Upload 11 files
Browse files- checkpoint-500/README.md +202 -0
- checkpoint-500/adapter_config.json +34 -0
- checkpoint-500/adapter_model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +17 -0
- checkpoint-500/tokenizer.json +3 -0
- checkpoint-500/tokenizer_config.json +2063 -0
- checkpoint-500/trainer_state.json +3541 -0
- checkpoint-500/training_args.bin +3 -0
checkpoint-500/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 0.13.1
|
checkpoint-500/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
+
"o_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"up_proj",
|
28 |
+
"down_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8ba2d7f029121c75d91bcd93c72c4dd3f95c5f0bde261030c6899f69f0f5aec
|
3 |
+
size 671149168
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae9485d557eabbefe5584291e50bd38e98635ec088ad35b02ff240afc91f55ab
|
3 |
+
size 1342453498
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2d4aad86b5c10e940f14a56eef17ee3a225079a45c3188386d46b45132e42e2
|
3 |
+
size 1064
|
checkpoint-500/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-500/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c85066e7642934ed09b44155e6566b0b5dab2637fb9433439ba5c9c7f8b50d3
|
3 |
+
size 17210018
|
checkpoint-500/tokenizer_config.json
ADDED
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"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 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 131072,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,3541 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.07800464127615593,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.00015600928255231187,
|
13 |
+
"grad_norm": 0.5937075614929199,
|
14 |
+
"learning_rate": 2.666666666666667e-06,
|
15 |
+
"loss": 3.7681,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.00031201856510462375,
|
20 |
+
"grad_norm": 0.5836828947067261,
|
21 |
+
"learning_rate": 5.333333333333334e-06,
|
22 |
+
"loss": 3.8601,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.00046802784765693557,
|
27 |
+
"grad_norm": 0.6111788749694824,
|
28 |
+
"learning_rate": 8.000000000000001e-06,
|
29 |
+
"loss": 3.643,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0006240371302092475,
|
34 |
+
"grad_norm": 0.5807424783706665,
|
35 |
+
"learning_rate": 1.0666666666666667e-05,
|
36 |
+
"loss": 3.724,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.0007800464127615594,
|
41 |
+
"grad_norm": 0.5708947777748108,
|
42 |
+
"learning_rate": 1.3333333333333333e-05,
|
43 |
+
"loss": 3.9727,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0009360556953138711,
|
48 |
+
"grad_norm": 0.5662252902984619,
|
49 |
+
"learning_rate": 1.6000000000000003e-05,
|
50 |
+
"loss": 3.6801,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.001092064977866183,
|
55 |
+
"grad_norm": 0.5653729438781738,
|
56 |
+
"learning_rate": 1.866666666666667e-05,
|
57 |
+
"loss": 3.6898,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.001248074260418495,
|
62 |
+
"grad_norm": 0.5451233983039856,
|
63 |
+
"learning_rate": 2.1333333333333335e-05,
|
64 |
+
"loss": 3.5484,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.0014040835429708068,
|
69 |
+
"grad_norm": 0.5682435035705566,
|
70 |
+
"learning_rate": 2.4e-05,
|
71 |
+
"loss": 3.538,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.0015600928255231187,
|
76 |
+
"grad_norm": 0.6180667877197266,
|
77 |
+
"learning_rate": 2.6666666666666667e-05,
|
78 |
+
"loss": 3.6757,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.0017161021080754305,
|
83 |
+
"grad_norm": 0.6358373165130615,
|
84 |
+
"learning_rate": 2.9333333333333336e-05,
|
85 |
+
"loss": 3.6489,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.0018721113906277423,
|
90 |
+
"grad_norm": 0.6643233895301819,
|
91 |
+
"learning_rate": 3.2000000000000005e-05,
|
92 |
+
"loss": 3.4313,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.0020281206731800542,
|
97 |
+
"grad_norm": 0.6591399908065796,
|
98 |
+
"learning_rate": 3.466666666666667e-05,
|
99 |
+
"loss": 3.472,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.002184129955732366,
|
104 |
+
"grad_norm": 0.8929205536842346,
|
105 |
+
"learning_rate": 3.733333333333334e-05,
|
106 |
+
"loss": 3.3531,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.0023401392382846778,
|
111 |
+
"grad_norm": 1.2845464944839478,
|
112 |
+
"learning_rate": 4e-05,
|
113 |
+
"loss": 3.143,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.00249614852083699,
|
118 |
+
"grad_norm": 1.216373085975647,
|
119 |
+
"learning_rate": 4.266666666666667e-05,
|
120 |
+
"loss": 3.1297,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.0026521578033893017,
|
125 |
+
"grad_norm": 0.9192391633987427,
|
126 |
+
"learning_rate": 4.5333333333333335e-05,
|
127 |
+
"loss": 2.9826,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.0028081670859416135,
|
132 |
+
"grad_norm": 0.8917486667633057,
|
133 |
+
"learning_rate": 4.8e-05,
|
134 |
+
"loss": 2.9068,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.0029641763684939253,
|
139 |
+
"grad_norm": 0.7141512632369995,
|
140 |
+
"learning_rate": 5.0666666666666674e-05,
|
141 |
+
"loss": 2.7797,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.0031201856510462375,
|
146 |
+
"grad_norm": 0.8795380592346191,
|
147 |
+
"learning_rate": 5.333333333333333e-05,
|
148 |
+
"loss": 2.2265,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.0032761949335985492,
|
153 |
+
"grad_norm": 1.047784447669983,
|
154 |
+
"learning_rate": 5.6000000000000006e-05,
|
155 |
+
"loss": 2.6089,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.003432204216150861,
|
160 |
+
"grad_norm": 1.0959978103637695,
|
161 |
+
"learning_rate": 5.866666666666667e-05,
|
162 |
+
"loss": 2.3416,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.0035882134987031728,
|
167 |
+
"grad_norm": 1.283445954322815,
|
168 |
+
"learning_rate": 6.133333333333334e-05,
|
169 |
+
"loss": 2.0565,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.0037442227812554845,
|
174 |
+
"grad_norm": 1.655569314956665,
|
175 |
+
"learning_rate": 6.400000000000001e-05,
|
176 |
+
"loss": 1.6648,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.0039002320638077967,
|
181 |
+
"grad_norm": 1.4048818349838257,
|
182 |
+
"learning_rate": 6.666666666666667e-05,
|
183 |
+
"loss": 1.7566,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.0040562413463601085,
|
188 |
+
"grad_norm": 1.0755441188812256,
|
189 |
+
"learning_rate": 6.933333333333334e-05,
|
190 |
+
"loss": 1.6591,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.00421225062891242,
|
195 |
+
"grad_norm": 0.7240940928459167,
|
196 |
+
"learning_rate": 7.2e-05,
|
197 |
+
"loss": 2.21,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.004368259911464732,
|
202 |
+
"grad_norm": 0.48980680108070374,
|
203 |
+
"learning_rate": 7.466666666666667e-05,
|
204 |
+
"loss": 1.8157,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.004524269194017044,
|
209 |
+
"grad_norm": 0.4145239591598511,
|
210 |
+
"learning_rate": 7.733333333333333e-05,
|
211 |
+
"loss": 1.8679,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.0046802784765693555,
|
216 |
+
"grad_norm": 0.3905705213546753,
|
217 |
+
"learning_rate": 8e-05,
|
218 |
+
"loss": 1.5733,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.004836287759121667,
|
223 |
+
"grad_norm": 0.40969792008399963,
|
224 |
+
"learning_rate": 8.266666666666667e-05,
|
225 |
+
"loss": 1.531,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.00499229704167398,
|
230 |
+
"grad_norm": 0.4269125759601593,
|
231 |
+
"learning_rate": 8.533333333333334e-05,
|
232 |
+
"loss": 1.3705,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.005148306324226292,
|
237 |
+
"grad_norm": 0.5876020789146423,
|
238 |
+
"learning_rate": 8.800000000000001e-05,
|
239 |
+
"loss": 1.4055,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.0053043156067786035,
|
244 |
+
"grad_norm": 0.39753037691116333,
|
245 |
+
"learning_rate": 9.066666666666667e-05,
|
246 |
+
"loss": 1.5403,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.005460324889330915,
|
251 |
+
"grad_norm": 0.4157419800758362,
|
252 |
+
"learning_rate": 9.333333333333334e-05,
|
253 |
+
"loss": 1.5698,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.005616334171883227,
|
258 |
+
"grad_norm": 0.4430864155292511,
|
259 |
+
"learning_rate": 9.6e-05,
|
260 |
+
"loss": 1.5466,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.005772343454435539,
|
265 |
+
"grad_norm": 0.5259338021278381,
|
266 |
+
"learning_rate": 9.866666666666668e-05,
|
267 |
+
"loss": 1.5878,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.0059283527369878505,
|
272 |
+
"grad_norm": 0.4409235417842865,
|
273 |
+
"learning_rate": 0.00010133333333333335,
|
274 |
+
"loss": 1.4203,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.006084362019540162,
|
279 |
+
"grad_norm": 0.5432307124137878,
|
280 |
+
"learning_rate": 0.00010400000000000001,
|
281 |
+
"loss": 1.3843,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.006240371302092475,
|
286 |
+
"grad_norm": 0.5789123177528381,
|
287 |
+
"learning_rate": 0.00010666666666666667,
|
288 |
+
"loss": 1.4649,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.006396380584644787,
|
293 |
+
"grad_norm": 0.5596875548362732,
|
294 |
+
"learning_rate": 0.00010933333333333333,
|
295 |
+
"loss": 1.3569,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.0065523898671970985,
|
300 |
+
"grad_norm": 0.6517161726951599,
|
301 |
+
"learning_rate": 0.00011200000000000001,
|
302 |
+
"loss": 1.4306,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.00670839914974941,
|
307 |
+
"grad_norm": 0.7665486335754395,
|
308 |
+
"learning_rate": 0.00011466666666666667,
|
309 |
+
"loss": 1.5369,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.006864408432301722,
|
314 |
+
"grad_norm": 0.8421632647514343,
|
315 |
+
"learning_rate": 0.00011733333333333334,
|
316 |
+
"loss": 1.5651,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.007020417714854034,
|
321 |
+
"grad_norm": 0.8437005877494812,
|
322 |
+
"learning_rate": 0.00012,
|
323 |
+
"loss": 1.33,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.0071764269974063455,
|
328 |
+
"grad_norm": 0.3544560670852661,
|
329 |
+
"learning_rate": 0.00012266666666666668,
|
330 |
+
"loss": 1.5436,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.007332436279958657,
|
335 |
+
"grad_norm": 0.35725343227386475,
|
336 |
+
"learning_rate": 0.00012533333333333334,
|
337 |
+
"loss": 1.5792,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.007488445562510969,
|
342 |
+
"grad_norm": 0.7203790545463562,
|
343 |
+
"learning_rate": 0.00012800000000000002,
|
344 |
+
"loss": 1.6707,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.007644454845063282,
|
349 |
+
"grad_norm": 0.352791428565979,
|
350 |
+
"learning_rate": 0.00013066666666666668,
|
351 |
+
"loss": 1.5251,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.0078004641276155934,
|
356 |
+
"grad_norm": 0.49014368653297424,
|
357 |
+
"learning_rate": 0.00013333333333333334,
|
358 |
+
"loss": 1.3478,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.007956473410167905,
|
363 |
+
"grad_norm": 0.29890525341033936,
|
364 |
+
"learning_rate": 0.00013600000000000003,
|
365 |
+
"loss": 1.3164,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.008112482692720217,
|
370 |
+
"grad_norm": 0.34632885456085205,
|
371 |
+
"learning_rate": 0.00013866666666666669,
|
372 |
+
"loss": 1.3785,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.008268491975272529,
|
377 |
+
"grad_norm": 0.3631187677383423,
|
378 |
+
"learning_rate": 0.00014133333333333334,
|
379 |
+
"loss": 1.7873,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.00842450125782484,
|
384 |
+
"grad_norm": 0.290487140417099,
|
385 |
+
