Add LoRA weights
Browse files- .gitattributes +1 -0
- README.md +207 -0
- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +1 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2063 -0
- trainer_state.json +2850 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: nvidia/Llama-3_3-Nemotron-Super-49B-v1
|
3 |
+
library_name: peft
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- base_model:adapter:nvidia/Llama-3_3-Nemotron-Super-49B-v1
|
7 |
+
- lora
|
8 |
+
- transformers
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Card for Model ID
|
12 |
+
|
13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
14 |
+
|
15 |
+
|
16 |
+
|
17 |
+
## Model Details
|
18 |
+
|
19 |
+
### Model Description
|
20 |
+
|
21 |
+
<!-- Provide a longer summary of what this model is. -->
|
22 |
+
|
23 |
+
|
24 |
+
|
25 |
+
- **Developed by:** [More Information Needed]
|
26 |
+
- **Funded by [optional]:** [More Information Needed]
|
27 |
+
- **Shared by [optional]:** [More Information Needed]
|
28 |
+
- **Model type:** [More Information Needed]
|
29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
30 |
+
- **License:** [More Information Needed]
|
31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
32 |
+
|
33 |
+
### Model Sources [optional]
|
34 |
+
|
35 |
+
<!-- Provide the basic links for the model. -->
|
36 |
+
|
37 |
+
- **Repository:** [More Information Needed]
|
38 |
+
- **Paper [optional]:** [More Information Needed]
|
39 |
+
- **Demo [optional]:** [More Information Needed]
|
40 |
+
|
41 |
+
## Uses
|
42 |
+
|
43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
44 |
+
|
45 |
+
### Direct Use
|
46 |
+
|
47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Downstream Use [optional]
|
52 |
+
|
53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
### Out-of-Scope Use
|
58 |
+
|
59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
## Bias, Risks, and Limitations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
66 |
+
|
67 |
+
[More Information Needed]
|
68 |
+
|
69 |
+
### Recommendations
|
70 |
+
|
71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
72 |
+
|
73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
74 |
+
|
75 |
+
## How to Get Started with the Model
|
76 |
+
|
77 |
+
Use the code below to get started with the model.
|
78 |
+
|
79 |
+
[More Information Needed]
|
80 |
+
|
81 |
+
## Training Details
|
82 |
+
|
83 |
+
### Training Data
|
84 |
+
|
85 |
+
<!-- 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. -->
|
86 |
+
|
87 |
+
[More Information Needed]
|
88 |
+
|
89 |
+
### Training Procedure
|
90 |
+
|
91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
92 |
+
|
93 |
+
#### Preprocessing [optional]
|
94 |
+
|
95 |
+
[More Information Needed]
|
96 |
+
|
97 |
+
|
98 |
+
#### Training Hyperparameters
|
99 |
+
|
100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
101 |
+
|
102 |
+
#### Speeds, Sizes, Times [optional]
|
103 |
+
|
104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
105 |
+
|
106 |
+
[More Information Needed]
|
107 |
+
|
108 |
+
## Evaluation
|
109 |
+
|
110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
111 |
+
|
112 |
+
### Testing Data, Factors & Metrics
|
113 |
+
|
114 |
+
#### Testing Data
|
115 |
+
|
116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Factors
|
121 |
+
|
122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
#### Metrics
|
127 |
+
|
128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
129 |
+
|
130 |
+
[More Information Needed]
|
131 |
+
|
132 |
+
### Results
|
133 |
+
|
134 |
+
[More Information Needed]
|
135 |
+
|
136 |
+
#### Summary
|
137 |
+
|
138 |
+
|
139 |
+
|
140 |
+
## Model Examination [optional]
|
141 |
+
|
142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
143 |
+
|
144 |
+
[More Information Needed]
|
145 |
+
|
146 |
+
## Environmental Impact
|
147 |
+
|
148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
149 |
+
|
150 |
+
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).
|
151 |
+
|
152 |
+
- **Hardware Type:** [More Information Needed]
|
153 |
+
- **Hours used:** [More Information Needed]
|
154 |
+
- **Cloud Provider:** [More Information Needed]
|
155 |
+
- **Compute Region:** [More Information Needed]
|
156 |
+
- **Carbon Emitted:** [More Information Needed]
|
157 |
+
|
158 |
+
## Technical Specifications [optional]
|
159 |
+
|
160 |
+
### Model Architecture and Objective
|
161 |
+
|
162 |
+
[More Information Needed]
|
163 |
+
|
164 |
+
### Compute Infrastructure
|
165 |
+
|
166 |
+
[More Information Needed]
|
167 |
+
|
168 |
+
#### Hardware
|
169 |
+
|
170 |
+
[More Information Needed]
|
171 |
+
|
172 |
+
#### Software
|
173 |
+
|
174 |
+
[More Information Needed]
|
175 |
+
|
176 |
+
## Citation [optional]
|
177 |
+
|
178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
179 |
+
|
180 |
+
**BibTeX:**
|
181 |
+
|
182 |
+
[More Information Needed]
|
183 |
+
|
184 |
+
**APA:**
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## Glossary [optional]
|
189 |
+
|
190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
191 |
+
|
192 |
+
[More Information Needed]
|
193 |
+
|
194 |
+
## More Information [optional]
|
195 |
+
|
196 |
+
[More Information Needed]
|
197 |
+
|
198 |
+
## Model Card Authors [optional]
|
199 |
+
|
200 |
+
[More Information Needed]
|
201 |
+
|
202 |
+
## Model Card Contact
|
203 |
+
|
204 |
+
[More Information Needed]
|
205 |
+
### Framework versions
|
206 |
+
|
207 |
+
- PEFT 0.17.0
|
adapter_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "nvidia/Llama-3_3-Nemotron-Super-49B-v1",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 128,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.05,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"qalora_group_size": 16,
|
24 |
+
"r": 64,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"v_proj",
|
29 |
+
"down_proj",
|
30 |
+
"o_proj",
|
31 |
+
"gate_proj",
|
32 |
+
"q_proj",
|
33 |
+
"k_proj",
|
34 |
+
"up_proj"
|
35 |
+
],
|
36 |
+
"target_parameters": null,
|
37 |
+
"task_type": "CAUSAL_LM",
|
38 |
+
"trainable_token_indices": null,
|
39 |
+
"use_dora": false,
|
40 |
+
"use_qalora": false,
|
41 |
+
"use_rslora": false
|
42 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2c29b1295e4e903262f4768ab24f6bb77d7fa86c3bd353cf9a1e66ba5360c34
|
3 |
+
size 2407124984
|
chat_template.jinja
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{{- bos_token }}{%- if messages[0]['role'] == 'system' %}{%- set system_message = messages[0]['content']|trim %}{%- set messages = messages[1:] %}{%- else %}{%- set system_message = "" %}{%- endif %}{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}{{- system_message }}{{- "<|eot_id|>" }}{%- for message in messages %}{%- if message['role'] == 'assistant' and '</think>' in message['content'] %}{%- set content = message['content'].split('</think>')[-1].lstrip() %}{%- else %}{%- set content = message['content'] %}{%- endif %}{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + content | trim + '<|eot_id|>' }}{%- endfor %}{%- if add_generation_prompt %}{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{%- endif %}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99863049112494c1dc8c014ee0434a4372ad6513922cc35ffd8861c3879f2958
|
3 |
+
size 4814766483
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61975850a742b24dfb145dba3df718e30db7966be6a80cb7cb87cc3eb81aed2a
|
3 |
+
size 14917
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de2ffc35ed58b7b2752f62587adb95a44180372762e9a9f13f450693d22144ab
|
3 |
+
size 14917
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:682a36a161c08f269cf6dc71861179f8327d966b453fdd4a0d7696177fa639e2
|
3 |
+
size 1465
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|eot_id|>"
|
17 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90883524dbec2e8c465564ac46b4e5298235668a5cf8523690f06f45f51646fe
|
3 |
+
size 17210197
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"clean_up_tokenization_spaces": true,
|
2054 |
+
"eos_token": "<|eot_id|>",
|
2055 |
+
"extra_special_tokens": {},
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 131072,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2850 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 4000,
|
3 |
+
"best_metric": 1.204215168952942,
|
4 |
+
"best_model_checkpoint": "/workspace/runs_wood_addon/woodsolo_addon_coder_emoji/checkpoint-4000",
|
5 |
+
"epoch": 0.5058168942842691,
|
6 |
+
"eval_steps": 2000,
|
7 |
+
"global_step": 4000,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.0012645422357106728,
|
14 |
+
"grad_norm": 0.7625910043716431,
|
15 |
+
"learning_rate": 1e-05,
|
16 |
+
"loss": 2.2557,
|
17 |
+
"step": 10
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.0025290844714213456,
|
21 |
+
"grad_norm": 0.4440048635005951,
|
22 |
+
"learning_rate": 1e-05,
|
23 |
+
"loss": 1.9805,
|
24 |
+
"step": 20
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0037936267071320183,
|
28 |
+
"grad_norm": 0.33925125002861023,
|
29 |
+
"learning_rate": 1e-05,
|
30 |
+
"loss": 1.8456,
|
31 |
+
"step": 30
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.005058168942842691,
|
35 |
+
"grad_norm": 0.2794567942619324,
|
36 |
+
"learning_rate": 1e-05,
|
37 |
+
"loss": 1.758,
|
38 |
+
"step": 40
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.006322711178553364,
|
42 |
+
"grad_norm": 0.28721487522125244,
|
43 |
+
"learning_rate": 1e-05,
|
44 |
+
"loss": 1.6982,
|
45 |
+
"step": 50
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.007587253414264037,
|
49 |
+
"grad_norm": 0.2807213068008423,
|
50 |
+
"learning_rate": 1e-05,
|
51 |
+
"loss": 1.6196,
|
52 |
+
"step": 60
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.008851795649974709,
|
56 |
+
"grad_norm": 0.2873045802116394,
|
57 |
+
"learning_rate": 1e-05,
|
58 |
+
"loss": 1.5954,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.010116337885685382,
|
63 |
+
"grad_norm": 0.3035956025123596,
|
64 |
+
"learning_rate": 1e-05,
|
65 |
+
"loss": 1.5789,
|
66 |
+
"step": 80
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.011380880121396054,
|
70 |
+
"grad_norm": 0.35515543818473816,
|
71 |
+
"learning_rate": 1e-05,
|
72 |
+
"loss": 1.5428,
|
73 |
+
"step": 90
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.012645422357106728,
|
77 |
+
"grad_norm": 0.35161280632019043,
|
78 |
+
"learning_rate": 1e-05,
|
79 |
+
"loss": 1.5253,
|
80 |
+
"step": 100
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.0139099645928174,
|
84 |
+
"grad_norm": 0.33513695001602173,
|
85 |
+
"learning_rate": 1e-05,
|
86 |
+
"loss": 1.493,
|
87 |
+
"step": 110
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.015174506828528073,
|
91 |
+
"grad_norm": 0.36546558141708374,
|
92 |
+
"learning_rate": 1e-05,
|
93 |
+
"loss": 1.4737,
|
94 |
+
"step": 120
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.016439049064238747,
|
98 |
+
"grad_norm": 0.3826790750026703,
|
99 |
+
"learning_rate": 1e-05,
|
100 |
+
"loss": 1.4696,
|
101 |
+
"step": 130
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.017703591299949417,
|
105 |
+
"grad_norm": 0.3949476182460785,
|
106 |
+
"learning_rate": 1e-05,
|
107 |
+
"loss": 1.4581,
|
108 |
+
"step": 140
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.01896813353566009,
|
112 |
