Training in progress, step 1640, checkpoint
Browse files- checkpoint-1640/README.md +202 -0
- checkpoint-1640/adapter_config.json +37 -0
- checkpoint-1640/adapter_model.safetensors +3 -0
- checkpoint-1640/optimizer.pt +3 -0
- checkpoint-1640/rng_state.pth +3 -0
- checkpoint-1640/scheduler.pt +3 -0
- checkpoint-1640/special_tokens_map.json +17 -0
- checkpoint-1640/tokenizer.json +3 -0
- checkpoint-1640/tokenizer_config.json +2064 -0
- checkpoint-1640/trainer_state.json +2493 -0
- checkpoint-1640/training_args.bin +3 -0
checkpoint-1640/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Llama-3.1-8B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
checkpoint-1640/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 32,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 16,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"gate_proj",
|
27 |
+
"down_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_proj",
|
30 |
+
"v_proj",
|
31 |
+
"o_proj",
|
32 |
+
"up_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
checkpoint-1640/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c50f58d78a041874a803bde1883dfc9586c84d4ddd679758cfea1e80787b7503
|
3 |
+
size 167832240
|
checkpoint-1640/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5e3d3e4f812f6ba653618a5038c2a925f53e8f74f3358e14be5a49f98db4d7a
|
3 |
+
size 335922386
|
checkpoint-1640/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a86f2590fd69995dde42ed8a93eeabd79d98de8845929841a28078e1b59bf4ac
|
3 |
+
size 14244
|
checkpoint-1640/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c75919a40ab63dcde22be089c0cea02d2f4dcf72be1b8e286810393b8de56ff
|
3 |
+
size 1064
|
checkpoint-1640/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 |
+
}
|
checkpoint-1640/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13574c77ca1d572525cfa7caac46cee99309100524dad568a7ef85ae383df39f
|
3 |
+
size 17210018
|
checkpoint-1640/tokenizer_config.json
ADDED
@@ -0,0 +1,2064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
+
"extra_special_tokens": {},
|
2057 |
+
"model_input_names": [
|
2058 |
+
"input_ids",
|
2059 |
+
"attention_mask"
|
2060 |
+
],
|
2061 |
+
"model_max_length": 131072,
|
2062 |
+
"pad_token": "<|eot_id|>",
|
2063 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2064 |
+
}
|
checkpoint-1640/trainer_state.json
ADDED
@@ -0,0 +1,2493 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.7281348788198103,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 1640,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01053740779768177,
|
13 |
+
"grad_norm": 3.3616116046905518,
|
14 |
+
"learning_rate": 4.982437653670531e-05,
|
15 |
+
"loss": 1.7881,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01053740779768177,
|
20 |
+
"eval_loss": 0.6833231449127197,
|
21 |
+
"eval_runtime": 13.3064,
|
22 |
+
"eval_samples_per_second": 36.073,
|
23 |
+
"eval_steps_per_second": 2.255,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.02107481559536354,
|
28 |
+
"grad_norm": 1.3658663034439087,
|
29 |
+
"learning_rate": 4.964875307341061e-05,
|
30 |
+
"loss": 0.5571,
|
31 |
+
"step": 20
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.02107481559536354,
|
35 |
+
"eval_loss": 0.5293903350830078,
|
36 |
+
"eval_runtime": 13.4286,
|
37 |
+
"eval_samples_per_second": 35.745,
|
38 |
+
"eval_steps_per_second": 2.234,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.03161222339304531,
|
43 |
+
"grad_norm": 1.0748717784881592,
|
44 |
+
"learning_rate": 4.947312961011591e-05,
|
45 |
+
"loss": 0.4482,
|
46 |
+
"step": 30
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.03161222339304531,
|
50 |
+
"eval_loss": 0.47912800312042236,
|
51 |
+
"eval_runtime": 13.4918,
|
52 |
+
"eval_samples_per_second": 35.577,
|
53 |
+
"eval_steps_per_second": 2.224,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.04214963119072708,
|
58 |
+
"grad_norm": 0.890529215335846,
|
59 |
+
"learning_rate": 4.929750614682122e-05,
|
60 |
+
"loss": 0.3722,
|
61 |
+
"step": 40
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.04214963119072708,
|
65 |
+
"eval_loss": 0.44374603033065796,
|
66 |
+
"eval_runtime": 13.5807,
|
67 |
+
"eval_samples_per_second": 35.344,
|
68 |
+
"eval_steps_per_second": 2.209,
|
69 |
+
"step": 40
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.05268703898840885,
|
73 |
+
"grad_norm": 0.8233364224433899,
|
74 |
+
"learning_rate": 4.9121882683526524e-05,
|
75 |
+
"loss": 0.3534,
|
76 |
+
"step": 50
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.05268703898840885,
|
80 |
+
"eval_loss": 0.4318523108959198,
|
81 |
+
"eval_runtime": 13.6096,
|
82 |
+
"eval_samples_per_second": 35.269,
|
83 |
+
"eval_steps_per_second": 2.204,
|
84 |
+
"step": 50
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.06322444678609063,
|
88 |
+
"grad_norm": 0.7144497036933899,
|
89 |
+
"learning_rate": 4.894625922023183e-05,
|
90 |
+
"loss": 0.3512,
|
91 |
+
"step": 60
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.06322444678609063,
|
95 |
+
"eval_loss": 0.41558387875556946,
|
96 |
+
"eval_runtime": 13.6488,
|
97 |
+
"eval_samples_per_second": 35.168,
|
98 |
+
"eval_steps_per_second": 2.198,
|
99 |
+
"step": 60
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.0737618545837724,
|
103 |
+
"grad_norm": 0.6796255707740784,
|
104 |
+
"learning_rate": 4.877063575693713e-05,
|
105 |
+
"loss": 0.3588,
|
106 |
+
"step": 70
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.0737618545837724,
|
110 |
+
"eval_loss": 0.4085235297679901,
|
111 |
+
"eval_runtime": 13.6512,
|
112 |
+
"eval_samples_per_second": 35.162,
|
113 |
+
"eval_steps_per_second": 2.198,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.08429926238145416,
|
118 |
+
"grad_norm": 0.6846384406089783,
|
119 |
+
"learning_rate": 4.8595012293642434e-05,
|
120 |
+
"loss": 0.3504,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.08429926238145416,
|
125 |
+
"eval_loss": 0.3993188142776489,
|
126 |
+
"eval_runtime": 13.6377,
|
127 |
+
"eval_samples_per_second": 35.197,
|
128 |
+
"eval_steps_per_second": 2.2,
|
129 |
+
"step": 80
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.09483667017913593,
|
133 |
+
"grad_norm": 0.7391332983970642,
|
134 |
+
"learning_rate": 4.841938883034774e-05,
|
135 |
+
"loss": 0.3299,
|
136 |
+
"step": 90
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.09483667017913593,
|
140 |
+
"eval_loss": 0.3922707140445709,
|
141 |
+
"eval_runtime": 13.6059,
|
142 |
+
"eval_samples_per_second": 35.279,
|
143 |
+
"eval_steps_per_second": 2.205,
|
144 |
+
"step": 90
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.1053740779768177,
|
148 |
+
"grad_norm": 0.6717132925987244,
|
149 |
+
"learning_rate": 4.824376536705304e-05,
|
150 |
+
"loss": 0.3358,
|
151 |
+
"step": 100
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.1053740779768177,
|
155 |
+
"eval_loss": 0.390600323677063,
|
156 |
+
"eval_runtime": 13.6022,
|
157 |
+
"eval_samples_per_second": 35.288,
|
158 |
+
"eval_steps_per_second": 2.206,
|
159 |
+
"step": 100
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.11591148577449947,
|
163 |
+
"grad_norm": 0.6522348523139954,
|
164 |
+
"learning_rate": 4.8068141903758344e-05,
|
165 |
+
"loss": 0.311,
|
166 |
+
"step": 110
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.11591148577449947,
|
170 |
+
"eval_loss": 0.3844388425350189,
|
171 |
+
"eval_runtime": 13.5921,
|
172 |
+
"eval_samples_per_second": 35.315,
|
173 |
+
"eval_steps_per_second": 2.207,
|
174 |
+
"step": 110
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.12644889357218125,
|
178 |
+
"grad_norm": 0.5558998584747314,
|
179 |
+
"learning_rate": 4.789251844046364e-05,
|
180 |
+
"loss": 0.3161,
|
181 |
+
"step": 120
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.12644889357218125,
|
185 |
+
"eval_loss": 0.3852270245552063,
|
186 |
+
"eval_runtime": 13.5961,
|
187 |
+
"eval_samples_per_second": 35.304,
|
188 |
+
"eval_steps_per_second": 2.207,
|
189 |
+
"step": 120
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.136986301369863,
|
193 |
+
"grad_norm": 0.639998197555542,
|
194 |
+
"learning_rate": 4.7716894977168955e-05,
|
195 |
+
"loss": 0.3037,
|
196 |
+
"step": 130
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.136986301369863,
|
200 |
+
"eval_loss": 0.3841981887817383,
|
201 |
+
"eval_runtime": 13.6057,
|
202 |
+
"eval_samples_per_second": 35.279,
|
203 |
+
"eval_steps_per_second": 2.205,
|
204 |
+
"step": 130
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.1475237091675448,
|
208 |
+
"grad_norm": 0.583459198474884,
|
209 |
+
"learning_rate": 4.754127151387426e-05,
|
210 |
+
"loss": 0.3232,
|
211 |
+
"step": 140
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 0.1475237091675448,
|
215 |
+
"eval_loss": 0.3742731213569641,
|
216 |
+
"eval_runtime": 13.5955,
|
217 |
+
"eval_samples_per_second": 35.306,
|
218 |
+
"eval_steps_per_second": 2.207,
|
219 |
+
"step": 140
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.15806111696522657,
|
223 |
+
"grad_norm": 0.5834677219390869,
|
224 |
+
"learning_rate": 4.736564805057956e-05,
|
225 |
+
"loss": 0.317,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.15806111696522657,
|
230 |
+
"eval_loss": 0.3765258193016052,
|
231 |
+
"eval_runtime": 13.5995,
|
232 |
+
"eval_samples_per_second": 35.295,
|
233 |
+
"eval_steps_per_second": 2.206,
|
234 |
+
"step": 150
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.16859852476290832,
|
238 |
+
"grad_norm": 0.5975239872932434,
|
239 |
+
"learning_rate": 4.7190024587284866e-05,
|
240 |
+
"loss": 0.2987,
|
241 |
+
"step": 160
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.16859852476290832,
|
245 |
+
"eval_loss": 0.37060925364494324,
|
246 |
+
"eval_runtime": 13.5971,
|
247 |
+
"eval_samples_per_second": 35.302,
|
248 |
+
"eval_steps_per_second": 2.206,
|
249 |
+
"step": 160
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.1791359325605901,
|
253 |
+
"grad_norm": 0.6860706806182861,
|
254 |
+
"learning_rate": 4.7014401123990165e-05,
|
255 |
+
"loss": 0.3166,
|
256 |
+
"step": 170
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.1791359325605901,
|
260 |
+
"eval_loss": 0.37034350633621216,
|
261 |
+
"eval_runtime": 13.5923,
|