"learning_rate": 0.000144,
|
386 |
+
"loss": 1.1681,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.008580510540377152,
|
391 |
+
"grad_norm": 0.3136501610279083,
|
392 |
+
"learning_rate": 0.00014666666666666666,
|
393 |
+
"loss": 1.1332,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.008736519822929464,
|
398 |
+
"grad_norm": 0.3708946406841278,
|
399 |
+
"learning_rate": 0.00014933333333333335,
|
400 |
+
"loss": 1.4316,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.008892529105481776,
|
405 |
+
"grad_norm": 0.3645316958427429,
|
406 |
+
"learning_rate": 0.000152,
|
407 |
+
"loss": 1.3522,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.009048538388034088,
|
412 |
+
"grad_norm": 0.4074520170688629,
|
413 |
+
"learning_rate": 0.00015466666666666667,
|
414 |
+
"loss": 1.5344,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.0092045476705864,
|
419 |
+
"grad_norm": 0.3106740713119507,
|
420 |
+
"learning_rate": 0.00015733333333333333,
|
421 |
+
"loss": 1.2959,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.009360556953138711,
|
426 |
+
"grad_norm": 0.32623976469039917,
|
427 |
+
"learning_rate": 0.00016,
|
428 |
+
"loss": 1.6472,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.009516566235691023,
|
433 |
+
"grad_norm": 0.35396724939346313,
|
434 |
+
"learning_rate": 0.00016266666666666667,
|
435 |
+
"loss": 1.2655,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.009672575518243335,
|
440 |
+
"grad_norm": 0.3455830216407776,
|
441 |
+
"learning_rate": 0.00016533333333333333,
|
442 |
+
"loss": 1.2153,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.009828584800795648,
|
447 |
+
"grad_norm": 0.3116808235645294,
|
448 |
+
"learning_rate": 0.000168,
|
449 |
+
"loss": 1.0851,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.00998459408334796,
|
454 |
+
"grad_norm": 0.3416989743709564,
|
455 |
+
"learning_rate": 0.00017066666666666668,
|
456 |
+
"loss": 1.5828,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.010140603365900272,
|
461 |
+
"grad_norm": 0.3509654104709625,
|
462 |
+
"learning_rate": 0.00017333333333333334,
|
463 |
+
"loss": 1.4832,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.010296612648452583,
|
468 |
+
"grad_norm": 0.3034147322177887,
|
469 |
+
"learning_rate": 0.00017600000000000002,
|
470 |
+
"loss": 1.4326,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.010452621931004895,
|
475 |
+
"grad_norm": 0.3084355890750885,
|
476 |
+
"learning_rate": 0.00017866666666666668,
|
477 |
+
"loss": 1.2452,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.010608631213557207,
|
482 |
+
"grad_norm": 0.3001956343650818,
|
483 |
+
"learning_rate": 0.00018133333333333334,
|
484 |
+
"loss": 1.2484,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.010764640496109519,
|
489 |
+
"grad_norm": 0.30605360865592957,
|
490 |
+
"learning_rate": 0.00018400000000000003,
|
491 |
+
"loss": 1.2137,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.01092064977866183,
|
496 |
+
"grad_norm": 0.32967764139175415,
|
497 |
+
"learning_rate": 0.0001866666666666667,
|
498 |
+
"loss": 1.4,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.011076659061214142,
|
503 |
+
"grad_norm": 0.3161776661872864,
|
504 |
+
"learning_rate": 0.00018933333333333335,
|
505 |
+
"loss": 1.3203,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.011232668343766454,
|
510 |
+
"grad_norm": 0.28808867931365967,
|
511 |
+
"learning_rate": 0.000192,
|
512 |
+
"loss": 1.3034,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.011388677626318766,
|
517 |
+
"grad_norm": 0.2804367244243622,
|
518 |
+
"learning_rate": 0.0001946666666666667,
|
519 |
+
"loss": 1.2753,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.011544686908871078,
|
524 |
+
"grad_norm": 0.30980467796325684,
|
525 |
+
"learning_rate": 0.00019733333333333335,
|
526 |
+
"loss": 1.3733,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.01170069619142339,
|
531 |
+
"grad_norm": 0.31240588426589966,
|
532 |
+
"learning_rate": 0.0002,
|
533 |
+
"loss": 1.1602,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.011856705473975701,
|
538 |
+
"grad_norm": 0.28906041383743286,
|
539 |
+
"learning_rate": 0.00019999991608372393,
|
540 |
+
"loss": 1.3243,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.012012714756528013,
|
545 |
+
"grad_norm": 0.2740985155105591,
|
546 |
+
"learning_rate": 0.00019999966433503652,
|
547 |
+
"loss": 1.1853,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.012168724039080325,
|
552 |
+
"grad_norm": 0.30425482988357544,
|
553 |
+
"learning_rate": 0.0001999992447543603,
|
554 |
+
"loss": 1.3282,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.012324733321632636,
|
559 |
+
"grad_norm": 0.3216018080711365,
|
560 |
+
"learning_rate": 0.00019999865734239946,
|
561 |
+
"loss": 1.3696,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.01248074260418495,
|
566 |
+
"grad_norm": 0.34770438075065613,
|
567 |
+
"learning_rate": 0.00019999790210013988,
|
568 |
+
"loss": 1.261,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.012636751886737262,
|
573 |
+
"grad_norm": 0.3883892297744751,
|
574 |
+
"learning_rate": 0.0001999969790288491,
|
575 |
+
"loss": 1.5873,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.012792761169289573,
|
580 |
+
"grad_norm": 0.3061410188674927,
|
581 |
+
"learning_rate": 0.00019999588813007633,
|
582 |
+
"loss": 1.5559,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.012948770451841885,
|
587 |
+
"grad_norm": 0.3044775128364563,
|
588 |
+
"learning_rate": 0.00019999462940565243,
|
589 |
+
"loss": 1.2439,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.013104779734394197,
|
594 |
+
"grad_norm": 0.3562803864479065,
|
595 |
+
"learning_rate": 0.00019999320285769,
|
596 |
+
"loss": 1.4121,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.013260789016946509,
|
601 |
+
"grad_norm": 0.3367731273174286,
|
602 |
+
"learning_rate": 0.0001999916084885832,
|
603 |
+
"loss": 1.1937,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.01341679829949882,
|
608 |
+
"grad_norm": 0.3613661527633667,
|
609 |
+
"learning_rate": 0.00019998984630100792,
|
610 |
+
"loss": 1.4267,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.013572807582051132,
|
615 |
+
"grad_norm": 0.30924999713897705,
|
616 |
+
"learning_rate": 0.0001999879162979217,
|
617 |
+
"loss": 1.3358,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.013728816864603444,
|
622 |
+
"grad_norm": 0.34925562143325806,
|
623 |
+
"learning_rate": 0.0001999858184825637,
|
624 |
+
"loss": 1.3758,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.013884826147155756,
|
629 |
+
"grad_norm": 0.3182036280632019,
|
630 |
+
"learning_rate": 0.00019998355285845475,
|
631 |
+
"loss": 1.3151,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.014040835429708068,
|
636 |
+
"grad_norm": 0.6028950810432434,
|
637 |
+
"learning_rate": 0.0001999811194293973,
|
638 |
+
"loss": 1.3797,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.01419684471226038,
|
643 |
+
"grad_norm": 0.3221015930175781,
|
644 |
+
"learning_rate": 0.00019997851819947537,
|
645 |
+
"loss": 1.3293,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.014352853994812691,
|
650 |
+
"grad_norm": 0.3003532290458679,
|
651 |
+
"learning_rate": 0.00019997574917305478,
|
652 |
+
"loss": 1.5671,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.014508863277365003,
|
657 |
+
"grad_norm": 0.32144418358802795,
|
658 |
+
"learning_rate": 0.00019997281235478278,
|
659 |
+
"loss": 1.3733,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.014664872559917315,
|
664 |
+
"grad_norm": 1.3427015542984009,
|
665 |
+
"learning_rate": 0.00019996970774958836,
|
666 |
+
"loss": 1.246,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.014820881842469626,
|
671 |
+
"grad_norm": 0.3254302144050598,
|
672 |
+
"learning_rate": 0.00019996643536268204,
|
673 |
+
"loss": 1.3829,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.014976891125021938,
|
678 |
+
"grad_norm": 0.2829325795173645,
|
679 |
+
"learning_rate": 0.0001999629951995559,
|
680 |
+
"loss": 1.2176,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.01513290040757425,
|
685 |
+
"grad_norm": 0.2943004071712494,
|
686 |
+
"learning_rate": 0.00019995938726598373,
|
687 |
+
"loss": 1.4021,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.015288909690126563,
|
692 |
+
"grad_norm": 0.2698727548122406,
|
693 |
+
"learning_rate": 0.00019995561156802079,
|
694 |
+
"loss": 1.2897,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.015444918972678875,
|
699 |
+
"grad_norm": 0.32416194677352905,
|
700 |
+
"learning_rate": 0.0001999516681120039,
|
701 |
+
"loss": 1.218,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.015600928255231187,
|
706 |
+
"grad_norm": 0.3309131860733032,
|
707 |
+
"learning_rate": 0.00019994755690455152,
|
708 |
+
"loss": 1.4658,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.015756937537783497,
|
713 |
+
"grad_norm": 0.31126394867897034,
|
714 |
+
"learning_rate": 0.0001999432779525635,
|
715 |
+
"loss": 1.5518,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.01591294682033581,
|
720 |
+
"grad_norm": 0.28427934646606445,
|
721 |
+
"learning_rate": 0.0001999388312632214,
|
722 |
+
"loss": 1.1435,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.01606895610288812,
|
727 |
+
"grad_norm": 0.28065958619117737,
|
728 |
+
"learning_rate": 0.00019993421684398824,
|
729 |
+
"loss": 1.3537,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.016224965385440434,
|
734 |
+
"grad_norm": 0.3787417411804199,
|
735 |
+
"learning_rate": 0.00019992943470260844,
|
736 |
+
"loss": 1.2151,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.016380974667992744,
|
741 |
+
"grad_norm": 0.32704487442970276,
|
742 |
+
"learning_rate": 0.00019992448484710797,
|
743 |
+
"loss": 1.1383,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.016536983950545057,
|
748 |
+
"grad_norm": 0.34436190128326416,
|
749 |
+
"learning_rate": 0.00019991936728579437,
|
750 |
+
"loss": 1.3949,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.01669299323309737,
|
755 |
+
"grad_norm": 0.29938092827796936,
|
756 |
+
"learning_rate": 0.00019991408202725655,
|
757 |
+
"loss": 1.2821,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.01684900251564968,
|
762 |
+
"grad_norm": 0.3192508816719055,
|
763 |
+
"learning_rate": 0.0001999086290803649,
|
764 |
+
"loss": 1.3655,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.017005011798201995,
|
769 |
+
"grad_norm": 0.2626635730266571,
|
770 |
+
"learning_rate": 0.00019990300845427125,
|
771 |
+
"loss": 1.2366,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.017161021080754305,
|
776 |
+
"grad_norm": 0.288725882768631,
|
777 |
+
"learning_rate": 0.0001998972201584088,
|
778 |
+
"loss": 1.0589,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.017317030363306618,
|
783 |
+
"grad_norm": 0.3340204358100891,
|
784 |
+
"learning_rate": 0.00019989126420249221,
|
785 |
+
"loss": 1.7077,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.017473039645858928,
|
790 |
+
"grad_norm": 0.27165043354034424,
|
791 |
+
"learning_rate": 0.00019988514059651752,
|
792 |
+
"loss": 1.3596,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.01762904892841124,
|
797 |
+
"grad_norm": 0.2751217186450958,
|
798 |
+
"learning_rate": 0.00019987884935076213,
|
799 |
+
"loss": 1.281,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.01778505821096355,
|
804 |
+
"grad_norm": 0.2712443172931671,
|
805 |
+
"learning_rate": 0.00019987239047578482,
|
806 |
+
"loss": 1.2686,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.017941067493515865,
|
811 |
+
"grad_norm": 0.2898474931716919,
|
812 |
+
"learning_rate": 0.00019986576398242566,
|
813 |
+
"loss": 1.2425,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.018097076776068175,
