 3190
|
2491 |
+
},
|
2492 |
+
{
|
2493 |
+
"epoch": 0.8662696264212236,
|
2494 |
+
"grad_norm": 2.0,
|
2495 |
+
"learning_rate": 7.733249843456483e-06,
|
2496 |
+
"loss": 0.1071,
|
2497 |
+
"step": 3200
|
2498 |
+
},
|
2499 |
+
{
|
2500 |
+
"epoch": 0.8662696264212236,
|
2501 |
+
"eval_loss": 0.128614142537117,
|
2502 |
+
"eval_runtime": 105.0877,
|
2503 |
+
"eval_samples_per_second": 4.872,
|
2504 |
+
"eval_steps_per_second": 0.152,
|
2505 |
+
"step": 3200
|
2506 |
+
},
|
2507 |
+
{
|
2508 |
+
"epoch": 0.8689767190037899,
|
2509 |
+
"grad_norm": 1.8984375,
|
2510 |
+
"learning_rate": 7.576706324358172e-06,
|
2511 |
+
"loss": 0.0834,
|
2512 |
+
"step": 3210
|
2513 |
+
},
|
2514 |
+
{
|
2515 |
+
"epoch": 0.8716838115863562,
|
2516 |
+
"grad_norm": 0.94921875,
|
2517 |
+
"learning_rate": 7.420162805259863e-06,
|
2518 |
+
"loss": 0.1098,
|
2519 |
+
"step": 3220
|
2520 |
+
},
|
2521 |
+
{
|
2522 |
+
"epoch": 0.8743909041689226,
|
2523 |
+
"grad_norm": 1.2890625,
|
2524 |
+
"learning_rate": 7.263619286161554e-06,
|
2525 |
+
"loss": 0.1152,
|
2526 |
+
"step": 3230
|
2527 |
+
},
|
2528 |
+
{
|
2529 |
+
"epoch": 0.8770979967514889,
|
2530 |
+
"grad_norm": 0.63671875,
|
2531 |
+
"learning_rate": 7.107075767063244e-06,
|
2532 |
+
"loss": 0.1093,
|
2533 |
+
"step": 3240
|
2534 |
+
},
|
2535 |
+
{
|
2536 |
+
"epoch": 0.8798050893340552,
|
2537 |
+
"grad_norm": 0.93359375,
|
2538 |
+
"learning_rate": 6.950532247964934e-06,
|
2539 |
+
"loss": 0.1116,
|
2540 |
+
"step": 3250
|
2541 |
+
},
|
2542 |
+
{
|
2543 |
+
"epoch": 0.8825121819166215,
|
2544 |
+
"grad_norm": 1.421875,
|
2545 |
+
"learning_rate": 6.793988728866625e-06,
|
2546 |
+
"loss": 0.0824,
|
2547 |
+
"step": 3260
|
2548 |
+
},
|
2549 |
+
{
|
2550 |
+
"epoch": 0.8852192744991879,
|
2551 |
+
"grad_norm": 1.6953125,
|
2552 |
+
"learning_rate": 6.637445209768316e-06,
|
2553 |
+
"loss": 0.1241,
|
2554 |
+
"step": 3270
|
2555 |
+
},
|
2556 |
+
{
|
2557 |
+
"epoch": 0.8879263670817542,
|
2558 |
+
"grad_norm": 1.0859375,
|
2559 |
+
"learning_rate": 6.4809016906700065e-06,
|
2560 |
+
"loss": 0.0967,
|
2561 |
+
"step": 3280
|
2562 |
+
},
|
2563 |
+
{
|
2564 |
+
"epoch": 0.8906334596643205,
|
2565 |
+
"grad_norm": 1.125,
|
2566 |
+
"learning_rate": 6.324358171571697e-06,
|
2567 |
+
"loss": 0.0893,
|
2568 |
+
"step": 3290
|
2569 |
+
},
|
2570 |
+
{
|
2571 |
+
"epoch": 0.8933405522468868,
|
2572 |
+
"grad_norm": 1.1875,
|
2573 |
+
"learning_rate": 6.167814652473388e-06,
|
2574 |
+
"loss": 0.1081,
|
2575 |
+
"step": 3300
|
2576 |
+
},
|
2577 |
+
{
|
2578 |
+
"epoch": 0.8933405522468868,
|
2579 |
+
"eval_loss": 0.12801626324653625,
|
2580 |
+
"eval_runtime": 103.0737,
|
2581 |
+
"eval_samples_per_second": 4.967,
|
2582 |
+
"eval_steps_per_second": 0.155,
|
2583 |
+
"step": 3300
|
2584 |
+
},
|
2585 |
+
{
|
2586 |
+
"epoch": 0.8960476448294532,
|
2587 |
+
"grad_norm": 1.3984375,
|
2588 |
+
"learning_rate": 6.011271133375079e-06,
|
2589 |
+
"loss": 0.1199,
|
2590 |
+
"step": 3310
|
2591 |
+
},
|
2592 |
+
{
|
2593 |
+
"epoch": 0.8987547374120195,
|
2594 |
+
"grad_norm": 1.640625,
|
2595 |
+
"learning_rate": 5.854727614276769e-06,
|
2596 |
+
"loss": 0.0997,
|
2597 |
+
"step": 3320
|
2598 |
+
},
|
2599 |
+
{
|
2600 |
+
"epoch": 0.9014618299945858,
|
2601 |
+
"grad_norm": 0.921875,
|
2602 |
+
"learning_rate": 5.69818409517846e-06,
|
2603 |
+
"loss": 0.1118,
|
2604 |
+
"step": 3330
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"epoch": 0.9041689225771521,
|
2608 |
+
"grad_norm": 1.3828125,
|
2609 |
+
"learning_rate": 5.54164057608015e-06,
|
2610 |
+
"loss": 0.083,
|
2611 |
+
"step": 3340
|
2612 |
+
},
|
2613 |
+
{
|
2614 |
+
"epoch": 0.9068760151597185,
|
2615 |
+
"grad_norm": 1.609375,
|
2616 |
+
"learning_rate": 5.3850970569818414e-06,
|
2617 |
+
"loss": 0.0765,
|
2618 |
+
"step": 3350
|
2619 |
+
},
|
2620 |
+
{
|
2621 |
+
"epoch": 0.9095831077422848,
|
2622 |
+
"grad_norm": 1.0546875,
|
2623 |
+
"learning_rate": 5.228553537883532e-06,
|
2624 |
+
"loss": 0.0925,
|
2625 |
+