262 |
+
"eval_samples_per_second": 35.314,
|
263 |
+
"eval_steps_per_second": 2.207,
|
264 |
+
"step": 170
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.18967334035827185,
|
268 |
+
"grad_norm": 0.7161134481430054,
|
269 |
+
"learning_rate": 4.683877766069547e-05,
|
270 |
+
"loss": 0.3036,
|
271 |
+
"step": 180
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.18967334035827185,
|
275 |
+
"eval_loss": 0.3633898198604584,
|
276 |
+
"eval_runtime": 13.6104,
|
277 |
+
"eval_samples_per_second": 35.267,
|
278 |
+
"eval_steps_per_second": 2.204,
|
279 |
+
"step": 180
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.20021074815595363,
|
283 |
+
"grad_norm": 0.8212491273880005,
|
284 |
+
"learning_rate": 4.6663154197400776e-05,
|
285 |
+
"loss": 0.3023,
|
286 |
+
"step": 190
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.20021074815595363,
|
290 |
+
"eval_loss": 0.36356136202812195,
|
291 |
+
"eval_runtime": 13.5967,
|
292 |
+
"eval_samples_per_second": 35.303,
|
293 |
+
"eval_steps_per_second": 2.206,
|
294 |
+
"step": 190
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.2107481559536354,
|
298 |
+
"grad_norm": 0.5965659022331238,
|
299 |
+
"learning_rate": 4.6487530734106075e-05,
|
300 |
+
"loss": 0.2999,
|
301 |
+
"step": 200
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.2107481559536354,
|
305 |
+
"eval_loss": 0.3622604310512543,
|
306 |
+
"eval_runtime": 13.5997,
|
307 |
+
"eval_samples_per_second": 35.295,
|
308 |
+
"eval_steps_per_second": 2.206,
|
309 |
+
"step": 200
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.22128556375131717,
|
313 |
+
"grad_norm": 0.6638055443763733,
|
314 |
+
"learning_rate": 4.631190727081138e-05,
|
315 |
+
"loss": 0.2924,
|
316 |
+
"step": 210
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.22128556375131717,
|
320 |
+
"eval_loss": 0.36028483510017395,
|
321 |
+
"eval_runtime": 13.6089,
|
322 |
+
"eval_samples_per_second": 35.271,
|
323 |
+
"eval_steps_per_second": 2.204,
|
324 |
+
"step": 210
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.23182297154899895,
|
328 |
+
"grad_norm": 0.4681139886379242,
|
329 |
+
"learning_rate": 4.6136283807516686e-05,
|
330 |
+
"loss": 0.3012,
|
331 |
+
"step": 220
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.23182297154899895,
|
335 |
+
"eval_loss": 0.3585042357444763,
|
336 |
+
"eval_runtime": 13.6099,
|
337 |
+
"eval_samples_per_second": 35.269,
|
338 |
+
"eval_steps_per_second": 2.204,
|
339 |
+
"step": 220
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.24236037934668073,
|
343 |
+
"grad_norm": 0.6495727300643921,
|
344 |
+
"learning_rate": 4.596066034422199e-05,
|
345 |
+
"loss": 0.2884,
|
346 |
+
"step": 230
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.24236037934668073,
|
350 |
+
"eval_loss": 0.36549657583236694,
|
351 |
+
"eval_runtime": 13.6085,
|
352 |
+
"eval_samples_per_second": 35.272,
|
353 |
+
"eval_steps_per_second": 2.205,
|
354 |
+
"step": 230
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.2528977871443625,
|
358 |
+
"grad_norm": 0.4928750991821289,
|
359 |
+
"learning_rate": 4.57850368809273e-05,
|
360 |
+
"loss": 0.2838,
|
361 |
+
"step": 240
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.2528977871443625,
|
365 |
+
"eval_loss": 0.35502439737319946,
|
366 |
+
"eval_runtime": 13.6002,
|
367 |
+
"eval_samples_per_second": 35.293,
|
368 |
+
"eval_steps_per_second": 2.206,
|
369 |
+
"step": 240
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.26343519494204426,
|
373 |
+
"grad_norm": 0.6839736700057983,
|
374 |
+
"learning_rate": 4.5609413417632596e-05,
|
375 |
+
"loss": 0.2861,
|
376 |
+
"step": 250
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.26343519494204426,
|
380 |
+
"eval_loss": 0.3560730516910553,
|
381 |
+
"eval_runtime": 13.6056,
|
382 |
+
"eval_samples_per_second": 35.28,
|
383 |
+
"eval_steps_per_second": 2.205,
|
384 |
+
"step": 250
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.273972602739726,
|
388 |
+
"grad_norm": 0.5583881735801697,
|
389 |
+
"learning_rate": 4.54337899543379e-05,
|
390 |
+
"loss": 0.3019,
|
391 |
+
"step": 260
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.273972602739726,
|
395 |
+
"eval_loss": 0.3566754162311554,
|
396 |
+
"eval_runtime": 13.5986,
|
397 |
+
"eval_samples_per_second": 35.298,
|
398 |
+
"eval_steps_per_second": 2.206,
|
399 |
+
"step": 260
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.2845100105374078,
|
403 |
+
"grad_norm": 0.5884770750999451,
|
404 |
+
"learning_rate": 4.525816649104321e-05,
|
405 |
+
"loss": 0.3112,
|
406 |
+
"step": 270
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 0.2845100105374078,
|
410 |
+
"eval_loss": 0.3552027940750122,
|
411 |
+
"eval_runtime": 13.6456,
|
412 |
+
"eval_samples_per_second": 35.176,
|
413 |
+
"eval_steps_per_second": 2.199,
|
414 |
+
"step": 270
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.2950474183350896,
|
418 |
+
"grad_norm": 0.540367603302002,
|
419 |
+
"learning_rate": 4.5082543027748506e-05,
|
420 |
+
"loss": 0.2805,
|
421 |
+
"step": 280
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.2950474183350896,
|
425 |
+
"eval_loss": 0.3551066815853119,
|
426 |
+
"eval_runtime": 13.59,
|
427 |
+
"eval_samples_per_second": 35.32,
|
428 |
+
"eval_steps_per_second": 2.208,
|
429 |
+
"step": 280
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.3055848261327713,
|
433 |
+
"grad_norm": 0.4952965974807739,
|
434 |
+
"learning_rate": 4.490691956445381e-05,
|
435 |
+
"loss": 0.318,
|
436 |
+
"step": 290
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.3055848261327713,
|
440 |
+
"eval_loss": 0.35322481393814087,
|
441 |
+
"eval_runtime": 13.5781,
|
442 |
+
"eval_samples_per_second": 35.351,
|
443 |
+
"eval_steps_per_second": 2.209,
|
444 |
+
"step": 290
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.31612223393045313,
|
448 |
+
"grad_norm": 0.48861801624298096,
|
449 |
+
"learning_rate": 4.473129610115912e-05,
|
450 |
+
"loss": 0.2878,
|
451 |
+
"step": 300
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.31612223393045313,
|
455 |
+
"eval_loss": 0.3530054986476898,
|
456 |
+
"eval_runtime": 13.5721,
|
457 |
+
"eval_samples_per_second": 35.367,
|
458 |
+
"eval_steps_per_second": 2.21,
|
459 |
+
"step": 300
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.3266596417281349,
|
463 |
+
"grad_norm": 0.523873507976532,
|
464 |
+
"learning_rate": 4.455567263786442e-05,
|
465 |
+
"loss": 0.3084,
|
466 |
+
"step": 310
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.3266596417281349,
|
470 |
+
"eval_loss": 0.35032400488853455,
|
471 |
+
"eval_runtime": 13.5686,
|
472 |
+
"eval_samples_per_second": 35.376,
|
473 |
+
"eval_steps_per_second": 2.211,
|
474 |
+
"step": 310
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.33719704952581664,
|
478 |
+
"grad_norm": 0.6253566741943359,
|
479 |
+
"learning_rate": 4.438004917456973e-05,
|
480 |
+
"loss": 0.2947,
|
481 |
+
"step": 320
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.33719704952581664,
|
485 |
+
"eval_loss": 0.3499966263771057,
|
486 |
+
"eval_runtime": 13.5767,
|
487 |
+
"eval_samples_per_second": 35.355,
|
488 |
+
"eval_steps_per_second": 2.21,
|
489 |
+
"step": 320
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.34773445732349845,
|
493 |
+
"grad_norm": 0.5352979898452759,
|
494 |
+
"learning_rate": 4.420442571127503e-05,
|
495 |
+
"loss": 0.2884,
|
496 |
+
"step": 330
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.34773445732349845,
|
500 |
+
"eval_loss": 0.34622183442115784,
|
501 |
+
"eval_runtime": 13.5616,
|
502 |
+
"eval_samples_per_second": 35.394,
|
503 |
+
"eval_steps_per_second": 2.212,
|
504 |
+
"step": 330
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.3582718651211802,
|
508 |
+
"grad_norm": 0.4931572675704956,
|
509 |
+
"learning_rate": 4.4028802247980333e-05,
|
510 |
+
"loss": 0.3085,
|
511 |
+
"step": 340
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 0.3582718651211802,
|
515 |
+
"eval_loss": 0.3468419909477234,
|
516 |
+
"eval_runtime": 13.5639,
|
517 |
+
"eval_samples_per_second": 35.388,
|
518 |
+
"eval_steps_per_second": 2.212,
|
519 |
+
"step": 340
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.36880927291886195,
|
523 |
+
"grad_norm": 0.5033659934997559,
|
524 |
+
"learning_rate": 4.385317878468563e-05,
|
525 |
+
"loss": 0.3084,
|
526 |
+
"step": 350
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.36880927291886195,
|
530 |
+
"eval_loss": 0.34584841132164,
|
531 |
+
"eval_runtime": 13.5544,
|
532 |
+
"eval_samples_per_second": 35.413,
|
533 |
+
"eval_steps_per_second": 2.213,
|
534 |
+
"step": 350
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.3793466807165437,
|
538 |
+
"grad_norm": 0.5806519389152527,
|
539 |
+
"learning_rate": 4.367755532139094e-05,
|
540 |
+
"loss": 0.2761,
|
541 |
+
"step": 360
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.3793466807165437,
|
545 |
+
"eval_loss": 0.34370240569114685,
|
546 |
+
"eval_runtime": 13.5617,
|
547 |
+
"eval_samples_per_second": 35.394,
|
548 |
+
"eval_steps_per_second": 2.212,
|
549 |
+
"step": 360
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.3898840885142255,
|
553 |
+
"grad_norm": 0.6204981803894043,
|
554 |
+
"learning_rate": 4.3501931858096244e-05,
|
555 |
+
"loss": 0.3024,
|
556 |
+
"step": 370
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.3898840885142255,
|
560 |
+
"eval_loss": 0.3421412408351898,
|
561 |
+
"eval_runtime": 13.5312,
|
562 |
+
"eval_samples_per_second": 35.474,
|
563 |
+
"eval_steps_per_second": 2.217,
|
564 |
+
"step": 370
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.40042149631190727,
|
568 |
+
"grad_norm": 0.48026618361473083,
|
569 |
+
"learning_rate": 4.332630839480154e-05,
|
570 |
+
"loss": 0.2788,
|
571 |
+
"step": 380
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.40042149631190727,
|
575 |
+
"eval_loss": 0.3414471745491028,
|
576 |
+
"eval_runtime": 13.5435,
|
577 |
+
"eval_samples_per_second": 35.441,
|
578 |
+
"eval_steps_per_second": 2.215,
|
579 |
+
"step": 380
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.410958904109589,
|
583 |
+
"grad_norm": 0.48742201924324036,
|
584 |
+
"learning_rate": 4.3150684931506855e-05,