|
818 |
+
"grad_norm": 0.29883307218551636,
|
819 |
+
"learning_rate": 0.00019985896988180605,
|
820 |
+
"loss": 1.6326,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.01825308605862049,
|
825 |
+
"grad_norm": 0.2548903524875641,
|
826 |
+
"learning_rate": 0.00019985200818532875,
|
827 |
+
"loss": 1.317,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.0184090953411728,
|
832 |
+
"grad_norm": 0.260768860578537,
|
833 |
+
"learning_rate": 0.0001998448789046777,
|
834 |
+
"loss": 1.4137,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.018565104623725112,
|
839 |
+
"grad_norm": 0.27813923358917236,
|
840 |
+
"learning_rate": 0.00019983758205181822,
|
841 |
+
"loss": 1.1758,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.018721113906277422,
|
846 |
+
"grad_norm": 0.29539602994918823,
|
847 |
+
"learning_rate": 0.00019983011763899673,
|
848 |
+
"loss": 1.2805,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.018877123188829736,
|
853 |
+
"grad_norm": 0.2691763937473297,
|
854 |
+
"learning_rate": 0.00019982248567874098,
|
855 |
+
"loss": 1.3098,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.019033132471382046,
|
860 |
+
"grad_norm": 0.2895521819591522,
|
861 |
+
"learning_rate": 0.00019981468618385988,
|
862 |
+
"loss": 1.1475,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.01918914175393436,
|
867 |
+
"grad_norm": 0.24555402994155884,
|
868 |
+
"learning_rate": 0.00019980671916744352,
|
869 |
+
"loss": 1.075,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.01934515103648667,
|
874 |
+
"grad_norm": 0.29935726523399353,
|
875 |
+
"learning_rate": 0.00019979858464286317,
|
876 |
+
"loss": 1.278,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.019501160319038983,
|
881 |
+
"grad_norm": 0.3469449579715729,
|
882 |
+
"learning_rate": 0.00019979028262377118,
|
883 |
+
"loss": 1.602,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.019657169601591296,
|
888 |
+
"grad_norm": 0.2707567811012268,
|
889 |
+
"learning_rate": 0.00019978181312410104,
|
890 |
+
"loss": 1.3181,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.019813178884143606,
|
895 |
+
"grad_norm": 0.32349273562431335,
|
896 |
+
"learning_rate": 0.00019977317615806737,
|
897 |
+
"loss": 1.4862,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.01996918816669592,
|
902 |
+
"grad_norm": 0.24527911841869354,
|
903 |
+
"learning_rate": 0.00019976437174016573,
|
904 |
+
"loss": 1.169,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.02012519744924823,
|
909 |
+
"grad_norm": 0.2882062494754791,
|
910 |
+
"learning_rate": 0.00019975539988517288,
|
911 |
+
"loss": 1.275,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.020281206731800543,
|
916 |
+
"grad_norm": 0.3206437826156616,
|
917 |
+
"learning_rate": 0.00019974626060814647,
|
918 |
+
"loss": 1.682,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.020437216014352853,
|
923 |
+
"grad_norm": 0.3423447012901306,
|
924 |
+
"learning_rate": 0.0001997369539244252,
|
925 |
+
"loss": 1.2018,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.020593225296905167,
|
930 |
+
"grad_norm": 0.29081955552101135,
|
931 |
+
"learning_rate": 0.0001997274798496287,
|
932 |
+
"loss": 1.5849,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.020749234579457477,
|
937 |
+
"grad_norm": 0.2659798860549927,
|
938 |
+
"learning_rate": 0.00019971783839965756,
|
939 |
+
"loss": 1.1371,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.02090524386200979,
|
944 |
+
"grad_norm": 0.3395417034626007,
|
945 |
+
"learning_rate": 0.00019970802959069328,
|
946 |
+
"loss": 1.5046,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.0210612531445621,
|
951 |
+
"grad_norm": 0.22527103126049042,
|
952 |
+
"learning_rate": 0.00019969805343919821,
|
953 |
+
"loss": 1.0543,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.021217262427114414,
|
958 |
+
"grad_norm": 0.30680522322654724,
|
959 |
+
"learning_rate": 0.0001996879099619156,
|
960 |
+
"loss": 1.5067,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.021373271709666724,
|
965 |
+
"grad_norm": 0.22828875482082367,
|
966 |
+
"learning_rate": 0.00019967759917586953,
|
967 |
+
"loss": 1.1201,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.021529280992219037,
|
972 |
+
"grad_norm": 0.2578384280204773,
|
973 |
+
"learning_rate": 0.00019966712109836476,
|
974 |
+
"loss": 1.104,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.021685290274771347,
|
979 |
+
"grad_norm": 0.23175813257694244,
|
980 |
+
"learning_rate": 0.000199656475746987,
|
981 |
+
"loss": 0.9706,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.02184129955732366,
|
986 |
+
"grad_norm": 0.29308339953422546,
|
987 |
+
"learning_rate": 0.00019964566313960264,
|
988 |
+
"loss": 1.4769,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.02199730883987597,
|
993 |
+
"grad_norm": 0.3059382438659668,
|
994 |
+
"learning_rate": 0.0001996346832943587,
|
995 |
+
"loss": 1.4555,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.022153318122428284,
|
1000 |
+
"grad_norm": 0.2929370701313019,
|
1001 |
+
"learning_rate": 0.00019962353622968295,
|
1002 |
+
"loss": 1.4051,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.022309327404980598,
|
1007 |
+
"grad_norm": 0.24365079402923584,
|
1008 |
+
"learning_rate": 0.00019961222196428378,
|
1009 |
+
"loss": 1.189,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.022465336687532908,
|
1014 |
+
"grad_norm": 0.27418485283851624,
|
1015 |
+
"learning_rate": 0.0001996007405171502,
|
1016 |
+
"loss": 1.206,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.02262134597008522,
|
1021 |
+
"grad_norm": 0.2554856836795807,
|
1022 |
+
"learning_rate": 0.00019958909190755187,
|
1023 |
+
"loss": 1.4053,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.02277735525263753,
|
1028 |
+
"grad_norm": 0.2674770951271057,
|
1029 |
+
"learning_rate": 0.00019957727615503888,
|
1030 |
+
"loss": 1.2412,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.022933364535189845,
|
1035 |
+
"grad_norm": 0.3177204728126526,
|
1036 |
+
"learning_rate": 0.00019956529327944198,
|
1037 |
+
"loss": 1.4231,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.023089373817742155,
|
1042 |
+
"grad_norm": 0.2678688168525696,
|
1043 |
+
"learning_rate": 0.00019955314330087225,
|
1044 |
+
"loss": 1.2494,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.02324538310029447,
|
1049 |
+
"grad_norm": 0.28164568543434143,
|
1050 |
+
"learning_rate": 0.00019954082623972142,
|
1051 |
+
"loss": 1.2008,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.02340139238284678,
|
1056 |
+
"grad_norm": 0.2897564172744751,
|
1057 |
+
"learning_rate": 0.0001995283421166614,
|
1058 |
+
"loss": 1.463,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.023557401665399092,
|
1063 |
+
"grad_norm": 0.276509165763855,
|
1064 |
+
"learning_rate": 0.00019951569095264473,
|
1065 |
+
"loss": 1.4891,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.023713410947951402,
|
1070 |
+
"grad_norm": 0.2585453689098358,
|
1071 |
+
"learning_rate": 0.0001995028727689041,
|
1072 |
+
"loss": 1.1551,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.023869420230503716,
|
1077 |
+
"grad_norm": 0.25659292936325073,
|
1078 |
+
"learning_rate": 0.00019948988758695263,
|
1079 |
+
"loss": 1.1622,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.024025429513056026,
|
1084 |
+
"grad_norm": 0.27132928371429443,
|
1085 |
+
"learning_rate": 0.00019947673542858367,
|
1086 |
+
"loss": 1.2015,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.02418143879560834,
|
1091 |
+
"grad_norm": 0.2951599955558777,
|
1092 |
+
"learning_rate": 0.00019946341631587087,
|
1093 |
+
"loss": 1.1842,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.02433744807816065,
|
1098 |
+
"grad_norm": 0.3114786148071289,
|
1099 |
+
"learning_rate": 0.00019944993027116797,
|
1100 |
+
"loss": 1.4509,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.024493457360712963,
|
1105 |
+
"grad_norm": 0.25183674693107605,
|
1106 |
+
"learning_rate": 0.00019943627731710897,
|
1107 |
+
"loss": 1.1474,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.024649466643265273,
|
1112 |
+
"grad_norm": 0.2717629075050354,
|
1113 |
+
"learning_rate": 0.00019942245747660796,
|
1114 |
+
"loss": 1.2899,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.024805475925817586,
|
1119 |
+
"grad_norm": 0.2532605826854706,
|
1120 |
+
"learning_rate": 0.00019940847077285916,
|
1121 |
+
"loss": 1.0811,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.0249614852083699,
|
1126 |
+
"grad_norm": 0.2951716482639313,
|
1127 |
+
"learning_rate": 0.0001993943172293368,
|
1128 |
+
"loss": 1.6252,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.02511749449092221,
|
1133 |
+
"grad_norm": 0.29894542694091797,
|
1134 |
+
"learning_rate": 0.0001993799968697951,
|
1135 |
+
"loss": 1.3754,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.025273503773474523,
|
1140 |
+
"grad_norm": 0.28648853302001953,
|
1141 |
+
"learning_rate": 0.00019936550971826834,
|
1142 |
+
"loss": 1.2769,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.025429513056026833,
|
1147 |
+
"grad_norm": 0.2540144920349121,
|
1148 |
+
"learning_rate": 0.00019935085579907063,
|
1149 |
+
"loss": 1.281,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.025585522338579147,
|
1154 |
+
"grad_norm": 0.30044910311698914,
|
1155 |
+
"learning_rate": 0.00019933603513679605,
|
1156 |
+
"loss": 1.1689,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.025741531621131457,
|
1161 |
+
"grad_norm": 0.31799909472465515,
|
1162 |
+
"learning_rate": 0.00019932104775631846,
|
1163 |
+
"loss": 1.287,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.02589754090368377,
|
1168 |
+
"grad_norm": 0.290565550327301,
|
1169 |
+
"learning_rate": 0.0001993058936827916,
|
1170 |
+
"loss": 1.4751,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.02605355018623608,
|
1175 |
+
"grad_norm": 0.28967443108558655,
|
1176 |
+
"learning_rate": 0.00019929057294164893,
|
1177 |
+
"loss": 1.2459,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.026209559468788394,
|
1182 |
+
"grad_norm": 0.25141966342926025,
|
1183 |
+
"learning_rate": 0.0001992750855586036,
|
1184 |
+
"loss": 1.1215,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.026365568751340704,
|
1189 |
+
"grad_norm": 0.2819644808769226,
|
1190 |
+
"learning_rate": 0.00019925943155964856,
|
1191 |
+
"loss": 1.5238,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.026521578033893017,
|
1196 |
+
"grad_norm": 0.2336016446352005,
|
1197 |
+
"learning_rate": 0.00019924361097105623,
|
1198 |
+
"loss": 1.2218,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.026677587316445327,
|
1203 |
+
"grad_norm": 0.23773479461669922,
|
1204 |
+
"learning_rate": 0.00019922762381937878,
|
1205 |
+
"loss": 1.0842,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.02683359659899764,
|
1210 |
+
"grad_norm": 0.266222208738327,
|
1211 |
+
"learning_rate": 0.0001992114701314478,
|
1212 |
+
"loss": 1.2076,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.02698960588154995,
|
1217 |
+
"grad_norm": 0.29275181889533997,
|
1218 |
+
"learning_rate": 0.00019919514993437445,
|
1219 |
+
"loss": 1.3901,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.027145615164102264,
|
1224 |
+
"grad_norm": 0.2334383726119995,
|
1225 |
+
"learning_rate": 0.00019917866325554938,
|
1226 |
+
"loss": 1.2012,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.027301624446654574,
|
1231 |
+
"grad_norm": 0.293888121843338,
|
1232 |
+
"learning_rate": 0.00019916201012264254,
|
1233 |
+
"loss": 1.6131,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.027457633729206888,
|
1238 |
+
"grad_norm": 0.3042750954627991,
|
1239 |
+
"learning_rate": 0.0001991451905636033,
|
1240 |
+