"step": 3360
|
2626 |
+
},
|
2627 |
+
{
|
2628 |
+
"epoch": 0.9122902003248511,
|
2629 |
+
"grad_norm": 1.203125,
|
2630 |
+
"learning_rate": 5.072010018785223e-06,
|
2631 |
+
"loss": 0.0941,
|
2632 |
+
"step": 3370
|
2633 |
+
},
|
2634 |
+
{
|
2635 |
+
"epoch": 0.9149972929074174,
|
2636 |
+
"grad_norm": 1.1796875,
|
2637 |
+
"learning_rate": 4.9154664996869136e-06,
|
2638 |
+
"loss": 0.1193,
|
2639 |
+
"step": 3380
|
2640 |
+
},
|
2641 |
+
{
|
2642 |
+
"epoch": 0.9177043854899838,
|
2643 |
+
"grad_norm": 0.333984375,
|
2644 |
+
"learning_rate": 4.758922980588603e-06,
|
2645 |
+
"loss": 0.1124,
|
2646 |
+
"step": 3390
|
2647 |
+
},
|
2648 |
+
{
|
2649 |
+
"epoch": 0.9204114780725501,
|
2650 |
+
"grad_norm": 1.6796875,
|
2651 |
+
"learning_rate": 4.602379461490294e-06,
|
2652 |
+
"loss": 0.0924,
|
2653 |
+
"step": 3400
|
2654 |
+
},
|
2655 |
+
{
|
2656 |
+
"epoch": 0.9204114780725501,
|
2657 |
+
"eval_loss": 0.12878485023975372,
|
2658 |
+
"eval_runtime": 123.0744,
|
2659 |
+
"eval_samples_per_second": 4.16,
|
2660 |
+
"eval_steps_per_second": 0.13,
|
2661 |
+
"step": 3400
|
2662 |
+
},
|
2663 |
+
{
|
2664 |
+
"epoch": 0.9231185706551164,
|
2665 |
+
"grad_norm": 0.86328125,
|
2666 |
+
"learning_rate": 4.445835942391985e-06,
|
2667 |
+
"loss": 0.0938,
|
2668 |
+
"step": 3410
|
2669 |
+
},
|
2670 |
+
{
|
2671 |
+
"epoch": 0.9258256632376828,
|
2672 |
+
"grad_norm": 2.328125,
|
2673 |
+
"learning_rate": 4.289292423293676e-06,
|
2674 |
+
"loss": 0.0839,
|
2675 |
+
"step": 3420
|
2676 |
+
},
|
2677 |
+
{
|
2678 |
+
"epoch": 0.9285327558202491,
|
2679 |
+
"grad_norm": 1.7578125,
|
2680 |
+
"learning_rate": 4.132748904195367e-06,
|
2681 |
+
"loss": 0.1368,
|
2682 |
+
"step": 3430
|
2683 |
+
},
|
2684 |
+
{
|
2685 |
+
"epoch": 0.9312398484028154,
|
2686 |
+
"grad_norm": 2.515625,
|
2687 |
+
"learning_rate": 3.976205385097057e-06,
|
2688 |
+
"loss": 0.1154,
|
2689 |
+
"step": 3440
|
2690 |
+
},
|
2691 |
+
{
|
2692 |
+
"epoch": 0.9339469409853817,
|
2693 |
+
"grad_norm": 0.205078125,
|
2694 |
+
"learning_rate": 3.819661865998748e-06,
|
2695 |
+
"loss": 0.095,
|
2696 |
+
"step": 3450
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 0.9366540335679481,
|
2700 |
+
"grad_norm": 0.87890625,
|
2701 |
+
"learning_rate": 3.6631183469004384e-06,
|
2702 |
+
"loss": 0.0872,
|
2703 |
+
"step": 3460
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 0.9393611261505144,
|
2707 |
+
"grad_norm": 2.515625,
|
2708 |
+
"learning_rate": 3.506574827802129e-06,
|
2709 |
+
"loss": 0.092,
|
2710 |
+
"step": 3470
|
2711 |
+
},
|
2712 |
+
{
|
2713 |
+
"epoch": 0.9420682187330807,
|
2714 |
+
"grad_norm": 1.125,
|
2715 |
+
"learning_rate": 3.35003130870382e-06,
|
2716 |
+
"loss": 0.0944,
|
2717 |
+
"step": 3480
|
2718 |
+
},
|
2719 |
+
{
|
2720 |
+
"epoch": 0.944775311315647,
|
2721 |
+
"grad_norm": 1.578125,
|
2722 |
+
"learning_rate": 3.193487789605511e-06,
|
2723 |
+
"loss": 0.1366,
|
2724 |
+
"step": 3490
|
2725 |
+
},
|
2726 |
+
{
|
2727 |
+
"epoch": 0.9474824038982134,
|
2728 |
+
"grad_norm": 0.5859375,
|
2729 |
+
"learning_rate": 3.036944270507201e-06,
|
2730 |
+
"loss": 0.0948,
|
2731 |
+
"step": 3500
|
2732 |
+
},
|
2733 |
+
{
|
2734 |
+
"epoch": 0.9474824038982134,
|
2735 |
+
"eval_loss": 0.1291881799697876,
|
2736 |
+
"eval_runtime": 104.6704,
|
2737 |
+
"eval_samples_per_second": 4.892,
|
2738 |
+
"eval_steps_per_second": 0.153,
|
2739 |
+
"step": 3500
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 0.9501894964807797,
|
2743 |
+
"grad_norm": 1.375,
|
2744 |
+
"learning_rate": 2.880400751408892e-06,
|
2745 |
+
"loss": 0.1181,
|
2746 |
+
"step": 3510
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 0.952896589063346,
|
2750 |
+
"grad_norm": 0.84375,
|
2751 |
+
"learning_rate": 2.7238572323105826e-06,
|
2752 |
+
"loss": 0.0819,
|
2753 |
+
"step": 3520
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 0.9556036816459123,
|
2757 |
+
"grad_norm": 0.9765625,
|
2758 |
+
"learning_rate": 2.5673137132122733e-06,
|
2759 |
+