|
585 |
+
"loss": 0.2708,
|
586 |
+
"step": 390
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.410958904109589,
|
590 |
+
"eval_loss": 0.3414710462093353,
|
591 |
+
"eval_runtime": 13.5593,
|
592 |
+
"eval_samples_per_second": 35.4,
|
593 |
+
"eval_steps_per_second": 2.213,
|
594 |
+
"step": 390
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.4214963119072708,
|
598 |
+
"grad_norm": 0.5737293362617493,
|
599 |
+
"learning_rate": 4.297506146821216e-05,
|
600 |
+
"loss": 0.2735,
|
601 |
+
"step": 400
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.4214963119072708,
|
605 |
+
"eval_loss": 0.34133002161979675,
|
606 |
+
"eval_runtime": 13.5644,
|
607 |
+
"eval_samples_per_second": 35.387,
|
608 |
+
"eval_steps_per_second": 2.212,
|
609 |
+
"step": 400
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.4320337197049526,
|
613 |
+
"grad_norm": 0.5055080652236938,
|
614 |
+
"learning_rate": 4.279943800491746e-05,
|
615 |
+
"loss": 0.2846,
|
616 |
+
"step": 410
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 0.4320337197049526,
|
620 |
+
"eval_loss": 0.3391459584236145,
|
621 |
+
"eval_runtime": 13.5574,
|
622 |
+
"eval_samples_per_second": 35.405,
|
623 |
+
"eval_steps_per_second": 2.213,
|
624 |
+
"step": 410
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.44257112750263433,
|
628 |
+
"grad_norm": 0.5293213129043579,
|
629 |
+
"learning_rate": 4.2623814541622765e-05,
|
630 |
+
"loss": 0.2757,
|
631 |
+
"step": 420
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 0.44257112750263433,
|
635 |
+
"eval_loss": 0.3393440246582031,
|
636 |
+
"eval_runtime": 13.5643,
|
637 |
+
"eval_samples_per_second": 35.387,
|
638 |
+
"eval_steps_per_second": 2.212,
|
639 |
+
"step": 420
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.45310853530031614,
|
643 |
+
"grad_norm": 0.6627737283706665,
|
644 |
+
"learning_rate": 4.2448191078328064e-05,
|
645 |
+
"loss": 0.2829,
|
646 |
+
"step": 430
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.45310853530031614,
|
650 |
+
"eval_loss": 0.34091198444366455,
|
651 |
+
"eval_runtime": 13.5863,
|
652 |
+
"eval_samples_per_second": 35.33,
|
653 |
+
"eval_steps_per_second": 2.208,
|
654 |
+
"step": 430
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.4636459430979979,
|
658 |
+
"grad_norm": 0.5125611424446106,
|
659 |
+
"learning_rate": 4.227256761503337e-05,
|
660 |
+
"loss": 0.2632,
|
661 |
+
"step": 440
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.4636459430979979,
|
665 |
+
"eval_loss": 0.3409743010997772,
|
666 |
+
"eval_runtime": 13.572,
|
667 |
+
"eval_samples_per_second": 35.367,
|
668 |
+
"eval_steps_per_second": 2.21,
|
669 |
+
"step": 440
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.47418335089567965,
|
673 |
+
"grad_norm": 0.613191545009613,
|
674 |
+
"learning_rate": 4.2096944151738675e-05,
|
675 |
+
"loss": 0.2709,
|
676 |
+
"step": 450
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.47418335089567965,
|
680 |
+
"eval_loss": 0.3384413421154022,
|
681 |
+
"eval_runtime": 13.5818,
|
682 |
+
"eval_samples_per_second": 35.341,
|
683 |
+
"eval_steps_per_second": 2.209,
|
684 |
+
"step": 450
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.48472075869336145,
|
688 |
+
"grad_norm": 0.4908188581466675,
|
689 |
+
"learning_rate": 4.1921320688443974e-05,
|
690 |
+
"loss": 0.2609,
|
691 |
+
"step": 460
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.48472075869336145,
|
695 |
+
"eval_loss": 0.33855584263801575,
|
696 |
+
"eval_runtime": 13.5848,
|
697 |
+
"eval_samples_per_second": 35.334,
|
698 |
+
"eval_steps_per_second": 2.208,
|
699 |
+
"step": 460
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.4952581664910432,
|
703 |
+
"grad_norm": 0.5873326659202576,
|
704 |
+
"learning_rate": 4.174569722514928e-05,
|
705 |
+
"loss": 0.2709,
|
706 |
+
"step": 470
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.4952581664910432,
|
710 |
+
"eval_loss": 0.3383730947971344,
|
711 |
+
"eval_runtime": 13.591,
|
712 |
+
"eval_samples_per_second": 35.317,
|
713 |
+
"eval_steps_per_second": 2.207,
|
714 |
+
"step": 470
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.505795574288725,
|
718 |
+
"grad_norm": 0.5365350246429443,
|
719 |
+
"learning_rate": 4.1570073761854585e-05,
|
720 |
+
"loss": 0.2848,
|
721 |
+
"step": 480
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.505795574288725,
|
725 |
+
"eval_loss": 0.3378843367099762,
|
726 |
+
"eval_runtime": 13.5963,
|
727 |
+
"eval_samples_per_second": 35.304,
|
728 |
+
"eval_steps_per_second": 2.206,
|
729 |
+
"step": 480
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.5163329820864068,
|
733 |
+
"grad_norm": 0.5642485022544861,
|
734 |
+
"learning_rate": 4.139445029855989e-05,
|
735 |
+
"loss": 0.2911,
|
736 |
+
"step": 490
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 0.5163329820864068,
|
740 |
+
"eval_loss": 0.3355303406715393,
|
741 |
+
"eval_runtime": 13.6025,
|
742 |
+
"eval_samples_per_second": 35.288,
|
743 |
+
"eval_steps_per_second": 2.205,
|
744 |
+
"step": 490
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.5268703898840885,
|
748 |
+
"grad_norm": 0.6058154702186584,
|
749 |
+
"learning_rate": 4.12188268352652e-05,
|
750 |
+
"loss": 0.262,
|
751 |
+
"step": 500
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.5268703898840885,
|
755 |
+
"eval_loss": 0.3364686667919159,
|
756 |
+
"eval_runtime": 13.6033,
|
757 |
+
"eval_samples_per_second": 35.286,
|
758 |
+
"eval_steps_per_second": 2.205,
|
759 |
+
"step": 500
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.5374077976817703,
|
763 |
+
"grad_norm": 0.666671633720398,
|
764 |
+
"learning_rate": 4.1043203371970496e-05,
|
765 |
+
"loss": 0.2797,
|
766 |
+
"step": 510
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.5374077976817703,
|
770 |
+
"eval_loss": 0.33817631006240845,
|
771 |
+
"eval_runtime": 13.6129,
|
772 |
+
"eval_samples_per_second": 35.261,
|
773 |
+
"eval_steps_per_second": 2.204,
|
774 |
+
"step": 510
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.547945205479452,
|
778 |
+
"grad_norm": 0.5990138053894043,
|
779 |
+
"learning_rate": 4.08675799086758e-05,
|
780 |
+
"loss": 0.2606,
|
781 |
+
"step": 520
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.547945205479452,
|
785 |
+
"eval_loss": 0.3355501890182495,
|
786 |
+
"eval_runtime": 13.6034,
|
787 |
+
"eval_samples_per_second": 35.285,
|
788 |
+
"eval_steps_per_second": 2.205,
|
789 |
+
"step": 520
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.5584826132771338,
|
793 |
+
"grad_norm": 0.5905662775039673,
|
794 |
+
"learning_rate": 4.069195644538111e-05,
|
795 |
+
"loss": 0.2687,
|
796 |
+
"step": 530
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 0.5584826132771338,
|
800 |
+
"eval_loss": 0.3357114791870117,
|
801 |
+
"eval_runtime": 13.5907,
|
802 |
+
"eval_samples_per_second": 35.318,
|
803 |
+
"eval_steps_per_second": 2.207,
|
804 |
+
"step": 530
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.5690200210748156,
|
808 |
+
"grad_norm": 0.6308056116104126,
|
809 |
+
"learning_rate": 4.0516332982086406e-05,
|
810 |
+
"loss": 0.2964,
|
811 |
+
"step": 540
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.5690200210748156,
|
815 |
+
"eval_loss": 0.3342372477054596,
|
816 |
+
"eval_runtime": 13.5897,
|
817 |
+
"eval_samples_per_second": 35.321,
|
818 |
+
"eval_steps_per_second": 2.208,
|
819 |
+
"step": 540
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.5795574288724974,
|
823 |
+
"grad_norm": 0.5483158230781555,
|
824 |
+
"learning_rate": 4.034070951879171e-05,
|
825 |
+
"loss": 0.262,
|
826 |
+
"step": 550
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 0.5795574288724974,
|
830 |
+
"eval_loss": 0.33271318674087524,
|
831 |
+
"eval_runtime": 13.5802,
|
832 |
+
"eval_samples_per_second": 35.346,
|
833 |
+
"eval_steps_per_second": 2.209,
|
834 |
+
"step": 550
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.5900948366701791,
|
838 |
+
"grad_norm": 0.5433160662651062,
|
839 |
+
"learning_rate": 4.016508605549702e-05,
|
840 |
+
"loss": 0.2575,
|
841 |
+
"step": 560
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.5900948366701791,
|
845 |
+
"eval_loss": 0.3352707326412201,
|
846 |
+
"eval_runtime": 13.5772,
|
847 |
+
"eval_samples_per_second": 35.353,
|
848 |
+
"eval_steps_per_second": 2.21,
|
849 |
+
"step": 560
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.6006322444678609,
|
853 |
+
"grad_norm": 0.7090951800346375,
|
854 |
+
"learning_rate": 3.998946259220232e-05,
|
855 |
+
"loss": 0.2624,
|
856 |
+
"step": 570
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.6006322444678609,
|
860 |
+
"eval_loss": 0.33547133207321167,
|
861 |
+
"eval_runtime": 13.5717,
|
862 |
+
"eval_samples_per_second": 35.368,
|
863 |
+
"eval_steps_per_second": 2.21,
|
864 |
+
"step": 570
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.6111696522655427,
|
868 |
+
"grad_norm": 0.7720335721969604,
|
869 |
+
"learning_rate": 3.981383912890763e-05,
|
870 |
+
"loss": 0.2628,
|
871 |
+
"step": 580
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.6111696522655427,
|
875 |
+
"eval_loss": 0.3337227702140808,
|
876 |
+
"eval_runtime": 13.5578,
|
877 |
+
"eval_samples_per_second": 35.404,
|
878 |
+
"eval_steps_per_second": 2.213,
|
879 |
+
"step": 580
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.6217070600632244,
|
883 |
+
"grad_norm": 0.5641891360282898,
|
884 |
+
"learning_rate": 3.963821566561293e-05,
|
885 |
+
"loss": 0.2617,
|
886 |
+
"step": 590
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.6217070600632244,
|
890 |
+
"eval_loss": 0.3328714668750763,
|
891 |
+
"eval_runtime": 13.5205,
|
892 |
+
"eval_samples_per_second": 35.502,
|
893 |
+
"eval_steps_per_second": 2.219,
|
894 |
+
"step": 590
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.6322444678609063,
|
898 |
+
"grad_norm": 0.5985394716262817,
|
899 |
+
"learning_rate": 3.946259220231823e-05,
|
900 |
+
"loss": 0.2543,
|
901 |
+
"step": 600
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 0.6322444678609063,
|
905 |
+
"eval_loss": 0.3321264386177063,
|
906 |
+
"eval_runtime": 13.5572,
|
907 |
+
"eval_samples_per_second": 35.406,
|
908 |
+