"loss": 1.3144,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.027613643011759198,
|
1245 |
+
"grad_norm": 0.2652626633644104,
|
1246 |
+
"learning_rate": 0.00019912820460666044,
|
1247 |
+
"loss": 1.4368,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.02776965229431151,
|
1252 |
+
"grad_norm": 0.28741374611854553,
|
1253 |
+
"learning_rate": 0.00019911105228032186,
|
1254 |
+
"loss": 1.4643,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.027925661576863825,
|
1259 |
+
"grad_norm": 0.2808038890361786,
|
1260 |
+
"learning_rate": 0.00019909373361337476,
|
1261 |
+
"loss": 1.3013,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.028081670859416135,
|
1266 |
+
"grad_norm": 0.22930848598480225,
|
1267 |
+
"learning_rate": 0.0001990762486348855,
|
1268 |
+
"loss": 1.0587,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.02823768014196845,
|
1273 |
+
"grad_norm": 0.24289073050022125,
|
1274 |
+
"learning_rate": 0.00019905859737419956,
|
1275 |
+
"loss": 1.1174,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.02839368942452076,
|
1280 |
+
"grad_norm": 0.2626672685146332,
|
1281 |
+
"learning_rate": 0.00019904077986094152,
|
1282 |
+
"loss": 1.1746,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.028549698707073072,
|
1287 |
+
"grad_norm": 0.3174870014190674,
|
1288 |
+
"learning_rate": 0.00019902279612501493,
|
1289 |
+
"loss": 1.4464,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.028705707989625382,
|
1294 |
+
"grad_norm": 0.2851637303829193,
|
1295 |
+
"learning_rate": 0.0001990046461966024,
|
1296 |
+
"loss": 1.3527,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.028861717272177696,
|
1301 |
+
"grad_norm": 0.2576538622379303,
|
1302 |
+
"learning_rate": 0.00019898633010616542,
|
1303 |
+
"loss": 1.2546,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.029017726554730006,
|
1308 |
+
"grad_norm": 0.2922312319278717,
|
1309 |
+
"learning_rate": 0.0001989678478844443,
|
1310 |
+
"loss": 1.1445,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.02917373583728232,
|
1315 |
+
"grad_norm": 0.25312724709510803,
|
1316 |
+
"learning_rate": 0.00019894919956245824,
|
1317 |
+
"loss": 1.0533,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.02932974511983463,
|
1322 |
+
"grad_norm": 0.3193413019180298,
|
1323 |
+
"learning_rate": 0.00019893038517150525,
|
1324 |
+
"loss": 1.655,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.029485754402386943,
|
1329 |
+
"grad_norm": 0.26104092597961426,
|
1330 |
+
"learning_rate": 0.00019891140474316194,
|
1331 |
+
"loss": 1.5094,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.029641763684939253,
|
1336 |
+
"grad_norm": 0.2679871916770935,
|
1337 |
+
"learning_rate": 0.00019889225830928365,
|
1338 |
+
"loss": 1.3535,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.029797772967491566,
|
1343 |
+
"grad_norm": 0.2835332751274109,
|
1344 |
+
"learning_rate": 0.00019887294590200435,
|
1345 |
+
"loss": 1.647,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.029953782250043876,
|
1350 |
+
"grad_norm": 0.2309991866350174,
|
1351 |
+
"learning_rate": 0.00019885346755373656,
|
1352 |
+
"loss": 1.1869,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.03010979153259619,
|
1357 |
+
"grad_norm": 0.28801408410072327,
|
1358 |
+
"learning_rate": 0.00019883382329717128,
|
1359 |
+
"loss": 1.4037,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.0302658008151485,
|
1364 |
+
"grad_norm": 0.309851735830307,
|
1365 |
+
"learning_rate": 0.00019881401316527793,
|
1366 |
+
"loss": 1.2832,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.030421810097700813,
|
1371 |
+
"grad_norm": 0.27529048919677734,
|
1372 |
+
"learning_rate": 0.0001987940371913044,
|
1373 |
+
"loss": 1.5466,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.030577819380253127,
|
1378 |
+
"grad_norm": 0.25759854912757874,
|
1379 |
+
"learning_rate": 0.00019877389540877687,
|
1380 |
+
"loss": 1.2432,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.030733828662805437,
|
1385 |
+
"grad_norm": 0.27557173371315,
|
1386 |
+
"learning_rate": 0.0001987535878514998,
|
1387 |
+
"loss": 1.5681,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.03088983794535775,
|
1392 |
+
"grad_norm": 0.25760918855667114,
|
1393 |
+
"learning_rate": 0.0001987331145535559,
|
1394 |
+
"loss": 1.3067,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.03104584722791006,
|
1399 |
+
"grad_norm": 0.299180269241333,
|
1400 |
+
"learning_rate": 0.000198712475549306,
|
1401 |
+
"loss": 1.4642,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.031201856510462374,
|
1406 |
+
"grad_norm": 0.2398681640625,
|
1407 |
+
"learning_rate": 0.00019869167087338907,
|
1408 |
+
"loss": 1.0748,
|
1409 |
+
"step": 200
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.03135786579301469,
|
1413 |
+
"grad_norm": 0.2560211420059204,
|
1414 |
+
"learning_rate": 0.00019867070056072214,
|
1415 |
+
"loss": 1.2508,
|
1416 |
+
"step": 201
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.031513875075566994,
|
1420 |
+
"grad_norm": 0.25509408116340637,
|
1421 |
+
"learning_rate": 0.00019864956464650025,
|
1422 |
+
"loss": 1.4073,
|
1423 |
+
"step": 202
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.03166988435811931,
|
1427 |
+
"grad_norm": 0.27500587701797485,
|
1428 |
+
"learning_rate": 0.00019862826316619628,
|
1429 |
+
"loss": 1.3473,
|
1430 |
+
"step": 203
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.03182589364067162,
|
1434 |
+
"grad_norm": 0.2923906445503235,
|
1435 |
+
"learning_rate": 0.0001986067961555611,
|
1436 |
+
"loss": 1.4293,
|
1437 |
+
"step": 204
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.031981902923223934,
|
1441 |
+
"grad_norm": 0.24456267058849335,
|
1442 |
+
"learning_rate": 0.00019858516365062334,
|
1443 |
+
"loss": 1.2196,
|
1444 |
+
"step": 205
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.03213791220577624,
|
1448 |
+
"grad_norm": 0.3021962344646454,
|
1449 |
+
"learning_rate": 0.00019856336568768935,
|
1450 |
+
"loss": 1.5066,
|
1451 |
+
"step": 206
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.032293921488328554,
|
1455 |
+
"grad_norm": 0.2485729455947876,
|
1456 |
+
"learning_rate": 0.00019854140230334322,
|
1457 |
+
"loss": 1.2002,
|
1458 |
+
"step": 207
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.03244993077088087,
|
1462 |
+
"grad_norm": 0.26055216789245605,
|
1463 |
+
"learning_rate": 0.0001985192735344467,
|
1464 |
+
"loss": 1.3207,
|
1465 |
+
"step": 208
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.03260594005343318,
|
1469 |
+
"grad_norm": 0.2658592760562897,
|
1470 |
+
"learning_rate": 0.00019849697941813898,
|
1471 |
+
"loss": 0.9025,
|
1472 |
+
"step": 209
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.03276194933598549,
|
1476 |
+
"grad_norm": 0.30481112003326416,
|
1477 |
+
"learning_rate": 0.00019847451999183694,
|
1478 |
+
"loss": 1.5238,
|
1479 |
+
"step": 210
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.0329179586185378,
|
1483 |
+
"grad_norm": 0.28382736444473267,
|
1484 |
+
"learning_rate": 0.00019845189529323475,
|
1485 |
+
"loss": 1.3224,
|
1486 |
+
"step": 211
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.033073967901090115,
|
1490 |
+
"grad_norm": 0.2757686972618103,
|
1491 |
+
"learning_rate": 0.00019842910536030403,
|
1492 |
+
"loss": 1.3672,
|
1493 |
+
"step": 212
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.03322997718364243,
|
1497 |
+
"grad_norm": 0.2743508219718933,
|
1498 |
+
"learning_rate": 0.00019840615023129372,
|
1499 |
+
"loss": 1.3628,
|
1500 |
+
"step": 213
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.03338598646619474,
|
1504 |
+
"grad_norm": 0.26412197947502136,
|
1505 |
+
"learning_rate": 0.00019838302994472997,
|
1506 |
+
"loss": 1.141,
|
1507 |
+
"step": 214
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.03354199574874705,
|
1511 |
+
"grad_norm": 0.2859683632850647,
|
1512 |
+
"learning_rate": 0.0001983597445394162,
|
1513 |
+
"loss": 1.1566,
|
1514 |
+
"step": 215
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.03369800503129936,
|
1518 |
+
"grad_norm": 0.24881964921951294,
|
1519 |
+
"learning_rate": 0.00019833629405443284,
|
1520 |
+
"loss": 1.2038,
|
1521 |
+
"step": 216
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.033854014313851676,
|
1525 |
+
"grad_norm": 0.25597479939460754,
|
1526 |
+
"learning_rate": 0.0001983126785291375,
|
1527 |
+
"loss": 0.9913,
|
1528 |
+
"step": 217
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.03401002359640399,
|
1532 |
+
"grad_norm": 0.26771095395088196,
|
1533 |
+
"learning_rate": 0.00019828889800316466,
|
1534 |
+
"loss": 1.5417,
|
1535 |
+
"step": 218
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.034166032878956296,
|
1539 |
+
"grad_norm": 0.2678371071815491,
|
1540 |
+
"learning_rate": 0.00019826495251642578,
|
1541 |
+
"loss": 1.208,
|
1542 |
+
"step": 219
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.03432204216150861,
|
1546 |
+
"grad_norm": 0.2947763204574585,
|
1547 |
+
"learning_rate": 0.00019824084210910925,
|
1548 |
+
"loss": 1.3908,
|
1549 |
+
"step": 220
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.03447805144406092,
|
1553 |
+
"grad_norm": 0.2821643650531769,
|
1554 |
+
"learning_rate": 0.00019821656682168012,
|
1555 |
+
"loss": 1.6573,
|
1556 |
+
"step": 221
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.034634060726613236,
|
1560 |
+
"grad_norm": 0.24507346749305725,
|
1561 |
+
"learning_rate": 0.00019819212669488026,
|
1562 |
+
"loss": 1.0647,
|
1563 |
+
"step": 222
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.03479007000916554,
|
1567 |
+
"grad_norm": 0.2718466520309448,
|
1568 |
+
"learning_rate": 0.00019816752176972813,
|
1569 |
+
"loss": 1.3013,
|
1570 |
+
"step": 223
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.034946079291717856,
|
1574 |
+
"grad_norm": 0.2902746796607971,
|
1575 |
+
"learning_rate": 0.0001981427520875188,
|
1576 |
+
"loss": 1.2212,
|
1577 |
+
"step": 224
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.03510208857427017,
|
1581 |
+
"grad_norm": 0.25822389125823975,
|
1582 |
+
"learning_rate": 0.0001981178176898239,
|
1583 |
+
"loss": 1.4543,
|
1584 |
+
"step": 225
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.03525809785682248,
|
1588 |
+
"grad_norm": 0.3506292700767517,
|
1589 |
+
"learning_rate": 0.00019809271861849145,
|
1590 |
+
"loss": 1.8549,
|
1591 |
+
"step": 226
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.03541410713937479,
|
1595 |
+
"grad_norm": 0.2610777020454407,
|
1596 |
+
"learning_rate": 0.00019806745491564586,
|
1597 |
+
"loss": 1.3161,
|
1598 |
+
"step": 227
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.0355701164219271,
|
1602 |
+
"grad_norm": 0.29803603887557983,
|
1603 |
+
"learning_rate": 0.0001980420266236878,
|
1604 |
+
"loss": 1.2983,
|
1605 |
+
"step": 228
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.03572612570447942,
|
1609 |
+
"grad_norm": 0.24572676420211792,
|
1610 |
+
"learning_rate": 0.0001980164337852943,
|
1611 |
+
"loss": 1.291,
|
1612 |
+
"step": 229
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.03588213498703173,
|
1616 |
+
"grad_norm": 0.25573092699050903,
|
1617 |
+
"learning_rate": 0.00019799067644341844,
|
1618 |
+
"loss": 1.3207,
|
1619 |
+
"step": 230
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.036038144269584044,
|
1623 |
+
"grad_norm": 0.28766271471977234,
|
1624 |
+
"learning_rate": 0.00019796475464128942,
|
1625 |
+
"loss": 1.4527,
|
1626 |
+
"step": 231
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.03619415355213635,
|
1630 |
+
"grad_norm": 0.2636454701423645,
|
1631 |
+
"learning_rate": 0.00019793866842241243,
|
1632 |
+
"loss": 1.3899,
|
1633 |
+
"step": 232
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.036350162834688664,