+
"grad_norm": 0.4194561243057251,
|
113 |
+
"learning_rate": 1e-05,
|
114 |
+
"loss": 1.4463,
|
115 |
+
"step": 150
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.020232675771370764,
|
119 |
+
"grad_norm": 0.4173735976219177,
|
120 |
+
"learning_rate": 1e-05,
|
121 |
+
"loss": 1.4247,
|
122 |
+
"step": 160
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.021497218007081438,
|
126 |
+
"grad_norm": 0.4227575957775116,
|
127 |
+
"learning_rate": 1e-05,
|
128 |
+
"loss": 1.4236,
|
129 |
+
"step": 170
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.02276176024279211,
|
133 |
+
"grad_norm": 0.397018700838089,
|
134 |
+
"learning_rate": 1e-05,
|
135 |
+
"loss": 1.406,
|
136 |
+
"step": 180
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.024026302478502782,
|
140 |
+
"grad_norm": 0.4334842562675476,
|
141 |
+
"learning_rate": 1e-05,
|
142 |
+
"loss": 1.3825,
|
143 |
+
"step": 190
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.025290844714213456,
|
147 |
+
"grad_norm": 0.41449373960494995,
|
148 |
+
"learning_rate": 1e-05,
|
149 |
+
"loss": 1.3982,
|
150 |
+
"step": 200
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.026555386949924126,
|
154 |
+
"grad_norm": 0.43625569343566895,
|
155 |
+
"learning_rate": 1e-05,
|
156 |
+
"loss": 1.4113,
|
157 |
+
"step": 210
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.0278199291856348,
|
161 |
+
"grad_norm": 0.4463559091091156,
|
162 |
+
"learning_rate": 1e-05,
|
163 |
+
"loss": 1.3878,
|
164 |
+
"step": 220
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.029084471421345473,
|
168 |
+
"grad_norm": 0.47697845101356506,
|
169 |
+
"learning_rate": 1e-05,
|
170 |
+
"loss": 1.3783,
|
171 |
+
"step": 230
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.030349013657056147,
|
175 |
+
"grad_norm": 0.5106356739997864,
|
176 |
+
"learning_rate": 1e-05,
|
177 |
+
"loss": 1.3906,
|
178 |
+
"step": 240
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.03161355589276682,
|
182 |
+
"grad_norm": 0.4943088889122009,
|
183 |
+
"learning_rate": 1e-05,
|
184 |
+
"loss": 1.3679,
|
185 |
+
"step": 250
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.032878098128477494,
|
189 |
+
"grad_norm": 0.4542694389820099,
|
190 |
+
"learning_rate": 1e-05,
|
191 |
+
"loss": 1.3709,
|
192 |
+
"step": 260
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.03414264036418816,
|
196 |
+
"grad_norm": 0.5167459845542908,
|
197 |
+
"learning_rate": 1e-05,
|
198 |
+
"loss": 1.3594,
|
199 |
+
"step": 270
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.035407182599898834,
|
203 |
+
"grad_norm": 0.49756181240081787,
|
204 |
+
"learning_rate": 1e-05,
|
205 |
+
"loss": 1.3524,
|
206 |
+
"step": 280
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.03667172483560951,
|
210 |
+
"grad_norm": 0.47113093733787537,
|
211 |
+
"learning_rate": 1e-05,
|
212 |
+
"loss": 1.3654,
|
213 |
+
"step": 290
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.03793626707132018,
|
217 |
+
"grad_norm": 0.5371273159980774,
|
218 |
+
"learning_rate": 1e-05,
|
219 |
+
"loss": 1.3583,
|
220 |
+
"step": 300
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.039200809307030855,
|
224 |
+
"grad_norm": 0.4939834475517273,
|
225 |
+
"learning_rate": 1e-05,
|
226 |
+
"loss": 1.3586,
|
227 |
+
"step": 310
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.04046535154274153,
|
231 |
+
"grad_norm": 0.5166125893592834,
|
232 |
+
"learning_rate": 1e-05,
|
233 |
+
"loss": 1.3438,
|
234 |
+
"step": 320
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.0417298937784522,
|
238 |
+
"grad_norm": 0.5029875636100769,
|
239 |
+
"learning_rate": 1e-05,
|
240 |
+
"loss": 1.3311,
|
241 |
+
"step": 330
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.042994436014162876,
|
245 |
+
"grad_norm": 0.5226624011993408,
|
246 |
+
"learning_rate": 1e-05,
|
247 |
+
"loss": 1.3392,
|
248 |
+
"step": 340
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.04425897824987354,
|
252 |
+
"grad_norm": 0.541220486164093,
|
253 |
+
"learning_rate": 1e-05,
|
254 |
+
"loss": 1.3384,
|
255 |
+
"step": 350
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.04552352048558422,
|
259 |
+
"grad_norm": 0.5207000970840454,
|
260 |
+
"learning_rate": 1e-05,
|
261 |
+
"loss": 1.3285,
|
262 |
+
"step": 360
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.04678806272129489,
|
266 |
+
"grad_norm": 0.5402618646621704,
|
267 |
+
"learning_rate": 1e-05,
|
268 |
+
"loss": 1.3331,
|
269 |
+
"step": 370
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.048052604957005564,
|
273 |
+
"grad_norm": 0.5383656620979309,
|
274 |
+
"learning_rate": 1e-05,
|
275 |
+
"loss": 1.3325,
|
276 |
+
"step": 380
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.04931714719271624,
|
280 |
+
"grad_norm": 0.5517101287841797,
|
281 |
+
"learning_rate": 1e-05,
|
282 |
+
"loss": 1.3415,
|
283 |
+
"step": 390
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.05058168942842691,
|
287 |
+
"grad_norm": 0.5149410963058472,
|
288 |
+
"learning_rate": 1e-05,
|
289 |
+
"loss": 1.3261,
|
290 |
+
"step": 400
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.051846231664137585,
|
294 |
+
"grad_norm": 0.5463008880615234,
|
295 |
+
"learning_rate": 1e-05,
|
296 |
+
"loss": 1.3341,
|
297 |
+
"step": 410
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.05311077389984825,
|
301 |
+
"grad_norm": 0.5317574143409729,
|
302 |
+
"learning_rate": 1e-05,
|
303 |
+
"loss": 1.3244,
|
304 |
+
"step": 420
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.054375316135558925,
|
308 |
+
"grad_norm": 0.5694941282272339,
|
309 |
+
"learning_rate": 1e-05,
|
310 |
+
"loss": 1.3027,
|
311 |
+
"step": 430
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.0556398583712696,
|
315 |
+
"grad_norm": 0.5492473244667053,
|
316 |
+
"learning_rate": 1e-05,
|
317 |
+
"loss": 1.3204,
|
318 |
+
"step": 440
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.05690440060698027,
|
322 |
+
"grad_norm": 0.5674126148223877,
|
323 |
+
"learning_rate": 1e-05,
|
324 |
+
"loss": 1.3265,
|
325 |
+
"step": 450
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.058168942842690946,
|
329 |
+
"grad_norm": 0.5834727883338928,
|
330 |
+
"learning_rate": 1e-05,
|
331 |
+
"loss": 1.318,
|
332 |
+
"step": 460
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.05943348507840162,
|
336 |
+
"grad_norm": 0.5941717028617859,
|
337 |
+
"learning_rate": 1e-05,
|
338 |
+
"loss": 1.3144,
|
339 |
+
"step": 470
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.06069802731411229,
|
343 |
+
"grad_norm": 0.5612233281135559,
|
344 |
+
"learning_rate": 1e-05,
|
345 |
+
"loss": 1.2982,
|
346 |
+
"step": 480
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.06196256954982297,
|
350 |
+
"grad_norm": 0.5824425220489502,
|
351 |
+
"learning_rate": 1e-05,
|
352 |
+
"loss": 1.2928,
|
353 |
+
"step": 490
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.06322711178553364,
|
357 |
+
"grad_norm": 0.5248660445213318,
|
358 |
+
"learning_rate": 1e-05,
|
359 |
+
"loss": 1.299,
|
360 |
+
"step": 500
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.06449165402124431,
|
364 |
+
"grad_norm": 0.5807384252548218,
|
365 |
+
"learning_rate": 1e-05,
|
366 |
+
"loss": 1.3052,
|
367 |
+
"step": 510
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.06575619625695499,
|
371 |
+
"grad_norm": 0.5710154175758362,
|
372 |
+
"learning_rate": 1e-05,
|
373 |
+
"loss": 1.3076,
|
374 |
+
"step": 520
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.06702073849266565,
|
378 |
+
"grad_norm": 0.5377432107925415,
|
379 |
+
"learning_rate": 1e-05,
|
380 |
+
"loss": 1.3065,
|
381 |
+
"step": 530
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.06828528072837632,
|
385 |
+
"grad_norm": 0.6114449501037598,
|
386 |
+
"learning_rate": 1e-05,
|
387 |
+
"loss": 1.3085,
|
388 |
+
"step": 540
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.069549822964087,
|
392 |
+
"grad_norm": 0.5822087526321411,
|
393 |
+
"learning_rate": 1e-05,
|
394 |
+
"loss": 1.2893,
|
395 |
+
"step": 550
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.07081436519979767,
|
399 |
+
"grad_norm": 0.5842393636703491,
|
400 |
+
"learning_rate": 1e-05,
|
401 |
+
"loss": 1.3094,
|
402 |
+
"step": 560
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.07207890743550835,
|
406 |
+
"grad_norm": 0.5934606194496155,
|
407 |
+
"learning_rate": 1e-05,
|
408 |
+
"loss": 1.2997,
|
409 |
+
"step": 570
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.07334344967121902,
|
413 |
+
"grad_norm": 0.5630069971084595,
|
414 |
+
"learning_rate": 1e-05,
|
415 |
+
"loss": 1.2987,
|
416 |
+
"step": 580
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.0746079919069297,
|
420 |
+
"grad_norm": 0.5744876265525818,
|
421 |
+
"learning_rate": 1e-05,
|
422 |
+
"loss": 1.3016,
|
423 |
+
"step": 590
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.07587253414264036,
|
427 |
+
"grad_norm": 0.5932934880256653,
|
428 |
+
"learning_rate": 1e-05,
|
429 |
+
"loss": 1.2987,
|
430 |
+
"step": 600
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.07713707637835104,
|
434 |
+
"grad_norm": 0.5708047151565552,
|
435 |
+
"learning_rate": 1e-05,
|
436 |
+
"loss": 1.3007,
|
437 |
+
"step": 610
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.07840161861406171,
|
441 |
+
"grad_norm": 0.6103700995445251,
|
442 |
+
"learning_rate": 1e-05,
|
443 |
+
"loss": 1.3071,
|
444 |
+
"step": 620
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.07966616084977238,
|
448 |
+
"grad_norm": 0.632308840751648,
|
449 |
+
"learning_rate": 1e-05,
|
450 |
+
"loss": 1.3037,
|
451 |
+
"step": 630
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.08093070308548306,
|
455 |
+
"grad_norm": 0.5914241075515747,
|
456 |
+
"learning_rate": 1e-05,
|
457 |
+
"loss": 1.2826,
|
458 |
+
"step": 640
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.08219524532119372,
|
462 |
+
"grad_norm": 0.5972428321838379,
|
463 |
+
"learning_rate": 1e-05,
|
464 |
+
"loss": 1.2837,
|
465 |
+
"step": 650
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.0834597875569044,
|
469 |
+
"grad_norm": 0.64115309715271,
|
470 |
+
"learning_rate": 1e-05,
|
471 |
+
"loss": 1.2884,
|
472 |
+
"step": 660
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.08472432979261507,
|
476 |
+
"grad_norm": 0.5938035845756531,
|
477 |
+
"learning_rate": 1e-05,
|
478 |
+
"loss": 1.2964,
|
479 |
+
"step": 670
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.08598887202832575,
|
483 |
+
"grad_norm": 0.5978350639343262,
|
484 |
+
"learning_rate": 1e-05,
|
485 |
+
"loss": 1.2889,
|
486 |
+
"step": 680
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.08725341426403642,
|
490 |
+
"grad_norm": 0.677268385887146,
|
491 |
+
"learning_rate": 1e-05,
|
492 |
+
"loss": 1.2757,
|
493 |
+
"step": 690
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.08851795649974709,
|
497 |
+
"grad_norm": 0.5865476727485657,
|
498 |
+
"learning_rate": 1e-05,
|
499 |
+
"loss": 1.2851,
|
500 |
+
"step": 700
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.08978249873545777,
|
504 |
+
"grad_norm": 0.5831303596496582,
|
505 |
+
"learning_rate": 1e-05,
|
506 |
+
"loss": 1.2693,
|
507 |
+
"step": 710