"eval_steps_per_second": 2.213,
|
909 |
+
"step": 600
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.642781875658588,
|
913 |
+
"grad_norm": 0.6638147234916687,
|
914 |
+
"learning_rate": 3.928696873902353e-05,
|
915 |
+
"loss": 0.2772,
|
916 |
+
"step": 610
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.642781875658588,
|
920 |
+
"eval_loss": 0.33292463421821594,
|
921 |
+
"eval_runtime": 13.5485,
|
922 |
+
"eval_samples_per_second": 35.428,
|
923 |
+
"eval_steps_per_second": 2.214,
|
924 |
+
"step": 610
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.6533192834562698,
|
928 |
+
"grad_norm": 0.6401410102844238,
|
929 |
+
"learning_rate": 3.911134527572884e-05,
|
930 |
+
"loss": 0.2725,
|
931 |
+
"step": 620
|
932 |
+
},
|
933 |
+
{
|
934 |
+
"epoch": 0.6533192834562698,
|
935 |
+
"eval_loss": 0.3313460648059845,
|
936 |
+
"eval_runtime": 13.5546,
|
937 |
+
"eval_samples_per_second": 35.412,
|
938 |
+
"eval_steps_per_second": 2.213,
|
939 |
+
"step": 620
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.6638566912539515,
|
943 |
+
"grad_norm": 0.5968373417854309,
|
944 |
+
"learning_rate": 3.893572181243414e-05,
|
945 |
+
"loss": 0.2626,
|
946 |
+
"step": 630
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.6638566912539515,
|
950 |
+
"eval_loss": 0.3308354616165161,
|
951 |
+
"eval_runtime": 13.5566,
|
952 |
+
"eval_samples_per_second": 35.407,
|
953 |
+
"eval_steps_per_second": 2.213,
|
954 |
+
"step": 630
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.6743940990516333,
|
958 |
+
"grad_norm": 0.4671958088874817,
|
959 |
+
"learning_rate": 3.876009834913945e-05,
|
960 |
+
"loss": 0.2667,
|
961 |
+
"step": 640
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.6743940990516333,
|
965 |
+
"eval_loss": 0.33001866936683655,
|
966 |
+
"eval_runtime": 13.5739,
|
967 |
+
"eval_samples_per_second": 35.362,
|
968 |
+
"eval_steps_per_second": 2.21,
|
969 |
+
"step": 640
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.684931506849315,
|
973 |
+
"grad_norm": 0.5390825867652893,
|
974 |
+
"learning_rate": 3.8584474885844754e-05,
|
975 |
+
"loss": 0.2599,
|
976 |
+
"step": 650
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.684931506849315,
|
980 |
+
"eval_loss": 0.3301464915275574,
|
981 |
+
"eval_runtime": 13.5678,
|
982 |
+
"eval_samples_per_second": 35.378,
|
983 |
+
"eval_steps_per_second": 2.211,
|
984 |
+
"step": 650
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.6954689146469969,
|
988 |
+
"grad_norm": 0.5784376263618469,
|
989 |
+
"learning_rate": 3.840885142255005e-05,
|
990 |
+
"loss": 0.2452,
|
991 |
+
"step": 660
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 0.6954689146469969,
|
995 |
+
"eval_loss": 0.33094659447669983,
|
996 |
+
"eval_runtime": 13.5767,
|
997 |
+
"eval_samples_per_second": 35.355,
|
998 |
+
"eval_steps_per_second": 2.21,
|
999 |
+
"step": 660
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.7060063224446786,
|
1003 |
+
"grad_norm": 0.5976417660713196,
|
1004 |
+
"learning_rate": 3.823322795925536e-05,
|
1005 |
+
"loss": 0.2688,
|
1006 |
+
"step": 670
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 0.7060063224446786,
|
1010 |
+
"eval_loss": 0.3312263488769531,
|
1011 |
+
"eval_runtime": 13.5986,
|
1012 |
+
"eval_samples_per_second": 35.298,
|
1013 |
+
"eval_steps_per_second": 2.206,
|
1014 |
+
"step": 670
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.7165437302423604,
|
1018 |
+
"grad_norm": 0.5902723073959351,
|
1019 |
+
"learning_rate": 3.8057604495960664e-05,
|
1020 |
+
"loss": 0.2596,
|
1021 |
+
"step": 680
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 0.7165437302423604,
|
1025 |
+
"eval_loss": 0.32888591289520264,
|
1026 |
+
"eval_runtime": 13.597,
|
1027 |
+
"eval_samples_per_second": 35.302,
|
1028 |
+
"eval_steps_per_second": 2.206,
|
1029 |
+
"step": 680
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.7270811380400422,
|
1033 |
+
"grad_norm": 0.6102134585380554,
|
1034 |
+
"learning_rate": 3.788198103266596e-05,
|
1035 |
+
"loss": 0.2623,
|
1036 |
+
"step": 690
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 0.7270811380400422,
|
1040 |
+
"eval_loss": 0.3287771940231323,
|
1041 |
+
"eval_runtime": 13.6069,
|
1042 |
+
"eval_samples_per_second": 35.276,
|
1043 |
+
"eval_steps_per_second": 2.205,
|
1044 |
+
"step": 690
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.7376185458377239,
|
1048 |
+
"grad_norm": 0.5212683081626892,
|
1049 |
+
"learning_rate": 3.770635756937127e-05,
|
1050 |
+
"loss": 0.2497,
|
1051 |
+
"step": 700
|
1052 |
+
},
|
1053 |
+
{
|
1054 |
+
"epoch": 0.7376185458377239,
|
1055 |
+
"eval_loss": 0.330812007188797,
|
1056 |
+
"eval_runtime": 13.6008,
|
1057 |
+
"eval_samples_per_second": 35.292,
|
1058 |
+
"eval_steps_per_second": 2.206,
|
1059 |
+
"step": 700
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.7481559536354057,
|
1063 |
+
"grad_norm": 0.614651620388031,
|
1064 |
+
"learning_rate": 3.7530734106076575e-05,
|
1065 |
+
"loss": 0.2568,
|
1066 |
+
"step": 710
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.7481559536354057,
|
1070 |
+
"eval_loss": 0.3295523524284363,
|
1071 |
+
"eval_runtime": 13.6076,
|
1072 |
+
"eval_samples_per_second": 35.274,
|
1073 |
+
"eval_steps_per_second": 2.205,
|
1074 |
+
"step": 710
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.7586933614330874,
|
1078 |
+
"grad_norm": 0.4703381061553955,
|
1079 |
+
"learning_rate": 3.7355110642781874e-05,
|
1080 |
+
"loss": 0.2325,
|
1081 |
+
"step": 720
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.7586933614330874,
|
1085 |
+
"eval_loss": 0.32799476385116577,
|
1086 |
+
"eval_runtime": 13.6031,
|
1087 |
+
"eval_samples_per_second": 35.286,
|
1088 |
+
"eval_steps_per_second": 2.205,
|
1089 |
+
"step": 720
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.7692307692307693,
|
1093 |
+
"grad_norm": 0.5316283702850342,
|
1094 |
+
"learning_rate": 3.717948717948718e-05,
|
1095 |
+
"loss": 0.2427,
|
1096 |
+
"step": 730
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.7692307692307693,
|
1100 |
+
"eval_loss": 0.32939499616622925,
|
1101 |
+
"eval_runtime": 13.602,
|
1102 |
+
"eval_samples_per_second": 35.289,
|
1103 |
+
"eval_steps_per_second": 2.206,
|
1104 |
+
"step": 730
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.779768177028451,
|
1108 |
+
"grad_norm": 0.5144335627555847,
|
1109 |
+
"learning_rate": 3.7003863716192485e-05,
|
1110 |
+
"loss": 0.2563,
|
1111 |
+
"step": 740
|
1112 |
+
},
|
1113 |
+
{
|
1114 |
+
"epoch": 0.779768177028451,
|
1115 |
+
"eval_loss": 0.3298059403896332,
|
1116 |
+
"eval_runtime": 13.5958,
|
1117 |
+
"eval_samples_per_second": 35.305,
|
1118 |
+
"eval_steps_per_second": 2.207,
|
1119 |
+
"step": 740
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.7903055848261328,
|
1123 |
+
"grad_norm": 0.5247990489006042,
|
1124 |
+
"learning_rate": 3.682824025289779e-05,
|
1125 |
+
"loss": 0.2358,
|
1126 |
+
"step": 750
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 0.7903055848261328,
|
1130 |
+
"eval_loss": 0.32794949412345886,
|
1131 |
+
"eval_runtime": 13.6027,
|
1132 |
+
"eval_samples_per_second": 35.287,
|
1133 |
+
"eval_steps_per_second": 2.205,
|
1134 |
+
"step": 750
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.8008429926238145,
|
1138 |
+
"grad_norm": 0.5819652676582336,
|
1139 |
+
"learning_rate": 3.6652616789603096e-05,
|
1140 |
+
"loss": 0.2423,
|
1141 |
+
"step": 760
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 0.8008429926238145,
|
1145 |
+
"eval_loss": 0.3263894319534302,
|
1146 |
+
"eval_runtime": 13.588,
|
1147 |
+
"eval_samples_per_second": 35.325,
|
1148 |
+
"eval_steps_per_second": 2.208,
|
1149 |
+
"step": 760
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.8113804004214963,
|
1153 |
+
"grad_norm": 0.5112130045890808,
|
1154 |
+
"learning_rate": 3.6476993326308395e-05,
|
1155 |
+
"loss": 0.2638,
|
1156 |
+
"step": 770
|
1157 |
+
},
|
1158 |
+
{
|
1159 |
+
"epoch": 0.8113804004214963,
|
1160 |
+
"eval_loss": 0.3270197808742523,
|
1161 |
+
"eval_runtime": 13.5821,
|
1162 |
+
"eval_samples_per_second": 35.341,
|
1163 |
+
"eval_steps_per_second": 2.209,
|
1164 |
+
"step": 770
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.821917808219178,
|
1168 |
+
"grad_norm": 0.5146061778068542,
|
1169 |
+
"learning_rate": 3.63013698630137e-05,
|
1170 |
+
"loss": 0.2375,
|
1171 |
+
"step": 780
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.821917808219178,
|
1175 |
+
"eval_loss": 0.3265083432197571,
|
1176 |
+
"eval_runtime": 13.5816,
|
1177 |
+
"eval_samples_per_second": 35.342,
|
1178 |
+
"eval_steps_per_second": 2.209,
|
1179 |
+
"step": 780
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.8324552160168599,
|
1183 |
+
"grad_norm": 0.5121347904205322,
|
1184 |
+
"learning_rate": 3.6125746399719e-05,
|
1185 |
+
"loss": 0.2468,
|
1186 |
+
"step": 790
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.8324552160168599,
|
1190 |
+
"eval_loss": 0.32619577646255493,
|
1191 |
+
"eval_runtime": 13.5874,
|
1192 |
+
"eval_samples_per_second": 35.327,
|
1193 |
+
"eval_steps_per_second": 2.208,
|
1194 |
+
"step": 790
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.8429926238145417,
|
1198 |
+
"grad_norm": 0.5837659239768982,
|
1199 |
+
"learning_rate": 3.5950122936424305e-05,
|
1200 |
+
"loss": 0.2392,
|
1201 |
+
"step": 800
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 0.8429926238145417,
|
1205 |
+
"eval_loss": 0.3283963203430176,
|
1206 |
+
"eval_runtime": 13.5978,
|
1207 |
+
"eval_samples_per_second": 35.3,
|
1208 |
+
"eval_steps_per_second": 2.206,
|
1209 |
+
"step": 800
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.8535300316122234,
|
1213 |
+
"grad_norm": 0.6293447613716125,
|
1214 |
+
"learning_rate": 3.577449947312961e-05,
|
1215 |
+
"loss": 0.2415,
|
1216 |
+
"step": 810
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"epoch": 0.8535300316122234,
|
1220 |
+
"eval_loss": 0.32890576124191284,
|
1221 |
+
"eval_runtime": 13.5797,
|
1222 |
+
"eval_samples_per_second": 35.347,
|
1223 |
+
"eval_steps_per_second": 2.209,
|
1224 |
+
"step": 810
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.8640674394099052,
|
1228 |
+
"grad_norm": 0.5239388942718506,