"loss": 0.1134,
|
2760 |
+
"step": 3530
|
2761 |
+
},
|
2762 |
+
{
|
2763 |
+
"epoch": 0.9583107742284787,
|
2764 |
+
"grad_norm": 0.5625,
|
2765 |
+
"learning_rate": 2.410770194113964e-06,
|
2766 |
+
"loss": 0.1183,
|
2767 |
+
"step": 3540
|
2768 |
+
},
|
2769 |
+
{
|
2770 |
+
"epoch": 0.961017866811045,
|
2771 |
+
"grad_norm": 0.84765625,
|
2772 |
+
"learning_rate": 2.2542266750156543e-06,
|
2773 |
+
"loss": 0.1021,
|
2774 |
+
"step": 3550
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 0.9637249593936112,
|
2778 |
+
"grad_norm": 1.0390625,
|
2779 |
+
"learning_rate": 2.0976831559173454e-06,
|
2780 |
+
"loss": 0.0871,
|
2781 |
+
"step": 3560
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 0.9664320519761775,
|
2785 |
+
"grad_norm": 1.1171875,
|
2786 |
+
"learning_rate": 1.9411396368190357e-06,
|
2787 |
+
"loss": 0.1036,
|
2788 |
+
"step": 3570
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 0.969139144558744,
|
2792 |
+
"grad_norm": 0.546875,
|
2793 |
+
"learning_rate": 1.7845961177207264e-06,
|
2794 |
+
"loss": 0.0874,
|
2795 |
+
"step": 3580
|
2796 |
+
},
|
2797 |
+
{
|
2798 |
+
"epoch": 0.9718462371413102,
|
2799 |
+
"grad_norm": 0.28515625,
|
2800 |
+
"learning_rate": 1.6280525986224169e-06,
|
2801 |
+
"loss": 0.085,
|
2802 |
+
"step": 3590
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 0.9745533297238765,
|
2806 |
+
"grad_norm": 0.90234375,
|
2807 |
+
"learning_rate": 1.4715090795241078e-06,
|
2808 |
+
"loss": 0.1162,
|
2809 |
+
"step": 3600
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 0.9745533297238765,
|
2813 |
+
"eval_loss": 0.12912487983703613,
|
2814 |
+
"eval_runtime": 106.4924,
|
2815 |
+
"eval_samples_per_second": 4.808,
|
2816 |
+
"eval_steps_per_second": 0.15,
|
2817 |
+
"step": 3600
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 0.9772604223064428,
|
2821 |
+
"grad_norm": 0.74609375,
|
2822 |
+
"learning_rate": 1.3149655604257985e-06,
|
2823 |
+
"loss": 0.1066,
|
2824 |
+
"step": 3610
|
2825 |
+
},
|
2826 |
+
{
|
2827 |
+
"epoch": 0.9799675148890092,
|
2828 |
+
"grad_norm": 1.4609375,
|
2829 |
+
"learning_rate": 1.1584220413274892e-06,
|
2830 |
+
"loss": 0.1533,
|
2831 |
+
"step": 3620
|
2832 |
+
},
|
2833 |
+
{
|
2834 |
+
"epoch": 0.9826746074715755,
|
2835 |
+
"grad_norm": 0.68359375,
|
2836 |
+
"learning_rate": 1.0018785222291797e-06,
|
2837 |
+
"loss": 0.0717,
|
2838 |
+
"step": 3630
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 0.9853817000541418,
|
2842 |
+
"grad_norm": 0.94921875,
|
2843 |
+
"learning_rate": 8.453350031308704e-07,
|
2844 |
+
"loss": 0.0667,
|
2845 |
+
"step": 3640
|
2846 |
+
},
|
2847 |
+
{
|
2848 |
+
"epoch": 0.9880887926367081,
|
2849 |
+
"grad_norm": 0.427734375,
|
2850 |
+
"learning_rate": 6.887914840325611e-07,
|
2851 |
+
"loss": 0.1175,
|
2852 |
+
"step": 3650
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 0.9907958852192745,
|
2856 |
+
"grad_norm": 1.046875,
|
2857 |
+
"learning_rate": 5.322479649342517e-07,
|
2858 |
+
"loss": 0.0871,
|
2859 |
+
"step": 3660
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 0.9935029778018408,
|
2863 |
+
"grad_norm": 1.8515625,
|
2864 |
+
"learning_rate": 3.757044458359424e-07,
|
2865 |
+
"loss": 0.122,
|
2866 |
+
"step": 3670
|
2867 |
+
},
|
2868 |
+
{
|
2869 |
+
"epoch": 0.9962100703844071,
|
2870 |
+
"grad_norm": 0.77734375,
|
2871 |
+
"learning_rate": 2.1916092673763307e-07,
|
2872 |
+
"loss": 0.0922,
|
2873 |
+
"step": 3680
|
2874 |
+
},
|
2875 |
+
{
|
2876 |
+
"epoch": 0.9989171629669734,
|
2877 |
+
"grad_norm": 3.140625,
|
2878 |
+
"learning_rate": 6.261740763932373e-08,
|
2879 |
+
"loss": 0.1331,
|
2880 |
+
"step": 3690
|
2881 |
+
}
|
2882 |
+
],
|
2883 |
+
"logging_steps": 10,
|
2884 |
+
"max_steps": 3694,
|
2885 |
+
"num_input_tokens_seen": 0,
|
2886 |
+
"num_train_epochs": 1,
|
2887 |
+
"save_steps": 500,
|
2888 |
+
"stateful_callbacks": {
|
2889 |
+
"TrainerControl": {
|
2890 |
+
"args": {
|
2891 |
+
"should_epoch_stop": false,
|
2892 |
+
"should_evaluate": false,