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.09104704097116843,
|
511 |
+
"grad_norm": 0.5956682562828064,
|
512 |
+
"learning_rate": 1e-05,
|
513 |
+
"loss": 1.3012,
|
514 |
+
"step": 720
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.09231158320687911,
|
518 |
+
"grad_norm": 0.5970422029495239,
|
519 |
+
"learning_rate": 1e-05,
|
520 |
+
"loss": 1.2953,
|
521 |
+
"step": 730
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.09357612544258978,
|
525 |
+
"grad_norm": 0.6019087433815002,
|
526 |
+
"learning_rate": 1e-05,
|
527 |
+
"loss": 1.2855,
|
528 |
+
"step": 740
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.09484066767830046,
|
532 |
+
"grad_norm": 0.6027910709381104,
|
533 |
+
"learning_rate": 1e-05,
|
534 |
+
"loss": 1.2831,
|
535 |
+
"step": 750
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.09610520991401113,
|
539 |
+
"grad_norm": 0.6293312907218933,
|
540 |
+
"learning_rate": 1e-05,
|
541 |
+
"loss": 1.2788,
|
542 |
+
"step": 760
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.0973697521497218,
|
546 |
+
"grad_norm": 0.6175749897956848,
|
547 |
+
"learning_rate": 1e-05,
|
548 |
+
"loss": 1.2759,
|
549 |
+
"step": 770
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.09863429438543247,
|
553 |
+
"grad_norm": 0.6667502522468567,
|
554 |
+
"learning_rate": 1e-05,
|
555 |
+
"loss": 1.2781,
|
556 |
+
"step": 780
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.09989883662114314,
|
560 |
+
"grad_norm": 0.5962637662887573,
|
561 |
+
"learning_rate": 1e-05,
|
562 |
+
"loss": 1.2727,
|
563 |
+
"step": 790
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.10116337885685382,
|
567 |
+
"grad_norm": 0.6042391061782837,
|
568 |
+
"learning_rate": 1e-05,
|
569 |
+
"loss": 1.28,
|
570 |
+
"step": 800
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.10242792109256449,
|
574 |
+
"grad_norm": 0.5914803147315979,
|
575 |
+
"learning_rate": 1e-05,
|
576 |
+
"loss": 1.2709,
|
577 |
+
"step": 810
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.10369246332827517,
|
581 |
+
"grad_norm": 0.6609341502189636,
|
582 |
+
"learning_rate": 1e-05,
|
583 |
+
"loss": 1.2799,
|
584 |
+
"step": 820
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.10495700556398584,
|
588 |
+
"grad_norm": 0.6625810861587524,
|
589 |
+
"learning_rate": 1e-05,
|
590 |
+
"loss": 1.2707,
|
591 |
+
"step": 830
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.1062215477996965,
|
595 |
+
"grad_norm": 0.6348279714584351,
|
596 |
+
"learning_rate": 1e-05,
|
597 |
+
"loss": 1.2733,
|
598 |
+
"step": 840
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.10748609003540718,
|
602 |
+
"grad_norm": 0.5888762474060059,
|
603 |
+
"learning_rate": 1e-05,
|
604 |
+
"loss": 1.2988,
|
605 |
+
"step": 850
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.10875063227111785,
|
609 |
+
"grad_norm": 0.6500024199485779,
|
610 |
+
"learning_rate": 1e-05,
|
611 |
+
"loss": 1.2713,
|
612 |
+
"step": 860
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.11001517450682853,
|
616 |
+
"grad_norm": 0.641412079334259,
|
617 |
+
"learning_rate": 1e-05,
|
618 |
+
"loss": 1.2717,
|
619 |
+
"step": 870
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.1112797167425392,
|
623 |
+
"grad_norm": 0.5919875502586365,
|
624 |
+
"learning_rate": 1e-05,
|
625 |
+
"loss": 1.2718,
|
626 |
+
"step": 880
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.11254425897824988,
|
630 |
+
"grad_norm": 0.580167293548584,
|
631 |
+
"learning_rate": 1e-05,
|
632 |
+
"loss": 1.2662,
|
633 |
+
"step": 890
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.11380880121396054,
|
637 |
+
"grad_norm": 0.6288133859634399,
|
638 |
+
"learning_rate": 1e-05,
|
639 |
+
"loss": 1.272,
|
640 |
+
"step": 900
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.11507334344967123,
|
644 |
+
"grad_norm": 0.6101668477058411,
|
645 |
+
"learning_rate": 1e-05,
|
646 |
+
"loss": 1.2687,
|
647 |
+
"step": 910
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.11633788568538189,
|
651 |
+
"grad_norm": 0.6252788305282593,
|
652 |
+
"learning_rate": 1e-05,
|
653 |
+
"loss": 1.274,
|
654 |
+
"step": 920
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.11760242792109256,
|
658 |
+
"grad_norm": 0.6325656771659851,
|
659 |
+
"learning_rate": 1e-05,
|
660 |
+
"loss": 1.2869,
|
661 |
+
"step": 930
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.11886697015680324,
|
665 |
+
"grad_norm": 0.6283508539199829,
|
666 |
+
"learning_rate": 1e-05,
|
667 |
+
"loss": 1.2789,
|
668 |
+
"step": 940
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.1201315123925139,
|
672 |
+
"grad_norm": 0.6235183477401733,
|
673 |
+
"learning_rate": 1e-05,
|
674 |
+
"loss": 1.257,
|
675 |
+
"step": 950
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.12139605462822459,
|
679 |
+
"grad_norm": 0.6445891857147217,
|
680 |
+
"learning_rate": 1e-05,
|
681 |
+
"loss": 1.2636,
|
682 |
+
"step": 960
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.12266059686393525,
|
686 |
+
"grad_norm": 0.6866258978843689,
|
687 |
+
"learning_rate": 1e-05,
|
688 |
+
"loss": 1.261,
|
689 |
+
"step": 970
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.12392513909964593,
|
693 |
+
"grad_norm": 0.600864052772522,
|
694 |
+
"learning_rate": 1e-05,
|
695 |
+
"loss": 1.278,
|
696 |
+
"step": 980
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.1251896813353566,
|
700 |
+
"grad_norm": 0.5925164222717285,
|
701 |
+
"learning_rate": 1e-05,
|
702 |
+
"loss": 1.2675,
|
703 |
+
"step": 990
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.12645422357106728,
|
707 |
+
"grad_norm": 0.5830930471420288,
|
708 |
+
"learning_rate": 1e-05,
|
709 |
+
"loss": 1.2714,
|
710 |
+
"step": 1000
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.12771876580677793,
|
714 |
+
"grad_norm": 0.6133884787559509,
|
715 |
+
"learning_rate": 1e-05,
|
716 |
+
"loss": 1.2662,
|
717 |
+
"step": 1010
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.12898330804248861,
|
721 |
+
"grad_norm": 0.6210865378379822,
|
722 |
+
"learning_rate": 1e-05,
|
723 |
+
"loss": 1.2612,
|
724 |
+
"step": 1020
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.1302478502781993,
|
728 |
+
"grad_norm": 0.6451679468154907,
|
729 |
+
"learning_rate": 1e-05,
|
730 |
+
"loss": 1.2707,
|
731 |
+
"step": 1030
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.13151239251390998,
|
735 |
+
"grad_norm": 0.618381142616272,
|
736 |
+
"learning_rate": 1e-05,
|
737 |
+
"loss": 1.2635,
|
738 |
+
"step": 1040
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.13277693474962063,
|
742 |
+
"grad_norm": 0.627230167388916,
|
743 |
+
"learning_rate": 1e-05,
|
744 |
+
"loss": 1.2561,
|
745 |
+
"step": 1050
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.1340414769853313,
|
749 |
+
"grad_norm": 0.6514145731925964,
|
750 |
+
"learning_rate": 1e-05,
|
751 |
+
"loss": 1.2699,
|
752 |
+
"step": 1060
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.135306019221042,
|
756 |
+
"grad_norm": 0.5999763607978821,
|
757 |
+
"learning_rate": 1e-05,
|
758 |
+
"loss": 1.2737,
|
759 |
+
"step": 1070
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.13657056145675264,
|
763 |
+
"grad_norm": 0.6173470616340637,
|
764 |
+
"learning_rate": 1e-05,
|
765 |
+
"loss": 1.2594,
|
766 |
+
"step": 1080
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.13783510369246332,
|
770 |
+
"grad_norm": 0.6110437512397766,
|
771 |
+
"learning_rate": 1e-05,
|
772 |
+
"loss": 1.2633,
|
773 |
+
"step": 1090
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.139099645928174,
|
777 |
+
"grad_norm": 0.6144809722900391,
|
778 |
+
"learning_rate": 1e-05,
|
779 |
+
"loss": 1.258,
|
780 |
+
"step": 1100
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.14036418816388468,
|
784 |
+
"grad_norm": 0.6366214156150818,
|
785 |
+
"learning_rate": 1e-05,
|
786 |
+
"loss": 1.2614,
|
787 |
+
"step": 1110
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.14162873039959534,
|
791 |
+
"grad_norm": 0.6725825071334839,
|
792 |
+
"learning_rate": 1e-05,
|
793 |
+
"loss": 1.2491,
|
794 |
+
"step": 1120
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.14289327263530602,
|
798 |
+
"grad_norm": 0.63374263048172,
|
799 |
+
"learning_rate": 1e-05,
|
800 |
+
"loss": 1.2653,
|
801 |
+
"step": 1130
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.1441578148710167,
|
805 |
+
"grad_norm": 0.6430857181549072,
|
806 |
+
"learning_rate": 1e-05,
|
807 |
+
"loss": 1.2587,
|
808 |
+
"step": 1140
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.14542235710672735,
|
812 |
+
"grad_norm": 0.6750744581222534,
|
813 |
+
"learning_rate": 1e-05,
|
814 |
+
"loss": 1.2492,
|
815 |
+
"step": 1150
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.14668689934243803,
|
819 |
+
"grad_norm": 0.6447614431381226,
|
820 |
+
"learning_rate": 1e-05,
|
821 |
+
"loss": 1.2744,
|
822 |
+
"step": 1160
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.1479514415781487,
|
826 |
+
"grad_norm": 0.6079798936843872,
|
827 |
+
"learning_rate": 1e-05,
|
828 |
+
"loss": 1.2562,
|
829 |
+
"step": 1170
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.1492159838138594,
|
833 |
+
"grad_norm": 0.6352636814117432,
|
834 |
+
"learning_rate": 1e-05,
|
835 |
+
"loss": 1.2574,
|
836 |
+
"step": 1180
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.15048052604957005,
|
840 |
+
"grad_norm": 0.6926299333572388,
|
841 |
+
"learning_rate": 1e-05,
|
842 |
+
"loss": 1.2493,
|
843 |
+
"step": 1190
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.15174506828528073,
|
847 |
+
"grad_norm": 0.6673220992088318,
|
848 |
+
"learning_rate": 1e-05,
|
849 |
+
"loss": 1.2597,
|
850 |
+
"step": 1200
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.1530096105209914,
|
854 |
+
"grad_norm": 0.6694420576095581,
|
855 |
+
"learning_rate": 1e-05,
|
856 |
+
"loss": 1.2481,
|
857 |
+
"step": 1210
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.1542741527567021,
|
861 |
+
"grad_norm": 0.6781032085418701,
|
862 |
+
"learning_rate": 1e-05,
|
863 |
+
"loss": 1.2488,
|
864 |
+
"step": 1220
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.15553869499241274,
|
868 |
+
"grad_norm": 0.6320050358772278,
|
869 |
+
"learning_rate": 1e-05,
|
870 |
+
"loss": 1.2568,
|
871 |
+
"step": 1230
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.15680323722812342,
|
875 |
+
"grad_norm": 0.6539678573608398,
|
876 |
+
"learning_rate": 1e-05,
|
877 |
+
"loss": 1.2507,
|
878 |
+
"step": 1240
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.1580677794638341,
|
882 |
+
"grad_norm": 0.6599031090736389,
|
883 |
+
"learning_rate": 1e-05,
|
884 |
+
"loss": 1.266,
|
885 |
+
"step": 1250
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.15933232169954475,
|
889 |
+
"grad_norm": 0.6231998801231384,
|
890 |
+
"learning_rate": 1e-05,
|
891 |
+
"loss": 1.2629,
|
892 |
+
"step": 1260
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.16059686393525544,
|
896 |
+
"grad_norm": 0.6079356670379639,
|
897 |
+
"learning_rate": 1e-05,
|
898 |
+
"loss": 1.2516,
|
899 |
+
"step": 1270
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.16186140617096612,
|
903 |
+
"grad_norm": 0.6586504578590393,
|
904 |
+
"learning_rate": 1e-05,
|
905 |
+
"loss": 1.26,
|
906 |
+
"step": 1280