|
1229 |
+
"learning_rate": 3.5598876009834916e-05,
|
1230 |
+
"loss": 0.2459,
|
1231 |
+
"step": 820
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 0.8640674394099052,
|
1235 |
+
"eval_loss": 0.3269563317298889,
|
1236 |
+
"eval_runtime": 13.5785,
|
1237 |
+
"eval_samples_per_second": 35.35,
|
1238 |
+
"eval_steps_per_second": 2.209,
|
1239 |
+
"step": 820
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.8746048472075869,
|
1243 |
+
"grad_norm": 0.5803388953208923,
|
1244 |
+
"learning_rate": 3.542325254654022e-05,
|
1245 |
+
"loss": 0.2561,
|
1246 |
+
"step": 830
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 0.8746048472075869,
|
1250 |
+
"eval_loss": 0.32730814814567566,
|
1251 |
+
"eval_runtime": 13.5623,
|
1252 |
+
"eval_samples_per_second": 35.392,
|
1253 |
+
"eval_steps_per_second": 2.212,
|
1254 |
+
"step": 830
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.8851422550052687,
|
1258 |
+
"grad_norm": 0.541553795337677,
|
1259 |
+
"learning_rate": 3.524762908324553e-05,
|
1260 |
+
"loss": 0.2407,
|
1261 |
+
"step": 840
|
1262 |
+
},
|
1263 |
+
{
|
1264 |
+
"epoch": 0.8851422550052687,
|
1265 |
+
"eval_loss": 0.32772594690322876,
|
1266 |
+
"eval_runtime": 13.5543,
|
1267 |
+
"eval_samples_per_second": 35.413,
|
1268 |
+
"eval_steps_per_second": 2.213,
|
1269 |
+
"step": 840
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.8956796628029505,
|
1273 |
+
"grad_norm": 0.547488272190094,
|
1274 |
+
"learning_rate": 3.507200561995083e-05,
|
1275 |
+
"loss": 0.2512,
|
1276 |
+
"step": 850
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.8956796628029505,
|
1280 |
+
"eval_loss": 0.32760006189346313,
|
1281 |
+
"eval_runtime": 13.5629,
|
1282 |
+
"eval_samples_per_second": 35.391,
|
1283 |
+
"eval_steps_per_second": 2.212,
|
1284 |
+
"step": 850
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.9062170706006323,
|
1288 |
+
"grad_norm": 0.5485065579414368,
|
1289 |
+
"learning_rate": 3.489638215665613e-05,
|
1290 |
+
"loss": 0.2341,
|
1291 |
+
"step": 860
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 0.9062170706006323,
|
1295 |
+
"eval_loss": 0.327595055103302,
|
1296 |
+
"eval_runtime": 13.5606,
|
1297 |
+
"eval_samples_per_second": 35.397,
|
1298 |
+
"eval_steps_per_second": 2.212,
|
1299 |
+
"step": 860
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.916754478398314,
|
1303 |
+
"grad_norm": 0.5831624865531921,
|
1304 |
+
"learning_rate": 3.472075869336143e-05,
|
1305 |
+
"loss": 0.2465,
|
1306 |
+
"step": 870
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.916754478398314,
|
1310 |
+
"eval_loss": 0.325825572013855,
|
1311 |
+
"eval_runtime": 13.5618,
|
1312 |
+
"eval_samples_per_second": 35.394,
|
1313 |
+
"eval_steps_per_second": 2.212,
|
1314 |
+
"step": 870
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.9272918861959958,
|
1318 |
+
"grad_norm": 0.528672456741333,
|
1319 |
+
"learning_rate": 3.454513523006674e-05,
|
1320 |
+
"loss": 0.2355,
|
1321 |
+
"step": 880
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 0.9272918861959958,
|
1325 |
+
"eval_loss": 0.32486769556999207,
|
1326 |
+
"eval_runtime": 13.553,
|
1327 |
+
"eval_samples_per_second": 35.417,
|
1328 |
+
"eval_steps_per_second": 2.214,
|
1329 |
+
"step": 880
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.9378292939936775,
|
1333 |
+
"grad_norm": 0.5654621124267578,
|
1334 |
+
"learning_rate": 3.436951176677204e-05,
|
1335 |
+
"loss": 0.244,
|
1336 |
+
"step": 890
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 0.9378292939936775,
|
1340 |
+
"eval_loss": 0.32602888345718384,
|
1341 |
+
"eval_runtime": 13.5581,
|
1342 |
+
"eval_samples_per_second": 35.403,
|
1343 |
+
"eval_steps_per_second": 2.213,
|
1344 |
+
"step": 890
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.9483667017913593,
|
1348 |
+
"grad_norm": 0.5009713172912598,
|
1349 |
+
"learning_rate": 3.419388830347735e-05,
|
1350 |
+
"loss": 0.2299,
|
1351 |
+
"step": 900
|
1352 |
+
},
|
1353 |
+
{
|
1354 |
+
"epoch": 0.9483667017913593,
|
1355 |
+
"eval_loss": 0.32582351565361023,
|
1356 |
+
"eval_runtime": 13.5546,
|
1357 |
+
"eval_samples_per_second": 35.412,
|
1358 |
+
"eval_steps_per_second": 2.213,
|
1359 |
+
"step": 900
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.958904109589041,
|
1363 |
+
"grad_norm": 0.5322644114494324,
|
1364 |
+
"learning_rate": 3.4018264840182654e-05,
|
1365 |
+
"loss": 0.2382,
|
1366 |
+
"step": 910
|
1367 |
+
},
|
1368 |
+
{
|
1369 |
+
"epoch": 0.958904109589041,
|
1370 |
+
"eval_loss": 0.32392945885658264,
|
1371 |
+
"eval_runtime": 13.5582,
|
1372 |
+
"eval_samples_per_second": 35.403,
|
1373 |
+
"eval_steps_per_second": 2.213,
|
1374 |
+
"step": 910
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.9694415173867229,
|
1378 |
+
"grad_norm": 0.5522642731666565,
|
1379 |
+
"learning_rate": 3.384264137688795e-05,
|
1380 |
+
"loss": 0.2478,
|
1381 |
+
"step": 920
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.9694415173867229,
|
1385 |
+
"eval_loss": 0.3241512179374695,
|
1386 |
+
"eval_runtime": 13.5666,
|
1387 |
+
"eval_samples_per_second": 35.381,
|
1388 |
+
"eval_steps_per_second": 2.211,
|
1389 |
+
"step": 920
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.9799789251844047,
|
1393 |
+
"grad_norm": 0.5779546499252319,
|
1394 |
+
"learning_rate": 3.366701791359326e-05,
|
1395 |
+
"loss": 0.2534,
|
1396 |
+
"step": 930
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.9799789251844047,
|
1400 |
+
"eval_loss": 0.3243790864944458,
|
1401 |
+
"eval_runtime": 13.524,
|
1402 |
+
"eval_samples_per_second": 35.492,
|
1403 |
+
"eval_steps_per_second": 2.218,
|
1404 |
+
"step": 930
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.9905163329820864,
|
1408 |
+
"grad_norm": 0.6141674518585205,
|
1409 |
+
"learning_rate": 3.3491394450298564e-05,
|
1410 |
+
"loss": 0.2401,
|
1411 |
+
"step": 940
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"epoch": 0.9905163329820864,
|
1415 |
+
"eval_loss": 0.3262033462524414,
|
1416 |
+
"eval_runtime": 13.5269,
|
1417 |
+
"eval_samples_per_second": 35.485,
|
1418 |
+
"eval_steps_per_second": 2.218,
|
1419 |
+
"step": 940
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 1.0010537407797682,
|
1423 |
+
"grad_norm": 0.42756763100624084,
|
1424 |
+
"learning_rate": 3.331577098700386e-05,
|
1425 |
+
"loss": 0.2338,
|
1426 |
+
"step": 950
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 1.0010537407797682,
|
1430 |
+
"eval_loss": 0.3266028165817261,
|
1431 |
+
"eval_runtime": 13.5168,
|
1432 |
+
"eval_samples_per_second": 35.511,
|
1433 |
+
"eval_steps_per_second": 2.219,
|
1434 |
+
"step": 950
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 1.01159114857745,
|
1438 |
+
"grad_norm": 0.5351940989494324,
|
1439 |
+
"learning_rate": 3.314014752370917e-05,
|
1440 |
+
"loss": 0.1934,
|
1441 |
+
"step": 960
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 1.01159114857745,
|
1445 |
+
"eval_loss": 0.3327268064022064,
|
1446 |
+
"eval_runtime": 13.5225,
|
1447 |
+
"eval_samples_per_second": 35.497,
|
1448 |
+
"eval_steps_per_second": 2.219,
|
1449 |
+
"step": 960
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.0221285563751317,
|
1453 |
+
"grad_norm": 0.5101184248924255,
|
1454 |
+
"learning_rate": 3.2964524060414474e-05,
|
1455 |
+
"loss": 0.208,
|
1456 |
+
"step": 970
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 1.0221285563751317,
|
1460 |
+
"eval_loss": 0.3375646471977234,
|
1461 |
+
"eval_runtime": 13.5136,
|
1462 |
+
"eval_samples_per_second": 35.52,
|
1463 |
+
"eval_steps_per_second": 2.22,
|
1464 |
+
"step": 970
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 1.0326659641728135,
|
1468 |
+
"grad_norm": 0.6187830567359924,
|
1469 |
+
"learning_rate": 3.278890059711977e-05,
|
1470 |
+
"loss": 0.2145,
|
1471 |
+
"step": 980
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 1.0326659641728135,
|
1475 |
+
"eval_loss": 0.3343217074871063,
|
1476 |
+
"eval_runtime": 13.5266,
|
1477 |
+
"eval_samples_per_second": 35.486,
|
1478 |
+
"eval_steps_per_second": 2.218,
|
1479 |
+
"step": 980
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 1.0432033719704952,
|
1483 |
+
"grad_norm": 0.669201672077179,
|
1484 |
+
"learning_rate": 3.261327713382508e-05,
|
1485 |
+
"loss": 0.2141,
|
1486 |
+
"step": 990
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 1.0432033719704952,
|
1490 |
+
"eval_loss": 0.33267149329185486,
|
1491 |
+
"eval_runtime": 13.5144,
|
1492 |
+
"eval_samples_per_second": 35.518,
|
1493 |
+
"eval_steps_per_second": 2.22,
|
1494 |
+
"step": 990
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.053740779768177,
|
1498 |
+
"grad_norm": 0.5544168949127197,
|
1499 |
+
"learning_rate": 3.2437653670530384e-05,
|
1500 |
+
"loss": 0.2074,
|
1501 |
+
"step": 1000
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.053740779768177,
|
1505 |
+
"eval_loss": 0.33638790249824524,
|
1506 |
+
"eval_runtime": 13.5127,
|
1507 |
+
"eval_samples_per_second": 35.522,
|
1508 |
+
"eval_steps_per_second": 2.22,
|
1509 |
+
"step": 1000
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 1.064278187565859,
|
1513 |
+
"grad_norm": 0.6323490738868713,
|
1514 |
+
"learning_rate": 3.226203020723569e-05,
|
1515 |
+
"loss": 0.2012,
|
1516 |
+
"step": 1010
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 1.064278187565859,
|
1520 |
+
"eval_loss": 0.3400089144706726,
|
1521 |
+
"eval_runtime": 13.5093,
|
1522 |
+
"eval_samples_per_second": 35.531,
|
1523 |
+
"eval_steps_per_second": 2.221,
|
1524 |
+
"step": 1010
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 1.0748155953635405,
|
1528 |
+
"grad_norm": 0.5988993048667908,
|
1529 |
+
"learning_rate": 3.2086406743940996e-05,
|
1530 |
+
"loss": 0.1954,
|
1531 |
+
"step": 1020
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 1.0748155953635405,
|
1535 |
+
"eval_loss": 0.3393259048461914,
|
1536 |
+
"eval_runtime": 13.5107,
|
1537 |
+
"eval_samples_per_second": 35.527,
|
1538 |
+
"eval_steps_per_second": 2.22,
|
1539 |
+
"step": 1020
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.0853530031612224,
|
1543 |
+
"grad_norm": 0.6308508515357971,
|
1544 |
+
"learning_rate": 3.1910783280646294e-05,
|
1545 |
+