|
2893 |
+
"should_log": false,
|
2894 |
+
"should_save": true,
|
2895 |
+
"should_training_stop": true
|
2896 |
+
},
|
2897 |
+
"attributes": {}
|
2898 |
+
}
|
2899 |
+
},
|
2900 |
+
"total_flos": 1.0990508415397056e+18,
|
2901 |
+
"train_batch_size": 32,
|
2902 |
+
"trial_name": null,
|
2903 |
+
"trial_params": null
|
2904 |
+
}
|
checkpoint-3694/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:685ee2596072507a9c0ce1ae768b36fc3337189cbe14f6c946fc5fb838a3c04b
|
3 |
+
size 5176
|
git_hash.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
a5b4a24649e45a6570b33cc01acb57807e4dfa5b
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": true,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.48145466,
|
8 |
+
0.4578275,
|
9 |
+
0.40821073
|
10 |
+
],
|
11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.26862954,
|
14 |
+
0.26130258,
|
15 |
+
0.27577711
|
16 |
+
],
|
17 |
+
"max_pixels": 12845056,
|
18 |
+
"merge_size": 2,
|
19 |
+
"min_pixels": 3136,
|
20 |
+
"patch_size": 14,
|
21 |
+
"processor_class": "ColQwen2Processor",
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"max_pixels": 12845056,
|
26 |
+
"min_pixels": 3136
|
27 |
+
},
|
28 |
+
"temporal_patch_size": 2
|
29 |
+
}
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"validation_set": {"ndcg_at_1": 0.81641, "ndcg_at_3": 0.87151, "ndcg_at_5": 0.87924, "ndcg_at_10": 0.88352, "ndcg_at_20": 0.88599, "ndcg_at_100": 0.89228, "ndcg_at_1000": 0.8945, "map_at_1": 0.81641, "map_at_3": 0.85872, "map_at_5": 0.86283, "map_at_10": 0.86451, "map_at_20": 0.86519, "map_at_100": 0.86613, "map_at_1000": 0.86625, "recall_at_1": 0.81641, "recall_at_3": 0.9082, "recall_at_5": 0.92773, "recall_at_10": 0.94141, "recall_at_20": 0.95117, "recall_at_100": 0.98438, "recall_at_1000": 1.0, "precision_at_1": 0.81641, "precision_at_3": 0.30273, "precision_at_5": 0.18555, "precision_at_10": 0.09414, "precision_at_20": 0.04756, "precision_at_100": 0.00984, "precision_at_1000": 0.001, "mrr_at_1": 0.8203125, "mrr_at_3": 0.8603515624999998, "mrr_at_5": 0.8628906249999998, "mrr_at_10": 0.8655544704861109, "mrr_at_20": 0.8665781348642675, "mrr_at_100": 0.8675737791279903, "mrr_at_1000": 0.8676711773156423, "naucs_at_1_max": 0.34667870891415986, "naucs_at_1_std": -0.20661616231925453, "naucs_at_1_diff1": 0.9396571084820124, "naucs_at_3_max": 0.5166729885733626, "naucs_at_3_std": 0.05950323676330907, "naucs_at_3_diff1": 0.9342216236825106, "naucs_at_5_max": 0.6329364969562152, "naucs_at_5_std": 0.2619697444169589, "naucs_at_5_diff1": 0.9376321560083725, "naucs_at_10_max": 0.660722672615821, "naucs_at_10_std": 0.437248626444334, "naucs_at_10_diff1": 0.9546510563783107, "naucs_at_20_max": 0.6658122614005673, "naucs_at_20_std": 0.4847758170885219, "naucs_at_20_diff1": 0.9508077573821819, "naucs_at_100_max": 0.6851951655323608, "naucs_at_100_std": 0.8932409444836575, "naucs_at_100_diff1": 0.9510016587980088, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.94762, "ndcg_at_5": 0.94762, "ndcg_at_10": 0.94762, "ndcg_at_20": 0.95512, "ndcg_at_100": 0.95512, "ndcg_at_1000": 0.95512, "map_at_1": 0.92, "map_at_3": 0.94, "map_at_5": 0.94, "map_at_10": 0.94, "map_at_20": 0.94201, "map_at_100": 0.94201, "map_at_1000": 0.94201, "recall_at_1": 0.92, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.97, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.097, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.92, "mrr_at_3": 0.94, "mrr_at_5": 0.94, "mrr_at_10": 0.94, "mrr_at_20": 0.9421501831501832, "mrr_at_100": 0.9421501831501832, "mrr_at_1000": 0.9421501831501832, "naucs_at_1_max": 0.5697362278244628, "naucs_at_1_std": -0.5218253968253984, "naucs_at_1_diff1": 0.9489379084967322, "naucs_at_3_max": 0.7642390289449176, "naucs_at_3_std": -0.8249299719887898, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 0.7642390289449118, "naucs_at_5_std": -0.8249299719887969, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 