Upload 18 files
Browse filesfirst time training
- README.md +202 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- checkpoint-4400/README.md +202 -0
- checkpoint-4400/adapter_config.json +31 -0
- checkpoint-4400/adapter_model.safetensors +3 -0
- checkpoint-4400/optimizer.pt +3 -0
- checkpoint-4400/rng_state.pth +3 -0
- checkpoint-4400/scheduler.pt +3 -0
- checkpoint-4400/special_tokens_map.json +24 -0
- checkpoint-4400/tokenizer.json +0 -0
- checkpoint-4400/tokenizer_config.json +130 -0
- checkpoint-4400/trainer_state.json +1573 -0
- checkpoint-4400/training_args.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +130 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
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 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"qkv_proj",
|
24 |
+
"o_proj",
|
25 |
+
"down_proj",
|
26 |
+
"gate_up_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b0f4d1be2d30f8d739c7de33ac8884c3189294518cfd14bf78ebe2cc8809e02
|
3 |
+
size 100697728
|
checkpoint-4400/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
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-4400/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"qkv_proj",
|
24 |
+
"o_proj",
|
25 |
+
"down_proj",
|
26 |
+
"gate_up_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
checkpoint-4400/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:860422fed9192d449bbaad799da52902bcea634b2470df0c171a7d422f11f958
|
3 |
+
size 100697728
|
checkpoint-4400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f371a2a4e4dafea8ac084da51d8c649b2abaad28bdc8fafdbcd3d6184181de0d
|
3 |
+
size 201541754
|
checkpoint-4400/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c80389514dd2139bf381c1cc48778a2407a96731c7238bb38f039e9982ddf96e
|
3 |
+
size 14180
|
checkpoint-4400/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3800e192756712ddbce2a75e8345dab77b19b165456e08cfc198eb6798665bfc
|
3 |
+
size 1064
|
checkpoint-4400/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-4400/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4400/tokenizer_config.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": true,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
}
|
117 |
+
},
|
118 |
+
"bos_token": "<s>",
|
119 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|endoftext|>",
|
122 |
+
"legacy": false,
|
123 |
+
"model_max_length": 4096,
|
124 |
+
"pad_token": "<unk>",
|
125 |
+
"padding_side": "left",
|
126 |
+
"sp_model_kwargs": {},
|
127 |
+
"tokenizer_class": "LlamaTokenizer",
|
128 |
+
"unk_token": "<unk>",
|
129 |
+
"use_default_system_prompt": false
|
130 |
+
}
|
checkpoint-4400/trainer_state.json
ADDED
@@ -0,0 +1,1573 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9952499434517078,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4400,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.004523863379325944,
|
13 |
+
"grad_norm": 1.2934283018112183,
|
14 |
+
"learning_rate": 1.1299435028248588e-07,
|
15 |
+
"loss": 1.8133,
|
16 |
+
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.009047726758651889,
|
20 |
+
"grad_norm": 1.8428480625152588,
|
21 |
+
"learning_rate": 2.2598870056497177e-07,
|
22 |
+
"loss": 1.6188,
|
23 |
+
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.013571590137977834,
|
27 |
+
"grad_norm": 1.6636091470718384,
|
28 |
+
"learning_rate": 3.3898305084745766e-07,
|
29 |
+
"loss": 1.6899,
|
30 |
+
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.018095453517303777,
|
34 |
+
"grad_norm": 2.0820469856262207,
|
35 |
+
"learning_rate": 4.5197740112994353e-07,
|
36 |
+
"loss": 1.703,
|
37 |
+
"step": 80
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.022619316896629722,
|
41 |
+
"grad_norm": 2.4241092205047607,
|
42 |
+
"learning_rate": 5.649717514124295e-07,
|
43 |
+
"loss": 1.7203,
|
44 |
+
"step": 100
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.027143180275955667,
|
48 |
+
"grad_norm": 4.02646017074585,
|
49 |
+
"learning_rate": 6.779661016949153e-07,
|
50 |
+
"loss": 1.6147,
|
51 |
+
"step": 120
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.03166704365528161,
|
55 |
+
"grad_norm": 2.3496134281158447,
|
56 |
+
"learning_rate": 7.909604519774013e-07,
|
57 |
+
"loss": 1.6992,
|
58 |
+
"step": 140
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.036190907034607554,
|
62 |
+
"grad_norm": 2.2215747833251953,
|
63 |
+
"learning_rate": 9.039548022598871e-07,
|
64 |
+
"loss": 1.4976,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.040714770413933496,
|
69 |
+
"grad_norm": 4.31510066986084,
|
70 |
+
"learning_rate": 1.016949152542373e-06,
|
71 |
+
"loss": 1.4859,
|
72 |
+
"step": 180
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.045238633793259445,
|
76 |
+
"grad_norm": 2.950899600982666,
|
77 |
+
"learning_rate": 1.129943502824859e-06,
|
78 |
+
"loss": 1.3391,
|
79 |
+
"step": 200
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.049762497172585386,
|
83 |
+
"grad_norm": 4.141122341156006,
|
84 |
+
"learning_rate": 1.2429378531073449e-06,
|
85 |
+
"loss": 1.3377,
|
86 |
+
"step": 220
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.054286360551911335,
|
90 |
+
"grad_norm": 2.346282720565796,
|
91 |
+
"learning_rate": 1.3559322033898307e-06,
|
92 |
+
"loss": 1.2225,
|
93 |
+
"step": 240
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.05881022393123728,
|
97 |
+
"grad_norm": 1.5768523216247559,
|
98 |
+
"learning_rate": 1.4689265536723166e-06,
|
99 |
+
"loss": 1.1489,
|
100 |
+
"step": 260
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.06333408731056323,
|
104 |
+
"grad_norm": 1.6714472770690918,
|
105 |
+
"learning_rate": 1.5819209039548026e-06,
|
106 |
+
"loss": 1.2574,
|
107 |
+
"step": 280
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.06785795068988916,
|
111 |
+
"grad_norm": 1.2765991687774658,
|
112 |
+
"learning_rate": 1.6949152542372882e-06,
|
113 |
+
"loss": 1.0654,
|
114 |
+
"step": 300
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.07238181406921511,
|
118 |
+
"grad_norm": 0.9537855386734009,
|
119 |
+
"learning_rate": 1.8079096045197741e-06,
|
120 |
+
"loss": 1.0468,
|
121 |
+
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.07690567744854106,
|
125 |
+
"grad_norm": 0.8233529329299927,
|
126 |
+
"learning_rate": 1.92090395480226e-06,
|
127 |
+
"loss": 1.0045,
|
128 |
+
"step": 340
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.08142954082786699,
|
132 |
+
"grad_norm": 0.977318286895752,