|
1637 |
+
"grad_norm": 0.3094368577003479,
|
1638 |
+
"learning_rate": 0.00019791241783056874,
|
1639 |
+
"loss": 1.2935,
|
1640 |
+
"step": 233
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.03650617211724098,
|
1644 |
+
"grad_norm": 0.2588469088077545,
|
1645 |
+
"learning_rate": 0.00019788600290981525,
|
1646 |
+
"loss": 1.2457,
|
1647 |
+
"step": 234
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.03666218139979329,
|
1651 |
+
"grad_norm": 0.26457706093788147,
|
1652 |
+
"learning_rate": 0.0001978594237044849,
|
1653 |
+
"loss": 1.1753,
|
1654 |
+
"step": 235
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.0368181906823456,
|
1658 |
+
"grad_norm": 0.2559141516685486,
|
1659 |
+
"learning_rate": 0.0001978326802591862,
|
1660 |
+
"loss": 1.2004,
|
1661 |
+
"step": 236
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.03697419996489791,
|
1665 |
+
"grad_norm": 0.2815738320350647,
|
1666 |
+
"learning_rate": 0.00019780577261880336,
|
1667 |
+
"loss": 1.3706,
|
1668 |
+
"step": 237
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.037130209247450224,
|
1672 |
+
"grad_norm": 0.2584588825702667,
|
1673 |
+
"learning_rate": 0.0001977787008284962,
|
1674 |
+
"loss": 1.4192,
|
1675 |
+
"step": 238
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.03728621853000254,
|
1679 |
+
"grad_norm": 0.290865421295166,
|
1680 |
+
"learning_rate": 0.00019775146493369994,
|
1681 |
+
"loss": 1.2308,
|
1682 |
+
"step": 239
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.037442227812554844,
|
1686 |
+
"grad_norm": 0.2788088023662567,
|
1687 |
+
"learning_rate": 0.0001977240649801253,
|
1688 |
+
"loss": 1.2095,
|
1689 |
+
"step": 240
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.03759823709510716,
|
1693 |
+
"grad_norm": 0.28903988003730774,
|
1694 |
+
"learning_rate": 0.00019769650101375837,
|
1695 |
+
"loss": 1.5138,
|
1696 |
+
"step": 241
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.03775424637765947,
|
1700 |
+
"grad_norm": 0.29985305666923523,
|
1701 |
+
"learning_rate": 0.00019766877308086036,
|
1702 |
+
"loss": 1.4594,
|
1703 |
+
"step": 242
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.037910255660211785,
|
1707 |
+
"grad_norm": 0.3033303916454315,
|
1708 |
+
"learning_rate": 0.00019764088122796783,
|
1709 |
+
"loss": 1.6108,
|
1710 |
+
"step": 243
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.03806626494276409,
|
1714 |
+
"grad_norm": 0.2854767143726349,
|
1715 |
+
"learning_rate": 0.0001976128255018924,
|
1716 |
+
"loss": 1.377,
|
1717 |
+
"step": 244
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.038222274225316405,
|
1721 |
+
"grad_norm": 0.30725011229515076,
|
1722 |
+
"learning_rate": 0.00019758460594972068,
|
1723 |
+
"loss": 1.2651,
|
1724 |
+
"step": 245
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.03837828350786872,
|
1728 |
+
"grad_norm": 0.28218191862106323,
|
1729 |
+
"learning_rate": 0.00019755622261881427,
|
1730 |
+
"loss": 1.4354,
|
1731 |
+
"step": 246
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.03853429279042103,
|
1735 |
+
"grad_norm": 0.2794611155986786,
|
1736 |
+
"learning_rate": 0.00019752767555680968,
|
1737 |
+
"loss": 1.4666,
|
1738 |
+
"step": 247
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.03869030207297334,
|
1742 |
+
"grad_norm": 0.2824796736240387,
|
1743 |
+
"learning_rate": 0.00019749896481161808,
|
1744 |
+
"loss": 1.3645,
|
1745 |
+
"step": 248
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.03884631135552565,
|
1749 |
+
"grad_norm": 0.26165372133255005,
|
1750 |
+
"learning_rate": 0.00019747009043142555,
|
1751 |
+
"loss": 1.3445,
|
1752 |
+
"step": 249
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.039002320638077966,
|
1756 |
+
"grad_norm": 0.29985979199409485,
|
1757 |
+
"learning_rate": 0.00019744105246469263,
|
1758 |
+
"loss": 1.4558,
|
1759 |
+
"step": 250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.03915832992063028,
|
1763 |
+
"grad_norm": 0.25439903140068054,
|
1764 |
+
"learning_rate": 0.00019741185096015448,
|
1765 |
+
"loss": 1.1075,
|
1766 |
+
"step": 251
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.03931433920318259,
|
1770 |
+
"grad_norm": 0.2533755898475647,
|
1771 |
+
"learning_rate": 0.00019738248596682078,
|
1772 |
+
"loss": 1.0891,
|
1773 |
+
"step": 252
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.0394703484857349,
|
1777 |
+
"grad_norm": 0.27487608790397644,
|
1778 |
+
"learning_rate": 0.0001973529575339755,
|
1779 |
+
"loss": 1.3128,
|
1780 |
+
"step": 253
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 0.03962635776828721,
|
1784 |
+
"grad_norm": 0.27824172377586365,
|
1785 |
+
"learning_rate": 0.00019732326571117703,
|
1786 |
+
"loss": 1.4045,
|
1787 |
+
"step": 254
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 0.039782367050839526,
|
1791 |
+
"grad_norm": 0.27959418296813965,
|
1792 |
+
"learning_rate": 0.00019729341054825782,
|
1793 |
+
"loss": 1.2169,
|
1794 |
+
"step": 255
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.03993837633339184,
|
1798 |
+
"grad_norm": 0.3103275001049042,
|
1799 |
+
"learning_rate": 0.00019726339209532462,
|
1800 |
+
"loss": 1.3043,
|
1801 |
+
"step": 256
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.040094385615944146,
|
1805 |
+
"grad_norm": 0.2712806463241577,
|
1806 |
+
"learning_rate": 0.00019723321040275815,
|
1807 |
+
"loss": 1.1747,
|
1808 |
+
"step": 257
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.04025039489849646,
|
1812 |
+
"grad_norm": 0.2961602210998535,
|
1813 |
+
"learning_rate": 0.0001972028655212131,
|
1814 |
+
"loss": 1.5744,
|
1815 |
+
"step": 258
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.04040640418104877,
|
1819 |
+
"grad_norm": 0.2686194181442261,
|
1820 |
+
"learning_rate": 0.00019717235750161806,
|
1821 |
+
"loss": 1.2442,
|
1822 |
+
"step": 259
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 0.04056241346360109,
|
1826 |
+
"grad_norm": 0.2742723822593689,
|
1827 |
+
"learning_rate": 0.00019714168639517544,
|
1828 |
+
"loss": 1.3225,
|
1829 |
+
"step": 260
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 0.04071842274615339,
|
1833 |
+
"grad_norm": 0.28742754459381104,
|
1834 |
+
"learning_rate": 0.00019711085225336132,
|
1835 |
+
"loss": 1.3711,
|
1836 |
+
"step": 261
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 0.04087443202870571,
|
1840 |
+
"grad_norm": 0.30374589562416077,
|
1841 |
+
"learning_rate": 0.00019707985512792543,
|
1842 |
+
"loss": 1.215,
|
1843 |
+
"step": 262
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.04103044131125802,
|
1847 |
+
"grad_norm": 0.2738686800003052,
|
1848 |
+
"learning_rate": 0.00019704869507089105,
|
1849 |
+
"loss": 1.4628,
|
1850 |
+
"step": 263
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 0.041186450593810334,
|
1854 |
+
"grad_norm": 0.2695278823375702,
|
1855 |
+
"learning_rate": 0.0001970173721345549,
|
1856 |
+
"loss": 1.4632,
|
1857 |
+
"step": 264
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.04134245987636264,
|
1861 |
+
"grad_norm": 0.2954547107219696,
|
1862 |
+
"learning_rate": 0.00019698588637148703,
|
1863 |
+
"loss": 1.2785,
|
1864 |
+
"step": 265
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 0.041498469158914954,
|
1868 |
+
"grad_norm": 0.2756305932998657,
|
1869 |
+
"learning_rate": 0.00019695423783453088,
|
1870 |
+
"loss": 1.4258,
|
1871 |
+
"step": 266
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.04165447844146727,
|
1875 |
+
"grad_norm": 0.2642769515514374,
|
1876 |
+
"learning_rate": 0.00019692242657680286,
|
1877 |
+
"loss": 1.3034,
|
1878 |
+
"step": 267
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 0.04181048772401958,
|
1882 |
+
"grad_norm": 0.2760365307331085,
|
1883 |
+
"learning_rate": 0.00019689045265169273,
|
1884 |
+
"loss": 1.5845,
|
1885 |
+
"step": 268
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 0.041966497006571894,
|
1889 |
+
"grad_norm": 0.23845522105693817,
|
1890 |
+
"learning_rate": 0.0001968583161128631,
|
1891 |
+
"loss": 1.113,
|
1892 |
+
"step": 269
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 0.0421225062891242,
|
1896 |
+
"grad_norm": 0.2855961322784424,
|
1897 |
+
"learning_rate": 0.0001968260170142496,
|
1898 |
+
"loss": 1.4019,
|
1899 |
+
"step": 270
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.042278515571676514,
|
1903 |
+
"grad_norm": 0.26462671160697937,
|
1904 |
+
"learning_rate": 0.00019679355541006054,
|
1905 |
+
"loss": 1.2425,
|
1906 |
+
"step": 271
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 0.04243452485422883,
|
1910 |
+
"grad_norm": 0.28468820452690125,
|
1911 |
+
"learning_rate": 0.00019676093135477713,
|
1912 |
+
"loss": 1.6525,
|
1913 |
+
"step": 272
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 0.04259053413678114,
|
1917 |
+
"grad_norm": 0.3233076333999634,
|
1918 |
+
"learning_rate": 0.0001967281449031531,
|
1919 |
+
"loss": 1.2168,
|
1920 |
+
"step": 273
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 0.04274654341933345,
|
1924 |
+
"grad_norm": 0.2688952684402466,
|
1925 |
+
"learning_rate": 0.00019669519611021486,
|
1926 |
+
"loss": 1.3948,
|
1927 |
+
"step": 274
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 0.04290255270188576,
|
1931 |
+
"grad_norm": 0.25911059975624084,
|
1932 |
+
"learning_rate": 0.00019666208503126112,
|
1933 |
+
"loss": 1.2875,
|
1934 |
+
"step": 275
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 0.043058561984438075,
|
1938 |
+
"grad_norm": 0.2789272964000702,
|
1939 |
+
"learning_rate": 0.00019662881172186313,
|
1940 |
+
"loss": 1.257,
|
1941 |
+
"step": 276
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.04321457126699039,
|
1945 |
+
"grad_norm": 0.26854726672172546,
|
1946 |
+
"learning_rate": 0.00019659537623786428,
|
1947 |
+
"loss": 1.4554,
|
1948 |
+
"step": 277
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 0.043370580549542695,
|
1952 |
+
"grad_norm": 0.31813284754753113,
|
1953 |
+
"learning_rate": 0.00019656177863538026,
|
1954 |
+
"loss": 1.667,
|
1955 |
+
"step": 278
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 0.04352658983209501,
|
1959 |
+
"grad_norm": 0.2801772356033325,
|
1960 |
+
"learning_rate": 0.00019652801897079869,
|
1961 |
+
"loss": 1.4555,
|
1962 |
+
"step": 279
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 0.04368259911464732,
|
1966 |
+
"grad_norm": 0.30256757140159607,
|
1967 |
+
"learning_rate": 0.00019649409730077935,
|
1968 |
+
"loss": 1.2628,
|
1969 |
+
"step": 280
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 0.043838608397199635,
|
1973 |
+
"grad_norm": 0.2807087302207947,
|
1974 |
+
"learning_rate": 0.00019646001368225382,
|
1975 |
+
"loss": 1.5143,
|
1976 |
+
"step": 281
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 0.04399461767975194,
|
1980 |
+
"grad_norm": 0.27217531204223633,
|
1981 |
+
"learning_rate": 0.0001964257681724255,
|
1982 |
+
"loss": 1.5372,
|
1983 |
+
"step": 282
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.044150626962304255,
|
1987 |
+
"grad_norm": 0.2996511459350586,
|
1988 |
+
"learning_rate": 0.00019639136082876953,
|
1989 |
+
"loss": 1.2692,
|
1990 |
+
"step": 283
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 0.04430663624485657,
|
1994 |
+
"grad_norm": 0.263231098651886,
|
1995 |
+
"learning_rate": 0.00019635679170903258,
|
1996 |
+
"loss": 1.2328,
|
1997 |
+
"step": 284
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 0.04446264552740888,
|
2001 |
+
"grad_norm": 0.3060413897037506,
|
2002 |
+
"learning_rate": 0.00019632206087123296,
|
2003 |
+
"loss": 1.5173,
|
2004 |
+
"step": 285
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 0.044618654809961196,
|
2008 |
+
"grad_norm": 0.25136467814445496,
|
2009 |
+
"learning_rate": 0.00019628716837366027,
|
2010 |
+