"loss": 0.2066,
|
1546 |
+
"step": 1030
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 1.0853530031612224,
|
1550 |
+
"eval_loss": 0.337782084941864,
|
1551 |
+
"eval_runtime": 13.5075,
|
1552 |
+
"eval_samples_per_second": 35.536,
|
1553 |
+
"eval_steps_per_second": 2.221,
|
1554 |
+
"step": 1030
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 1.095890410958904,
|
1558 |
+
"grad_norm": 0.5316015481948853,
|
1559 |
+
"learning_rate": 3.17351598173516e-05,
|
1560 |
+
"loss": 0.2074,
|
1561 |
+
"step": 1040
|
1562 |
+
},
|
1563 |
+
{
|
1564 |
+
"epoch": 1.095890410958904,
|
1565 |
+
"eval_loss": 0.3380493223667145,
|
1566 |
+
"eval_runtime": 13.531,
|
1567 |
+
"eval_samples_per_second": 35.474,
|
1568 |
+
"eval_steps_per_second": 2.217,
|
1569 |
+
"step": 1040
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 1.106427818756586,
|
1573 |
+
"grad_norm": 0.6207646131515503,
|
1574 |
+
"learning_rate": 3.15595363540569e-05,
|
1575 |
+
"loss": 0.2088,
|
1576 |
+
"step": 1050
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"epoch": 1.106427818756586,
|
1580 |
+
"eval_loss": 0.340431809425354,
|
1581 |
+
"eval_runtime": 13.5161,
|
1582 |
+
"eval_samples_per_second": 35.513,
|
1583 |
+
"eval_steps_per_second": 2.22,
|
1584 |
+
"step": 1050
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 1.1169652265542676,
|
1588 |
+
"grad_norm": 0.5499827265739441,
|
1589 |
+
"learning_rate": 3.1383912890762205e-05,
|
1590 |
+
"loss": 0.2049,
|
1591 |
+
"step": 1060
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 1.1169652265542676,
|
1595 |
+
"eval_loss": 0.34178677201271057,
|
1596 |
+
"eval_runtime": 13.5149,
|
1597 |
+
"eval_samples_per_second": 35.516,
|
1598 |
+
"eval_steps_per_second": 2.22,
|
1599 |
+
"step": 1060
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.1275026343519494,
|
1603 |
+
"grad_norm": 0.5874269604682922,
|
1604 |
+
"learning_rate": 3.120828942746751e-05,
|
1605 |
+
"loss": 0.2027,
|
1606 |
+
"step": 1070
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 1.1275026343519494,
|
1610 |
+
"eval_loss": 0.3401419222354889,
|
1611 |
+
"eval_runtime": 13.5078,
|
1612 |
+
"eval_samples_per_second": 35.535,
|
1613 |
+
"eval_steps_per_second": 2.221,
|
1614 |
+
"step": 1070
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 1.1380400421496313,
|
1618 |
+
"grad_norm": 0.5852048397064209,
|
1619 |
+
"learning_rate": 3.1032665964172816e-05,
|
1620 |
+
"loss": 0.1999,
|
1621 |
+
"step": 1080
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 1.1380400421496313,
|
1625 |
+
"eval_loss": 0.3392138183116913,
|
1626 |
+
"eval_runtime": 13.5107,
|
1627 |
+
"eval_samples_per_second": 35.527,
|
1628 |
+
"eval_steps_per_second": 2.22,
|
1629 |
+
"step": 1080
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.148577449947313,
|
1633 |
+
"grad_norm": 0.6016051769256592,
|
1634 |
+
"learning_rate": 3.085704250087812e-05,
|
1635 |
+
"loss": 0.2044,
|
1636 |
+
"step": 1090
|
1637 |
+
},
|
1638 |
+
{
|
1639 |
+
"epoch": 1.148577449947313,
|
1640 |
+
"eval_loss": 0.34129372239112854,
|
1641 |
+
"eval_runtime": 13.5118,
|
1642 |
+
"eval_samples_per_second": 35.525,
|
1643 |
+
"eval_steps_per_second": 2.22,
|
1644 |
+
"step": 1090
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 1.1591148577449948,
|
1648 |
+
"grad_norm": 0.5797489285469055,
|
1649 |
+
"learning_rate": 3.068141903758342e-05,
|
1650 |
+
"loss": 0.1974,
|
1651 |
+
"step": 1100
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 1.1591148577449948,
|
1655 |
+
"eval_loss": 0.34007471799850464,
|
1656 |
+
"eval_runtime": 13.5066,
|
1657 |
+
"eval_samples_per_second": 35.538,
|
1658 |
+
"eval_steps_per_second": 2.221,
|
1659 |
+
"step": 1100
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 1.1696522655426764,
|
1663 |
+
"grad_norm": 0.6308450102806091,
|
1664 |
+
"learning_rate": 3.0505795574288726e-05,
|
1665 |
+
"loss": 0.2037,
|
1666 |
+
"step": 1110
|
1667 |
+
},
|
1668 |
+
{
|
1669 |
+
"epoch": 1.1696522655426764,
|
1670 |
+
"eval_loss": 0.3387734293937683,
|
1671 |
+
"eval_runtime": 13.5225,
|
1672 |
+
"eval_samples_per_second": 35.496,
|
1673 |
+
"eval_steps_per_second": 2.219,
|
1674 |
+
"step": 1110
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 1.1801896733403583,
|
1678 |
+
"grad_norm": 0.6952560544013977,
|
1679 |
+
"learning_rate": 3.0330172110994032e-05,
|
1680 |
+
"loss": 0.2009,
|
1681 |
+
"step": 1120
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 1.1801896733403583,
|
1685 |
+
"eval_loss": 0.3363548815250397,
|
1686 |
+
"eval_runtime": 13.515,
|
1687 |
+
"eval_samples_per_second": 35.516,
|
1688 |
+
"eval_steps_per_second": 2.22,
|
1689 |
+
"step": 1120
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 1.1907270811380402,
|
1693 |
+
"grad_norm": 0.6670855283737183,
|
1694 |
+
"learning_rate": 3.015454864769933e-05,
|
1695 |
+
"loss": 0.2046,
|
1696 |
+
"step": 1130
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 1.1907270811380402,
|
1700 |
+
"eval_loss": 0.3387907147407532,
|
1701 |
+
"eval_runtime": 13.5274,
|
1702 |
+
"eval_samples_per_second": 35.484,
|
1703 |
+
"eval_steps_per_second": 2.218,
|
1704 |
+
"step": 1130
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 1.2012644889357218,
|
1708 |
+
"grad_norm": 0.7167879343032837,
|
1709 |
+
"learning_rate": 2.997892518440464e-05,
|
1710 |
+
"loss": 0.2039,
|
1711 |
+
"step": 1140
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 1.2012644889357218,
|
1715 |
+
"eval_loss": 0.33721429109573364,
|
1716 |
+
"eval_runtime": 13.5247,
|
1717 |
+
"eval_samples_per_second": 35.491,
|
1718 |
+
"eval_steps_per_second": 2.218,
|
1719 |
+
"step": 1140
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 1.2118018967334037,
|
1723 |
+
"grad_norm": 0.5917449593544006,
|
1724 |
+
"learning_rate": 2.9803301721109945e-05,
|
1725 |
+
"loss": 0.1997,
|
1726 |
+
"step": 1150
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 1.2118018967334037,
|
1730 |
+
"eval_loss": 0.33842217922210693,
|
1731 |
+
"eval_runtime": 13.5215,
|
1732 |
+
"eval_samples_per_second": 35.499,
|
1733 |
+
"eval_steps_per_second": 2.219,
|
1734 |
+
"step": 1150
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 1.2223393045310853,
|
1738 |
+
"grad_norm": 0.6303601264953613,
|
1739 |
+
"learning_rate": 2.9627678257815244e-05,
|
1740 |
+
"loss": 0.2063,
|
1741 |
+
"step": 1160
|
1742 |
+
},
|
1743 |
+
{
|
1744 |
+
"epoch": 1.2223393045310853,
|
1745 |
+
"eval_loss": 0.3402339816093445,
|
1746 |
+
"eval_runtime": 13.5168,
|
1747 |
+
"eval_samples_per_second": 35.511,
|
1748 |
+
"eval_steps_per_second": 2.219,
|
1749 |
+
"step": 1160
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.2328767123287672,
|
1753 |
+
"grad_norm": 0.7068540453910828,
|
1754 |
+
"learning_rate": 2.945205479452055e-05,
|
1755 |
+
"loss": 0.1959,
|
1756 |
+
"step": 1170
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 1.2328767123287672,
|
1760 |
+
"eval_loss": 0.3410193622112274,
|
1761 |
+
"eval_runtime": 13.5262,
|
1762 |
+
"eval_samples_per_second": 35.487,
|
1763 |
+
"eval_steps_per_second": 2.218,
|
1764 |
+
"step": 1170
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 1.2434141201264488,
|
1768 |
+
"grad_norm": 0.6145871877670288,
|
1769 |
+
"learning_rate": 2.9276431331225852e-05,
|
1770 |
+
"loss": 0.1979,
|
1771 |
+
"step": 1180
|
1772 |
+
},
|
1773 |
+
{
|
1774 |
+
"epoch": 1.2434141201264488,
|
1775 |
+
"eval_loss": 0.34399738907814026,
|
1776 |
+
"eval_runtime": 13.5178,
|
1777 |
+
"eval_samples_per_second": 35.509,
|
1778 |
+
"eval_steps_per_second": 2.219,
|
1779 |
+
"step": 1180
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 1.2539515279241307,
|
1783 |
+
"grad_norm": 0.6426234841346741,
|
1784 |
+
"learning_rate": 2.9100807867931158e-05,
|
1785 |
+
"loss": 0.2077,
|
1786 |
+
"step": 1190
|
1787 |
+
},
|
1788 |
+
{
|
1789 |
+
"epoch": 1.2539515279241307,
|
1790 |
+
"eval_loss": 0.339756041765213,
|
1791 |
+
"eval_runtime": 13.5275,
|
1792 |
+
"eval_samples_per_second": 35.483,
|
1793 |
+
"eval_steps_per_second": 2.218,
|
1794 |
+
"step": 1190
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.2644889357218125,
|
1798 |
+
"grad_norm": 0.6372554302215576,
|
1799 |
+
"learning_rate": 2.8925184404636463e-05,
|
1800 |
+
"loss": 0.1938,
|
1801 |
+
"step": 1200
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 1.2644889357218125,
|
1805 |
+
"eval_loss": 0.3394372761249542,
|
1806 |
+
"eval_runtime": 13.5262,
|
1807 |
+
"eval_samples_per_second": 35.487,
|
1808 |
+
"eval_steps_per_second": 2.218,
|
1809 |
+
"step": 1200
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.2750263435194942,
|
1813 |
+
"grad_norm": 0.49700266122817993,
|
1814 |
+
"learning_rate": 2.8749560941341762e-05,
|
1815 |
+
"loss": 0.1973,
|
1816 |
+
"step": 1210
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 1.2750263435194942,
|
1820 |
+
"eval_loss": 0.34174108505249023,
|
1821 |
+
"eval_runtime": 13.5375,
|
1822 |
+
"eval_samples_per_second": 35.457,
|
1823 |
+
"eval_steps_per_second": 2.216,
|
1824 |
+
"step": 1210
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 1.285563751317176,
|
1828 |
+
"grad_norm": 0.6628106832504272,
|
1829 |
+
"learning_rate": 2.8573937478047068e-05,
|
1830 |
+
"loss": 0.1892,
|
1831 |
+
"step": 1220
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 1.285563751317176,
|
1835 |
+
"eval_loss": 0.3427627980709076,
|
1836 |
+
"eval_runtime": 13.5801,
|
1837 |
+
"eval_samples_per_second": 35.346,
|
1838 |
+
"eval_steps_per_second": 2.209,
|
1839 |
+
"step": 1220
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 1.2961011591148577,
|
1843 |
+
"grad_norm": 0.6381083130836487,
|
1844 |
+
"learning_rate": 2.839831401475237e-05,
|
1845 |
+
"loss": 0.2023,
|
1846 |
+
"step": 1230
|
1847 |
+
},
|
1848 |
+
{
|
1849 |
+
"epoch": 1.2961011591148577,
|
1850 |
+
"eval_loss": 0.3431331515312195,
|
1851 |
+
"eval_runtime": 13.5304,
|
1852 |
+
"eval_samples_per_second": 35.476,
|
1853 |
+
"eval_steps_per_second": 2.217,
|
1854 |
+
"step": 1230
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 1.3066385669125395,
|
1858 |
+
"grad_norm": 0.6037564873695374,
|
1859 |
+
"learning_rate": 2.8222690551457676e-05,
|
1860 |
+
"loss": 0.1925,
|
1861 |