|
133 |
+
"learning_rate": 2.033898305084746e-06,
|
134 |
+
"loss": 1.0425,
|
135 |
+
"step": 360
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.08595340420719294,
|
139 |
+
"grad_norm": 0.7735580205917358,
|
140 |
+
"learning_rate": 2.146892655367232e-06,
|
141 |
+
"loss": 0.8498,
|
142 |
+
"step": 380
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.09047726758651889,
|
146 |
+
"grad_norm": 0.9134358763694763,
|
147 |
+
"learning_rate": 2.259887005649718e-06,
|
148 |
+
"loss": 0.8149,
|
149 |
+
"step": 400
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.09500113096584484,
|
153 |
+
"grad_norm": 1.034114956855774,
|
154 |
+
"learning_rate": 2.372881355932204e-06,
|
155 |
+
"loss": 0.9009,
|
156 |
+
"step": 420
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.09952499434517077,
|
160 |
+
"grad_norm": 0.8178341388702393,
|
161 |
+
"learning_rate": 2.4858757062146898e-06,
|
162 |
+
"loss": 0.8489,
|
163 |
+
"step": 440
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.10404885772449672,
|
167 |
+
"grad_norm": 0.9051856398582458,
|
168 |
+
"learning_rate": 2.5988700564971753e-06,
|
169 |
+
"loss": 0.8824,
|
170 |
+
"step": 460
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.10857272110382267,
|
174 |
+
"grad_norm": 0.7567653059959412,
|
175 |
+
"learning_rate": 2.7118644067796613e-06,
|
176 |
+
"loss": 0.8307,
|
177 |
+
"step": 480
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.1130965844831486,
|
181 |
+
"grad_norm": 0.800140917301178,
|
182 |
+
"learning_rate": 2.8248587570621473e-06,
|
183 |
+
"loss": 0.7441,
|
184 |
+
"step": 500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.11762044786247455,
|
188 |
+
"grad_norm": 0.6388680338859558,
|
189 |
+
"learning_rate": 2.9378531073446333e-06,
|
190 |
+
"loss": 0.7953,
|
191 |
+
"step": 520
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.1221443112418005,
|
195 |
+
"grad_norm": 1.6128122806549072,
|
196 |
+
"learning_rate": 3.0508474576271192e-06,
|
197 |
+
"loss": 0.7497,
|
198 |
+
"step": 540
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.12666817462112645,
|
202 |
+
"grad_norm": 0.7322567105293274,
|
203 |
+
"learning_rate": 3.163841807909605e-06,
|
204 |
+
"loss": 0.7005,
|
205 |
+
"step": 560
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.1311920380004524,
|
209 |
+
"grad_norm": 0.678276777267456,
|
210 |
+
"learning_rate": 3.2768361581920903e-06,
|
211 |
+
"loss": 0.678,
|
212 |
+
"step": 580
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.13571590137977832,
|
216 |
+
"grad_norm": 0.5271691679954529,
|
217 |
+
"learning_rate": 3.3898305084745763e-06,
|
218 |
+
"loss": 0.6971,
|
219 |
+
"step": 600
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.14023976475910427,
|
223 |
+
"grad_norm": 1.0406115055084229,
|
224 |
+
"learning_rate": 3.5028248587570623e-06,
|
225 |
+
"loss": 0.6432,
|
226 |
+
"step": 620
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.14476362813843022,
|
230 |
+
"grad_norm": 1.0237056016921997,
|
231 |
+
"learning_rate": 3.6158192090395483e-06,
|
232 |
+
"loss": 0.6278,
|
233 |
+
"step": 640
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.14928749151775617,
|
237 |
+
"grad_norm": 0.4786810278892517,
|
238 |
+
"learning_rate": 3.7288135593220342e-06,
|
239 |
+
"loss": 0.6545,
|
240 |
+
"step": 660
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.15381135489708211,
|
244 |
+
"grad_norm": 0.9167463183403015,
|
245 |
+
"learning_rate": 3.84180790960452e-06,
|
246 |
+
"loss": 0.5941,
|
247 |
+
"step": 680
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.15833521827640806,
|
251 |
+
"grad_norm": 0.764803409576416,
|
252 |
+
"learning_rate": 3.954802259887006e-06,
|
253 |
+
"loss": 0.5993,
|
254 |
+
"step": 700
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.16285908165573398,
|
258 |
+
"grad_norm": 0.5060482025146484,
|
259 |
+
"learning_rate": 4.067796610169492e-06,
|
260 |
+
"loss": 0.7018,
|
261 |
+
"step": 720
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.16738294503505993,
|
265 |
+
"grad_norm": 1.2368682622909546,
|
266 |
+
"learning_rate": 4.180790960451978e-06,
|
267 |
+
"loss": 0.656,
|
268 |
+
"step": 740
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.17190680841438588,
|
272 |
+
"grad_norm": 0.4092175364494324,
|
273 |
+
"learning_rate": 4.293785310734464e-06,
|
274 |
+
"loss": 0.6578,
|
275 |
+
"step": 760
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.17643067179371183,
|
279 |
+
"grad_norm": 1.4677420854568481,
|
280 |
+
"learning_rate": 4.40677966101695e-06,
|
281 |
+
"loss": 0.6246,
|
282 |
+
"step": 780
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.18095453517303778,
|
286 |
+
"grad_norm": 0.56260085105896,
|
287 |
+
"learning_rate": 4.519774011299436e-06,
|
288 |
+
"loss": 0.6593,
|
289 |
+
"step": 800
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.18547839855236373,
|
293 |
+
"grad_norm": 0.6638891696929932,
|
294 |
+
"learning_rate": 4.632768361581922e-06,
|
295 |
+
"loss": 0.6385,
|
296 |
+
"step": 820
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.19000226193168968,
|
300 |
+
"grad_norm": 0.9223029613494873,
|
301 |
+
"learning_rate": 4.745762711864408e-06,
|
302 |
+
"loss": 0.6267,
|
303 |
+
"step": 840
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.1945261253110156,
|
307 |
+
"grad_norm": 0.666900634765625,
|
308 |
+
"learning_rate": 4.8587570621468936e-06,
|
309 |
+
"loss": 0.5532,
|
310 |
+
"step": 860
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.19904998869034154,
|
314 |
+
"grad_norm": 0.7605287432670593,
|
315 |
+
"learning_rate": 4.9717514124293796e-06,
|
316 |
+
"loss": 0.6349,
|
317 |
+
"step": 880
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.2035738520696675,
|
321 |
+
"grad_norm": 0.7302986979484558,
|
322 |
+
"learning_rate": 4.9997779957257335e-06,
|
323 |
+
"loss": 0.6167,
|
324 |
+
"step": 900
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.20809771544899344,
|
328 |
+
"grad_norm": 0.9552111625671387,
|
329 |
+
"learning_rate": 4.998791389568115e-06,
|
330 |
+
"loss": 0.6314,
|
331 |
+
"step": 920
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.2126215788283194,
|
335 |
+
"grad_norm": 1.1077909469604492,
|
336 |
+
"learning_rate": 4.997015825567898e-06,
|
337 |
+
"loss": 0.6525,
|
338 |
+
"step": 940
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.21714544220764534,
|
342 |
+
"grad_norm": 0.6709986925125122,
|
343 |
+
"learning_rate": 4.994451864334162e-06,