"loss": 1.1781,
|
2011 |
+
"step": 286
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.0447746640925135,
|
2015 |
+
"grad_norm": 0.27105534076690674,
|
2016 |
+
"learning_rate": 0.00019625211427487548,
|
2017 |
+
"loss": 1.4542,
|
2018 |
+
"step": 287
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 0.044930673375065816,
|
2022 |
+
"grad_norm": 0.27552956342697144,
|
2023 |
+
"learning_rate": 0.00019621689863371083,
|
2024 |
+
"loss": 1.3352,
|
2025 |
+
"step": 288
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.04508668265761813,
|
2029 |
+
"grad_norm": 0.26462072134017944,
|
2030 |
+
"learning_rate": 0.00019618152150926955,
|
2031 |
+
"loss": 1.2531,
|
2032 |
+
"step": 289
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 0.04524269194017044,
|
2036 |
+
"grad_norm": 0.2736480236053467,
|
2037 |
+
"learning_rate": 0.000196145982960926,
|
2038 |
+
"loss": 1.402,
|
2039 |
+
"step": 290
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 0.04539870122272275,
|
2043 |
+
"grad_norm": 0.2739974856376648,
|
2044 |
+
"learning_rate": 0.00019611028304832546,
|
2045 |
+
"loss": 1.4881,
|
2046 |
+
"step": 291
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 0.04555471050527506,
|
2050 |
+
"grad_norm": 0.25353673100471497,
|
2051 |
+
"learning_rate": 0.000196074421831384,
|
2052 |
+
"loss": 1.3935,
|
2053 |
+
"step": 292
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 0.04571071978782738,
|
2057 |
+
"grad_norm": 0.2595098614692688,
|
2058 |
+
"learning_rate": 0.00019603839937028838,
|
2059 |
+
"loss": 1.3306,
|
2060 |
+
"step": 293
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 0.04586672907037969,
|
2064 |
+
"grad_norm": 0.27779051661491394,
|
2065 |
+
"learning_rate": 0.00019600221572549606,
|
2066 |
+
"loss": 1.5111,
|
2067 |
+
"step": 294
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.046022738352932,
|
2071 |
+
"grad_norm": 0.26458942890167236,
|
2072 |
+
"learning_rate": 0.00019596587095773495,
|
2073 |
+
"loss": 1.1354,
|
2074 |
+
"step": 295
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 0.04617874763548431,
|
2078 |
+
"grad_norm": 0.3711000084877014,
|
2079 |
+
"learning_rate": 0.00019592936512800342,
|
2080 |
+
"loss": 1.387,
|
2081 |
+
"step": 296
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 0.046334756918036624,
|
2085 |
+
"grad_norm": 0.26172423362731934,
|
2086 |
+
"learning_rate": 0.00019589269829757008,
|
2087 |
+
"loss": 1.1995,
|
2088 |
+
"step": 297
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 0.04649076620058894,
|
2092 |
+
"grad_norm": 0.30684447288513184,
|
2093 |
+
"learning_rate": 0.00019585587052797389,
|
2094 |
+
"loss": 1.2853,
|
2095 |
+
"step": 298
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 0.046646775483141244,
|
2099 |
+
"grad_norm": 0.27383920550346375,
|
2100 |
+
"learning_rate": 0.00019581888188102375,
|
2101 |
+
"loss": 1.1397,
|
2102 |
+
"step": 299
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 0.04680278476569356,
|
2106 |
+
"grad_norm": 0.28926682472229004,
|
2107 |
+
"learning_rate": 0.00019578173241879872,
|
2108 |
+
"loss": 1.2977,
|
2109 |
+
"step": 300
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.04695879404824587,
|
2113 |
+
"grad_norm": 0.2573678195476532,
|
2114 |
+
"learning_rate": 0.00019574442220364767,
|
2115 |
+
"loss": 1.315,
|
2116 |
+
"step": 301
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 0.047114803330798184,
|
2120 |
+
"grad_norm": 0.286785751581192,
|
2121 |
+
"learning_rate": 0.00019570695129818926,
|
2122 |
+
"loss": 1.196,
|
2123 |
+
"step": 302
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 0.0472708126133505,
|
2127 |
+
"grad_norm": 0.26392433047294617,
|
2128 |
+
"learning_rate": 0.0001956693197653119,
|
2129 |
+
"loss": 1.067,
|
2130 |
+
"step": 303
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 0.047426821895902804,
|
2134 |
+
"grad_norm": 0.29351645708084106,
|
2135 |
+
"learning_rate": 0.00019563152766817354,
|
2136 |
+
"loss": 1.2977,
|
2137 |
+
"step": 304
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 0.04758283117845512,
|
2141 |
+
"grad_norm": 0.3556276857852936,
|
2142 |
+
"learning_rate": 0.00019559357507020162,
|
2143 |
+
"loss": 1.1268,
|
2144 |
+
"step": 305
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 0.04773884046100743,
|
2148 |
+
"grad_norm": 0.3044413924217224,
|
2149 |
+
"learning_rate": 0.00019555546203509297,
|
2150 |
+
"loss": 1.3528,
|
2151 |
+
"step": 306
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.047894849743559745,
|
2155 |
+
"grad_norm": 0.25455671548843384,
|
2156 |
+
"learning_rate": 0.00019551718862681364,
|
2157 |
+
"loss": 1.2099,
|
2158 |
+
"step": 307
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 0.04805085902611205,
|
2162 |
+
"grad_norm": 0.2863021492958069,
|
2163 |
+
"learning_rate": 0.00019547875490959885,
|
2164 |
+
"loss": 1.514,
|
2165 |
+
"step": 308
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 0.048206868308664365,
|
2169 |
+
"grad_norm": 0.2713131010532379,
|
2170 |
+
"learning_rate": 0.00019544016094795295,
|
2171 |
+
"loss": 1.2479,
|
2172 |
+
"step": 309
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 0.04836287759121668,
|
2176 |
+
"grad_norm": 0.28673309087753296,
|
2177 |
+
"learning_rate": 0.00019540140680664913,
|
2178 |
+
"loss": 1.4822,
|
2179 |
+
"step": 310
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 0.04851888687376899,
|
2183 |
+
"grad_norm": 0.28506314754486084,
|
2184 |
+
"learning_rate": 0.00019536249255072948,
|
2185 |
+
"loss": 1.1714,
|
2186 |
+
"step": 311
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 0.0486748961563213,
|
2190 |
+
"grad_norm": 0.2814370393753052,
|
2191 |
+
"learning_rate": 0.00019532341824550479,
|
2192 |
+
"loss": 1.3045,
|
2193 |
+
"step": 312
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.04883090543887361,
|
2197 |
+
"grad_norm": 0.2505611181259155,
|
2198 |
+
"learning_rate": 0.0001952841839565544,
|
2199 |
+
"loss": 1.1565,
|
2200 |
+
"step": 313
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 0.048986914721425925,
|
2204 |
+
"grad_norm": 0.27159830927848816,
|
2205 |
+
"learning_rate": 0.0001952447897497263,
|
2206 |
+
"loss": 1.0939,
|
2207 |
+
"step": 314
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 0.04914292400397824,
|
2211 |
+
"grad_norm": 0.27552008628845215,
|
2212 |
+
"learning_rate": 0.00019520523569113677,
|
2213 |
+
"loss": 1.4382,
|
2214 |
+
"step": 315
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.049298933286530545,
|
2218 |
+
"grad_norm": 0.2567708492279053,
|
2219 |
+
"learning_rate": 0.00019516552184717037,
|
2220 |
+
"loss": 1.2241,
|
2221 |
+
"step": 316
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 0.04945494256908286,
|
2225 |
+
"grad_norm": 0.27663713693618774,
|
2226 |
+
"learning_rate": 0.00019512564828447988,
|
2227 |
+
"loss": 1.2449,
|
2228 |
+
"step": 317
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.04961095185163517,
|
2232 |
+
"grad_norm": 0.2683660089969635,
|
2233 |
+
"learning_rate": 0.0001950856150699861,
|
2234 |
+
"loss": 1.1652,
|
2235 |
+
"step": 318
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.049766961134187486,
|
2239 |
+
"grad_norm": 0.25226572155952454,
|
2240 |
+
"learning_rate": 0.0001950454222708778,
|
2241 |
+
"loss": 1.1307,
|
2242 |
+
"step": 319
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 0.0499229704167398,
|
2246 |
+
"grad_norm": 0.23380513489246368,
|
2247 |
+
"learning_rate": 0.0001950050699546116,
|
2248 |
+
"loss": 1.1257,
|
2249 |
+
"step": 320
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 0.050078979699292106,
|
2253 |
+
"grad_norm": 0.2385280281305313,
|
2254 |
+
"learning_rate": 0.0001949645581889118,
|
2255 |
+
"loss": 0.9917,
|
2256 |
+
"step": 321
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 0.05023498898184442,
|
2260 |
+
"grad_norm": 0.23746567964553833,
|
2261 |
+
"learning_rate": 0.00019492388704177036,
|
2262 |
+
"loss": 1.1364,
|
2263 |
+
"step": 322
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 0.05039099826439673,
|
2267 |
+
"grad_norm": 0.27820831537246704,
|
2268 |
+
"learning_rate": 0.00019488305658144667,
|
2269 |
+
"loss": 1.3707,
|
2270 |
+
"step": 323
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 0.050547007546949047,
|
2274 |
+
"grad_norm": 0.2663419544696808,
|
2275 |
+
"learning_rate": 0.00019484206687646753,
|
2276 |
+
"loss": 1.3662,
|
2277 |
+
"step": 324
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.05070301682950135,
|
2281 |
+
"grad_norm": 0.27196773886680603,
|
2282 |
+
"learning_rate": 0.00019480091799562704,
|
2283 |
+
"loss": 1.2766,
|
2284 |
+
"step": 325
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 0.05085902611205367,
|
2288 |
+
"grad_norm": 0.296779602766037,
|
2289 |
+
"learning_rate": 0.00019475961000798645,
|
2290 |
+
"loss": 1.5789,
|
2291 |
+
"step": 326
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 0.05101503539460598,
|
2295 |
+
"grad_norm": 0.3267677128314972,
|
2296 |
+
"learning_rate": 0.0001947181429828739,
|
2297 |
+
"loss": 1.2782,
|
2298 |
+
"step": 327
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 0.051171044677158294,
|
2302 |
+
"grad_norm": 0.2852894067764282,
|
2303 |
+
"learning_rate": 0.00019467651698988462,
|
2304 |
+
"loss": 1.1466,
|
2305 |
+
"step": 328
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 0.0513270539597106,
|
2309 |
+
"grad_norm": 0.2959722876548767,
|
2310 |
+
"learning_rate": 0.0001946347320988806,
|
2311 |
+
"loss": 1.1929,
|
2312 |
+
"step": 329
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 0.051483063242262914,
|
2316 |
+
"grad_norm": 0.25998443365097046,
|
2317 |
+
"learning_rate": 0.00019459278837999046,
|
2318 |
+
"loss": 1.4104,
|
2319 |
+
"step": 330
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.05163907252481523,
|
2323 |
+
"grad_norm": 0.27319809794425964,
|
2324 |
+
"learning_rate": 0.00019455068590360942,
|
2325 |
+
"loss": 1.417,
|
2326 |
+
"step": 331
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 0.05179508180736754,
|
2330 |
+
"grad_norm": 0.22395959496498108,
|
2331 |
+
"learning_rate": 0.00019450842474039913,
|
2332 |
+
"loss": 1.2159,
|
2333 |
+
"step": 332
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 0.05195109108991985,
|
2337 |
+
"grad_norm": 0.24947980046272278,
|
2338 |
+
"learning_rate": 0.00019446600496128758,
|
2339 |
+
"loss": 1.1063,
|
2340 |
+
"step": 333
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 0.05210710037247216,
|
2344 |
+
"grad_norm": 0.235429584980011,
|
2345 |
+
"learning_rate": 0.00019442342663746902,
|
2346 |
+
"loss": 1.2234,
|
2347 |
+
"step": 334
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 0.052263109655024474,
|
2351 |
+
"grad_norm": 0.27443963289260864,
|
2352 |
+
"learning_rate": 0.00019438068984040365,
|
2353 |
+
"loss": 1.2038,
|
2354 |
+
"step": 335
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 0.05241911893757679,
|
2358 |
+
"grad_norm": 0.26688772439956665,
|
2359 |
+
"learning_rate": 0.00019433779464181778,
|
2360 |
+
"loss": 1.2956,
|
2361 |
+
"step": 336
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 0.052575128220129094,
|
2365 |
+
"grad_norm": 0.23804551362991333,
|
2366 |
+
"learning_rate": 0.00019429474111370352,
|
2367 |
+
"loss": 0.9525,
|
2368 |
+
"step": 337
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 0.05273113750268141,
|
2372 |
+
"grad_norm": 0.262890487909317,
|
2373 |
+
"learning_rate": 0.0001942515293283187,
|
2374 |
+
"loss": 1.2713,
|
2375 |
+
"step": 338
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 0.05288714678523372,
|
2379 |
+
"grad_norm": 0.29796820878982544,
|
2380 |
+
"learning_rate": 0.00019420815935818672,
|
2381 |
+
"loss": 1.5058,
|
2382 |
+
"step": 339
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 0.053043156067786035,