0.7642390289449118, "naucs_at_10_std": -0.8249299719887969, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.97286, "ndcg_at_5": 0.97286, "ndcg_at_10": 0.97286, "ndcg_at_20": 0.97286, "ndcg_at_100": 0.97286, "ndcg_at_1000": 0.97286, "map_at_1": 0.93, "map_at_3": 0.96333, "map_at_5": 0.96333, "map_at_10": 0.96333, "map_at_20": 0.96333, "map_at_100": 0.96333, "map_at_1000": 0.96333, "recall_at_1": 0.93, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.93, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.93, "mrr_at_3": 0.9633333333333334, "mrr_at_5": 0.9633333333333334, "mrr_at_10": 0.9633333333333334, "mrr_at_20": 0.9633333333333334, "mrr_at_100": 0.9633333333333334, "mrr_at_1000": 0.9633333333333334, "naucs_at_1_max": 0.7465652927837806, "naucs_at_1_std": 0.10897692410297374, "naucs_at_1_diff1": 0.9626517273576113, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.97, "ndcg_at_3": 0.98762, "ndcg_at_5": 0.98762, "ndcg_at_10": 0.98762, "ndcg_at_20": 0.98762, "ndcg_at_100": 0.98762, "ndcg_at_1000": 0.98762, "map_at_1": 0.97, "map_at_3": 0.98333, "map_at_5": 0.98333, "map_at_10": 0.98333, "map_at_20": 0.98333, "map_at_100": 0.98333, "map_at_1000": 0.98333, "recall_at_1": 0.97, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.97, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.97, "mrr_at_3": 0.9833333333333333, "mrr_at_5": 0.9833333333333333, "mrr_at_10": 0.9833333333333333, "mrr_at_20": 0.9833333333333333, "mrr_at_100": 0.9833333333333333, "mrr_at_1000": 0.9833333333333333, "naucs_at_1_max": 0.8638344226579567, "naucs_at_1_std": -0.28197945845004707, "naucs_at_1_diff1": 0.9564270152505465, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.85, "ndcg_at_3": 0.92809, "ndcg_at_5": 0.9324, "ndcg_at_10": 0.9324, "ndcg_at_20": 0.93503, "ndcg_at_100": 0.93503, "ndcg_at_1000": 0.93503, "map_at_1": 0.85, "map_at_3": 0.91, "map_at_5": 0.9125, "map_at_10": 0.9125, "map_at_20": 0.91327, "map_at_100": 0.91327, "map_at_1000": 0.91327, "recall_at_1": 0.85, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.85, "precision_at_3": 0.32667, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.87, "mrr_at_3": 0.9266666666666667, "mrr_at_5": 0.9266666666666667, "mrr_at_10": 0.9266666666666667, "mrr_at_20": 0.9274358974358975, "mrr_at_100": 0.9274358974358975, "mrr_at_1000": 0.9274358974358975, "naucs_at_1_max": 0.47617962902700983, "naucs_at_1_std": 0.33045883501464407, "naucs_at_1_diff1": 0.8781646599414249, "naucs_at_3_max": 1.0, "naucs_at_3_std": 0.6381886087768379, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.7222222222222276, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 0.7222222222222276, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "infovqa_subsampled": {"ndcg_at_1": 0.86, "ndcg_at_3": 0.88671, "ndcg_at_5": 0.89825, "ndcg_at_10": 0.90151, "ndcg_at_20": 0.90849, "ndcg_at_100": 0.91162, "ndcg_at_1000": 0.91339, "map_at_1": 0.86, "map_at_3": 0.88067, "map_at_5": 0.88707, "map_at_10": 0.88843, "map_at_20": 0.89056, "map_at_100": 0.89092, "map_at_1000": 0.89099, "recall_at_1": 0.86, "recall_at_3": 0.904, "recall_at_5": 0.932, "recall_at_10": 0.942, "recall_at_20": 0.968, "recall_at_100": 0.986, "recall_at_1000": 1.0, "precision_at_1": 0.86, "precision_at_3": 0.30133, "precision_at_5": 0.1864, "precision_at_10": 0.0942, "precision_at_20": 0.0484, "precision_at_100": 0.00986, "precision_at_1000": 0.001, "mrr_at_1": 0.858, "mrr_at_3": 0.8799999999999999, "mrr_at_5": 0.8859999999999999, "mrr_at_10": 0.8877992063492062, "mrr_at_20": 0.8897055999555997, "mrr_at_100": 0.8900658496714725, "mrr_at_1000": 0.8901272220832652, "naucs_at_1_max": 0.6271096023278367, "naucs_at_1_std": -0.043875571567133, "naucs_at_1_diff1": 0.9370583344880139, "naucs_at_3_max": 0.6881127450980395, "naucs_at_3_std": -0.021095938375348355, "naucs_at_3_diff1": 0.9083313881108002, "naucs_at_5_max": 0.8094002306805071, "naucs_at_5_std": 0.05795847750865092, "naucs_at_5_diff1": 0.9197424067666282, "naucs_at_10_max": 0.877426832802087, "naucs_at_10_std": 