|
344 |
+
"loss": 0.5795,
|
345 |
+
"step": 960
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.22166930558697126,
|
349 |
+
"grad_norm": 0.5601279735565186,
|
350 |
+
"learning_rate": 4.991100315401203e-06,
|
351 |
+
"loss": 0.6191,
|
352 |
+
"step": 980
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.2261931689662972,
|
356 |
+
"grad_norm": 1.1237138509750366,
|
357 |
+
"learning_rate": 4.986962236972929e-06,
|
358 |
+
"loss": 0.6329,
|
359 |
+
"step": 1000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.23071703234562316,
|
363 |
+
"grad_norm": 0.987455427646637,
|
364 |
+
"learning_rate": 4.982038935588749e-06,
|
365 |
+
"loss": 0.572,
|
366 |
+
"step": 1020
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.2352408957249491,
|
370 |
+
"grad_norm": 1.0568902492523193,
|
371 |
+
"learning_rate": 4.976331965711056e-06,
|
372 |
+
"loss": 0.6261,
|
373 |
+
"step": 1040
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.23976475910427505,
|
377 |
+
"grad_norm": 0.5604099035263062,
|
378 |
+
"learning_rate": 4.969843129234422e-06,
|
379 |
+
"loss": 0.554,
|
380 |
+
"step": 1060
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.244288622483601,
|
384 |
+
"grad_norm": 0.9130414128303528,
|
385 |
+
"learning_rate": 4.962574474916678e-06,
|
386 |
+
"loss": 0.5794,
|
387 |
+
"step": 1080
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.24881248586292695,
|
391 |
+
"grad_norm": 1.5077348947525024,
|
392 |
+
"learning_rate": 4.954528297732047e-06,
|
393 |
+
"loss": 0.6414,
|
394 |
+
"step": 1100
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.2533363492422529,
|
398 |
+
"grad_norm": 0.5713602900505066,
|
399 |
+
"learning_rate": 4.94570713814654e-06,
|
400 |
+
"loss": 0.6231,
|
401 |
+
"step": 1120
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2578602126215788,
|
405 |
+
"grad_norm": 1.139797568321228,
|
406 |
+
"learning_rate": 4.93611378131584e-06,
|
407 |
+
"loss": 0.6535,
|
408 |
+
"step": 1140
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.2623840760009048,
|
412 |
+
"grad_norm": 1.476881980895996,
|
413 |
+
"learning_rate": 4.925751256205924e-06,
|
414 |
+
"loss": 0.561,
|
415 |
+
"step": 1160
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.2669079393802307,
|
419 |
+
"grad_norm": 0.9005554914474487,
|
420 |
+
"learning_rate": 4.914622834636717e-06,
|
421 |
+
"loss": 0.6006,
|
422 |
+
"step": 1180
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.27143180275955664,
|
426 |
+
"grad_norm": 0.6789364218711853,
|
427 |
+
"learning_rate": 4.902732030249057e-06,
|
428 |
+
"loss": 0.6368,
|
429 |
+
"step": 1200
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.2759556661388826,
|
433 |
+
"grad_norm": 0.8574463725090027,
|
434 |
+
"learning_rate": 4.890082597395316e-06,
|
435 |
+
"loss": 0.6138,
|
436 |
+
"step": 1220
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.28047952951820854,
|
440 |
+
"grad_norm": 1.226874589920044,
|
441 |
+
"learning_rate": 4.876678529954011e-06,
|
442 |
+
"loss": 0.618,
|
443 |
+
"step": 1240
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.2850033928975345,
|
447 |
+
"grad_norm": 0.49481701850891113,
|
448 |
+
"learning_rate": 4.8625240600688e-06,
|
449 |
+
"loss": 0.5962,
|
450 |
+
"step": 1260
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.28952725627686043,
|
454 |
+
"grad_norm": 0.8259846568107605,
|
455 |
+
"learning_rate": 4.847623656812241e-06,
|
456 |
+
"loss": 0.5725,
|
457 |
+
"step": 1280
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.2940511196561864,
|
461 |
+
"grad_norm": 1.3541384935379028,
|
462 |
+
"learning_rate": 4.831982024774742e-06,
|
463 |
+
"loss": 0.6237,
|
464 |
+
"step": 1300
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.29857498303551233,
|
468 |
+
"grad_norm": 0.6489030718803406,
|
469 |
+
"learning_rate": 4.815604102579159e-06,
|
470 |
+
"loss": 0.6559,
|
471 |
+
"step": 1320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.30309884641483825,
|
475 |
+
"grad_norm": 0.6666083931922913,
|
476 |
+
"learning_rate": 4.798495061321492e-06,
|
477 |
+
"loss": 0.5905,
|
478 |
+
"step": 1340
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.30762270979416423,
|
482 |
+
"grad_norm": 1.033155918121338,
|
483 |
+
"learning_rate": 4.780660302938188e-06,
|
484 |
+
"loss": 0.5638,
|
485 |
+
"step": 1360
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.31214657317349015,
|
489 |
+
"grad_norm": 0.6378616690635681,
|
490 |
+
"learning_rate": 4.762105458500556e-06,
|
491 |
+
"loss": 0.5433,
|
492 |
+
"step": 1380
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.3166704365528161,
|
496 |
+
"grad_norm": 1.3384662866592407,
|
497 |
+
"learning_rate": 4.742836386436831e-06,
|
498 |
+
"loss": 0.5535,
|
499 |
+
"step": 1400
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.32119429993214205,
|
503 |
+
"grad_norm": 0.6671473979949951,
|
504 |
+
"learning_rate": 4.722859170682468e-06,
|
505 |
+
"loss": 0.612,
|
506 |
+
"step": 1420
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.32571816331146797,
|
510 |
+
"grad_norm": 0.98403000831604,
|
511 |
+
"learning_rate": 4.702180118759219e-06,
|
512 |
+
"loss": 0.5735,
|
513 |
+
"step": 1440
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.33024202669079394,
|
517 |
+
"grad_norm": 1.0076704025268555,
|
518 |
+
"learning_rate": 4.680805759783622e-06,
|
519 |
+
"loss": 0.5879,
|
520 |
+
"step": 1460
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.33476589007011986,
|
524 |
+
"grad_norm": 0.9248991012573242,
|
525 |
+
"learning_rate": 4.6587428424055324e-06,
|
526 |
+
"loss": 0.5747,
|
527 |
+
"step": 1480
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.33928975344944584,
|
531 |
+
"grad_norm": 0.7047035098075867,
|
532 |
+
"learning_rate": 4.635998332677325e-06,
|
533 |
+
"loss": 0.5827,
|
534 |
+
"step": 1500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.34381361682877176,
|
538 |
+
"grad_norm": 0.9783876538276672,
|
539 |
+
"learning_rate": 4.612579411854468e-06,
|
540 |
+
"loss": 0.5671,
|
541 |
+
"step": 1520
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.34833748020809774,
|
545 |
+
"grad_norm": 0.8747379183769226,
|
546 |
+
"learning_rate": 4.588493474128137e-06,
|
547 |
+
"loss": 0.5934,
|
548 |
+
"step": 1540
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.35286134358742366,
|
552 |
+
"grad_norm": 0.8138028383255005,
|
553 |
+
"learning_rate": 4.563748124290612e-06,
|
554 |
+
"loss": 0.7145,