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.1631259484066768,
|
910 |
+
"grad_norm": 0.6095693111419678,
|
911 |
+
"learning_rate": 1e-05,
|
912 |
+
"loss": 1.243,
|
913 |
+
"step": 1290
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.16439049064238745,
|
917 |
+
"grad_norm": 0.6308146119117737,
|
918 |
+
"learning_rate": 1e-05,
|
919 |
+
"loss": 1.2413,
|
920 |
+
"step": 1300
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.16565503287809813,
|
924 |
+
"grad_norm": 0.6520269513130188,
|
925 |
+
"learning_rate": 1e-05,
|
926 |
+
"loss": 1.2533,
|
927 |
+
"step": 1310
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.1669195751138088,
|
931 |
+
"grad_norm": 0.6644425392150879,
|
932 |
+
"learning_rate": 1e-05,
|
933 |
+
"loss": 1.2677,
|
934 |
+
"step": 1320
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.16818411734951946,
|
938 |
+
"grad_norm": 0.6227694749832153,
|
939 |
+
"learning_rate": 1e-05,
|
940 |
+
"loss": 1.2491,
|
941 |
+
"step": 1330
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.16944865958523014,
|
945 |
+
"grad_norm": 0.7065048813819885,
|
946 |
+
"learning_rate": 1e-05,
|
947 |
+
"loss": 1.2426,
|
948 |
+
"step": 1340
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.17071320182094082,
|
952 |
+
"grad_norm": 0.6393408179283142,
|
953 |
+
"learning_rate": 1e-05,
|
954 |
+
"loss": 1.2637,
|
955 |
+
"step": 1350
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.1719777440566515,
|
959 |
+
"grad_norm": 0.623533308506012,
|
960 |
+
"learning_rate": 1e-05,
|
961 |
+
"loss": 1.2459,
|
962 |
+
"step": 1360
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.17324228629236216,
|
966 |
+
"grad_norm": 0.5883052945137024,
|
967 |
+
"learning_rate": 1e-05,
|
968 |
+
"loss": 1.2536,
|
969 |
+
"step": 1370
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.17450682852807284,
|
973 |
+
"grad_norm": 0.6799809336662292,
|
974 |
+
"learning_rate": 1e-05,
|
975 |
+
"loss": 1.2309,
|
976 |
+
"step": 1380
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.17577137076378352,
|
980 |
+
"grad_norm": 0.6791123151779175,
|
981 |
+
"learning_rate": 1e-05,
|
982 |
+
"loss": 1.2581,
|
983 |
+
"step": 1390
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.17703591299949417,
|
987 |
+
"grad_norm": 0.6528906226158142,
|
988 |
+
"learning_rate": 1e-05,
|
989 |
+
"loss": 1.2483,
|
990 |
+
"step": 1400
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.17830045523520485,
|
994 |
+
"grad_norm": 0.6595279574394226,
|
995 |
+
"learning_rate": 1e-05,
|
996 |
+
"loss": 1.2403,
|
997 |
+
"step": 1410
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.17956499747091553,
|
1001 |
+
"grad_norm": 0.6212822794914246,
|
1002 |
+
"learning_rate": 1e-05,
|
1003 |
+
"loss": 1.2481,
|
1004 |
+
"step": 1420
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.1808295397066262,
|
1008 |
+
"grad_norm": 0.5926348567008972,
|
1009 |
+
"learning_rate": 1e-05,
|
1010 |
+
"loss": 1.2396,
|
1011 |
+
"step": 1430
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.18209408194233687,
|
1015 |
+
"grad_norm": 0.6357258558273315,
|
1016 |
+
"learning_rate": 1e-05,
|
1017 |
+
"loss": 1.2559,
|
1018 |
+
"step": 1440
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.18335862417804755,
|
1022 |
+
"grad_norm": 0.6357143521308899,
|
1023 |
+
"learning_rate": 1e-05,
|
1024 |
+
"loss": 1.2539,
|
1025 |
+
"step": 1450
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.18462316641375823,
|
1029 |
+
"grad_norm": 0.6369765400886536,
|
1030 |
+
"learning_rate": 1e-05,
|
1031 |
+
"loss": 1.2454,
|
1032 |
+
"step": 1460
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.18588770864946888,
|
1036 |
+
"grad_norm": 0.6946889758110046,
|
1037 |
+
"learning_rate": 1e-05,
|
1038 |
+
"loss": 1.2446,
|
1039 |
+
"step": 1470
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.18715225088517956,
|
1043 |
+
"grad_norm": 0.6069193482398987,
|
1044 |
+
"learning_rate": 1e-05,
|
1045 |
+
"loss": 1.2441,
|
1046 |
+
"step": 1480
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.18841679312089024,
|
1050 |
+
"grad_norm": 0.6216751337051392,
|
1051 |
+
"learning_rate": 1e-05,
|
1052 |
+
"loss": 1.2368,
|
1053 |
+
"step": 1490
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.18968133535660092,
|
1057 |
+
"grad_norm": 0.6576444506645203,
|
1058 |
+
"learning_rate": 1e-05,
|
1059 |
+
"loss": 1.2482,
|
1060 |
+
"step": 1500
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.19094587759231157,
|
1064 |
+
"grad_norm": 0.6438011527061462,
|
1065 |
+
"learning_rate": 1e-05,
|
1066 |
+
"loss": 1.2312,
|
1067 |
+
"step": 1510
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.19221041982802226,
|
1071 |
+
"grad_norm": 0.6504274606704712,
|
1072 |
+
"learning_rate": 1e-05,
|
1073 |
+
"loss": 1.247,
|
1074 |
+
"step": 1520
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.19347496206373294,
|
1078 |
+
"grad_norm": 0.6167164444923401,
|
1079 |
+
"learning_rate": 1e-05,
|
1080 |
+
"loss": 1.2452,
|
1081 |
+
"step": 1530
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.1947395042994436,
|
1085 |
+
"grad_norm": 0.6499640941619873,
|
1086 |
+
"learning_rate": 1e-05,
|
1087 |
+
"loss": 1.2488,
|
1088 |
+
"step": 1540
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.19600404653515427,
|
1092 |
+
"grad_norm": 0.638342022895813,
|
1093 |
+
"learning_rate": 1e-05,
|
1094 |
+
"loss": 1.2408,
|
1095 |
+
"step": 1550
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.19726858877086495,
|
1099 |
+
"grad_norm": 0.6280787587165833,
|
1100 |
+
"learning_rate": 1e-05,
|
1101 |
+
"loss": 1.2302,
|
1102 |
+
"step": 1560
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.19853313100657563,
|
1106 |
+
"grad_norm": 0.6687835454940796,
|
1107 |
+
"learning_rate": 1e-05,
|
1108 |
+
"loss": 1.2362,
|
1109 |
+
"step": 1570
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.19979767324228628,
|
1113 |
+
"grad_norm": 0.6204760074615479,
|
1114 |
+
"learning_rate": 1e-05,
|
1115 |
+
"loss": 1.2204,
|
1116 |
+
"step": 1580
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.20106221547799696,
|
1120 |
+
"grad_norm": 0.6064612865447998,
|
1121 |
+
"learning_rate": 1e-05,
|
1122 |
+
"loss": 1.239,
|
1123 |
+
"step": 1590
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 0.20232675771370764,
|
1127 |
+
"grad_norm": 0.6709041595458984,
|
1128 |
+
"learning_rate": 1e-05,
|
1129 |
+
"loss": 1.2347,
|
1130 |
+
"step": 1600
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.2035912999494183,
|
1134 |
+
"grad_norm": 0.666481077671051,
|
1135 |
+
"learning_rate": 1e-05,
|
1136 |
+
"loss": 1.2447,
|
1137 |
+
"step": 1610
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.20485584218512898,
|
1141 |
+
"grad_norm": 0.6072632074356079,
|
1142 |
+
"learning_rate": 1e-05,
|
1143 |
+
"loss": 1.2361,
|
1144 |
+
"step": 1620
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.20612038442083966,
|
1148 |
+
"grad_norm": 0.6355836987495422,
|
1149 |
+
"learning_rate": 1e-05,
|
1150 |
+
"loss": 1.2436,
|
1151 |
+
"step": 1630
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 0.20738492665655034,
|
1155 |
+
"grad_norm": 0.6270642280578613,
|
1156 |
+
"learning_rate": 1e-05,
|
1157 |
+
"loss": 1.2446,
|
1158 |
+
"step": 1640
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 0.208649468892261,
|
1162 |
+
"grad_norm": 0.6585315465927124,
|
1163 |
+
"learning_rate": 1e-05,
|
1164 |
+
"loss": 1.2503,
|
1165 |
+
"step": 1650
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 0.20991401112797167,
|
1169 |
+
"grad_norm": 0.6357535719871521,
|
1170 |
+
"learning_rate": 1e-05,
|
1171 |
+
"loss": 1.2358,
|
1172 |
+
"step": 1660
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.21117855336368235,
|
1176 |
+
"grad_norm": 0.6732521653175354,
|
1177 |
+
"learning_rate": 1e-05,
|
1178 |
+
"loss": 1.252,
|
1179 |
+
"step": 1670
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.212443095599393,
|
1183 |
+
"grad_norm": 0.6809791922569275,
|
1184 |
+
"learning_rate": 1e-05,
|
1185 |
+
"loss": 1.2278,
|
1186 |
+
"step": 1680
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.2137076378351037,
|
1190 |
+
"grad_norm": 0.6528928875923157,
|
1191 |
+
"learning_rate": 1e-05,
|
1192 |
+
"loss": 1.2444,
|
1193 |
+
"step": 1690
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.21497218007081437,
|
1197 |
+
"grad_norm": 0.6465297937393188,
|
1198 |
+
"learning_rate": 1e-05,
|
1199 |
+
"loss": 1.2327,
|
1200 |
+
"step": 1700
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.21623672230652505,
|
1204 |
+
"grad_norm": 0.6362217664718628,
|
1205 |
+
"learning_rate": 1e-05,
|
1206 |
+
"loss": 1.2399,
|
1207 |
+
"step": 1710
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.2175012645422357,
|
1211 |
+
"grad_norm": 0.646859884262085,
|
1212 |
+
"learning_rate": 1e-05,
|
1213 |
+
"loss": 1.2343,
|
1214 |
+
"step": 1720
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.21876580677794638,
|
1218 |
+
"grad_norm": 0.5919581055641174,
|
1219 |
+
"learning_rate": 1e-05,
|
1220 |
+
"loss": 1.2248,
|
1221 |
+
"step": 1730
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.22003034901365706,
|
1225 |
+
"grad_norm": 0.6531901359558105,
|
1226 |
+
"learning_rate": 1e-05,
|
1227 |
+
"loss": 1.2396,
|
1228 |
+
"step": 1740
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.22129489124936774,
|
1232 |
+
"grad_norm": 0.63343745470047,
|
1233 |
+
"learning_rate": 1e-05,
|
1234 |
+
"loss": 1.2372,
|
1235 |
+
"step": 1750
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.2225594334850784,
|
1239 |
+
"grad_norm": 0.6176961064338684,
|
1240 |
+
"learning_rate": 1e-05,
|
1241 |
+
"loss": 1.2496,
|
1242 |
+
"step": 1760
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.22382397572078908,
|
1246 |
+
"grad_norm": 0.6093595027923584,
|
1247 |
+
"learning_rate": 1e-05,
|
1248 |
+
"loss": 1.237,
|
1249 |
+
"step": 1770
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.22508851795649976,
|
1253 |
+
"grad_norm": 0.6258598566055298,
|
1254 |
+
"learning_rate": 1e-05,
|
1255 |
+
"loss": 1.2396,
|
1256 |
+
"step": 1780
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.2263530601922104,
|
1260 |
+
"grad_norm": 0.6147506237030029,
|
1261 |
+
"learning_rate": 1e-05,
|
1262 |
+
"loss": 1.2298,
|
1263 |
+
"step": 1790
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.2276176024279211,
|
1267 |
+
"grad_norm": 0.6585720181465149,
|
1268 |
+
"learning_rate": 1e-05,
|
1269 |
+
"loss": 1.2331,
|
1270 |
+
"step": 1800
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.22888214466363177,
|
1274 |
+
"grad_norm": 0.6150441765785217,
|
1275 |
+
"learning_rate": 1e-05,
|
1276 |
+
"loss": 1.2248,
|
1277 |
+
"step": 1810
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.23014668689934245,
|
1281 |
+
"grad_norm": 0.6929159164428711,
|
1282 |
+
"learning_rate": 1e-05,
|
1283 |
+
"loss": 1.2405,
|
1284 |
+
"step": 1820
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.2314112291350531,
|
1288 |
+
"grad_norm": 0.6271383166313171,
|
1289 |
+
"learning_rate": 1e-05,
|
1290 |
+
"loss": 1.2521,
|
1291 |
+
"step": 1830
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 0.23267577137076378,
|
1295 |
+
"grad_norm": 0.6828703880310059,
|
1296 |
+
"learning_rate": 1e-05,
|