0.2035963810811664, "naucs_at_10_diff1": 0.9250619788145158, "naucs_at_20_max": 0.9557948179271724, "naucs_at_20_std": 0.38013538748832426, "naucs_at_20_diff1": 0.9325980392156829, "naucs_at_100_max": 0.9626517273576126, "naucs_at_100_std": 0.448312658396679, "naucs_at_100_diff1": 0.981325863678799, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.47, "ndcg_at_3": 0.53112, "ndcg_at_5": 0.56176, "ndcg_at_10": 0.58036, "ndcg_at_20": 0.59124, "ndcg_at_100": 0.61372, "ndcg_at_1000": 0.62957, "map_at_1": 0.47, "map_at_3": 0.51567, "map_at_5": 0.53277, "map_at_10": 0.54035, "map_at_20": 0.54347, "map_at_100": 0.54625, "map_at_1000": 0.54684, "recall_at_1": 0.47, "recall_at_3": 0.576, "recall_at_5": 0.65, "recall_at_10": 0.708, "recall_at_20": 0.75, "recall_at_100": 0.876, "recall_at_1000": 1.0, "precision_at_1": 0.47, "precision_at_3": 0.192, "precision_at_5": 0.13, "precision_at_10": 0.0708, "precision_at_20": 0.0375, "precision_at_100": 0.00876, "precision_at_1000": 0.001, "mrr_at_1": 0.47, "mrr_at_3": 0.5140000000000002, "mrr_at_5": 0.5322999999999999, "mrr_at_10": 0.5393452380952379, "mrr_at_20": 0.5430581398134026, "mrr_at_100": 0.5455877170766977, "mrr_at_1000": 0.5461605124926291, "naucs_at_1_max": 0.5899734964859769, "naucs_at_1_std": 0.37540315668719265, "naucs_at_1_diff1": 0.8310658104669103, "naucs_at_3_max": 0.5424525576127407, "naucs_at_3_std": 0.425733305596006, "naucs_at_3_diff1": 0.7247359175276799, "naucs_at_5_max": 0.5197754089022696, "naucs_at_5_std": 0.5280852795182682, "naucs_at_5_diff1": 0.6994124827081123, "naucs_at_10_max": 0.4841097869266883, "naucs_at_10_std": 0.5795468783396347, "naucs_at_10_diff1": 0.6604425085310391, "naucs_at_20_max": 0.4785557299843014, "naucs_at_20_std": 0.6286844583987442, "naucs_at_20_diff1": 0.6366300366300363, "naucs_at_100_max": 0.531426717344952, "naucs_at_100_std": 0.8670699298538366, "naucs_at_100_diff1": 0.5190043570965052, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "arxivqa_subsampled": {"ndcg_at_1": 0.8, "ndcg_at_3": 0.84812, "ndcg_at_5": 0.86369, "ndcg_at_10": 0.87151, "ndcg_at_20": 0.87714, "ndcg_at_100": 0.88221, "ndcg_at_1000": 0.88366, "map_at_1": 0.8, "map_at_3": 0.837, "map_at_5": 0.8456, "map_at_10": 0.84885, "map_at_20": 0.85044, "map_at_100": 0.85123, "map_at_1000": 0.85132, "recall_at_1": 0.8, "recall_at_3": 0.88, "recall_at_5": 0.918, "recall_at_10": 0.942, "recall_at_20": 0.964, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.8, "precision_at_3": 0.29333, "precision_at_5": 0.1836, "precision_at_10": 0.0942, "precision_at_20": 0.0482, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.794, "mrr_at_3": 0.8339999999999999, "mrr_at_5": 0.8417999999999999, "mrr_at_10": 0.8457571428571429, "mrr_at_20": 0.8470214830491145, "mrr_at_100": 0.847837729621968, "mrr_at_1000": 0.847903412604169, "naucs_at_1_max": 0.7301598401598397, "naucs_at_1_std": 0.13073426573426558, "naucs_at_1_diff1": 0.9151098901098901, "naucs_at_3_max": 0.7855154311167684, "naucs_at_3_std": 0.19653197581928136, "naucs_at_3_diff1": 0.8981466751511297, "naucs_at_5_max": 0.8119719432488443, "naucs_at_5_std": 0.1740338411787435, "naucs_at_5_diff1": 0.9070278517911231, "naucs_at_10_max": 0.8026658939437882, "naucs_at_10_std": 0.2013587044013021, "naucs_at_10_diff1": 0.9108149006729143, "naucs_at_20_max": 0.9162257495590788, "naucs_at_20_std": 0.37184873949579655, "naucs_at_20_diff1": 0.9110384894698595, "naucs_at_100_max": 0.947712418300658, "naucs_at_100_std": 0.3913165266106556, "naucs_at_100_diff1": 0.9738562091503188, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.82143, "ndcg_at_3": 0.88125, "ndcg_at_5": 0.88724, "ndcg_at_10": 0.89646, "ndcg_at_20": 0.90181, "ndcg_at_100": 0.90464, "ndcg_at_1000": 0.90464, "map_at_1": 0.82143, "map_at_3": 0.86726, "map_at_5": 0.87065, "map_at_10": 0.87444, "map_at_20": 0.87587, "map_at_100": 0.87633, "map_at_1000": 0.87633, "recall_at_1": 0.82143, "recall_at_3": 0.92143, "recall_at_5": 0.93571, "recall_at_10": 0.96429, "recall_at_20": 