|
555 |
+
"step": 1560
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.3573852069667496,
|
559 |
+
"grad_norm": 0.5983314514160156,
|
560 |
+
"learning_rate": 4.538351175334167e-06,
|
561 |
+
"loss": 0.5961,
|
562 |
+
"step": 1580
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.36190907034607556,
|
566 |
+
"grad_norm": 0.7765645980834961,
|
567 |
+
"learning_rate": 4.512310645984231e-06,
|
568 |
+
"loss": 0.6588,
|
569 |
+
"step": 1600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.3664329337254015,
|
573 |
+
"grad_norm": 0.6621695756912231,
|
574 |
+
"learning_rate": 4.485634758167589e-06,
|
575 |
+
"loss": 0.6608,
|
576 |
+
"step": 1620
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.37095679710472745,
|
580 |
+
"grad_norm": 0.5030168294906616,
|
581 |
+
"learning_rate": 4.458331934416427e-06,
|
582 |
+
"loss": 0.5647,
|
583 |
+
"step": 1640
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.3754806604840534,
|
587 |
+
"grad_norm": 0.7155460715293884,
|
588 |
+
"learning_rate": 4.430410795209031e-06,
|
589 |
+
"loss": 0.5815,
|
590 |
+
"step": 1660
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.38000452386337935,
|
594 |
+
"grad_norm": 1.0417250394821167,
|
595 |
+
"learning_rate": 4.401880156248006e-06,
|
596 |
+
"loss": 0.6304,
|
597 |
+
"step": 1680
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.38452838724270527,
|
601 |
+
"grad_norm": 1.251464605331421,
|
602 |
+
"learning_rate": 4.372749025676829e-06,
|
603 |
+
"loss": 0.5852,
|
604 |
+
"step": 1700
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.3890522506220312,
|
608 |
+
"grad_norm": 0.53974848985672,
|
609 |
+
"learning_rate": 4.343026601235666e-06,
|
610 |
+
"loss": 0.5883,
|
611 |
+
"step": 1720
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.39357611400135717,
|
615 |
+
"grad_norm": 0.720723569393158,
|
616 |
+
"learning_rate": 4.312722267357311e-06,
|
617 |
+
"loss": 0.6516,
|
618 |
+
"step": 1740
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.3980999773806831,
|
622 |
+
"grad_norm": 0.8760417103767395,
|
623 |
+
"learning_rate": 4.281845592204188e-06,
|
624 |
+
"loss": 0.5926,
|
625 |
+
"step": 1760
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.40262384076000907,
|
629 |
+
"grad_norm": 0.7676084637641907,
|
630 |
+
"learning_rate": 4.2504063246473395e-06,
|
631 |
+
"loss": 0.6594,
|
632 |
+
"step": 1780
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.407147704139335,
|
636 |
+
"grad_norm": 0.6235904097557068,
|
637 |
+
"learning_rate": 4.218414391188353e-06,
|
638 |
+
"loss": 0.6249,
|
639 |
+
"step": 1800
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.41167156751866096,
|
643 |
+
"grad_norm": 0.5731521248817444,
|
644 |
+
"learning_rate": 4.185879892825222e-06,
|
645 |
+
"loss": 0.613,
|
646 |
+
"step": 1820
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.4161954308979869,
|
650 |
+
"grad_norm": 0.8284727334976196,
|
651 |
+
"learning_rate": 4.152813101863087e-06,
|
652 |
+
"loss": 0.6487,
|
653 |
+
"step": 1840
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.4207192942773128,
|
657 |
+
"grad_norm": 0.5617169141769409,
|
658 |
+
"learning_rate": 4.119224458670905e-06,
|
659 |
+
"loss": 0.5878,
|
660 |
+
"step": 1860
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.4252431576566388,
|
664 |
+
"grad_norm": 0.647582471370697,
|
665 |
+
"learning_rate": 4.085124568385057e-06,
|
666 |
+
"loss": 0.6037,
|
667 |
+
"step": 1880
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.4297670210359647,
|
671 |
+
"grad_norm": 0.7462798357009888,
|
672 |
+
"learning_rate": 4.050524197560921e-06,
|
673 |
+
"loss": 0.5911,
|
674 |
+
"step": 1900
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.4342908844152907,
|
678 |
+
"grad_norm": 0.6552990674972534,
|
679 |
+
"learning_rate": 4.015434270773485e-06,
|
680 |
+
"loss": 0.6064,
|
681 |
+
"step": 1920
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.4388147477946166,
|
685 |
+
"grad_norm": 0.8512873649597168,
|
686 |
+
"learning_rate": 3.979865867168071e-06,
|
687 |
+
"loss": 0.5766,
|
688 |
+
"step": 1940
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.4433386111739425,
|
692 |
+
"grad_norm": 0.6242995262145996,
|
693 |
+
"learning_rate": 3.943830216962254e-06,
|
694 |
+
"loss": 0.603,
|
695 |
+
"step": 1960
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.4478624745532685,
|
699 |
+
"grad_norm": 0.933954119682312,
|
700 |
+
"learning_rate": 3.9073386979000715e-06,
|
701 |
+
"loss": 0.6316,
|
702 |
+
"step": 1980
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.4523863379325944,
|
706 |
+
"grad_norm": 0.5889476537704468,
|
707 |
+
"learning_rate": 3.870402831659676e-06,
|
708 |
+
"loss": 0.5686,
|
709 |
+
"step": 2000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.4569102013119204,
|
713 |
+
"grad_norm": 0.5107278227806091,
|
714 |
+
"learning_rate": 3.833034280215518e-06,
|
715 |
+
"loss": 0.6149,
|
716 |
+
"step": 2020
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.4614340646912463,
|
720 |
+
"grad_norm": 0.546362042427063,
|
721 |
+
"learning_rate": 3.795244842156246e-06,
|
722 |
+
"loss": 0.6593,
|
723 |
+
"step": 2040
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.4659579280705723,
|
727 |
+
"grad_norm": 0.7260658740997314,
|
728 |
+
"learning_rate": 3.757046448959474e-06,
|
729 |
+
"loss": 0.576,
|
730 |
+
"step": 2060
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.4704817914498982,
|
734 |
+
"grad_norm": 0.5332072377204895,
|
735 |
+
"learning_rate": 3.718451161224584e-06,
|
736 |
+
"loss": 0.6064,
|
737 |
+
"step": 2080
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.47500565482922413,
|
741 |
+
"grad_norm": 0.5485090613365173,
|
742 |
+
"learning_rate": 3.679471164864763e-06,
|
743 |
+
"loss": 0.6147,
|
744 |
+
"step": 2100
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.4795295182085501,
|
748 |
+
"grad_norm": 0.6777561902999878,
|
749 |
+
"learning_rate": 3.640118767259474e-06,
|
750 |
+
"loss": 0.5975,
|
751 |
+
"step": 2120
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.48405338158787603,
|
755 |
+
"grad_norm": 0.5616791248321533,
|
756 |
+
"learning_rate": 3.600406393368577e-06,
|
757 |
+
"loss": 0.5684,
|
758 |
+
"step": 2140
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.488577244967202,
|
762 |
+
"grad_norm": 0.7273005843162537,
|
763 |
+
"learning_rate": 3.560346581809328e-06,
|
764 |
+
"loss": 0.5439,
|
765 |
+
"step": 2160