+
"step": 1240
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 1.3066385669125395,
|
1865 |
+
"eval_loss": 0.3404982388019562,
|
1866 |
+
"eval_runtime": 13.5282,
|
1867 |
+
"eval_samples_per_second": 35.481,
|
1868 |
+
"eval_steps_per_second": 2.218,
|
1869 |
+
"step": 1240
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 1.3171759747102212,
|
1873 |
+
"grad_norm": 0.6601694822311401,
|
1874 |
+
"learning_rate": 2.804706708816298e-05,
|
1875 |
+
"loss": 0.1926,
|
1876 |
+
"step": 1250
|
1877 |
+
},
|
1878 |
+
{
|
1879 |
+
"epoch": 1.3171759747102212,
|
1880 |
+
"eval_loss": 0.34181320667266846,
|
1881 |
+
"eval_runtime": 13.5621,
|
1882 |
+
"eval_samples_per_second": 35.393,
|
1883 |
+
"eval_steps_per_second": 2.212,
|
1884 |
+
"step": 1250
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 1.327713382507903,
|
1888 |
+
"grad_norm": 0.5349809527397156,
|
1889 |
+
"learning_rate": 2.7871443624868284e-05,
|
1890 |
+
"loss": 0.1936,
|
1891 |
+
"step": 1260
|
1892 |
+
},
|
1893 |
+
{
|
1894 |
+
"epoch": 1.327713382507903,
|
1895 |
+
"eval_loss": 0.34073132276535034,
|
1896 |
+
"eval_runtime": 13.6477,
|
1897 |
+
"eval_samples_per_second": 35.171,
|
1898 |
+
"eval_steps_per_second": 2.198,
|
1899 |
+
"step": 1260
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 1.338250790305585,
|
1903 |
+
"grad_norm": 0.6491771340370178,
|
1904 |
+
"learning_rate": 2.769582016157359e-05,
|
1905 |
+
"loss": 0.1993,
|
1906 |
+
"step": 1270
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 1.338250790305585,
|
1910 |
+
"eval_loss": 0.34483978152275085,
|
1911 |
+
"eval_runtime": 13.5329,
|
1912 |
+
"eval_samples_per_second": 35.469,
|
1913 |
+
"eval_steps_per_second": 2.217,
|
1914 |
+
"step": 1270
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 1.3487881981032666,
|
1918 |
+
"grad_norm": 0.6270915865898132,
|
1919 |
+
"learning_rate": 2.7520196698278895e-05,
|
1920 |
+
"loss": 0.2007,
|
1921 |
+
"step": 1280
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 1.3487881981032666,
|
1925 |
+
"eval_loss": 0.34615617990493774,
|
1926 |
+
"eval_runtime": 13.5185,
|
1927 |
+
"eval_samples_per_second": 35.507,
|
1928 |
+
"eval_steps_per_second": 2.219,
|
1929 |
+
"step": 1280
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.3593256059009484,
|
1933 |
+
"grad_norm": 0.6853300333023071,
|
1934 |
+
"learning_rate": 2.7344573234984194e-05,
|
1935 |
+
"loss": 0.2131,
|
1936 |
+
"step": 1290
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 1.3593256059009484,
|
1940 |
+
"eval_loss": 0.3406980335712433,
|
1941 |
+
"eval_runtime": 13.5247,
|
1942 |
+
"eval_samples_per_second": 35.491,
|
1943 |
+
"eval_steps_per_second": 2.218,
|
1944 |
+
"step": 1290
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 1.36986301369863,
|
1948 |
+
"grad_norm": 0.5863353610038757,
|
1949 |
+
"learning_rate": 2.71689497716895e-05,
|
1950 |
+
"loss": 0.1846,
|
1951 |
+
"step": 1300
|
1952 |
+
},
|
1953 |
+
{
|
1954 |
+
"epoch": 1.36986301369863,
|
1955 |
+
"eval_loss": 0.34115493297576904,
|
1956 |
+
"eval_runtime": 13.5104,
|
1957 |
+
"eval_samples_per_second": 35.528,
|
1958 |
+
"eval_steps_per_second": 2.221,
|
1959 |
+
"step": 1300
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 1.380400421496312,
|
1963 |
+
"grad_norm": 0.7511035203933716,
|
1964 |
+
"learning_rate": 2.6993326308394802e-05,
|
1965 |
+
"loss": 0.1911,
|
1966 |
+
"step": 1310
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 1.380400421496312,
|
1970 |
+
"eval_loss": 0.34829092025756836,
|
1971 |
+
"eval_runtime": 13.5081,
|
1972 |
+
"eval_samples_per_second": 35.534,
|
1973 |
+
"eval_steps_per_second": 2.221,
|
1974 |
+
"step": 1310
|
1975 |
+
},
|
1976 |
+
{
|
1977 |
+
"epoch": 1.3909378292939936,
|
1978 |
+
"grad_norm": 0.6482399106025696,
|
1979 |
+
"learning_rate": 2.6817702845100107e-05,
|
1980 |
+
"loss": 0.2013,
|
1981 |
+
"step": 1320
|
1982 |
+
},
|
1983 |
+
{
|
1984 |
+
"epoch": 1.3909378292939936,
|
1985 |
+
"eval_loss": 0.3465197682380676,
|
1986 |
+
"eval_runtime": 13.5316,
|
1987 |
+
"eval_samples_per_second": 35.473,
|
1988 |
+
"eval_steps_per_second": 2.217,
|
1989 |
+
"step": 1320
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 1.4014752370916754,
|
1993 |
+
"grad_norm": 0.570846438407898,
|
1994 |
+
"learning_rate": 2.6642079381805413e-05,
|
1995 |
+
"loss": 0.1889,
|
1996 |
+
"step": 1330
|
1997 |
+
},
|
1998 |
+
{
|
1999 |
+
"epoch": 1.4014752370916754,
|
2000 |
+
"eval_loss": 0.34688571095466614,
|
2001 |
+
"eval_runtime": 13.5157,
|
2002 |
+
"eval_samples_per_second": 35.514,
|
2003 |
+
"eval_steps_per_second": 2.22,
|
2004 |
+
"step": 1330
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 1.4120126448893573,
|
2008 |
+
"grad_norm": 0.6336379051208496,
|
2009 |
+
"learning_rate": 2.6466455918510712e-05,
|
2010 |
+
"loss": 0.1994,
|
2011 |
+
"step": 1340
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 1.4120126448893573,
|
2015 |
+
"eval_loss": 0.3466794788837433,
|
2016 |
+
"eval_runtime": 13.5071,
|
2017 |
+
"eval_samples_per_second": 35.537,
|
2018 |
+
"eval_steps_per_second": 2.221,
|
2019 |
+
"step": 1340
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 1.422550052687039,
|
2023 |
+
"grad_norm": 0.653731644153595,
|
2024 |
+
"learning_rate": 2.6290832455216018e-05,
|
2025 |
+
"loss": 0.1894,
|
2026 |
+
"step": 1350
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 1.422550052687039,
|
2030 |
+
"eval_loss": 0.34787434339523315,
|
2031 |
+
"eval_runtime": 13.5062,
|
2032 |
+
"eval_samples_per_second": 35.539,
|
2033 |
+
"eval_steps_per_second": 2.221,
|
2034 |
+
"step": 1350
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 1.4330874604847208,
|
2038 |
+
"grad_norm": 0.6545577049255371,
|
2039 |
+
"learning_rate": 2.611520899192132e-05,
|
2040 |
+
"loss": 0.1981,
|
2041 |
+
"step": 1360
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 1.4330874604847208,
|
2045 |
+
"eval_loss": 0.34745165705680847,
|
2046 |
+
"eval_runtime": 13.4977,
|
2047 |
+
"eval_samples_per_second": 35.562,
|
2048 |
+
"eval_steps_per_second": 2.223,
|
2049 |
+
"step": 1360
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 1.4436248682824027,
|
2053 |
+
"grad_norm": 0.7751778364181519,
|
2054 |
+
"learning_rate": 2.5939585528626625e-05,
|
2055 |
+
"loss": 0.183,
|
2056 |
+
"step": 1370
|
2057 |
+
},
|
2058 |
+
{
|
2059 |
+
"epoch": 1.4436248682824027,
|
2060 |
+
"eval_loss": 0.3481937348842621,
|
2061 |
+
"eval_runtime": 13.5303,
|
2062 |
+
"eval_samples_per_second": 35.476,
|
2063 |
+
"eval_steps_per_second": 2.217,
|
2064 |
+
"step": 1370
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 1.4541622760800843,
|
2068 |
+
"grad_norm": 0.7329134345054626,
|
2069 |
+
"learning_rate": 2.576396206533193e-05,
|
2070 |
+
"loss": 0.1906,
|
2071 |
+
"step": 1380
|
2072 |
+
},
|
2073 |
+
{
|
2074 |
+
"epoch": 1.4541622760800843,
|
2075 |
+
"eval_loss": 0.3493328094482422,
|
2076 |
+
"eval_runtime": 13.5155,
|
2077 |
+
"eval_samples_per_second": 35.515,
|
2078 |
+
"eval_steps_per_second": 2.22,
|
2079 |
+
"step": 1380
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 1.464699683877766,
|
2083 |
+
"grad_norm": 0.7945630550384521,
|
2084 |
+
"learning_rate": 2.5588338602037233e-05,
|
2085 |
+
"loss": 0.1913,
|
2086 |
+
"step": 1390
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"epoch": 1.464699683877766,
|
2090 |
+
"eval_loss": 0.3451732397079468,
|
2091 |
+
"eval_runtime": 13.5276,
|
2092 |
+
"eval_samples_per_second": 35.483,
|
2093 |
+
"eval_steps_per_second": 2.218,
|
2094 |
+
"step": 1390
|
2095 |
+
},
|
2096 |
+
{
|
2097 |
+
"epoch": 1.4752370916754478,
|
2098 |
+
"grad_norm": 0.7154361009597778,
|
2099 |
+
"learning_rate": 2.541271513874254e-05,
|
2100 |
+
"loss": 0.1853,
|
2101 |
+
"step": 1400
|
2102 |
+
},
|
2103 |
+
{
|
2104 |
+
"epoch": 1.4752370916754478,
|
2105 |
+
"eval_loss": 0.3447299301624298,
|
2106 |
+
"eval_runtime": 13.5329,
|
2107 |
+
"eval_samples_per_second": 35.469,
|
2108 |
+
"eval_steps_per_second": 2.217,
|
2109 |
+
"step": 1400
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 1.4857744994731297,
|
2113 |
+
"grad_norm": 0.6370890140533447,
|
2114 |
+
"learning_rate": 2.5237091675447845e-05,
|
2115 |
+
"loss": 0.1822,
|
2116 |
+
"step": 1410
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 1.4857744994731297,
|
2120 |
+
"eval_loss": 0.34814396500587463,
|
2121 |
+
"eval_runtime": 13.5296,
|
2122 |
+
"eval_samples_per_second": 35.478,
|
2123 |
+
"eval_steps_per_second": 2.217,
|
2124 |
+
"step": 1410
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 1.4963119072708113,
|
2128 |
+
"grad_norm": 0.7020454406738281,
|
2129 |
+
"learning_rate": 2.5061468212153144e-05,
|
2130 |
+
"loss": 0.1918,
|
2131 |
+
"step": 1420
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 1.4963119072708113,
|
2135 |
+
"eval_loss": 0.35007527470588684,
|
2136 |
+
"eval_runtime": 13.5235,
|
2137 |
+
"eval_samples_per_second": 35.494,
|
2138 |
+
"eval_steps_per_second": 2.218,
|
2139 |
+
"step": 1420
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 1.5068493150684932,
|
2143 |
+
"grad_norm": 0.7104793787002563,
|
2144 |
+
"learning_rate": 2.4885844748858446e-05,
|
2145 |
+
"loss": 0.2008,
|
2146 |
+
"step": 1430
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 1.5068493150684932,
|
2150 |
+
"eval_loss": 0.3479911684989929,
|
2151 |
+
"eval_runtime": 13.5547,
|
2152 |
+
"eval_samples_per_second": 35.412,
|
2153 |
+
"eval_steps_per_second": 2.213,
|
2154 |
+
"step": 1430
|
2155 |
+
},
|
2156 |
+
{
|
2157 |
+
"epoch": 1.517386722866175,
|
2158 |
+
"grad_norm": 0.8473650217056274,
|
2159 |
+
"learning_rate": 2.4710221285563755e-05,
|
2160 |
+
"loss": 0.2042,
|
2161 |
+
"step": 1440
|
2162 |
+
},
|
2163 |
+
{
|
2164 |
+
"epoch": 1.517386722866175,
|
2165 |
+
"eval_loss": 0.34348005056381226,
|
2166 |
+
"eval_runtime": 13.5204,
|
2167 |
+
"eval_samples_per_second": 35.502,
|
2168 |
+
"eval_steps_per_second": 2.219,
|
2169 |
+
"step": 1440
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 1.5279241306638567,
|
2173 |
+
"grad_norm": 0.6656286716461182,
|
2174 |
+
"learning_rate": 2.4534597822269057e-05,
|
2175 |
+
"loss": 0.1968,
|
2176 |
+
"step": 1450
|
2177 |
+
},
|
2178 |
+
{
|