|
2386 |
+
"grad_norm": 0.275143563747406,
|
2387 |
+
"learning_rate": 0.00019416463127609656,
|
2388 |
+
"loss": 1.2604,
|
2389 |
+
"step": 340
|
2390 |
+
},
|
2391 |
+
{
|
2392 |
+
"epoch": 0.05319916535033835,
|
2393 |
+
"grad_norm": 0.27801284193992615,
|
2394 |
+
"learning_rate": 0.00019412094515510248,
|
2395 |
+
"loss": 1.2588,
|
2396 |
+
"step": 341
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 0.053355174632890655,
|
2400 |
+
"grad_norm": 0.2604374885559082,
|
2401 |
+
"learning_rate": 0.00019407710106852404,
|
2402 |
+
"loss": 1.1432,
|
2403 |
+
"step": 342
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 0.05351118391544297,
|
2407 |
+
"grad_norm": 0.2863079011440277,
|
2408 |
+
"learning_rate": 0.00019403309908994586,
|
2409 |
+
"loss": 1.4854,
|
2410 |
+
"step": 343
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 0.05366719319799528,
|
2414 |
+
"grad_norm": 0.2515758275985718,
|
2415 |
+
"learning_rate": 0.00019398893929321761,
|
2416 |
+
"loss": 1.1682,
|
2417 |
+
"step": 344
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 0.053823202480547595,
|
2421 |
+
"grad_norm": 0.27037686109542847,
|
2422 |
+
"learning_rate": 0.00019394462175245381,
|
2423 |
+
"loss": 1.3679,
|
2424 |
+
"step": 345
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 0.0539792117630999,
|
2428 |
+
"grad_norm": 0.2368054836988449,
|
2429 |
+
"learning_rate": 0.00019390014654203369,
|
2430 |
+
"loss": 1.1406,
|
2431 |
+
"step": 346
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 0.054135221045652215,
|
2435 |
+
"grad_norm": 0.27759966254234314,
|
2436 |
+
"learning_rate": 0.0001938555137366011,
|
2437 |
+
"loss": 1.1669,
|
2438 |
+
"step": 347
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 0.05429123032820453,
|
2442 |
+
"grad_norm": 0.3004835546016693,
|
2443 |
+
"learning_rate": 0.00019381072341106452,
|
2444 |
+
"loss": 1.4811,
|
2445 |
+
"step": 348
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 0.05444723961075684,
|
2449 |
+
"grad_norm": 0.30656251311302185,
|
2450 |
+
"learning_rate": 0.0001937657756405966,
|
2451 |
+
"loss": 1.515,
|
2452 |
+
"step": 349
|
2453 |
+
},
|
2454 |
+
{
|
2455 |
+
"epoch": 0.05460324889330915,
|
2456 |
+
"grad_norm": 0.31442925333976746,
|
2457 |
+
"learning_rate": 0.00019372067050063438,
|
2458 |
+
"loss": 1.4848,
|
2459 |
+
"step": 350
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 0.05475925817586146,
|
2463 |
+
"grad_norm": 0.2230207473039627,
|
2464 |
+
"learning_rate": 0.00019367540806687893,
|
2465 |
+
"loss": 0.9535,
|
2466 |
+
"step": 351
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 0.054915267458413776,
|
2470 |
+
"grad_norm": 0.2552795708179474,
|
2471 |
+
"learning_rate": 0.0001936299884152954,
|
2472 |
+
"loss": 1.2254,
|
2473 |
+
"step": 352
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 0.05507127674096609,
|
2477 |
+
"grad_norm": 0.29775241017341614,
|
2478 |
+
"learning_rate": 0.0001935844116221127,
|
2479 |
+
"loss": 1.3821,
|
2480 |
+
"step": 353
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 0.055227286023518396,
|
2484 |
+
"grad_norm": 0.24480530619621277,
|
2485 |
+
"learning_rate": 0.00019353867776382354,
|
2486 |
+
"loss": 1.1073,
|
2487 |
+
"step": 354
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 0.05538329530607071,
|
2491 |
+
"grad_norm": 0.2612270414829254,
|
2492 |
+
"learning_rate": 0.00019349278691718427,
|
2493 |
+
"loss": 1.3114,
|
2494 |
+
"step": 355
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 0.05553930458862302,
|
2498 |
+
"grad_norm": 0.307085245847702,
|
2499 |
+
"learning_rate": 0.0001934467391592146,
|
2500 |
+
"loss": 1.3602,
|
2501 |
+
"step": 356
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 0.055695313871175336,
|
2505 |
+
"grad_norm": 0.2688599228858948,
|
2506 |
+
"learning_rate": 0.00019340053456719768,
|
2507 |
+
"loss": 1.4347,
|
2508 |
+
"step": 357
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 0.05585132315372765,
|
2512 |
+
"grad_norm": 0.25372791290283203,
|
2513 |
+
"learning_rate": 0.00019335417321867987,
|
2514 |
+
"loss": 1.3468,
|
2515 |
+
"step": 358
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 0.05600733243627996,
|
2519 |
+
"grad_norm": 0.2706502377986908,
|
2520 |
+
"learning_rate": 0.0001933076551914706,
|
2521 |
+
"loss": 1.4489,
|
2522 |
+
"step": 359
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 0.05616334171883227,
|
2526 |
+
"grad_norm": 0.22997525334358215,
|
2527 |
+
"learning_rate": 0.00019326098056364222,
|
2528 |
+
"loss": 1.1305,
|
2529 |
+
"step": 360
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.056319351001384584,
|
2533 |
+
"grad_norm": 0.30573347210884094,
|
2534 |
+
"learning_rate": 0.00019321414941353003,
|
2535 |
+
"loss": 1.4231,
|
2536 |
+
"step": 361
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 0.0564753602839369,
|
2540 |
+
"grad_norm": 0.30873847007751465,
|
2541 |
+
"learning_rate": 0.00019316716181973188,
|
2542 |
+
"loss": 1.3478,
|
2543 |
+
"step": 362
|
2544 |
+
},
|
2545 |
+
{
|
2546 |
+
"epoch": 0.056631369566489204,
|
2547 |
+
"grad_norm": 0.2514902651309967,
|
2548 |
+
"learning_rate": 0.00019312001786110828,
|
2549 |
+
"loss": 1.2094,
|
2550 |
+
"step": 363
|
2551 |
+
},
|
2552 |
+
{
|
2553 |
+
"epoch": 0.05678737884904152,
|
2554 |
+
"grad_norm": 0.26067742705345154,
|
2555 |
+
"learning_rate": 0.00019307271761678213,
|
2556 |
+
"loss": 1.5841,
|
2557 |
+
"step": 364
|
2558 |
+
},
|
2559 |
+
{
|
2560 |
+
"epoch": 0.05694338813159383,
|
2561 |
+
"grad_norm": 0.23508694767951965,
|
2562 |
+
"learning_rate": 0.00019302526116613864,
|
2563 |
+
"loss": 1.103,
|
2564 |
+
"step": 365
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 0.057099397414146144,
|
2568 |
+
"grad_norm": 0.24878567457199097,
|
2569 |
+
"learning_rate": 0.00019297764858882514,
|
2570 |
+
"loss": 1.0968,
|
2571 |
+
"step": 366
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 0.05725540669669845,
|
2575 |
+
"grad_norm": 0.23707476258277893,
|
2576 |
+
"learning_rate": 0.00019292987996475113,
|
2577 |
+
"loss": 1.0831,
|
2578 |
+
"step": 367
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 0.057411415979250764,
|
2582 |
+
"grad_norm": 0.2691617012023926,
|
2583 |
+
"learning_rate": 0.0001928819553740878,
|
2584 |
+
"loss": 1.2254,
|
2585 |
+
"step": 368
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 0.05756742526180308,
|
2589 |
+
"grad_norm": 0.26831138134002686,
|
2590 |
+
"learning_rate": 0.00019283387489726827,
|
2591 |
+
"loss": 1.3084,
|
2592 |
+
"step": 369
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 0.05772343454435539,
|
2596 |
+
"grad_norm": 0.281770259141922,
|
2597 |
+
"learning_rate": 0.00019278563861498723,
|
2598 |
+
"loss": 1.3377,
|
2599 |
+
"step": 370
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 0.0578794438269077,
|
2603 |
+
"grad_norm": 0.2634589970111847,
|
2604 |
+
"learning_rate": 0.00019273724660820088,
|
2605 |
+
"loss": 1.2648,
|
2606 |
+
"step": 371
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 0.05803545310946001,
|
2610 |
+
"grad_norm": 0.27592259645462036,
|
2611 |
+
"learning_rate": 0.00019268869895812672,
|
2612 |
+
"loss": 1.2751,
|
2613 |
+
"step": 372
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 0.058191462392012325,
|
2617 |
+
"grad_norm": 0.23107245564460754,
|
2618 |
+
"learning_rate": 0.00019263999574624355,
|
2619 |
+
"loss": 1.2651,
|
2620 |
+
"step": 373
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 0.05834747167456464,
|
2624 |
+
"grad_norm": 0.2582552134990692,
|
2625 |
+
"learning_rate": 0.0001925911370542912,
|
2626 |
+
"loss": 1.4914,
|
2627 |
+
"step": 374
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 0.05850348095711695,
|
2631 |
+
"grad_norm": 0.27152058482170105,
|
2632 |
+
"learning_rate": 0.00019254212296427044,
|
2633 |
+
"loss": 1.2227,
|
2634 |
+
"step": 375
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 0.05865949023966926,
|
2638 |
+
"grad_norm": 0.23554329574108124,
|
2639 |
+
"learning_rate": 0.00019249295355844285,
|
2640 |
+
"loss": 1.4113,
|
2641 |
+
"step": 376
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 0.05881549952222157,
|
2645 |
+
"grad_norm": 0.2793971300125122,
|
2646 |
+
"learning_rate": 0.00019244362891933077,
|
2647 |
+
"loss": 1.3325,
|
2648 |
+
"step": 377
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 0.058971508804773885,
|
2652 |
+
"grad_norm": 0.2800885736942291,
|
2653 |
+
"learning_rate": 0.00019239414912971696,
|
2654 |
+
"loss": 1.358,
|
2655 |
+
"step": 378
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 0.0591275180873262,
|
2659 |
+
"grad_norm": 0.27139201760292053,
|
2660 |
+
"learning_rate": 0.0001923445142726446,
|
2661 |
+
"loss": 1.2269,
|
2662 |
+
"step": 379
|
2663 |
+
},
|
2664 |
+
{
|
2665 |
+
"epoch": 0.059283527369878505,
|
2666 |
+
"grad_norm": 0.276579886674881,
|
2667 |
+
"learning_rate": 0.0001922947244314172,
|
2668 |
+
"loss": 1.1521,
|
2669 |
+
"step": 380
|
2670 |
+
},
|
2671 |
+
{
|
2672 |
+
"epoch": 0.05943953665243082,
|
2673 |
+
"grad_norm": 0.28917452692985535,
|
2674 |
+
"learning_rate": 0.0001922447796895982,
|
2675 |
+
"loss": 1.2803,
|
2676 |
+
"step": 381
|
2677 |
+
},
|
2678 |
+
{
|
2679 |
+
"epoch": 0.05959554593498313,
|
2680 |
+
"grad_norm": 0.28668197989463806,
|
2681 |
+
"learning_rate": 0.00019219468013101124,
|
2682 |
+
"loss": 1.4025,
|
2683 |
+
"step": 382
|
2684 |
+
},
|
2685 |
+
{
|
2686 |
+
"epoch": 0.059751555217535446,
|
2687 |
+
"grad_norm": 0.2973851263523102,
|
2688 |
+
"learning_rate": 0.00019214442583973966,
|
2689 |
+
"loss": 1.5472,
|
2690 |
+
"step": 383
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 0.05990756450008775,
|
2694 |
+
"grad_norm": 0.25934460759162903,
|
2695 |
+
"learning_rate": 0.00019209401690012653,
|
2696 |
+
"loss": 1.2496,
|
2697 |
+
"step": 384
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 0.060063573782640066,
|
2701 |
+
"grad_norm": 0.22885724902153015,
|
2702 |
+
"learning_rate": 0.00019204345339677442,
|
2703 |
+
"loss": 1.2088,
|
2704 |
+
"step": 385
|
2705 |
+
},
|
2706 |
+
{
|
2707 |
+
"epoch": 0.06021958306519238,
|
2708 |
+
"grad_norm": 0.28346025943756104,
|
2709 |
+
"learning_rate": 0.00019199273541454538,
|
2710 |
+
"loss": 1.1561,
|
2711 |
+
"step": 386
|
2712 |
+
},
|
2713 |
+
{
|
2714 |
+
"epoch": 0.06037559234774469,
|
2715 |
+
"grad_norm": 0.2574789822101593,
|
2716 |
+
"learning_rate": 0.00019194186303856067,
|
2717 |
+
"loss": 1.3209,
|
2718 |
+
"step": 387
|
2719 |
+
},
|
2720 |
+
{
|
2721 |
+
"epoch": 0.060531601630297,
|
2722 |
+
"grad_norm": 0.26535728573799133,
|
2723 |
+
"learning_rate": 0.00019189083635420075,
|
2724 |
+
"loss": 1.3022,
|
2725 |
+
"step": 388
|
2726 |
+
},
|
2727 |
+
{
|
2728 |
+
"epoch": 0.06068761091284931,
|
2729 |
+
"grad_norm": 0.2844642698764801,
|
2730 |
+
"learning_rate": 0.00019183965544710495,
|
2731 |
+
"loss": 1.3881,
|
2732 |
+
"step": 389
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 0.060843620195401626,
|
2736 |
+
"grad_norm": 0.24562187492847443,
|
2737 |
+
"learning_rate": 0.00019178832040317155,
|
2738 |
+
"loss": 1.159,
|
2739 |
+
"step": 390
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 0.06099962947795394,
|
2743 |
+
"grad_norm": 0.25778669118881226,
|
2744 |
+
"learning_rate": 0.0001917368313085574,
|
2745 |
+
"loss": 1.5154,
|
2746 |
+
"step": 391
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 0.061155638760506253,
|
2750 |
+
"grad_norm": 0.22877171635627747,
|
2751 |
+
"learning_rate": 0.00019168518824967795,
|
2752 |
+
"loss": 1.201,
|
2753 |
+
"step": 392
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 0.06131164804305856,
|
2757 |
+
"grad_norm": 0.2764502465724945,
|
2758 |
+
"learning_rate": 0.00019163339131320718,
|
2759 |
+
"loss": 1.4165,