0.98571, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.82143, "precision_at_3": 0.30714, "precision_at_5": 0.18714, "precision_at_10": 0.09643, "precision_at_20": 0.04929, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.8285714285714286, "mrr_at_3": 0.8708333333333336, "mrr_at_5": 0.8742261904761907, "mrr_at_10": 0.8779606009070298, "mrr_at_20": 0.8793680292629874, "mrr_at_100": 0.8798495301637429, "mrr_at_1000": 0.8798495301637429, "naucs_at_1_max": 0.4043094907866057, "naucs_at_1_std": 0.16813948880523036, "naucs_at_1_diff1": 0.8608282147810575, "naucs_at_3_max": 0.5415287327052029, "naucs_at_3_std": 0.32170443935149834, "naucs_at_3_diff1": 0.7899371869960117, "naucs_at_5_max": 0.5449216723726537, "naucs_at_5_std": 0.295959124390499, "naucs_at_5_diff1": 0.768025728810043, "naucs_at_10_max": 0.6852007469654555, "naucs_at_10_std": 0.596965452847805, "naucs_at_10_diff1": 0.7665732959850585, "naucs_at_20_max": 0.8231792717086873, "naucs_at_20_std": 0.7496498599439745, "naucs_at_20_diff1": 0.6626984126984181, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.62237, "ndcg_at_3": 0.72528, "ndcg_at_5": 0.7518, "ndcg_at_10": 0.7704, "ndcg_at_20": 0.77829, "ndcg_at_100": 0.78521, "ndcg_at_1000": 0.787, "map_at_1": 0.62237, "map_at_3": 0.70014, "map_at_5": 0.71487, "map_at_10": 0.72262, "map_at_20": 0.72486, "map_at_100": 0.72587, "map_at_1000": 0.72594, "recall_at_1": 0.62237, "recall_at_3": 0.79796, "recall_at_5": 0.8623, "recall_at_10": 0.91942, "recall_at_20": 0.95009, "recall_at_100": 0.98677, "recall_at_1000": 1.0, "precision_at_1": 0.62237, "precision_at_3": 0.26599, "precision_at_5": 0.17246, "precision_at_10": 0.09194, "precision_at_20": 0.0475, "precision_at_100": 0.00987, "precision_at_1000": 0.001, "mrr_at_1": 0.6277811184606134, "mrr_at_3": 0.7027460412908401, "mrr_at_5": 0.7170875927039494, "mrr_at_10": 0.7253199896916075, "mrr_at_20": 0.7277180395724787, "mrr_at_100": 0.7287256043001191, "mrr_at_1000": 0.7287991066528416, "naucs_at_1_max": 0.13553936519738788, "naucs_at_1_std": -0.3187519674953281, "naucs_at_1_diff1": 0.7778249427309417, "naucs_at_3_max": 0.2141299663362708, "naucs_at_3_std": -0.2863201435902689, "naucs_at_3_diff1": 0.6746349432069665, "naucs_at_5_max": 0.26199278239549034, "naucs_at_5_std": -0.2097766943253057, "naucs_at_5_diff1": 0.6504413592115734, "naucs_at_10_max": 0.33005867437923625, "naucs_at_10_std": 0.042015716590848955, "naucs_at_10_diff1": 0.5806124077911619, "naucs_at_20_max": 0.38884886089913584, "naucs_at_20_std": 0.25394752368146895, "naucs_at_20_diff1": 0.576841503912515, "naucs_at_100_max": 0.6555237795463111, "naucs_at_100_std": 0.7055850937111812, "naucs_at_100_diff1": 0.6635432021140835, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.74, "ndcg_at_3": 0.84833, "ndcg_at_5": 0.85651, "ndcg_at_10": 0.86656, "ndcg_at_20": 0.86887, "ndcg_at_100": 0.87251, "ndcg_at_1000": 0.87251, "map_at_1": 0.74, "map_at_3": 0.82333, "map_at_5": 0.82783, "map_at_10": 0.83218, "map_at_20": 0.8327, "map_at_100": 0.83316, "map_at_1000": 0.83316, "recall_at_1": 0.74, "recall_at_3": 0.92, "recall_at_5": 0.94, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.74, "precision_at_3": 0.30667, "precision_at_5": 0.188, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.76, "mrr_at_3": 0.8333333333333335, "mrr_at_5": 0.8378333333333334, "mrr_at_10": 0.8423571428571431, "mrr_at_20": 0.8428834586466167, "mrr_at_100": 0.84334179197995, "mrr_at_1000": 0.84334179197995, "naucs_at_1_max": -0.18346782368922665, "naucs_at_1_std": -0.312314991281781, "naucs_at_1_diff1": 0.6844410202343775, "naucs_at_3_max": 0.05304621848739506, "naucs_at_3_std": 0.02485994397759261, "naucs_at_3_diff1": 0.6601890756302518, "naucs_at_5_max": 0.30104263927793357, "naucs_at_5_std": 0.15561780267662587, "naucs_at_5_diff1": 0.7639277933395614, "naucs_at_10_max": -0.35434173669467856, "naucs_at_10_std": -0.3963585434173691, "naucs_at_10_diff1": 0.8638344226579531, "naucs_at_20_max": -0.5929038281979383, "naucs_at_20_std": -0.5088702147525547, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"151646": {