2179 |
+
"epoch": 1.5279241306638567,
|
2180 |
+
"eval_loss": 0.3460903763771057,
|
2181 |
+
"eval_runtime": 13.5325,
|
2182 |
+
"eval_samples_per_second": 35.47,
|
2183 |
+
"eval_steps_per_second": 2.217,
|
2184 |
+
"step": 1450
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 1.5384615384615383,
|
2188 |
+
"grad_norm": 0.6165732145309448,
|
2189 |
+
"learning_rate": 2.435897435897436e-05,
|
2190 |
+
"loss": 0.1948,
|
2191 |
+
"step": 1460
|
2192 |
+
},
|
2193 |
+
{
|
2194 |
+
"epoch": 1.5384615384615383,
|
2195 |
+
"eval_loss": 0.3462531864643097,
|
2196 |
+
"eval_runtime": 13.5278,
|
2197 |
+
"eval_samples_per_second": 35.483,
|
2198 |
+
"eval_steps_per_second": 2.218,
|
2199 |
+
"step": 1460
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 1.5489989462592202,
|
2203 |
+
"grad_norm": 0.8803408741950989,
|
2204 |
+
"learning_rate": 2.418335089567966e-05,
|
2205 |
+
"loss": 0.1814,
|
2206 |
+
"step": 1470
|
2207 |
+
},
|
2208 |
+
{
|
2209 |
+
"epoch": 1.5489989462592202,
|
2210 |
+
"eval_loss": 0.3515132665634155,
|
2211 |
+
"eval_runtime": 13.5309,
|
2212 |
+
"eval_samples_per_second": 35.474,
|
2213 |
+
"eval_steps_per_second": 2.217,
|
2214 |
+
"step": 1470
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 1.559536354056902,
|
2218 |
+
"grad_norm": 0.628629744052887,
|
2219 |
+
"learning_rate": 2.4007727432384967e-05,
|
2220 |
+
"loss": 0.1894,
|
2221 |
+
"step": 1480
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 1.559536354056902,
|
2225 |
+
"eval_loss": 0.3480067551136017,
|
2226 |
+
"eval_runtime": 13.5314,
|
2227 |
+
"eval_samples_per_second": 35.473,
|
2228 |
+
"eval_steps_per_second": 2.217,
|
2229 |
+
"step": 1480
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 1.5700737618545837,
|
2233 |
+
"grad_norm": 0.6435084939002991,
|
2234 |
+
"learning_rate": 2.3832103969090273e-05,
|
2235 |
+
"loss": 0.1898,
|
2236 |
+
"step": 1490
|
2237 |
+
},
|
2238 |
+
{
|
2239 |
+
"epoch": 1.5700737618545837,
|
2240 |
+
"eval_loss": 0.3466918170452118,
|
2241 |
+
"eval_runtime": 13.5167,
|
2242 |
+
"eval_samples_per_second": 35.512,
|
2243 |
+
"eval_steps_per_second": 2.219,
|
2244 |
+
"step": 1490
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 1.5806111696522656,
|
2248 |
+
"grad_norm": 0.5330148935317993,
|
2249 |
+
"learning_rate": 2.3656480505795575e-05,
|
2250 |
+
"loss": 0.188,
|
2251 |
+
"step": 1500
|
2252 |
+
},
|
2253 |
+
{
|
2254 |
+
"epoch": 1.5806111696522656,
|
2255 |
+
"eval_loss": 0.3500882387161255,
|
2256 |
+
"eval_runtime": 13.516,
|
2257 |
+
"eval_samples_per_second": 35.514,
|
2258 |
+
"eval_steps_per_second": 2.22,
|
2259 |
+
"step": 1500
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 1.5911485774499474,
|
2263 |
+
"grad_norm": 0.5372351408004761,
|
2264 |
+
"learning_rate": 2.3480857042500877e-05,
|
2265 |
+
"loss": 0.1963,
|
2266 |
+
"step": 1510
|
2267 |
+
},
|
2268 |
+
{
|
2269 |
+
"epoch": 1.5911485774499474,
|
2270 |
+
"eval_loss": 0.35102787613868713,
|
2271 |
+
"eval_runtime": 13.5059,
|
2272 |
+
"eval_samples_per_second": 35.54,
|
2273 |
+
"eval_steps_per_second": 2.221,
|
2274 |
+
"step": 1510
|
2275 |
+
},
|
2276 |
+
{
|
2277 |
+
"epoch": 1.601685985247629,
|
2278 |
+
"grad_norm": 0.6970928907394409,
|
2279 |
+
"learning_rate": 2.3305233579206183e-05,
|
2280 |
+
"loss": 0.194,
|
2281 |
+
"step": 1520
|
2282 |
+
},
|
2283 |
+
{
|
2284 |
+
"epoch": 1.601685985247629,
|
2285 |
+
"eval_loss": 0.3498727083206177,
|
2286 |
+
"eval_runtime": 13.5044,
|
2287 |
+
"eval_samples_per_second": 35.544,
|
2288 |
+
"eval_steps_per_second": 2.221,
|
2289 |
+
"step": 1520
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 1.6122233930453107,
|
2293 |
+
"grad_norm": 0.6487205028533936,
|
2294 |
+
"learning_rate": 2.312961011591149e-05,
|
2295 |
+
"loss": 0.1926,
|
2296 |
+
"step": 1530
|
2297 |
+
},
|
2298 |
+
{
|
2299 |
+
"epoch": 1.6122233930453107,
|
2300 |
+
"eval_loss": 0.3481922745704651,
|
2301 |
+
"eval_runtime": 13.5029,
|
2302 |
+
"eval_samples_per_second": 35.548,
|
2303 |
+
"eval_steps_per_second": 2.222,
|
2304 |
+
"step": 1530
|
2305 |
+
},
|
2306 |
+
{
|
2307 |
+
"epoch": 1.6227608008429928,
|
2308 |
+
"grad_norm": 0.6962392330169678,
|
2309 |
+
"learning_rate": 2.295398665261679e-05,
|
2310 |
+
"loss": 0.1957,
|
2311 |
+
"step": 1540
|
2312 |
+
},
|
2313 |
+
{
|
2314 |
+
"epoch": 1.6227608008429928,
|
2315 |
+
"eval_loss": 0.3489096462726593,
|
2316 |
+
"eval_runtime": 13.5,
|
2317 |
+
"eval_samples_per_second": 35.555,
|
2318 |
+
"eval_steps_per_second": 2.222,
|
2319 |
+
"step": 1540
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 1.6332982086406744,
|
2323 |
+
"grad_norm": 0.9060853719711304,
|
2324 |
+
"learning_rate": 2.2778363189322093e-05,
|
2325 |
+
"loss": 0.2036,
|
2326 |
+
"step": 1550
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 1.6332982086406744,
|
2330 |
+
"eval_loss": 0.34907764196395874,
|
2331 |
+
"eval_runtime": 13.4978,
|
2332 |
+
"eval_samples_per_second": 35.561,
|
2333 |
+
"eval_steps_per_second": 2.223,
|
2334 |
+
"step": 1550
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 1.643835616438356,
|
2338 |
+
"grad_norm": 0.7215871810913086,
|
2339 |
+
"learning_rate": 2.2602739726027396e-05,
|
2340 |
+
"loss": 0.1932,
|
2341 |
+
"step": 1560
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 1.643835616438356,
|
2345 |
+
"eval_loss": 0.34920182824134827,
|
2346 |
+
"eval_runtime": 13.4995,
|
2347 |
+
"eval_samples_per_second": 35.557,
|
2348 |
+
"eval_steps_per_second": 2.222,
|
2349 |
+
"step": 1560
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 1.654373024236038,
|
2353 |
+
"grad_norm": 0.9014811515808105,
|
2354 |
+
"learning_rate": 2.2427116262732705e-05,
|
2355 |
+
"loss": 0.1852,
|
2356 |
+
"step": 1570
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 1.654373024236038,
|
2360 |
+
"eval_loss": 0.3518800139427185,
|
2361 |
+
"eval_runtime": 13.4922,
|
2362 |
+
"eval_samples_per_second": 35.576,
|
2363 |
+
"eval_steps_per_second": 2.224,
|
2364 |
+
"step": 1570
|
2365 |
+
},
|
2366 |
+
{
|
2367 |
+
"epoch": 1.6649104320337198,
|
2368 |
+
"grad_norm": 0.8547218441963196,
|
2369 |
+
"learning_rate": 2.2251492799438007e-05,
|
2370 |
+
"loss": 0.179,
|
2371 |
+
"step": 1580
|
2372 |
+
},
|
2373 |
+
{
|
2374 |
+
"epoch": 1.6649104320337198,
|
2375 |
+
"eval_loss": 0.3540193438529968,
|
2376 |
+
"eval_runtime": 13.4989,
|
2377 |
+
"eval_samples_per_second": 35.558,
|
2378 |
+
"eval_steps_per_second": 2.222,
|
2379 |
+
"step": 1580
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 1.6754478398314014,
|
2383 |
+
"grad_norm": 0.7223723530769348,
|
2384 |
+
"learning_rate": 2.207586933614331e-05,
|
2385 |
+
"loss": 0.1871,
|
2386 |
+
"step": 1590
|
2387 |
+
},
|
2388 |
+
{
|
2389 |
+
"epoch": 1.6754478398314014,
|
2390 |
+
"eval_loss": 0.3551488220691681,
|
2391 |
+
"eval_runtime": 13.5204,
|
2392 |
+
"eval_samples_per_second": 35.502,
|
2393 |
+
"eval_steps_per_second": 2.219,
|
2394 |
+
"step": 1590
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 1.685985247629083,
|
2398 |
+
"grad_norm": 0.7338292002677917,
|
2399 |
+
"learning_rate": 2.190024587284861e-05,
|
2400 |
+
"loss": 0.1865,
|
2401 |
+
"step": 1600
|
2402 |
+
},
|
2403 |
+
{
|
2404 |
+
"epoch": 1.685985247629083,
|
2405 |
+
"eval_loss": 0.3537011742591858,
|
2406 |
+
"eval_runtime": 13.5153,
|
2407 |
+
"eval_samples_per_second": 35.515,
|
2408 |
+
"eval_steps_per_second": 2.22,
|
2409 |
+
"step": 1600
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 1.6965226554267652,
|
2413 |
+
"grad_norm": 0.6816204190254211,
|
2414 |
+
"learning_rate": 2.1724622409553917e-05,
|
2415 |
+
"loss": 0.1859,
|
2416 |
+
"step": 1610
|
2417 |
+
},
|
2418 |
+
{
|
2419 |
+
"epoch": 1.6965226554267652,
|
2420 |
+
"eval_loss": 0.3547250032424927,
|
2421 |
+
"eval_runtime": 13.5235,
|
2422 |
+
"eval_samples_per_second": 35.494,
|
2423 |
+
"eval_steps_per_second": 2.218,
|
2424 |
+
"step": 1610
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 1.7070600632244468,
|
2428 |
+
"grad_norm": 0.6339895725250244,
|
2429 |
+
"learning_rate": 2.1548998946259223e-05,
|
2430 |
+
"loss": 0.1925,
|
2431 |
+
"step": 1620
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 1.7070600632244468,
|
2435 |
+
"eval_loss": 0.35097014904022217,
|
2436 |
+
"eval_runtime": 13.5126,
|
2437 |
+
"eval_samples_per_second": 35.522,
|
2438 |
+
"eval_steps_per_second": 2.22,
|
2439 |
+
"step": 1620
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 1.7175974710221285,
|
2443 |
+
"grad_norm": 0.9739067554473877,
|
2444 |
+
"learning_rate": 2.1373375482964525e-05,
|
2445 |
+
"loss": 0.184,
|
2446 |
+
"step": 1630
|
2447 |
+
},
|
2448 |
+
{
|
2449 |
+
"epoch": 1.7175974710221285,
|
2450 |
+
"eval_loss": 0.3519115746021271,
|
2451 |
+
"eval_runtime": 13.5322,
|
2452 |
+
"eval_samples_per_second": 35.471,
|
2453 |
+
"eval_steps_per_second": 2.217,
|
2454 |
+
"step": 1630
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 1.7281348788198103,
|
2458 |
+
"grad_norm": 0.6770708560943604,
|
2459 |
+
"learning_rate": 2.1197752019669827e-05,
|
2460 |
+
"loss": 0.1799,
|
2461 |
+
"step": 1640
|
2462 |
+
},
|
2463 |
+
{
|
2464 |
+
"epoch": 1.7281348788198103,
|
2465 |
+
"eval_loss": 0.35324668884277344,
|
2466 |
+
"eval_runtime": 13.526,
|
2467 |
+
"eval_samples_per_second": 35.487,
|
2468 |
+
"eval_steps_per_second": 2.218,
|
2469 |
+
"step": 1640
|
2470 |
+
}
|
2471 |
+
],
|
2472 |
+
"logging_steps": 10,
|
2473 |
+
"max_steps": 2847,
|
2474 |
+
"num_input_tokens_seen": 0,
|
2475 |
+
"num_train_epochs": 3,
|
2476 |
+
"save_steps": 10,
|
2477 |
+
"stateful_callbacks": {
|
2478 |
+
"TrainerControl": {
|
2479 |
+
"args": {
|
2480 |
+
"should_epoch_stop": false,
|
2481 |
+
"should_evaluate": false,
|
2482 |
+
"should_log": false,
|
2483 |
+
"should_save": true,
|
2484 |
+
"should_training_stop": false
|
2485 |
+
},
|
2486 |
+
"attributes": {}
|
2487 |
+
}
|
2488 |
+
},
|
2489 |
+
"total_flos": 1.966894246822871e+17,
|
2490 |
+
"train_batch_size": 16,
|
2491 |
+
"trial_name": null,
|
2492 |
+
"trial_params": null
|
2493 |
+
}
|
checkpoint-1640/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b0de208437fea36dff15ca77d3c3e30091c141220f1de003345ef564472f4ff
|
3 |
+
size 5880
|