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.4931011083465279,
|
769 |
+
"grad_norm": 0.399677574634552,
|
770 |
+
"learning_rate": 3.51995198089748e-06,
|
771 |
+
"loss": 0.6252,
|
772 |
+
"step": 2180
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.4976249717258539,
|
776 |
+
"grad_norm": 0.5627871155738831,
|
777 |
+
"learning_rate": 3.479235344653767e-06,
|
778 |
+
"loss": 0.6454,
|
779 |
+
"step": 2200
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.5021488351051798,
|
783 |
+
"grad_norm": 0.7673916816711426,
|
784 |
+
"learning_rate": 3.4382095287769962e-06,
|
785 |
+
"loss": 0.5485,
|
786 |
+
"step": 2220
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.5066726984845058,
|
790 |
+
"grad_norm": 0.8236356377601624,
|
791 |
+
"learning_rate": 3.396887486585047e-06,
|
792 |
+
"loss": 0.6054,
|
793 |
+
"step": 2240
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.5111965618638317,
|
797 |
+
"grad_norm": 0.9059731364250183,
|
798 |
+
"learning_rate": 3.355282264925047e-06,
|
799 |
+
"loss": 0.5705,
|
800 |
+
"step": 2260
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.5157204252431576,
|
804 |
+
"grad_norm": 0.8679450750350952,
|
805 |
+
"learning_rate": 3.3134070000540114e-06,
|
806 |
+
"loss": 0.5901,
|
807 |
+
"step": 2280
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.5202442886224836,
|
811 |
+
"grad_norm": 0.5972412824630737,
|
812 |
+
"learning_rate": 3.2712749134912582e-06,
|
813 |
+
"loss": 0.5561,
|
814 |
+
"step": 2300
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.5247681520018096,
|
818 |
+
"grad_norm": 0.830877959728241,
|
819 |
+
"learning_rate": 3.2288993078439034e-06,
|
820 |
+
"loss": 0.6464,
|
821 |
+
"step": 2320
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.5292920153811355,
|
825 |
+
"grad_norm": 1.2185938358306885,
|
826 |
+
"learning_rate": 3.1862935626067492e-06,
|
827 |
+
"loss": 0.5784,
|
828 |
+
"step": 2340
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.5338158787604614,
|
832 |
+
"grad_norm": 0.6374582648277283,
|
833 |
+
"learning_rate": 3.1434711299379025e-06,
|
834 |
+
"loss": 0.5661,
|
835 |
+
"step": 2360
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.5383397421397874,
|
839 |
+
"grad_norm": 0.7829556465148926,
|
840 |
+
"learning_rate": 3.100445530411442e-06,
|
841 |
+
"loss": 0.5385,
|
842 |
+
"step": 2380
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.5428636055191133,
|
846 |
+
"grad_norm": 0.8443902134895325,
|
847 |
+
"learning_rate": 3.0572303487484935e-06,
|
848 |
+
"loss": 0.5565,
|
849 |
+
"step": 2400
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.5473874688984393,
|
853 |
+
"grad_norm": 1.1685762405395508,
|
854 |
+
"learning_rate": 3.013839229528046e-06,
|
855 |
+
"loss": 0.5781,
|
856 |
+
"step": 2420
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.5519113322777652,
|
860 |
+
"grad_norm": 0.9711598753929138,
|
861 |
+
"learning_rate": 2.9702858728788714e-06,
|
862 |
+
"loss": 0.6448,
|
863 |
+
"step": 2440
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.5564351956570912,
|
867 |
+
"grad_norm": 0.43809574842453003,
|
868 |
+
"learning_rate": 2.9265840301538995e-06,
|
869 |
+
"loss": 0.558,
|
870 |
+
"step": 2460
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.5609590590364171,
|
874 |
+
"grad_norm": 0.6405979990959167,
|
875 |
+
"learning_rate": 2.8827474995884304e-06,
|
876 |
+
"loss": 0.6875,
|
877 |
+
"step": 2480
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.565482922415743,
|
881 |
+
"grad_norm": 0.6583331823348999,
|
882 |
+
"learning_rate": 2.8387901219435298e-06,
|
883 |
+
"loss": 0.5485,
|
884 |
+
"step": 2500
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.570006785795069,
|
888 |
+
"grad_norm": 0.7614380121231079,
|
889 |
+
"learning_rate": 2.7947257761360136e-06,
|
890 |
+
"loss": 0.5632,
|
891 |
+
"step": 2520
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.5745306491743949,
|
895 |
+
"grad_norm": 0.69844651222229,
|
896 |
+
"learning_rate": 2.750568374856372e-06,
|
897 |
+
"loss": 0.6059,
|
898 |
+
"step": 2540
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.5790545125537209,
|
902 |
+
"grad_norm": 0.7071551084518433,
|
903 |
+
"learning_rate": 2.7063318601760386e-06,
|
904 |
+
"loss": 0.5265,
|
905 |
+
"step": 2560
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.5835783759330468,
|
909 |
+
"grad_norm": 0.6122928857803345,
|
910 |
+
"learning_rate": 2.6620301991453755e-06,
|
911 |
+
"loss": 0.5629,
|
912 |
+
"step": 2580
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.5881022393123728,
|
916 |
+
"grad_norm": 0.8555611968040466,
|
917 |
+
"learning_rate": 2.617677379383781e-06,
|
918 |
+
"loss": 0.5967,
|
919 |
+
"step": 2600
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.5926261026916987,
|
923 |
+
"grad_norm": 0.5617034435272217,
|
924 |
+
"learning_rate": 2.5732874046632938e-06,
|
925 |
+
"loss": 0.6009,
|
926 |
+
"step": 2620
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.5971499660710247,
|
930 |
+
"grad_norm": 0.6981135606765747,
|
931 |
+
"learning_rate": 2.528874290487102e-06,
|
932 |
+
"loss": 0.5641,
|
933 |
+
"step": 2640
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.6016738294503506,
|
937 |
+
"grad_norm": 0.5575506687164307,
|
938 |
+
"learning_rate": 2.4844520596643495e-06,
|
939 |
+
"loss": 0.5759,
|
940 |
+
"step": 2660
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.6061976928296765,
|
944 |
+
"grad_norm": 0.7685838341712952,
|
945 |
+
"learning_rate": 2.4400347378826296e-06,
|
946 |
+
"loss": 0.5343,
|
947 |
+
"step": 2680
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.6107215562090025,
|
951 |
+
"grad_norm": 0.7420554161071777,
|
952 |
+
"learning_rate": 2.395636349279577e-06,
|
953 |
+
"loss": 0.6218,
|
954 |
+
"step": 2700
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.6152454195883285,
|
958 |
+
"grad_norm": 0.43521085381507874,
|
959 |
+
"learning_rate": 2.3512709120149436e-06,
|
960 |
+
"loss": 0.5303,
|
961 |
+
"step": 2720
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.6197692829676543,
|
965 |
+
"grad_norm": 0.6557121276855469,
|
966 |
+
"learning_rate": 2.3069524338445666e-06,
|
967 |
+
"loss": 0.5794,
|
968 |
+
"step": 2740
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.6242931463469803,
|
972 |
+
"grad_norm": 0.7263210415840149,
|
973 |
+
"learning_rate": 2.2626949076976153e-06,
|
974 |
+
"loss": 0.6239,
|
975 |
+
"step": 2760