1297 |
+
"loss": 1.2347,
|
1298 |
+
"step": 1840
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.23394031360647446,
|
1302 |
+
"grad_norm": 0.6458522081375122,
|
1303 |
+
"learning_rate": 1e-05,
|
1304 |
+
"loss": 1.2343,
|
1305 |
+
"step": 1850
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.23520485584218512,
|
1309 |
+
"grad_norm": 0.6284289956092834,
|
1310 |
+
"learning_rate": 1e-05,
|
1311 |
+
"loss": 1.2416,
|
1312 |
+
"step": 1860
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.2364693980778958,
|
1316 |
+
"grad_norm": 0.6882743835449219,
|
1317 |
+
"learning_rate": 1e-05,
|
1318 |
+
"loss": 1.2389,
|
1319 |
+
"step": 1870
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.23773394031360648,
|
1323 |
+
"grad_norm": 0.6235172748565674,
|
1324 |
+
"learning_rate": 1e-05,
|
1325 |
+
"loss": 1.2444,
|
1326 |
+
"step": 1880
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 0.23899848254931716,
|
1330 |
+
"grad_norm": 0.6821162104606628,
|
1331 |
+
"learning_rate": 1e-05,
|
1332 |
+
"loss": 1.2242,
|
1333 |
+
"step": 1890
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 0.2402630247850278,
|
1337 |
+
"grad_norm": 0.6522544026374817,
|
1338 |
+
"learning_rate": 1e-05,
|
1339 |
+
"loss": 1.2499,
|
1340 |
+
"step": 1900
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.2415275670207385,
|
1344 |
+
"grad_norm": 0.6642081141471863,
|
1345 |
+
"learning_rate": 1e-05,
|
1346 |
+
"loss": 1.2398,
|
1347 |
+
"step": 1910
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.24279210925644917,
|
1351 |
+
"grad_norm": 0.6181321144104004,
|
1352 |
+
"learning_rate": 1e-05,
|
1353 |
+
"loss": 1.2122,
|
1354 |
+
"step": 1920
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.24405665149215983,
|
1358 |
+
"grad_norm": 0.6123504042625427,
|
1359 |
+
"learning_rate": 1e-05,
|
1360 |
+
"loss": 1.2368,
|
1361 |
+
"step": 1930
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.2453211937278705,
|
1365 |
+
"grad_norm": 0.6677888035774231,
|
1366 |
+
"learning_rate": 1e-05,
|
1367 |
+
"loss": 1.2444,
|
1368 |
+
"step": 1940
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.2465857359635812,
|
1372 |
+
"grad_norm": 0.6353912353515625,
|
1373 |
+
"learning_rate": 1e-05,
|
1374 |
+
"loss": 1.2404,
|
1375 |
+
"step": 1950
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.24785027819929187,
|
1379 |
+
"grad_norm": 0.6119335293769836,
|
1380 |
+
"learning_rate": 1e-05,
|
1381 |
+
"loss": 1.2221,
|
1382 |
+
"step": 1960
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.24911482043500252,
|
1386 |
+
"grad_norm": 0.6059813499450684,
|
1387 |
+
"learning_rate": 1e-05,
|
1388 |
+
"loss": 1.2478,
|
1389 |
+
"step": 1970
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.2503793626707132,
|
1393 |
+
"grad_norm": 0.6676130294799805,
|
1394 |
+
"learning_rate": 1e-05,
|
1395 |
+
"loss": 1.2327,
|
1396 |
+
"step": 1980
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.25164390490642385,
|
1400 |
+
"grad_norm": 0.6429268717765808,
|
1401 |
+
"learning_rate": 1e-05,
|
1402 |
+
"loss": 1.2455,
|
1403 |
+
"step": 1990
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.25290844714213456,
|
1407 |
+
"grad_norm": 0.666034460067749,
|
1408 |
+
"learning_rate": 1e-05,
|
1409 |
+
"loss": 1.2313,
|
1410 |
+
"step": 2000
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.25290844714213456,
|
1414 |
+
"eval_loss": 1.235161304473877,
|
1415 |
+
"eval_runtime": 746.8846,
|
1416 |
+
"eval_samples_per_second": 17.831,
|
1417 |
+
"eval_steps_per_second": 0.558,
|
1418 |
+
"step": 2000
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 0.2541729893778452,
|
1422 |
+
"grad_norm": 0.6502974629402161,
|
1423 |
+
"learning_rate": 1e-05,
|
1424 |
+
"loss": 1.2385,
|
1425 |
+
"step": 2010
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.25543753161355587,
|
1429 |
+
"grad_norm": 0.5858250856399536,
|
1430 |
+
"learning_rate": 1e-05,
|
1431 |
+
"loss": 1.2317,
|
1432 |
+
"step": 2020
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 0.2567020738492666,
|
1436 |
+
"grad_norm": 0.6707966327667236,
|
1437 |
+
"learning_rate": 1e-05,
|
1438 |
+
"loss": 1.2255,
|
1439 |
+
"step": 2030
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 0.25796661608497723,
|
1443 |
+
"grad_norm": 0.6669822931289673,
|
1444 |
+
"learning_rate": 1e-05,
|
1445 |
+
"loss": 1.2483,
|
1446 |
+
"step": 2040
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 0.25923115832068794,
|
1450 |
+
"grad_norm": 0.612241268157959,
|
1451 |
+
"learning_rate": 1e-05,
|
1452 |
+
"loss": 1.2349,
|
1453 |
+
"step": 2050
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 0.2604957005563986,
|
1457 |
+
"grad_norm": 0.6187138557434082,
|
1458 |
+
"learning_rate": 1e-05,
|
1459 |
+
"loss": 1.2252,
|
1460 |
+
"step": 2060
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 0.26176024279210924,
|
1464 |
+
"grad_norm": 0.6674805283546448,
|
1465 |
+
"learning_rate": 1e-05,
|
1466 |
+
"loss": 1.2291,
|
1467 |
+
"step": 2070
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.26302478502781995,
|
1471 |
+
"grad_norm": 0.6246201992034912,
|
1472 |
+
"learning_rate": 1e-05,
|
1473 |
+
"loss": 1.2269,
|
1474 |
+
"step": 2080
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 0.2642893272635306,
|
1478 |
+
"grad_norm": 0.663379967212677,
|
1479 |
+
"learning_rate": 1e-05,
|
1480 |
+
"loss": 1.2287,
|
1481 |
+
"step": 2090
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 0.26555386949924126,
|
1485 |
+
"grad_norm": 0.6754018068313599,
|
1486 |
+
"learning_rate": 1e-05,
|
1487 |
+
"loss": 1.232,
|
1488 |
+
"step": 2100
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 0.26681841173495197,
|
1492 |
+
"grad_norm": 0.656735897064209,
|
1493 |
+
"learning_rate": 1e-05,
|
1494 |
+
"loss": 1.2289,
|
1495 |
+
"step": 2110
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 0.2680829539706626,
|
1499 |
+
"grad_norm": 0.6500769853591919,
|
1500 |
+
"learning_rate": 1e-05,
|
1501 |
+
"loss": 1.2222,
|
1502 |
+
"step": 2120
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 0.26934749620637327,
|
1506 |
+
"grad_norm": 0.6518767476081848,
|
1507 |
+
"learning_rate": 1e-05,
|
1508 |
+
"loss": 1.2345,
|
1509 |
+
"step": 2130
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.270612038442084,
|
1513 |
+
"grad_norm": 0.6453396677970886,
|
1514 |
+
"learning_rate": 1e-05,
|
1515 |
+
"loss": 1.2387,
|
1516 |
+
"step": 2140
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 0.27187658067779463,
|
1520 |
+
"grad_norm": 0.5995469689369202,
|
1521 |
+
"learning_rate": 1e-05,
|
1522 |
+
"loss": 1.2435,
|
1523 |
+
"step": 2150
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 0.2731411229135053,
|
1527 |
+
"grad_norm": 0.6072849035263062,
|
1528 |
+
"learning_rate": 1e-05,
|
1529 |
+
"loss": 1.2306,
|
1530 |
+
"step": 2160
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 0.274405665149216,
|
1534 |
+
"grad_norm": 0.6768641471862793,
|
1535 |
+
"learning_rate": 1e-05,
|
1536 |
+
"loss": 1.2224,
|
1537 |
+
"step": 2170
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 0.27567020738492665,
|
1541 |
+
"grad_norm": 0.6150994300842285,
|
1542 |
+
"learning_rate": 1e-05,
|
1543 |
+
"loss": 1.2327,
|
1544 |
+
"step": 2180
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 0.27693474962063735,
|
1548 |
+
"grad_norm": 0.6202618479728699,
|
1549 |
+
"learning_rate": 1e-05,
|
1550 |
+
"loss": 1.221,
|
1551 |
+
"step": 2190
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.278199291856348,
|
1555 |
+
"grad_norm": 0.6036882400512695,
|
1556 |
+
"learning_rate": 1e-05,
|
1557 |
+
"loss": 1.2237,
|
1558 |
+
"step": 2200
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 0.27946383409205866,
|
1562 |
+
"grad_norm": 0.692686140537262,
|
1563 |
+
"learning_rate": 1e-05,
|
1564 |
+
"loss": 1.2337,
|
1565 |
+
"step": 2210
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 0.28072837632776937,
|
1569 |
+
"grad_norm": 0.6191428303718567,
|
1570 |
+
"learning_rate": 1e-05,
|
1571 |
+
"loss": 1.217,
|
1572 |
+
"step": 2220
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 0.28199291856348,
|
1576 |
+
"grad_norm": 0.6755371689796448,
|
1577 |
+
"learning_rate": 1e-05,
|
1578 |
+
"loss": 1.2332,
|
1579 |
+
"step": 2230
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 0.2832574607991907,
|
1583 |
+
"grad_norm": 0.6544322371482849,
|
1584 |
+
"learning_rate": 1e-05,
|
1585 |
+
"loss": 1.2317,
|
1586 |
+
"step": 2240
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 0.2845220030349014,
|
1590 |
+
"grad_norm": 0.6297930479049683,
|
1591 |
+
"learning_rate": 1e-05,
|
1592 |
+
"loss": 1.2226,
|
1593 |
+
"step": 2250
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.28578654527061204,
|
1597 |
+
"grad_norm": 0.6312263011932373,
|
1598 |
+
"learning_rate": 1e-05,
|
1599 |
+
"loss": 1.2143,
|
1600 |
+
"step": 2260
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 0.2870510875063227,
|
1604 |
+
"grad_norm": 0.6556478142738342,
|
1605 |
+
"learning_rate": 1e-05,
|
1606 |
+
"loss": 1.222,
|
1607 |
+
"step": 2270
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 0.2883156297420334,
|
1611 |
+
"grad_norm": 0.7173165678977966,
|
1612 |
+
"learning_rate": 1e-05,
|
1613 |
+
"loss": 1.2244,
|
1614 |
+
"step": 2280
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.28958017197774405,
|
1618 |
+
"grad_norm": 0.6031741499900818,
|
1619 |
+
"learning_rate": 1e-05,
|
1620 |
+
"loss": 1.2315,
|
1621 |
+
"step": 2290
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 0.2908447142134547,
|
1625 |
+
"grad_norm": 0.6408299207687378,
|
1626 |
+
"learning_rate": 1e-05,
|
1627 |
+
"loss": 1.2192,
|
1628 |
+
"step": 2300
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 0.2921092564491654,
|
1632 |
+
"grad_norm": 0.6189217567443848,
|
1633 |
+
"learning_rate": 1e-05,
|
1634 |
+
"loss": 1.2406,
|
1635 |
+
"step": 2310
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.29337379868487606,
|
1639 |
+
"grad_norm": 0.6057764291763306,
|
1640 |
+
"learning_rate": 1e-05,
|
1641 |
+
"loss": 1.2374,
|
1642 |
+
"step": 2320
|
1643 |
+
},
|
1644 |
+
{
|
1645 |
+
"epoch": 0.29463834092058677,
|
1646 |
+
"grad_norm": 0.5918446183204651,
|
1647 |
+
"learning_rate": 1e-05,
|
1648 |
+
"loss": 1.215,
|
1649 |
+
"step": 2330
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 0.2959028831562974,
|
1653 |
+
"grad_norm": 0.6488243937492371,
|
1654 |
+
"learning_rate": 1e-05,
|
1655 |
+
"loss": 1.2274,
|
1656 |
+
"step": 2340
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 0.2971674253920081,
|
1660 |
+
"grad_norm": 0.6417980790138245,
|
1661 |
+
"learning_rate": 1e-05,
|
1662 |
+
"loss": 1.2293,
|
1663 |
+
"step": 2350
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 0.2984319676277188,
|
1667 |
+
"grad_norm": 0.6471421718597412,
|
1668 |
+
"learning_rate": 1e-05,
|
1669 |
+
"loss": 1.233,
|
1670 |
+
"step": 2360
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 0.29969650986342944,
|
1674 |
+
"grad_norm": 0.6851580739021301,
|
1675 |
+
"learning_rate": 1e-05,
|
1676 |
+
"loss": 1.233,
|
1677 |
+
"step": 2370
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.3009610520991401,
|
1681 |
+
"grad_norm": 0.6430463790893555,
|
1682 |
+
"learning_rate": 1e-05,
|
1683 |