|
29 |
+
"content": "<|object_ref_start|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"151647": {
|
37 |
+
"content": "<|object_ref_end|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"151648": {
|
45 |
+
"content": "<|box_start|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"151649": {
|
53 |
+
"content": "<|box_end|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"151650": {
|
61 |
+
"content": "<|quad_start|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"151651": {
|
69 |
+
"content": "<|quad_end|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"151652": {
|
77 |
+
"content": "<|vision_start|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"151653": {
|
85 |
+
"content": "<|vision_end|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"151654": {
|
93 |
+
"content": "<|vision_pad|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"151655": {
|
101 |
+
"content": "<|image_pad|>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"151656": {
|
109 |
+
"content": "<|video_pad|>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
}
|
116 |
+
},
|
117 |
+
"additional_special_tokens": [
|
118 |
+
"<|im_start|>",
|
119 |
+
"<|im_end|>",
|
120 |
+
"<|object_ref_start|>",
|
121 |
+
"<|object_ref_end|>",
|
122 |
+
"<|box_start|>",
|
123 |
+
"<|box_end|>",
|
124 |
+
"<|quad_start|>",
|
125 |
+
"<|quad_end|>",
|
126 |
+
"<|vision_start|>",
|
127 |
+
"<|vision_end|>",
|
128 |
+
"<|vision_pad|>",
|
129 |
+
"<|image_pad|>",
|
130 |
+
"<|video_pad|>"
|
131 |
+
],
|
132 |
+
"bos_token": null,
|
133 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
134 |
+
"clean_up_tokenization_spaces": false,
|
135 |
+
"eos_token": "<|im_end|>",
|
136 |
+
"errors": "replace",
|
137 |
+
"model_max_length": 32768,
|
138 |
+
"pad_token": "<|endoftext|>",
|
139 |
+
"padding_side": "left",
|
140 |
+
"processor_class": "ColQwen2Processor",
|
141 |
+
"split_special_tokens": false,
|
142 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
143 |
+
"unk_token": null
|
144 |
+
}
|
training_config.yml
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
config:
|
2 |
+
(): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
|
3 |
+
output_dir: !path ../../../models/colqwen2-multi
|
4 |
+
processor:
|
5 |
+
(): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
|
6 |
+
class_to_instanciate: !ext colpali_engine.models.ColQwen2Processor
|
7 |
+
pretrained_model_name_or_path: "./models/Qwen2-VL-2B-Instruct" # "./models/paligemma-3b-mix-448"
|
8 |
+
# max_length: 50
|
9 |
+
|
10 |
+
model:
|
11 |
+
(): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
|
12 |
+
class_to_instanciate: !ext colpali_engine.models.ColQwen2
|
13 |
+
pretrained_model_name_or_path: "./models/colqwen2_base"
|
14 |
+
torch_dtype: !ext torch.bfloat16
|
15 |
+
use_cache: false
|
16 |
+
# device_map: "auto"
|
17 |
+
# quantization_config:
|
18 |
+
# (): transformers.BitsAndBytesConfig
|
19 |
+
# load_in_4bit: true
|
20 |
+
# bnb_4bit_quant_type: "nf4"
|
21 |
+
# bnb_4bit_compute_dtype: "bfloat16"
|
22 |
+
# bnb_4bit_use_double_quant: true
|
23 |
+
|
24 |
+
dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_train_set_detailed
|
25 |
+
eval_dataset_loader: !import ../data/test_data.yaml
|
26 |
+
|
27 |
+
# max_length: 50
|
28 |
+
run_eval: true
|
29 |
+
add_suffix: true
|
30 |
+
loss_func:
|
31 |
+
(): colpali_engine.loss.late_interaction_losses.ColbertPairwiseCELoss
|
32 |
+
tr_args: !import ../tr_args/default_tr_args.yaml
|
33 |
+
peft_config:
|
34 |
+
(): peft.LoraConfig
|
35 |
+
r: 32
|
36 |
+
lora_alpha: 32
|
37 |
+
lora_dropout: 0.1
|
38 |
+
init_lora_weights: "gaussian"
|
39 |
+
bias: "none"
|
40 |
+
task_type: "FEATURE_EXTRACTION"
|
41 |
+
target_modules: '(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
42 |
+
# target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
43 |
+
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|