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.6288170097263063,
|
979 |
+
"grad_norm": 0.5805336833000183,
|
980 |
+
"learning_rate": 2.2185123072585253e-06,
|
981 |
+
"loss": 0.5821,
|
982 |
+
"step": 2780
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.6333408731056323,
|
986 |
+
"grad_norm": 0.8271047472953796,
|
987 |
+
"learning_rate": 2.174418582555005e-06,
|
988 |
+
"loss": 0.5924,
|
989 |
+
"step": 2800
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.6378647364849581,
|
993 |
+
"grad_norm": 0.49003851413726807,
|
994 |
+
"learning_rate": 2.1304276555535123e-06,
|
995 |
+
"loss": 0.5567,
|
996 |
+
"step": 2820
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.6423885998642841,
|
1000 |
+
"grad_norm": 0.6948228478431702,
|
1001 |
+
"learning_rate": 2.086553415763597e-06,
|
1002 |
+
"loss": 0.541,
|
1003 |
+
"step": 2840
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.6469124632436101,
|
1007 |
+
"grad_norm": 0.7717708945274353,
|
1008 |
+
"learning_rate": 2.0428097158524768e-06,
|
1009 |
+
"loss": 0.6128,
|
1010 |
+
"step": 2860
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.6514363266229359,
|
1014 |
+
"grad_norm": 0.8652535676956177,
|
1015 |
+
"learning_rate": 1.999210367271261e-06,
|
1016 |
+
"loss": 0.5484,
|
1017 |
+
"step": 2880
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.6559601900022619,
|
1021 |
+
"grad_norm": 0.48044684529304504,
|
1022 |
+
"learning_rate": 1.9557691358941796e-06,
|
1023 |
+
"loss": 0.6335,
|
1024 |
+
"step": 2900
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.6604840533815879,
|
1028 |
+
"grad_norm": 0.6042224764823914,
|
1029 |
+
"learning_rate": 1.9124997376722038e-06,
|
1030 |
+
"loss": 0.5719,
|
1031 |
+
"step": 2920
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.6650079167609139,
|
1035 |
+
"grad_norm": 0.45004037022590637,
|
1036 |
+
"learning_rate": 1.869415834302429e-06,
|
1037 |
+
"loss": 0.5828,
|
1038 |
+
"step": 2940
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.6695317801402397,
|
1042 |
+
"grad_norm": 0.7315308451652527,
|
1043 |
+
"learning_rate": 1.826531028914593e-06,
|
1044 |
+
"loss": 0.5809,
|
1045 |
+
"step": 2960
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.6740556435195657,
|
1049 |
+
"grad_norm": 0.4399823546409607,
|
1050 |
+
"learning_rate": 1.7838588617760733e-06,
|
1051 |
+
"loss": 0.5933,
|
1052 |
+
"step": 2980
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.6785795068988917,
|
1056 |
+
"grad_norm": 1.064976692199707,
|
1057 |
+
"learning_rate": 1.7414128060167457e-06,
|
1058 |
+
"loss": 0.5469,
|
1059 |
+
"step": 3000
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.6831033702782175,
|
1063 |
+
"grad_norm": 0.7710141539573669,
|
1064 |
+
"learning_rate": 1.6992062633750346e-06,
|
1065 |
+
"loss": 0.585,
|
1066 |
+
"step": 3020
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.6876272336575435,
|
1070 |
+
"grad_norm": 0.673542857170105,
|
1071 |
+
"learning_rate": 1.657252559966502e-06,
|
1072 |
+
"loss": 0.5436,
|
1073 |
+
"step": 3040
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.6921510970368695,
|
1077 |
+
"grad_norm": 0.6577861309051514,
|
1078 |
+
"learning_rate": 1.6155649420763214e-06,
|
1079 |
+
"loss": 0.6201,
|
1080 |
+
"step": 3060
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.6966749604161955,
|
1084 |
+
"grad_norm": 0.9896159768104553,
|
1085 |
+
"learning_rate": 1.5741565719769447e-06,
|
1086 |
+
"loss": 0.6079,
|
1087 |
+
"step": 3080
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.7011988237955213,
|
1091 |
+
"grad_norm": 0.7078260183334351,
|
1092 |
+
"learning_rate": 1.5330405237723078e-06,
|
1093 |
+
"loss": 0.6218,
|
1094 |
+
"step": 3100
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.7057226871748473,
|
1098 |
+
"grad_norm": 1.2103734016418457,
|
1099 |
+
"learning_rate": 1.4922297792698645e-06,
|
1100 |
+
"loss": 0.5955,
|
1101 |
+
"step": 3120
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.7102465505541733,
|
1105 |
+
"grad_norm": 0.6530666947364807,
|
1106 |
+
"learning_rate": 1.4517372238817668e-06,
|
1107 |
+
"loss": 0.5647,
|
1108 |
+
"step": 3140
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.7147704139334992,
|
1112 |
+
"grad_norm": 0.6449224352836609,
|
1113 |
+
"learning_rate": 1.4115756425564798e-06,
|
1114 |
+
"loss": 0.6194,
|
1115 |
+
"step": 3160
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.7192942773128251,
|
1119 |
+
"grad_norm": 0.5960292220115662,
|
1120 |
+
"learning_rate": 1.3717577157421169e-06,
|
1121 |
+
"loss": 0.5926,
|
1122 |
+
"step": 3180
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.7238181406921511,
|
1126 |
+
"grad_norm": 0.6450957655906677,
|
1127 |
+
"learning_rate": 1.3322960153827632e-06,
|
1128 |
+
"loss": 0.6137,
|
1129 |
+
"step": 3200
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.7283420040714771,
|
1133 |
+
"grad_norm": 0.5211399793624878,
|
1134 |
+
"learning_rate": 1.293203000949072e-06,
|
1135 |
+
"loss": 0.5796,
|
1136 |
+
"step": 3220
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.732865867450803,
|
1140 |
+
"grad_norm": 0.6112457513809204,
|
1141 |
+
"learning_rate": 1.2544910155043545e-06,
|
1142 |
+
"loss": 0.6187,
|
1143 |
+
"step": 3240
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.7373897308301289,
|
1147 |
+
"grad_norm": 0.5904879570007324,
|
1148 |
+
"learning_rate": 1.2161722818074412e-06,
|
1149 |
+
"loss": 0.5708,
|
1150 |
+
"step": 3260
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.7419135942094549,
|
1154 |
+
"grad_norm": 0.5986872911453247,
|
1155 |
+
"learning_rate": 1.1782588984535129e-06,
|
1156 |
+
"loss": 0.5455,
|
1157 |
+
"step": 3280
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.7464374575887808,
|
1161 |
+
"grad_norm": 0.716018795967102,
|
1162 |
+
"learning_rate": 1.14076283605415e-06,
|
1163 |
+
"loss": 0.6109,
|
1164 |
+
"step": 3300
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.7509613209681067,
|
1168 |
+
"grad_norm": 0.5863745212554932,
|
1169 |
+
"learning_rate": 1.1036959334577708e-06,
|
1170 |
+
"loss": 0.5875,
|
1171 |
+
"step": 3320
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.7554851843474327,
|
1175 |
+
"grad_norm": 0.8205773830413818,
|
1176 |
+
"learning_rate": 1.0670698940116937e-06,
|
1177 |
+
"loss": 0.6015,
|
1178 |
+
"step": 3340
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.7600090477267587,
|
1182 |
+
"grad_norm": 0.6910251975059509,
|
1183 |
+
"learning_rate": 1.030896281866964e-06,