+
"loss": 1.2375,
|
1684 |
+
"step": 2380
|
1685 |
+
},
|
1686 |
+
{
|
1687 |
+
"epoch": 0.3022255943348508,
|
1688 |
+
"grad_norm": 0.602081298828125,
|
1689 |
+
"learning_rate": 1e-05,
|
1690 |
+
"loss": 1.2318,
|
1691 |
+
"step": 2390
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 0.30349013657056145,
|
1695 |
+
"grad_norm": 0.5792240500450134,
|
1696 |
+
"learning_rate": 1e-05,
|
1697 |
+
"loss": 1.2312,
|
1698 |
+
"step": 2400
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 0.3047546788062721,
|
1702 |
+
"grad_norm": 0.6368668675422668,
|
1703 |
+
"learning_rate": 1e-05,
|
1704 |
+
"loss": 1.2213,
|
1705 |
+
"step": 2410
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 0.3060192210419828,
|
1709 |
+
"grad_norm": 0.6738857626914978,
|
1710 |
+
"learning_rate": 1e-05,
|
1711 |
+
"loss": 1.2255,
|
1712 |
+
"step": 2420
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 0.30728376327769347,
|
1716 |
+
"grad_norm": 0.6146492958068848,
|
1717 |
+
"learning_rate": 1e-05,
|
1718 |
+
"loss": 1.2207,
|
1719 |
+
"step": 2430
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.3085483055134042,
|
1723 |
+
"grad_norm": 0.6410118341445923,
|
1724 |
+
"learning_rate": 1e-05,
|
1725 |
+
"loss": 1.2362,
|
1726 |
+
"step": 2440
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 0.30981284774911483,
|
1730 |
+
"grad_norm": 0.6220910549163818,
|
1731 |
+
"learning_rate": 1e-05,
|
1732 |
+
"loss": 1.2181,
|
1733 |
+
"step": 2450
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 0.3110773899848255,
|
1737 |
+
"grad_norm": 0.6798377633094788,
|
1738 |
+
"learning_rate": 1e-05,
|
1739 |
+
"loss": 1.2395,
|
1740 |
+
"step": 2460
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 0.3123419322205362,
|
1744 |
+
"grad_norm": 0.6111645698547363,
|
1745 |
+
"learning_rate": 1e-05,
|
1746 |
+
"loss": 1.2161,
|
1747 |
+
"step": 2470
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 0.31360647445624684,
|
1751 |
+
"grad_norm": 0.6094909310340881,
|
1752 |
+
"learning_rate": 1e-05,
|
1753 |
+
"loss": 1.2216,
|
1754 |
+
"step": 2480
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 0.3148710166919575,
|
1758 |
+
"grad_norm": 0.6226049065589905,
|
1759 |
+
"learning_rate": 1e-05,
|
1760 |
+
"loss": 1.211,
|
1761 |
+
"step": 2490
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.3161355589276682,
|
1765 |
+
"grad_norm": 0.6357924342155457,
|
1766 |
+
"learning_rate": 1e-05,
|
1767 |
+
"loss": 1.211,
|
1768 |
+
"step": 2500
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 0.31740010116337886,
|
1772 |
+
"grad_norm": 0.5930837988853455,
|
1773 |
+
"learning_rate": 1e-05,
|
1774 |
+
"loss": 1.2237,
|
1775 |
+
"step": 2510
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 0.3186646433990895,
|
1779 |
+
"grad_norm": 0.5923945903778076,
|
1780 |
+
"learning_rate": 1e-05,
|
1781 |
+
"loss": 1.2339,
|
1782 |
+
"step": 2520
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 0.3199291856348002,
|
1786 |
+
"grad_norm": 0.6714406609535217,
|
1787 |
+
"learning_rate": 1e-05,
|
1788 |
+
"loss": 1.235,
|
1789 |
+
"step": 2530
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 0.32119372787051087,
|
1793 |
+
"grad_norm": 0.6265254616737366,
|
1794 |
+
"learning_rate": 1e-05,
|
1795 |
+
"loss": 1.2204,
|
1796 |
+
"step": 2540
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 0.3224582701062215,
|
1800 |
+
"grad_norm": 0.5776836276054382,
|
1801 |
+
"learning_rate": 1e-05,
|
1802 |
+
"loss": 1.2039,
|
1803 |
+
"step": 2550
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.32372281234193223,
|
1807 |
+
"grad_norm": 0.6492641568183899,
|
1808 |
+
"learning_rate": 1e-05,
|
1809 |
+
"loss": 1.2229,
|
1810 |
+
"step": 2560
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 0.3249873545776429,
|
1814 |
+
"grad_norm": 0.656096875667572,
|
1815 |
+
"learning_rate": 1e-05,
|
1816 |
+
"loss": 1.2223,
|
1817 |
+
"step": 2570
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 0.3262518968133536,
|
1821 |
+
"grad_norm": 0.6536464095115662,
|
1822 |
+
"learning_rate": 1e-05,
|
1823 |
+
"loss": 1.2281,
|
1824 |
+
"step": 2580
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.32751643904906425,
|
1828 |
+
"grad_norm": 0.6183327436447144,
|
1829 |
+
"learning_rate": 1e-05,
|
1830 |
+
"loss": 1.2317,
|
1831 |
+
"step": 2590
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 0.3287809812847749,
|
1835 |
+
"grad_norm": 0.6506100296974182,
|
1836 |
+
"learning_rate": 1e-05,
|
1837 |
+
"loss": 1.2073,
|
1838 |
+
"step": 2600
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 0.3300455235204856,
|
1842 |
+
"grad_norm": 0.6467426419258118,
|
1843 |
+
"learning_rate": 1e-05,
|
1844 |
+
"loss": 1.2274,
|
1845 |
+
"step": 2610
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.33131006575619626,
|
1849 |
+
"grad_norm": 0.6739821434020996,
|
1850 |
+
"learning_rate": 1e-05,
|
1851 |
+
"loss": 1.2304,
|
1852 |
+
"step": 2620
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 0.3325746079919069,
|
1856 |
+
"grad_norm": 0.6055969595909119,
|
1857 |
+
"learning_rate": 1e-05,
|
1858 |
+
"loss": 1.2165,
|
1859 |
+
"step": 2630
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 0.3338391502276176,
|
1863 |
+
"grad_norm": 0.6366581320762634,
|
1864 |
+
"learning_rate": 1e-05,
|
1865 |
+
"loss": 1.2206,
|
1866 |
+
"step": 2640
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 0.3351036924633283,
|
1870 |
+
"grad_norm": 0.6851908564567566,
|
1871 |
+
"learning_rate": 1e-05,
|
1872 |
+
"loss": 1.2241,
|
1873 |
+
"step": 2650
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 0.3363682346990389,
|
1877 |
+
"grad_norm": 0.6131047010421753,
|
1878 |
+
"learning_rate": 1e-05,
|
1879 |
+
"loss": 1.2081,
|
1880 |
+
"step": 2660
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 0.33763277693474963,
|
1884 |
+
"grad_norm": 0.6366882920265198,
|
1885 |
+
"learning_rate": 1e-05,
|
1886 |
+
"loss": 1.2265,
|
1887 |
+
"step": 2670
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.3388973191704603,
|
1891 |
+
"grad_norm": 0.6722800135612488,
|
1892 |
+
"learning_rate": 1e-05,
|
1893 |
+
"loss": 1.2228,
|
1894 |
+
"step": 2680
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 0.34016186140617094,
|
1898 |
+
"grad_norm": 0.6239178776741028,
|
1899 |
+
"learning_rate": 1e-05,
|
1900 |
+
"loss": 1.2185,
|
1901 |
+
"step": 2690
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 0.34142640364188165,
|
1905 |
+
"grad_norm": 0.6169383525848389,
|
1906 |
+
"learning_rate": 1e-05,
|
1907 |
+
"loss": 1.2223,
|
1908 |
+
"step": 2700
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 0.3426909458775923,
|
1912 |
+
"grad_norm": 0.6219863891601562,
|
1913 |
+
"learning_rate": 1e-05,
|
1914 |
+
"loss": 1.23,
|
1915 |
+
"step": 2710
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 0.343955488113303,
|
1919 |
+
"grad_norm": 0.6282393932342529,
|
1920 |
+
"learning_rate": 1e-05,
|
1921 |
+
"loss": 1.219,
|
1922 |
+
"step": 2720
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 0.34522003034901366,
|
1926 |
+
"grad_norm": 0.6174669861793518,
|
1927 |
+
"learning_rate": 1e-05,
|
1928 |
+
"loss": 1.2258,
|
1929 |
+
"step": 2730
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.3464845725847243,
|
1933 |
+
"grad_norm": 0.6178705096244812,
|
1934 |
+
"learning_rate": 1e-05,
|
1935 |
+
"loss": 1.2261,
|
1936 |
+
"step": 2740
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 0.347749114820435,
|
1940 |
+
"grad_norm": 0.6490427255630493,
|
1941 |
+
"learning_rate": 1e-05,
|
1942 |
+
"loss": 1.2099,
|
1943 |
+
"step": 2750
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 0.3490136570561457,
|
1947 |
+
"grad_norm": 0.6057268977165222,
|
1948 |
+
"learning_rate": 1e-05,
|
1949 |
+
"loss": 1.2037,
|
1950 |
+
"step": 2760
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 0.35027819929185633,
|
1954 |
+
"grad_norm": 0.5861403346061707,
|
1955 |
+
"learning_rate": 1e-05,
|
1956 |
+
"loss": 1.2243,
|
1957 |
+
"step": 2770
|
1958 |
+
},
|
1959 |
+
{
|
1960 |
+
"epoch": 0.35154274152756704,
|
1961 |
+
"grad_norm": 0.6274175643920898,
|
1962 |
+
"learning_rate": 1e-05,
|
1963 |
+
"loss": 1.2244,
|
1964 |
+
"step": 2780
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 0.3528072837632777,
|
1968 |
+
"grad_norm": 0.6302198171615601,
|
1969 |
+
"learning_rate": 1e-05,
|
1970 |
+
"loss": 1.2222,
|
1971 |
+
"step": 2790
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.35407182599898834,
|
1975 |
+
"grad_norm": 0.6314812898635864,
|
1976 |
+
"learning_rate": 1e-05,
|
1977 |
+
"loss": 1.2004,
|
1978 |
+
"step": 2800
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 0.35533636823469905,
|
1982 |
+
"grad_norm": 0.6489315032958984,
|
1983 |
+
"learning_rate": 1e-05,
|
1984 |
+
"loss": 1.2178,
|
1985 |
+
"step": 2810
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 0.3566009104704097,
|
1989 |
+
"grad_norm": 0.6509455442428589,
|
1990 |
+
"learning_rate": 1e-05,
|
1991 |
+
"loss": 1.2024,
|
1992 |
+
"step": 2820
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 0.35786545270612036,
|
1996 |
+
"grad_norm": 0.641886293888092,
|
1997 |
+
"learning_rate": 1e-05,
|
1998 |
+
"loss": 1.2229,
|
1999 |
+
"step": 2830
|
2000 |
+
},
|
2001 |
+
{
|
2002 |
+
"epoch": 0.35912999494183107,
|
2003 |
+
"grad_norm": 0.6359536051750183,
|
2004 |
+
"learning_rate": 1e-05,
|
2005 |
+
"loss": 1.2158,
|
2006 |
+
"step": 2840
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 0.3603945371775417,
|
2010 |
+
"grad_norm": 0.6850735545158386,
|
2011 |
+
"learning_rate": 1e-05,
|
2012 |
+
"loss": 1.2212,
|
2013 |
+
"step": 2850
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 0.3616590794132524,
|
2017 |
+
"grad_norm": 0.6814893484115601,
|
2018 |
+
"learning_rate": 1e-05,
|
2019 |
+
"loss": 1.2261,
|
2020 |
+
"step": 2860
|
2021 |
+
},
|
2022 |
+
{
|
2023 |
+
"epoch": 0.3629236216489631,
|
2024 |
+
"grad_norm": 0.6300289034843445,
|
2025 |
+
"learning_rate": 1e-05,
|
2026 |
+
"loss": 1.2022,
|
2027 |
+
"step": 2870
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 0.36418816388467373,
|
2031 |
+
"grad_norm": 0.5974512696266174,
|
2032 |
+
"learning_rate": 1e-05,
|
2033 |
+
"loss": 1.2144,
|
2034 |
+
"step": 2880
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 0.36545270612038444,
|
2038 |
+
"grad_norm": 0.6321489810943604,
|
2039 |
+
"learning_rate": 1e-05,
|
2040 |
+
"loss": 1.2203,
|
2041 |
+
"step": 2890
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 0.3667172483560951,
|
2045 |
+
"grad_norm": 0.5945002436637878,
|
2046 |
+
"learning_rate": 1e-05,
|
2047 |
+
"loss": 1.2376,
|
2048 |
+
"step": 2900
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 0.36798179059180575,
|
2052 |
+
"grad_norm": 0.6462925672531128,
|
2053 |
+
"learning_rate": 1e-05,
|
2054 |
+
"loss": 1.1991,
|
2055 |
+
"step": 2910
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 0.36924633282751645,
|
2059 |
+
"grad_norm": 0.6013085246086121,
|
2060 |
+
"learning_rate": 1e-05,
|
2061 |
+
"loss": 1.2396,
|
2062 |
+
"step": 2920
|
2063 |
+
},
|
2064 |
+
{
|
2065 |
+
"epoch": 0.3705108750632271,
|
2066 |
+
"grad_norm": 0.6148044466972351,
|
2067 |
+
"learning_rate": 1e-05,
|
2068 |
+
"loss": 1.2276,
|
2069 |
+
"step": 2930
|
2070 |
+
},
|
2071 |
+
{
|
2072 |
+
"epoch": 0.37177541729893776,
|
2073 |
+
"grad_norm": 0.6378566026687622,
|
2074 |
+
"learning_rate": 1e-05,
|
2075 |
+
"loss": 1.2164,
|
2076 |
+
"step": 2940
|
2077 |
+
},
|
2078 |
+
{
|
2079 |
+
"epoch": 0.37303995953464847,
|
2080 |
+
"grad_norm": 0.6143125891685486,
|
2081 |
+
"learning_rate": 1e-05,
|
2082 |
+
"loss": 1.2265,
|
2083 |
+
"step": 2950
|
2084 |
+
},
|
2085 |
+
{
|
2086 |
+
"epoch": 0.3743045017703591,
|
2087 |
+
"grad_norm": 0.6377760171890259,
|
2088 |
+
"learning_rate": 1e-05,
|
2089 |
+
"loss": 1.223,
|
2090 |
+
"step": 2960
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 0.37556904400606983,
|
2094 |
+
"grad_norm": 0.595260500907898,
|
2095 |
+
"learning_rate": 1e-05,
|
2096 |
+
"loss": 1.228,
|
2097 |
+
"step": 2970
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 0.3768335862417805,
|
2101 |
+
"grad_norm": 0.6682959198951721,
|
2102 |
+
"learning_rate": 1e-05,
|
2103 |
+
"loss": 1.2116,
|
2104 |
+
"step": 2980
|
2105 |
+
},
|
2106 |
+
{
|
2107 |
+
"epoch": 0.37809812847749114,
|
2108 |
+
"grad_norm": 0.6373882293701172,
|
2109 |
+
"learning_rate": 1e-05,
|
2110 |
+
"loss": 1.2062,
|
2111 |
+
"step": 2990
|
2112 |
+
},
|
2113 |
+
{
|
2114 |
+
"epoch": 0.37936267071320184,
|
2115 |
+
"grad_norm": 0.6503208875656128,
|
2116 |
+
"learning_rate": 1e-05,
|
2117 |
+
"loss": 1.2198,
|
2118 |
+
"step": 3000
|
2119 |
+
},
|
2120 |
+
{
|
2121 |
+
"epoch": 0.3806272129489125,
|
2122 |
+
"grad_norm": 0.5843953490257263,
|
2123 |
+
"learning_rate": 1e-05,
|
2124 |
+
"loss": 1.2121,
|
2125 |
+
"step": 3010
|
2126 |
+
},
|
2127 |
+
{
|
2128 |
+
"epoch": 0.38189175518462315,
|
2129 |
+
"grad_norm": 0.604332447052002,
|
2130 |
+
"learning_rate": 1e-05,
|
2131 |
+
"loss": 1.2094,
|
2132 |
+
"step": 3020
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 0.38315629742033386,
|
2136 |
+
"grad_norm": 0.6302861571311951,
|
2137 |
+
"learning_rate": 1e-05,
|
2138 |
+
"loss": 1.2315,
|
2139 |
+
"step": 3030
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 0.3844208396560445,
|
2143 |
+
"grad_norm": 0.5992172956466675,
|
2144 |
+
"learning_rate": 1e-05,
|
2145 |
+
"loss": 1.2071,
|
2146 |
+
"step": 3040
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 0.38568538189175516,
|
2150 |
+
"grad_norm": 0.6451935172080994,
|
2151 |
+
"learning_rate": 1e-05,
|
2152 |
+
"loss": 1.2042,
|
2153 |
+
"step": 3050
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 0.38694992412746587,
|
2157 |
+
"grad_norm": 0.6427459120750427,
|
2158 |
+
"learning_rate": 1e-05,
|
2159 |
+
"loss": 1.2106,
|
2160 |
+
"step": 3060
|
2161 |
+
},
|
2162 |
+
{
|
2163 |
+
"epoch": 0.3882144663631765,
|
2164 |
+
"grad_norm": 0.619175136089325,
|
2165 |
+
"learning_rate": 1e-05,
|
2166 |
+
"loss": 1.2181,
|
2167 |
+
"step": 3070
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"epoch": 0.3894790085988872,
|
2171 |
+
"grad_norm": 0.6177219748497009,
|
2172 |
+
"learning_rate": 1e-05,
|
2173 |
+
"loss": 1.212,
|
2174 |
+
"step": 3080
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 0.3907435508345979,
|
2178 |
+
"grad_norm": 0.6541352272033691,
|
2179 |
+
"learning_rate": 1e-05,
|
2180 |
+
"loss": 1.2273,
|
2181 |
+
"step": 3090
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 0.39200809307030854,
|
2185 |
+
"grad_norm": 0.6039160490036011,
|
2186 |
+
"learning_rate": 1e-05,
|
2187 |
+
"loss": 1.2083,
|
2188 |
+
"step": 3100
|
2189 |
+
},
|
2190 |
+
{
|
2191 |
+
"epoch": 0.39327263530601925,
|
2192 |
+
"grad_norm": 0.6636294722557068,
|
2193 |
+
"learning_rate": 1e-05,
|
2194 |
+
"loss": 1.2243,
|
2195 |
+
"step": 3110
|
2196 |
+
},
|
2197 |
+
{
|
2198 |
+
"epoch": 0.3945371775417299,
|
2199 |
+
"grad_norm": 0.6710155010223389,
|
2200 |
+
"learning_rate": 1e-05,
|
2201 |
+
"loss": 1.2231,
|
2202 |
+
"step": 3120
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 0.39580171977744055,
|
2206 |
+
"grad_norm": 0.6997529864311218,
|
2207 |
+
"learning_rate": 1e-05,
|
2208 |
+
"loss": 1.2139,
|
2209 |
+
"step": 3130
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 0.39706626201315126,
|
2213 |
+
"grad_norm": 0.6152109503746033,
|
2214 |
+
"learning_rate": 1e-05,
|
2215 |
+
"loss": 1.211,
|
2216 |
+
"step": 3140
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 0.3983308042488619,
|
2220 |
+
"grad_norm": 0.568949818611145,
|
2221 |
+
"learning_rate": 1e-05,
|
2222 |
+
"loss": 1.2128,
|
2223 |
+
"step": 3150
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 0.39959534648457257,
|
2227 |
+
"grad_norm": 0.6256394982337952,
|
2228 |
+
"learning_rate": 1e-05,
|
2229 |
+
"loss": 1.2259,
|
2230 |
+
"step": 3160
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"epoch": 0.4008598887202833,
|
2234 |
+
"grad_norm": 0.6586698293685913,
|
2235 |
+
"learning_rate": 1e-05,
|
2236 |
+
"loss": 1.2281,
|
2237 |
+
"step": 3170
|
2238 |
+
},
|
2239 |
+
{
|
2240 |
+
"epoch": 0.40212443095599393,
|
2241 |
+
"grad_norm": 0.6269087791442871,
|
2242 |
+
"learning_rate": 1e-05,
|
2243 |
+
"loss": 1.2133,
|
2244 |
+
"step": 3180
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 0.4033889731917046,
|
2248 |
+
"grad_norm": 0.6131490468978882,
|
2249 |
+
"learning_rate": 1e-05,
|
2250 |
+
"loss": 1.2005,
|
2251 |
+
"step": 3190
|
2252 |
+
},
|
2253 |
+
{
|
2254 |
+
"epoch": 0.4046535154274153,
|
2255 |
+
"grad_norm": 0.6410918235778809,
|
2256 |
+
"learning_rate": 1e-05,
|
2257 |
+
"loss": 1.2167,
|
2258 |
+
"step": 3200
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 0.40591805766312594,
|
2262 |
+
"grad_norm": 0.5742530226707458,
|
2263 |
+
"learning_rate": 1e-05,
|
2264 |
+
"loss": 1.2294,
|
2265 |
+
"step": 3210
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 0.4071825998988366,
|
2269 |
+
"grad_norm": 0.5909201502799988,
|
2270 |
+
"learning_rate": 1e-05,
|
2271 |
+
"loss": 1.2073,
|
2272 |
+
"step": 3220
|
2273 |
+
},
|
2274 |
+
{
|
2275 |
+
"epoch": 0.4084471421345473,
|
2276 |
+
"grad_norm": 0.6320379972457886,
|
2277 |
+
"learning_rate": 1e-05,
|
2278 |
+
"loss": 1.2176,
|
2279 |
+
"step": 3230
|
2280 |
+
},
|
2281 |
+
{
|
2282 |
+
"epoch": 0.40971168437025796,
|
2283 |
+
"grad_norm": 0.6358179450035095,
|
2284 |
+
"learning_rate": 1e-05,
|
2285 |
+
"loss": 1.2173,
|
2286 |
+
"step": 3240
|
2287 |
+
},
|
2288 |
+
{
|
2289 |
+
"epoch": 0.41097622660596866,
|
2290 |
+
"grad_norm": 0.6459697484970093,
|
2291 |
+
"learning_rate": 1e-05,
|
2292 |
+
"loss": 1.2048,
|
2293 |
+
"step": 3250
|
2294 |
+
},
|
2295 |
+
{
|
2296 |
+
"epoch": 0.4122407688416793,
|
2297 |
+
"grad_norm": 0.6121228933334351,
|
2298 |
+
"learning_rate": 1e-05,
|
2299 |
+
"loss": 1.1907,
|
2300 |
+
"step": 3260
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 0.41350531107738997,
|
2304 |
+
"grad_norm": 0.6053618788719177,
|
2305 |
+
"learning_rate": 1e-05,
|
2306 |
+
"loss": 1.21,
|
2307 |
+
"step": 3270
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 0.4147698533131007,
|
2311 |
+
"grad_norm": 0.6074268817901611,
|
2312 |
+
"learning_rate": 1e-05,
|
2313 |
+
"loss": 1.2131,
|
2314 |
+
"step": 3280
|
2315 |
+
},
|
2316 |
+
{
|
2317 |
+
"epoch": 0.41603439554881133,
|
2318 |
+
"grad_norm": 0.6343367099761963,
|
2319 |
+
"learning_rate": 1e-05,
|
2320 |
+
"loss": 1.2186,
|
2321 |
+
"step": 3290
|
2322 |
+
},
|
2323 |
+
{
|
2324 |
+
"epoch": 0.417298937784522,
|
2325 |
+
"grad_norm": 0.6467527151107788,
|
2326 |
+
"learning_rate": 1e-05,
|
2327 |
+
"loss": 1.2146,
|
2328 |
+
"step": 3300
|
2329 |
+
},
|
2330 |
+
{
|
2331 |
+
"epoch": 0.4185634800202327,
|
2332 |
+
"grad_norm": 0.653825581073761,
|
2333 |
+
"learning_rate": 1e-05,
|
2334 |
+
"loss": 1.204,
|
2335 |
+
"step": 3310
|
2336 |
+
},
|
2337 |
+
{
|
2338 |
+
"epoch": 0.41982802225594334,
|
2339 |
+
"grad_norm": 0.6280072927474976,
|
2340 |
+
"learning_rate": 1e-05,
|
2341 |
+
"loss": 1.2135,
|
2342 |
+
"step": 3320
|
2343 |
+
},
|
2344 |
+
{
|
2345 |
+
"epoch": 0.421092564491654,
|
2346 |
+
"grad_norm": 0.6239051222801208,
|
2347 |
+
"learning_rate": 1e-05,
|
2348 |
+
"loss": 1.2126,
|
2349 |
+
"step": 3330
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 0.4223571067273647,
|
2353 |
+
"grad_norm": 0.5642049908638,
|
2354 |
+
"learning_rate": 1e-05,
|
2355 |
+
"loss": 1.2008,
|
2356 |
+
"step": 3340
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 0.42362164896307536,
|
2360 |
+
"grad_norm": 0.6263325214385986,
|
2361 |
+
"learning_rate": 1e-05,
|
2362 |
+
"loss": 1.2063,
|
2363 |
+
"step": 3350
|
2364 |
+
},
|
2365 |
+
{
|
2366 |
+
"epoch": 0.424886191198786,
|
2367 |
+
"grad_norm": 0.627679705619812,
|
2368 |
+
"learning_rate": 1e-05,
|
2369 |
+
"loss": 1.2052,
|
2370 |
+
"step": 3360
|
2371 |
+
},
|
2372 |
+
{
|
2373 |
+
"epoch": 0.4261507334344967,
|
2374 |
+
"grad_norm": 0.5806178450584412,
|
2375 |
+
"learning_rate": 1e-05,
|
2376 |
+
"loss": 1.2059,
|
2377 |
+
"step": 3370
|
2378 |
+
},
|
2379 |
+
{
|
2380 |
+
"epoch": 0.4274152756702074,
|
2381 |
+
"grad_norm": 0.6369416117668152,
|
2382 |
+
"learning_rate": 1e-05,
|
2383 |
+
"loss": 1.2299,
|
2384 |
+
"step": 3380
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 0.4286798179059181,
|
2388 |
+
"grad_norm": 0.6234344244003296,
|
2389 |
+
"learning_rate": 1e-05,
|
2390 |
+
"loss": 1.2068,
|
2391 |
+
"step": 3390
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 0.42994436014162873,
|
2395 |
+
"grad_norm": 0.592321515083313,
|
2396 |
+
"learning_rate": 1e-05,
|
2397 |
+
"loss": 1.206,
|
2398 |
+
"step": 3400
|
2399 |
+
},
|
2400 |
+
{
|
2401 |
+
"epoch": 0.4312089023773394,
|
2402 |
+
"grad_norm": 0.5816251039505005,
|
2403 |
+
"learning_rate": 1e-05,
|
2404 |
+
"loss": 1.1902,
|
2405 |
+
"step": 3410
|
2406 |
+
},
|
2407 |
+
{
|
2408 |
+
"epoch": 0.4324734446130501,
|
2409 |
+
"grad_norm": 0.6836596131324768,
|
2410 |
+
"learning_rate": 1e-05,
|
2411 |
+
"loss": 1.209,
|
2412 |
+
"step": 3420
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 0.43373798684876075,
|
2416 |
+
"grad_norm": 0.577930212020874,
|
2417 |
+
"learning_rate": 1e-05,
|
2418 |
+
"loss": 1.2074,
|
2419 |
+
"step": 3430
|
2420 |
+
},
|
2421 |
+
{
|
2422 |
+
"epoch": 0.4350025290844714,
|
2423 |
+
"grad_norm": 0.6183462738990784,
|
2424 |
+
"learning_rate": 1e-05,
|
2425 |
+
"loss": 1.2091,
|
2426 |
+
"step": 3440
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 0.4362670713201821,
|
2430 |
+
"grad_norm": 0.616744875907898,
|
2431 |
+
"learning_rate": 1e-05,
|
2432 |
+
"loss": 1.1935,
|
2433 |
+
"step": 3450
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 0.43753161355589276,
|
2437 |
+
"grad_norm": 0.6340389847755432,
|
2438 |
+
"learning_rate": 1e-05,
|
2439 |
+
"loss": 1.2116,
|
2440 |
+
"step": 3460
|
2441 |
+
},
|
2442 |
+
{
|
2443 |
+
"epoch": 0.4387961557916034,
|
2444 |
+
"grad_norm": 0.6423779129981995,
|
2445 |
+
"learning_rate": 1e-05,
|
2446 |
+
"loss": 1.2073,
|
2447 |
+
"step": 3470
|
2448 |
+
},
|
2449 |
+
{
|
2450 |
+
"epoch": 0.4400606980273141,
|
2451 |
+
"grad_norm": 0.6088785529136658,
|
2452 |
+
"learning_rate": 1e-05,
|
2453 |
+
"loss": 1.2217,
|
2454 |
+
"step": 3480
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 0.4413252402630248,
|
2458 |
+
"grad_norm": 0.6500691771507263,
|
2459 |
+
"learning_rate": 1e-05,
|
2460 |
+
"loss": 1.1927,
|
2461 |
+
"step": 3490
|
2462 |
+
},
|
2463 |
+
{
|