|
1184 |
+
"loss": 0.5625,
|
1185 |
+
"step": 3360
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.7645329111060846,
|
1189 |
+
"grad_norm": 0.42625927925109863,
|
1190 |
+
"learning_rate": 9.951865183271443e-07,
|
1191 |
+
"loss": 0.5823,
|
1192 |
+
"step": 3380
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.7690567744854105,
|
1196 |
+
"grad_norm": 0.742891788482666,
|
1197 |
+
"learning_rate": 9.599518782421954e-07,
|
1198 |
+
"loss": 0.5209,
|
1199 |
+
"step": 3400
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.7735806378647365,
|
1203 |
+
"grad_norm": 0.6565542817115784,
|
1204 |
+
"learning_rate": 9.252034864486062e-07,
|
1205 |
+
"loss": 0.5896,
|
1206 |
+
"step": 3420
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.7781045012440624,
|
1210 |
+
"grad_norm": 0.7679634690284729,
|
1211 |
+
"learning_rate": 8.909523142568807e-07,
|
1212 |
+
"loss": 0.6889,
|
1213 |
+
"step": 3440
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.7826283646233884,
|
1217 |
+
"grad_norm": 0.8022564649581909,
|
1218 |
+
"learning_rate": 8.572091759875081e-07,
|
1219 |
+
"loss": 0.5643,
|
1220 |
+
"step": 3460
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.7871522280027143,
|
1224 |
+
"grad_norm": 1.0336594581604004,
|
1225 |
+
"learning_rate": 8.239847255564889e-07,
|
1226 |
+
"loss": 0.6212,
|
1227 |
+
"step": 3480
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.7916760913820403,
|
1231 |
+
"grad_norm": 0.6547170877456665,
|
1232 |
+
"learning_rate": 7.912894531115184e-07,
|
1233 |
+
"loss": 0.5685,
|
1234 |
+
"step": 3500
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.7961999547613662,
|
1238 |
+
"grad_norm": 0.725557267665863,
|
1239 |
+
"learning_rate": 7.591336817198683e-07,
|
1240 |
+
"loss": 0.5953,
|
1241 |
+
"step": 3520
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.8007238181406922,
|
1245 |
+
"grad_norm": 0.8147058486938477,
|
1246 |
+
"learning_rate": 7.275275641090238e-07,
|
1247 |
+
"loss": 0.628,
|
1248 |
+
"step": 3540
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.8052476815200181,
|
1252 |
+
"grad_norm": 0.5000850558280945,
|
1253 |
+
"learning_rate": 6.964810794611093e-07,
|
1254 |
+
"loss": 0.5696,
|
1255 |
+
"step": 3560
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.809771544899344,
|
1259 |
+
"grad_norm": 0.9064733386039734,
|
1260 |
+
"learning_rate": 6.660040302620974e-07,
|
1261 |
+
"loss": 0.6752,
|
1262 |
+
"step": 3580
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.81429540827867,
|
1266 |
+
"grad_norm": 0.7876561284065247,
|
1267 |
+
"learning_rate": 6.361060392068177e-07,
|
1268 |
+
"loss": 0.6045,
|
1269 |
+
"step": 3600
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.818819271657996,
|
1273 |
+
"grad_norm": 0.5467254519462585,
|
1274 |
+
"learning_rate": 6.067965461607275e-07,
|
1275 |
+
"loss": 0.5963,
|
1276 |
+
"step": 3620
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.8233431350373219,
|
1280 |
+
"grad_norm": 0.5970877408981323,
|
1281 |
+
"learning_rate": 5.780848051794066e-07,
|
1282 |
+
"loss": 0.6115,
|
1283 |
+
"step": 3640
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.8278669984166478,
|
1287 |
+
"grad_norm": 0.809258759021759,
|
1288 |
+
"learning_rate": 5.499798815867208e-07,
|
1289 |
+
"loss": 0.53,
|
1290 |
+
"step": 3660
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.8323908617959738,
|
1294 |
+
"grad_norm": 0.9609009027481079,
|
1295 |
+
"learning_rate": 5.224906491125778e-07,
|
1296 |
+
"loss": 0.5172,
|
1297 |
+
"step": 3680
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.8369147251752997,
|
1301 |
+
"grad_norm": 0.5807494521141052,
|
1302 |
+
"learning_rate": 4.95625787091169e-07,
|
1303 |
+
"loss": 0.5784,
|
1304 |
+
"step": 3700
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.8414385885546256,
|
1308 |
+
"grad_norm": 0.8828917145729065,
|
1309 |
+
"learning_rate": 4.693937777205973e-07,
|
1310 |
+
"loss": 0.6114,
|
1311 |
+
"step": 3720
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.8459624519339516,
|
1315 |
+
"grad_norm": 1.2154064178466797,
|
1316 |
+
"learning_rate": 4.438029033847402e-07,
|
1317 |
+
"loss": 0.5837,
|
1318 |
+
"step": 3740
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.8504863153132776,
|
1322 |
+
"grad_norm": 0.5537241101264954,
|
1323 |
+
"learning_rate": 4.1886124403820864e-07,
|
1324 |
+
"loss": 0.5766,
|
1325 |
+
"step": 3760
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.8550101786926034,
|
1329 |
+
"grad_norm": 0.9004805088043213,
|
1330 |
+
"learning_rate": 3.94576674655211e-07,
|
1331 |
+
"loss": 0.6033,
|
1332 |
+
"step": 3780
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.8595340420719294,
|
1336 |
+
"grad_norm": 0.7978100776672363,
|
1337 |
+
"learning_rate": 3.7095686274314757e-07,
|
1338 |
+
"loss": 0.5284,
|
1339 |
+
"step": 3800
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.8640579054512554,
|
1343 |
+
"grad_norm": 0.7304428219795227,
|
1344 |
+
"learning_rate": 3.4800926592169995e-07,
|
1345 |
+
"loss": 0.6011,
|
1346 |
+
"step": 3820
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.8685817688305814,
|
1350 |
+
"grad_norm": 0.7252260446548462,
|
1351 |
+
"learning_rate": 3.2574112956819613e-07,
|
1352 |
+
"loss": 0.5691,
|
1353 |
+
"step": 3840
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.8731056322099072,
|
1357 |
+
"grad_norm": 0.6625013947486877,
|
1358 |
+
"learning_rate": 3.041594845299856e-07,
|
1359 |
+
"loss": 0.5782,
|
1360 |
+
"step": 3860
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.8776294955892332,
|
1364 |
+
"grad_norm": 0.5668479800224304,
|
1365 |
+
"learning_rate": 2.832711449045461e-07,
|
1366 |
+
"loss": 0.5781,
|
1367 |
+
"step": 3880
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.8821533589685592,
|
1371 |
+
"grad_norm": 0.6604365110397339,
|
1372 |
+
"learning_rate": 2.630827058880345e-07,
|
1373 |
+
"loss": 0.5579,
|
1374 |
+
"step": 3900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.886677222347885,
|
1378 |
+
"grad_norm": 0.9126925468444824,
|
1379 |
+
"learning_rate": 2.4360054169294377e-07,
|
1380 |
+
"loss": 0.6684,
|
1381 |
+
"step": 3920
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.891201085727211,
|
1385 |
+
"grad_norm": 0.5072206854820251,
|
1386 |
+
"learning_rate": 2.2483080353553537e-07,
|
1387 |
+
"loss": 0.6443,
|
1388 |
+
"step": 3940
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.895724949106537,