2464 |
+
"epoch": 0.4425897824987355,
|
2465 |
+
"grad_norm": 0.6340954899787903,
|
2466 |
+
"learning_rate": 1e-05,
|
2467 |
+
"loss": 1.214,
|
2468 |
+
"step": 3500
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 0.44385432473444614,
|
2472 |
+
"grad_norm": 0.5911884307861328,
|
2473 |
+
"learning_rate": 1e-05,
|
2474 |
+
"loss": 1.2212,
|
2475 |
+
"step": 3510
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 0.4451188669701568,
|
2479 |
+
"grad_norm": 0.6097255349159241,
|
2480 |
+
"learning_rate": 1e-05,
|
2481 |
+
"loss": 1.2094,
|
2482 |
+
"step": 3520
|
2483 |
+
},
|
2484 |
+
{
|
2485 |
+
"epoch": 0.4463834092058675,
|
2486 |
+
"grad_norm": 0.6120964288711548,
|
2487 |
+
"learning_rate": 1e-05,
|
2488 |
+
"loss": 1.2173,
|
2489 |
+
"step": 3530
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 0.44764795144157815,
|
2493 |
+
"grad_norm": 0.6476565003395081,
|
2494 |
+
"learning_rate": 1e-05,
|
2495 |
+
"loss": 1.2225,
|
2496 |
+
"step": 3540
|
2497 |
+
},
|
2498 |
+
{
|
2499 |
+
"epoch": 0.4489124936772888,
|
2500 |
+
"grad_norm": 0.602401852607727,
|
2501 |
+
"learning_rate": 1e-05,
|
2502 |
+
"loss": 1.2012,
|
2503 |
+
"step": 3550
|
2504 |
+
},
|
2505 |
+
{
|
2506 |
+
"epoch": 0.4501770359129995,
|
2507 |
+
"grad_norm": 0.6021948456764221,
|
2508 |
+
"learning_rate": 1e-05,
|
2509 |
+
"loss": 1.2029,
|
2510 |
+
"step": 3560
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 0.45144157814871017,
|
2514 |
+
"grad_norm": 0.6265749931335449,
|
2515 |
+
"learning_rate": 1e-05,
|
2516 |
+
"loss": 1.2084,
|
2517 |
+
"step": 3570
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 0.4527061203844208,
|
2521 |
+
"grad_norm": 0.6242750287055969,
|
2522 |
+
"learning_rate": 1e-05,
|
2523 |
+
"loss": 1.2199,
|
2524 |
+
"step": 3580
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 0.4539706626201315,
|
2528 |
+
"grad_norm": 0.6115322709083557,
|
2529 |
+
"learning_rate": 1e-05,
|
2530 |
+
"loss": 1.2084,
|
2531 |
+
"step": 3590
|
2532 |
+
},
|
2533 |
+
{
|
2534 |
+
"epoch": 0.4552352048558422,
|
2535 |
+
"grad_norm": 0.5960603952407837,
|
2536 |
+
"learning_rate": 1e-05,
|
2537 |
+
"loss": 1.1994,
|
2538 |
+
"step": 3600
|
2539 |
+
},
|
2540 |
+
{
|
2541 |
+
"epoch": 0.45649974709155283,
|
2542 |
+
"grad_norm": 0.5775576829910278,
|
2543 |
+
"learning_rate": 1e-05,
|
2544 |
+
"loss": 1.2106,
|
2545 |
+
"step": 3610
|
2546 |
+
},
|
2547 |
+
{
|
2548 |
+
"epoch": 0.45776428932726354,
|
2549 |
+
"grad_norm": 0.6044995188713074,
|
2550 |
+
"learning_rate": 1e-05,
|
2551 |
+
"loss": 1.2079,
|
2552 |
+
"step": 3620
|
2553 |
+
},
|
2554 |
+
{
|
2555 |
+
"epoch": 0.4590288315629742,
|
2556 |
+
"grad_norm": 0.5952639579772949,
|
2557 |
+
"learning_rate": 1e-05,
|
2558 |
+
"loss": 1.2034,
|
2559 |
+
"step": 3630
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 0.4602933737986849,
|
2563 |
+
"grad_norm": 0.6244965195655823,
|
2564 |
+
"learning_rate": 1e-05,
|
2565 |
+
"loss": 1.1865,
|
2566 |
+
"step": 3640
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"epoch": 0.46155791603439555,
|
2570 |
+
"grad_norm": 0.6486892104148865,
|
2571 |
+
"learning_rate": 1e-05,
|
2572 |
+
"loss": 1.2006,
|
2573 |
+
"step": 3650
|
2574 |
+
},
|
2575 |
+
{
|
2576 |
+
"epoch": 0.4628224582701062,
|
2577 |
+
"grad_norm": 0.6212941408157349,
|
2578 |
+
"learning_rate": 1e-05,
|
2579 |
+
"loss": 1.194,
|
2580 |
+
"step": 3660
|
2581 |
+
},
|
2582 |
+
{
|
2583 |
+
"epoch": 0.4640870005058169,
|
2584 |
+
"grad_norm": 0.6290844678878784,
|
2585 |
+
"learning_rate": 1e-05,
|
2586 |
+
"loss": 1.2139,
|
2587 |
+
"step": 3670
|
2588 |
+
},
|
2589 |
+
{
|
2590 |
+
"epoch": 0.46535154274152757,
|
2591 |
+
"grad_norm": 0.5951138734817505,
|
2592 |
+
"learning_rate": 1e-05,
|
2593 |
+
"loss": 1.2063,
|
2594 |
+
"step": 3680
|
2595 |
+
},
|
2596 |
+
{
|
2597 |
+
"epoch": 0.4666160849772382,
|
2598 |
+
"grad_norm": 0.6083012819290161,
|
2599 |
+
"learning_rate": 1e-05,
|
2600 |
+
"loss": 1.2113,
|
2601 |
+
"step": 3690
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 0.46788062721294893,
|
2605 |
+
"grad_norm": 0.5908785462379456,
|
2606 |
+
"learning_rate": 1e-05,
|
2607 |
+
"loss": 1.1952,
|
2608 |
+
"step": 3700
|
2609 |
+
},
|
2610 |
+
{
|
2611 |
+
"epoch": 0.4691451694486596,
|
2612 |
+
"grad_norm": 0.5933132767677307,
|
2613 |
+
"learning_rate": 1e-05,
|
2614 |
+
"loss": 1.2151,
|
2615 |
+
"step": 3710
|
2616 |
+
},
|
2617 |
+
{
|
2618 |
+
"epoch": 0.47040971168437024,
|
2619 |
+
"grad_norm": 0.6214738488197327,
|
2620 |
+
"learning_rate": 1e-05,
|
2621 |
+
"loss": 1.2189,
|
2622 |
+
"step": 3720
|
2623 |
+
},
|
2624 |
+
{
|
2625 |
+
"epoch": 0.47167425392008094,
|
2626 |
+
"grad_norm": 0.6605792045593262,
|
2627 |
+
"learning_rate": 1e-05,
|
2628 |
+
"loss": 1.1958,
|
2629 |
+
"step": 3730
|
2630 |
+
},
|
2631 |
+
{
|
2632 |
+
"epoch": 0.4729387961557916,
|
2633 |
+
"grad_norm": 0.6238041520118713,
|
2634 |
+
"learning_rate": 1e-05,
|
2635 |
+
"loss": 1.1957,
|
2636 |
+
"step": 3740
|
2637 |
+
},
|
2638 |
+
{
|
2639 |
+
"epoch": 0.47420333839150225,
|
2640 |
+
"grad_norm": 0.5770658254623413,
|
2641 |
+
"learning_rate": 1e-05,
|
2642 |
+
"loss": 1.2055,
|
2643 |
+
"step": 3750
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 0.47546788062721296,
|
2647 |
+
"grad_norm": 0.6447641253471375,
|
2648 |
+
"learning_rate": 1e-05,
|
2649 |
+
"loss": 1.2185,
|
2650 |
+
"step": 3760
|
2651 |
+
},
|
2652 |
+
{
|
2653 |
+
"epoch": 0.4767324228629236,
|
2654 |
+
"grad_norm": 0.5972367525100708,
|
2655 |
+
"learning_rate": 1e-05,
|
2656 |
+
"loss": 1.1986,
|
2657 |
+
"step": 3770
|
2658 |
+
},
|
2659 |
+
{
|
2660 |
+
"epoch": 0.4779969650986343,
|
2661 |
+
"grad_norm": 0.6158856749534607,
|
2662 |
+
"learning_rate": 1e-05,
|
2663 |
+
"loss": 1.2185,
|
2664 |
+
"step": 3780
|
2665 |
+
},
|
2666 |
+
{
|
2667 |
+
"epoch": 0.47926150733434497,
|
2668 |
+
"grad_norm": 0.6071646213531494,
|
2669 |
+
"learning_rate": 1e-05,
|
2670 |
+
"loss": 1.2022,
|
2671 |
+
"step": 3790
|
2672 |
+
},
|
2673 |
+
{
|
2674 |
+
"epoch": 0.4805260495700556,
|
2675 |
+
"grad_norm": 0.5575715899467468,
|
2676 |
+
"learning_rate": 1e-05,
|
2677 |
+
"loss": 1.2023,
|
2678 |
+
"step": 3800
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 0.48179059180576633,
|
2682 |
+
"grad_norm": 0.6392408609390259,
|
2683 |
+
"learning_rate": 1e-05,
|
2684 |
+
"loss": 1.1987,
|
2685 |
+
"step": 3810
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 0.483055134041477,
|
2689 |
+
"grad_norm": 0.6005633473396301,
|
2690 |
+
"learning_rate": 1e-05,
|
2691 |
+
"loss": 1.1945,
|
2692 |
+
"step": 3820
|
2693 |
+
},
|
2694 |
+
{
|
2695 |
+
"epoch": 0.48431967627718764,
|
2696 |
+
"grad_norm": 0.6631231307983398,
|
2697 |
+
"learning_rate": 1e-05,
|
2698 |
+
"loss": 1.213,
|
2699 |
+
"step": 3830
|
2700 |
+
},
|
2701 |
+
{
|
2702 |
+
"epoch": 0.48558421851289835,
|
2703 |
+
"grad_norm": 0.5975536108016968,
|
2704 |
+
"learning_rate": 1e-05,
|
2705 |
+
"loss": 1.2113,
|
2706 |
+
"step": 3840
|
2707 |
+
},
|
2708 |
+
{
|
2709 |
+
"epoch": 0.486848760748609,
|
2710 |
+
"grad_norm": 0.5995634198188782,
|
2711 |
+
"learning_rate": 1e-05,
|
2712 |
+
"loss": 1.193,
|
2713 |
+
"step": 3850
|
2714 |
+
},
|
2715 |
+
{
|
2716 |
+
"epoch": 0.48811330298431965,
|
2717 |
+
"grad_norm": 0.5777637362480164,
|
2718 |
+
"learning_rate": 1e-05,
|
2719 |
+
"loss": 1.1964,
|
2720 |
+
"step": 3860
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 0.48937784522003036,
|
2724 |
+
"grad_norm": 0.6348541975021362,
|
2725 |
+
"learning_rate": 1e-05,
|
2726 |
+
"loss": 1.1853,
|
2727 |
+
"step": 3870
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 0.490642387455741,
|
2731 |
+
"grad_norm": 0.6015579104423523,
|
2732 |
+
"learning_rate": 1e-05,
|
2733 |
+
"loss": 1.2045,
|
2734 |
+
"step": 3880
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 0.4919069296914517,
|
2738 |
+
"grad_norm": 0.5699253082275391,
|
2739 |
+
"learning_rate": 1e-05,
|
2740 |
+
"loss": 1.1988,
|
2741 |
+
"step": 3890
|
2742 |
+
},
|
2743 |
+
{
|
2744 |
+
"epoch": 0.4931714719271624,
|
2745 |
+
"grad_norm": 0.6055163741111755,
|
2746 |
+
"learning_rate": 1e-05,
|
2747 |
+
"loss": 1.2091,
|
2748 |
+
"step": 3900
|
2749 |
+
},
|
2750 |
+
{
|
2751 |
+
"epoch": 0.494436014162873,
|
2752 |
+
"grad_norm": 0.6187211871147156,
|
2753 |
+
"learning_rate": 1e-05,
|
2754 |
+
"loss": 1.1928,
|
2755 |
+
"step": 3910
|
2756 |
+
},
|
2757 |
+
{
|
2758 |
+
"epoch": 0.49570055639858374,
|
2759 |
+
"grad_norm": 0.6191034913063049,
|
2760 |
+
"learning_rate": 1e-05,
|
2761 |
+
"loss": 1.2083,
|
2762 |
+
"step": 3920
|
2763 |
+
},
|
2764 |
+
{
|
2765 |
+
"epoch": 0.4969650986342944,
|
2766 |
+
"grad_norm": 0.590437114238739,
|
2767 |
+
"learning_rate": 1e-05,
|
2768 |
+
"loss": 1.1926,
|
2769 |
+
"step": 3930
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 0.49822964087000504,
|
2773 |
+
"grad_norm": 0.666506826877594,
|
2774 |
+
"learning_rate": 1e-05,
|
2775 |
+
"loss": 1.2117,
|
2776 |
+
"step": 3940
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 0.49949418310571575,
|
2780 |
+
"grad_norm": 0.6087044477462769,
|
2781 |
+
"learning_rate": 1e-05,
|
2782 |
+
"loss": 1.2069,
|
2783 |
+
"step": 3950
|
2784 |
+
},
|
2785 |
+
{
|
2786 |
+
"epoch": 0.5007587253414264,
|
2787 |
+
"grad_norm": 0.6013064980506897,
|
2788 |
+
"learning_rate": 1e-05,
|
2789 |
+
"loss": 1.2017,
|
2790 |
+
"step": 3960
|
2791 |
+
},
|
2792 |
+
{
|
2793 |
+
"epoch": 0.5020232675771371,
|
2794 |
+
"grad_norm": 0.6218295693397522,
|
2795 |
+
"learning_rate": 1e-05,
|
2796 |
+
"loss": 1.1996,
|
2797 |
+
"step": 3970
|
2798 |
+
},
|
2799 |
+
{
|
2800 |
+
"epoch": 0.5032878098128477,
|
2801 |
+
"grad_norm": 0.5749101042747498,
|
2802 |
+
"learning_rate": 1e-05,
|
2803 |
+
"loss": 1.2085,
|
2804 |
+
"step": 3980
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 0.5045523520485584,
|
2808 |
+
"grad_norm": 0.6124399900436401,
|
2809 |
+
"learning_rate": 1e-05,
|
2810 |
+
"loss": 1.1967,
|
2811 |
+
"step": 3990
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 0.5058168942842691,
|
2815 |
+
"grad_norm": 0.5921447277069092,
|
2816 |
+
"learning_rate": 1e-05,
|
2817 |
+
"loss": 1.2155,
|
2818 |
+
"step": 4000
|
2819 |
+
},
|
2820 |
+
{
|
2821 |
+
"epoch": 0.5058168942842691,
|
2822 |
+
"eval_loss": 1.204215168952942,
|
2823 |
+
"eval_runtime": 743.3261,
|
2824 |
+
"eval_samples_per_second": 17.917,
|
2825 |
+
"eval_steps_per_second": 0.561,
|
2826 |
+
"step": 4000
|
2827 |
+
}
|
2828 |
+
],
|
2829 |
+
"logging_steps": 10,
|
2830 |
+
"max_steps": 7908,
|
2831 |
+
"num_input_tokens_seen": 0,
|
2832 |
+
"num_train_epochs": 1,
|
2833 |
+
"save_steps": 2000,
|
2834 |
+
"stateful_callbacks": {
|
2835 |
+
"TrainerControl": {
|
2836 |
+
"args": {
|
2837 |
+
"should_epoch_stop": false,
|
2838 |
+
"should_evaluate": false,
|
2839 |
+
"should_log": false,
|
2840 |
+
"should_save": true,
|
2841 |
+
"should_training_stop": false
|
2842 |
+
},
|
2843 |
+
"attributes": {}
|
2844 |
+
}
|
2845 |
+
},
|
2846 |
+
"total_flos": 3.886407329377157e+19,
|
2847 |
+
"train_batch_size": 16,
|
2848 |
+
"trial_name": null,
|
2849 |
+
"trial_params": null
|
2850 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baf7b2e6175729b7490c2f5ceb1ee2a5f200cdee6c5ba9449933732ab08e4f68
|
3 |
+
size 5777
|