|
1392 |
+
"grad_norm": 0.5561603307723999,
|
1393 |
+
"learning_rate": 2.067794176936838e-07,
|
1394 |
+
"loss": 0.6012,
|
1395 |
+
"step": 3960
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.900248812485863,
|
1399 |
+
"grad_norm": 0.5377748012542725,
|
1400 |
+
"learning_rate": 1.8945208363573553e-07,
|
1401 |
+
"loss": 0.5513,
|
1402 |
+
"step": 3980
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.9047726758651888,
|
1406 |
+
"grad_norm": 0.6415522694587708,
|
1407 |
+
"learning_rate": 1.7285427222098388e-07,
|
1408 |
+
"loss": 0.6421,
|
1409 |
+
"step": 4000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.9092965392445148,
|
1413 |
+
"grad_norm": 0.7068675756454468,
|
1414 |
+
"learning_rate": 1.569912239723237e-07,
|
1415 |
+
"loss": 0.6059,
|
1416 |
+
"step": 4020
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.9138204026238408,
|
1420 |
+
"grad_norm": 0.5292190909385681,
|
1421 |
+
"learning_rate": 1.4186794742162918e-07,
|
1422 |
+
"loss": 0.5233,
|
1423 |
+
"step": 4040
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.9183442660031667,
|
1427 |
+
"grad_norm": 0.7200678586959839,
|
1428 |
+
"learning_rate": 1.27489217528384e-07,
|
1429 |
+
"loss": 0.607,
|
1430 |
+
"step": 4060
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.9228681293824926,
|
1434 |
+
"grad_norm": 0.5470794439315796,
|
1435 |
+
"learning_rate": 1.138595741720519e-07,
|
1436 |
+
"loss": 0.6102,
|
1437 |
+
"step": 4080
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.9273919927618186,
|
1441 |
+
"grad_norm": 0.6571109294891357,
|
1442 |
+
"learning_rate": 1.009833207186775e-07,
|
1443 |
+
"loss": 0.5965,
|
1444 |
+
"step": 4100
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.9319158561411446,
|
1448 |
+
"grad_norm": 0.534355640411377,
|
1449 |
+
"learning_rate": 8.886452266215817e-08,
|
1450 |
+
"loss": 0.6624,
|
1451 |
+
"step": 4120
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.9364397195204704,
|
1455 |
+
"grad_norm": 0.7418869137763977,
|
1456 |
+
"learning_rate": 7.750700634062303e-08,
|
1457 |
+
"loss": 0.6008,
|
1458 |
+
"step": 4140
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.9409635828997964,
|
1462 |
+
"grad_norm": 0.6004541516304016,
|
1463 |
+
"learning_rate": 6.691435772831933e-08,
|
1464 |
+
"loss": 0.582,
|
1465 |
+
"step": 4160
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.9454874462791224,
|
1469 |
+
"grad_norm": 0.48619237542152405,
|
1470 |
+
"learning_rate": 5.708992130339458e-08,
|
1471 |
+
"loss": 0.5868,
|
1472 |
+
"step": 4180
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.9500113096584483,
|
1476 |
+
"grad_norm": 0.5165609121322632,
|
1477 |
+
"learning_rate": 4.8036798991923925e-08,
|
1478 |
+
"loss": 0.5558,
|
1479 |
+
"step": 4200
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.9545351730377742,
|
1483 |
+
"grad_norm": 0.7379537224769592,
|
1484 |
+
"learning_rate": 3.9757849188520046e-08,
|
1485 |
+
"loss": 0.617,
|
1486 |
+
"step": 4220
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.9590590364171002,
|
1490 |
+
"grad_norm": 0.6974282264709473,
|
1491 |
+
"learning_rate": 3.2255685853837815e-08,
|
1492 |
+
"loss": 0.5584,
|
1493 |
+
"step": 4240
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.9635828997964262,
|
1497 |
+
"grad_norm": 0.6777763366699219,
|
1498 |
+
"learning_rate": 2.553267768925116e-08,
|
1499 |
+
"loss": 0.553,
|
1500 |
+
"step": 4260
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.9681067631757521,
|
1504 |
+
"grad_norm": 1.0349258184432983,
|
1505 |
+
"learning_rate": 1.959094738897216e-08,
|
1506 |
+
"loss": 0.5674,
|
1507 |
+
"step": 4280
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.972630626555078,
|
1511 |
+
"grad_norm": 1.0187406539916992,
|
1512 |
+
"learning_rate": 1.4432370969836851e-08,
|
1513 |
+
"loss": 0.6268,
|
1514 |
+
"step": 4300
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.977154489934404,
|
1518 |
+
"grad_norm": 0.4671124219894409,
|
1519 |
+
"learning_rate": 1.0058577178982954e-08,
|
1520 |
+
"loss": 0.6393,
|
1521 |
+
"step": 4320
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.9816783533137299,
|
1525 |
+
"grad_norm": 0.6963977217674255,
|
1526 |
+
"learning_rate": 6.4709469795945505e-09,
|
1527 |
+
"loss": 0.6028,
|
1528 |
+
"step": 4340
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.9862022166930559,
|
1532 |
+
"grad_norm": 0.7137852907180786,
|
1533 |
+
"learning_rate": 3.67061311488226e-09,
|
1534 |
+
"loss": 0.5654,
|
1535 |
+
"step": 4360
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.9907260800723818,
|
1539 |
+
"grad_norm": 0.6567050218582153,
|
1540 |
+
"learning_rate": 1.6584597504365475e-09,
|
1541 |
+
"loss": 0.5807,
|
1542 |
+
"step": 4380
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.9952499434517078,
|
1546 |
+
"grad_norm": 0.9630624651908875,
|
1547 |
+
"learning_rate": 4.3512219506519626e-10,
|
1548 |
+
"loss": 0.5787,
|
1549 |
+
"step": 4400
|
1550 |
+
}
|
1551 |
+
],
|
1552 |
+
"logging_steps": 20,
|
1553 |
+
"max_steps": 4421,
|
1554 |
+
"num_input_tokens_seen": 0,
|
1555 |
+
"num_train_epochs": 1,
|
1556 |
+
"save_steps": 100,
|
1557 |
+
"stateful_callbacks": {
|
1558 |
+
"TrainerControl": {
|
1559 |
+
"args": {
|
1560 |
+
"should_epoch_stop": false,
|
1561 |
+
"should_evaluate": false,
|
1562 |
+
"should_log": false,
|
1563 |
+
"should_save": true,
|
1564 |
+
"should_training_stop": false
|
1565 |
+
},
|
1566 |
+
"attributes": {}
|
1567 |
+
}
|
1568 |
+
},
|
1569 |
+
"total_flos": 1.1225101215714509e+17,
|
1570 |
+
"train_batch_size": 4,
|
1571 |
+
"trial_name": null,
|
1572 |
+
"trial_params": null
|
1573 |
+
}
|
checkpoint-4400/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aea02cd52a6bd221ffa620d5ceaa1c146062e7958ebf17d7c66581378628b22a
|
3 |
+
size 5368
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": true,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
}
|
117 |
+
},
|
118 |
+
"bos_token": "<s>",
|
119 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|endoftext|>",
|
122 |
+
"legacy": false,
|
123 |
+
"model_max_length": 4096,
|
124 |
+
"pad_token": "<unk>",
|
125 |
+
"padding_side": "left",
|
126 |
+
"sp_model_kwargs": {},
|
127 |
+
"tokenizer_class": "LlamaTokenizer",
|
128 |
+
"unk_token": "<unk>",
|
129 |
+
"use_default_system_prompt": false
|
130 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aea02cd52a6bd221ffa620d5ceaa1c146062e7958ebf17d7c66581378628b22a
|
3 |
+
size 5368
|