|
2760 |
+
"step": 393
|
2761 |
+
},
|
2762 |
+
{
|
2763 |
+
"epoch": 0.061467657325610874,
|
2764 |
+
"grad_norm": 0.23493847250938416,
|
2765 |
+
"learning_rate": 0.00019158144058607708,
|
2766 |
+
"loss": 1.1334,
|
2767 |
+
"step": 394
|
2768 |
+
},
|
2769 |
+
{
|
2770 |
+
"epoch": 0.06162366660816319,
|
2771 |
+
"grad_norm": 0.2605098783969879,
|
2772 |
+
"learning_rate": 0.00019152933615547798,
|
2773 |
+
"loss": 1.1613,
|
2774 |
+
"step": 395
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 0.0617796758907155,
|
2778 |
+
"grad_norm": 0.23720701038837433,
|
2779 |
+
"learning_rate": 0.000191477078108858,
|
2780 |
+
"loss": 1.1966,
|
2781 |
+
"step": 396
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 0.06193568517326781,
|
2785 |
+
"grad_norm": 0.27043676376342773,
|
2786 |
+
"learning_rate": 0.00019142466653392318,
|
2787 |
+
"loss": 1.2793,
|
2788 |
+
"step": 397
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 0.06209169445582012,
|
2792 |
+
"grad_norm": 0.27630025148391724,
|
2793 |
+
"learning_rate": 0.0001913721015186372,
|
2794 |
+
"loss": 1.3858,
|
2795 |
+
"step": 398
|
2796 |
+
},
|
2797 |
+
{
|
2798 |
+
"epoch": 0.062247703738372434,
|
2799 |
+
"grad_norm": 0.29454129934310913,
|
2800 |
+
"learning_rate": 0.0001913193831512213,
|
2801 |
+
"loss": 1.5234,
|
2802 |
+
"step": 399
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 0.06240371302092475,
|
2806 |
+
"grad_norm": 0.26943233609199524,
|
2807 |
+
"learning_rate": 0.00019126651152015403,
|
2808 |
+
"loss": 1.3181,
|
2809 |
+
"step": 400
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 0.06255972230347706,
|
2813 |
+
"grad_norm": 0.28831520676612854,
|
2814 |
+
"learning_rate": 0.0001912134867141712,
|
2815 |
+
"loss": 1.46,
|
2816 |
+
"step": 401
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 0.06271573158602937,
|
2820 |
+
"grad_norm": 0.26342567801475525,
|
2821 |
+
"learning_rate": 0.0001911603088222657,
|
2822 |
+
"loss": 1.4073,
|
2823 |
+
"step": 402
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 0.06287174086858167,
|
2827 |
+
"grad_norm": 0.2623300552368164,
|
2828 |
+
"learning_rate": 0.0001911069779336873,
|
2829 |
+
"loss": 1.3473,
|
2830 |
+
"step": 403
|
2831 |
+
},
|
2832 |
+
{
|
2833 |
+
"epoch": 0.06302775015113399,
|
2834 |
+
"grad_norm": 0.25125861167907715,
|
2835 |
+
"learning_rate": 0.00019105349413794272,
|
2836 |
+
"loss": 1.0346,
|
2837 |
+
"step": 404
|
2838 |
+
},
|
2839 |
+
{
|
2840 |
+
"epoch": 0.0631837594336863,
|
2841 |
+
"grad_norm": 0.30890092253685,
|
2842 |
+
"learning_rate": 0.00019099985752479506,
|
2843 |
+
"loss": 1.5751,
|
2844 |
+
"step": 405
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 0.06333976871623861,
|
2848 |
+
"grad_norm": 0.31404733657836914,
|
2849 |
+
"learning_rate": 0.00019094606818426403,
|
2850 |
+
"loss": 1.5458,
|
2851 |
+
"step": 406
|
2852 |
+
},
|
2853 |
+
{
|
2854 |
+
"epoch": 0.06349577799879093,
|
2855 |
+
"grad_norm": 0.2684463858604431,
|
2856 |
+
"learning_rate": 0.00019089212620662568,
|
2857 |
+
"loss": 1.2342,
|
2858 |
+
"step": 407
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 0.06365178728134324,
|
2862 |
+
"grad_norm": 0.2748461365699768,
|
2863 |
+
"learning_rate": 0.00019083803168241223,
|
2864 |
+
"loss": 1.3353,
|
2865 |
+
"step": 408
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 0.06380779656389556,
|
2869 |
+
"grad_norm": 0.3061840832233429,
|
2870 |
+
"learning_rate": 0.00019078378470241183,
|
2871 |
+
"loss": 1.3197,
|
2872 |
+
"step": 409
|
2873 |
+
},
|
2874 |
+
{
|
2875 |
+
"epoch": 0.06396380584644787,
|
2876 |
+
"grad_norm": 0.25601011514663696,
|
2877 |
+
"learning_rate": 0.00019072938535766865,
|
2878 |
+
"loss": 1.3904,
|
2879 |
+
"step": 410
|
2880 |
+
},
|
2881 |
+
{
|
2882 |
+
"epoch": 0.06411981512900018,
|
2883 |
+
"grad_norm": 0.2844060957431793,
|
2884 |
+
"learning_rate": 0.00019067483373948243,
|
2885 |
+
"loss": 1.42,
|
2886 |
+
"step": 411
|
2887 |
+
},
|
2888 |
+
{
|
2889 |
+
"epoch": 0.06427582441155248,
|
2890 |
+
"grad_norm": 0.2969295382499695,
|
2891 |
+
"learning_rate": 0.00019062012993940859,
|
2892 |
+
"loss": 1.4255,
|
2893 |
+
"step": 412
|
2894 |
+
},
|
2895 |
+
{
|
2896 |
+
"epoch": 0.0644318336941048,
|
2897 |
+
"grad_norm": 0.2655050456523895,
|
2898 |
+
"learning_rate": 0.00019056527404925789,
|
2899 |
+
"loss": 1.1618,
|
2900 |
+
"step": 413
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 0.06458784297665711,
|
2904 |
+
"grad_norm": 0.2571544349193573,
|
2905 |
+
"learning_rate": 0.00019051026616109638,
|
2906 |
+
"loss": 1.2064,
|
2907 |
+
"step": 414
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 0.06474385225920942,
|
2911 |
+
"grad_norm": 0.29847028851509094,
|
2912 |
+
"learning_rate": 0.0001904551063672452,
|
2913 |
+
"loss": 1.2847,
|
2914 |
+
"step": 415
|
2915 |
+
},
|
2916 |
+
{
|
2917 |
+
"epoch": 0.06489986154176174,
|
2918 |
+
"grad_norm": 0.24265627562999725,
|
2919 |
+
"learning_rate": 0.00019039979476028043,
|
2920 |
+
"loss": 1.2745,
|
2921 |
+
"step": 416
|
2922 |
+
},
|
2923 |
+
{
|
2924 |
+
"epoch": 0.06505587082431405,
|
2925 |
+
"grad_norm": 0.24038730561733246,
|
2926 |
+
"learning_rate": 0.000190344331433033,
|
2927 |
+
"loss": 1.2761,
|
2928 |
+
"step": 417
|
2929 |
+
},
|
2930 |
+
{
|
2931 |
+
"epoch": 0.06521188010686636,
|
2932 |
+
"grad_norm": 0.26194193959236145,
|
2933 |
+
"learning_rate": 0.00019028871647858834,
|
2934 |
+
"loss": 1.5021,
|
2935 |
+
"step": 418
|
2936 |
+
},
|
2937 |
+
{
|
2938 |
+
"epoch": 0.06536788938941868,
|
2939 |
+
"grad_norm": 0.2636980712413788,
|
2940 |
+
"learning_rate": 0.00019023294999028653,
|
2941 |
+
"loss": 1.5029,
|
2942 |
+
"step": 419
|
2943 |
+
},
|
2944 |
+
{
|
2945 |
+
"epoch": 0.06552389867197098,
|
2946 |
+
"grad_norm": 0.26995277404785156,
|
2947 |
+
"learning_rate": 0.00019017703206172185,
|
2948 |
+
"loss": 1.3068,
|
2949 |
+
"step": 420
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 0.06567990795452329,
|
2953 |
+
"grad_norm": 0.26835623383522034,
|
2954 |
+
"learning_rate": 0.0001901209627867428,
|
2955 |
+
"loss": 1.2868,
|
2956 |
+
"step": 421
|
2957 |
+
},
|
2958 |
+
{
|
2959 |
+
"epoch": 0.0658359172370756,
|
2960 |
+
"grad_norm": 0.24785400927066803,
|
2961 |
+
"learning_rate": 0.0001900647422594519,
|
2962 |
+
"loss": 1.1875,
|
2963 |
+
"step": 422
|
2964 |
+
},
|
2965 |
+
{
|
2966 |
+
"epoch": 0.06599192651962792,
|
2967 |
+
"grad_norm": 0.3184250593185425,
|
2968 |
+
"learning_rate": 0.0001900083705742054,
|
2969 |
+
"loss": 1.3802,
|
2970 |
+
"step": 423
|
2971 |
+
},
|
2972 |
+
{
|
2973 |
+
"epoch": 0.06614793580218023,
|
2974 |
+
"grad_norm": 0.2850029766559601,
|
2975 |
+
"learning_rate": 0.00018995184782561345,
|
2976 |
+
"loss": 1.3043,
|
2977 |
+
"step": 424
|
2978 |
+
},
|
2979 |
+
{
|
2980 |
+
"epoch": 0.06630394508473254,
|
2981 |
+
"grad_norm": 0.2940841317176819,
|
2982 |
+
"learning_rate": 0.00018989517410853955,
|
2983 |
+
"loss": 1.287,
|
2984 |
+
"step": 425
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 0.06645995436728486,
|
2988 |
+
"grad_norm": 0.2668844163417816,
|
2989 |
+
"learning_rate": 0.0001898383495181007,
|
2990 |
+
"loss": 1.3723,
|
2991 |
+
"step": 426
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 0.06661596364983717,
|
2995 |
+
"grad_norm": 0.2814147472381592,
|
2996 |
+
"learning_rate": 0.00018978137414966698,
|
2997 |
+
"loss": 1.2339,
|
2998 |
+
"step": 427
|
2999 |
+
},
|
3000 |
+
{
|
3001 |
+
"epoch": 0.06677197293238948,
|
3002 |
+
"grad_norm": 0.3722403049468994,
|
3003 |
+
"learning_rate": 0.0001897242480988617,
|
3004 |
+
"loss": 1.2755,
|
3005 |
+
"step": 428
|
3006 |
+
},
|
3007 |
+
{
|
3008 |
+
"epoch": 0.06692798221494178,
|
3009 |
+
"grad_norm": 0.2689428925514221,
|
3010 |
+
"learning_rate": 0.00018966697146156092,
|
3011 |
+
"loss": 1.4238,
|
3012 |
+
"step": 429
|
3013 |
+
},
|
3014 |
+
{
|
3015 |
+
"epoch": 0.0670839914974941,
|
3016 |
+
"grad_norm": 0.29616808891296387,
|
3017 |
+
"learning_rate": 0.00018960954433389345,
|
3018 |
+
"loss": 1.3167,
|
3019 |
+
"step": 430
|
3020 |
+
},
|
3021 |
+
{
|
3022 |
+
"epoch": 0.06724000078004641,
|
3023 |
+
"grad_norm": 0.2477925419807434,
|
3024 |
+
"learning_rate": 0.0001895519668122408,
|
3025 |
+
"loss": 1.1773,
|
3026 |
+
"step": 431
|
3027 |
+
},
|
3028 |
+
{
|
3029 |
+
"epoch": 0.06739601006259872,
|
3030 |
+
"grad_norm": 0.23961544036865234,
|
3031 |
+
"learning_rate": 0.0001894942389932367,
|
3032 |
+
"loss": 1.1387,
|
3033 |
+
"step": 432
|
3034 |
+
},
|
3035 |
+
{
|
3036 |
+
"epoch": 0.06755201934515104,
|
3037 |
+
"grad_norm": 0.26128751039505005,
|
3038 |
+
"learning_rate": 0.00018943636097376726,
|
3039 |
+
"loss": 1.0468,
|
3040 |
+
"step": 433
|
3041 |
+
},
|
3042 |
+
{
|
3043 |
+
"epoch": 0.06770802862770335,
|
3044 |
+
"grad_norm": 0.33279022574424744,
|
3045 |
+
"learning_rate": 0.00018937833285097066,
|
3046 |
+
"loss": 1.8791,
|
3047 |
+
"step": 434
|
3048 |
+
},
|
3049 |
+
{
|
3050 |
+
"epoch": 0.06786403791025566,
|
3051 |
+
"grad_norm": 0.2876769006252289,
|
3052 |
+
"learning_rate": 0.00018932015472223693,
|
3053 |
+
"loss": 1.3633,
|
3054 |
+
"step": 435
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 0.06802004719280798,
|
3058 |
+
"grad_norm": 0.24108922481536865,
|
3059 |
+
"learning_rate": 0.00018926182668520792,
|
3060 |
+
"loss": 1.2012,
|
3061 |
+
"step": 436
|
3062 |
+
},
|
3063 |
+
{
|
3064 |
+
"epoch": 0.06817605647536028,
|
3065 |
+
"grad_norm": 0.29062169790267944,
|
3066 |
+
"learning_rate": 0.0001892033488377771,
|
3067 |
+
"loss": 1.3658,
|
3068 |
+
"step": 437
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 0.06833206575791259,
|
3072 |
+
"grad_norm": 0.26536259055137634,
|
3073 |
+
"learning_rate": 0.0001891447212780893,
|
3074 |
+
"loss": 1.2464,
|
3075 |
+
"step": 438
|
3076 |
+
},
|
3077 |
+
{
|
3078 |
+
"epoch": 0.0684880750404649,
|
3079 |
+
"grad_norm": 0.2940811514854431,
|
3080 |
+
"learning_rate": 0.0001890859441045407,
|
3081 |
+
"loss": 1.4609,
|
3082 |
+
"step": 439
|
3083 |
+
},
|
3084 |
+
{
|
3085 |
+
"epoch": 0.06864408432301722,
|
3086 |
+
"grad_norm": 0.27625903487205505,
|
3087 |
+
"learning_rate": 0.0001890270174157784,
|
3088 |
+
"loss": 1.4098,
|
3089 |
+
"step": 440
|
3090 |
+
},
|
3091 |
+
{
|
3092 |
+
"epoch": 0.06880009360556953,
|
3093 |
+
"grad_norm": 0.2586573362350464,
|
3094 |
+
"learning_rate": 0.00018896794131070073,
|
3095 |
+
"loss": 1.3857,
|
3096 |
+
"step": 441
|
3097 |
+
},
|
3098 |
+
{
|
3099 |
+
"epoch": 0.06895610288812185,
|
3100 |
+
"grad_norm": 0.28287774324417114,
|
3101 |
+
"learning_rate": 0.0001889087158884565,
|
3102 |
+
"loss": 1.2967,
|
3103 |
+
"step": 442
|
3104 |
+
},
|
3105 |
+
{
|
3106 |
+
"epoch": 0.06911211217067416,
|
3107 |
+
"grad_norm": 0.2692122459411621,
|
3108 |
+
"learning_rate": 0.00018884934124844532,
|
3109 |
+
"loss": 1.5216,
|
3110 |
+
"step": 443
|
3111 |
+
},
|
3112 |
+
{
|
3113 |
+
"epoch": 0.06926812145322647,
|
3114 |
+
"grad_norm": 0.3004090189933777,
|
3115 |
+
"learning_rate": 0.00018878981749031716,
|
3116 |
+
"loss": 1.1913,
|
3117 |
+
"step": 444
|
3118 |
+
},
|
3119 |
+
{
|
3120 |
+
"epoch": 0.06942413073577879,
|
3121 |
+
"grad_norm": 0.253542423248291,
|
3122 |
+
"learning_rate": 0.00018873014471397224,
|
3123 |
+
"loss": 1.1299,
|
3124 |
+
"step": 445
|
3125 |
+
},
|
3126 |
+
{
|
3127 |
+
"epoch": 0.06958014001833109,
|
3128 |
+
"grad_norm": 0.3034575283527374,
|
3129 |
+
"learning_rate": 0.00018867032301956088,
|
3130 |
+
"loss": 1.3577,
|
3131 |
+
"step": 446
|
3132 |
+
},
|
3133 |
+
{
|
3134 |
+
"epoch": 0.0697361493008834,
|
3135 |
+
"grad_norm": 0.31302767992019653,
|
3136 |
+
"learning_rate": 0.00018861035250748343,
|
3137 |
+
"loss": 1.6029,
|
3138 |
+
"step": 447
|
3139 |
+
},
|
3140 |
+
{
|
3141 |
+
"epoch": 0.06989215858343571,
|
3142 |
+
"grad_norm": 0.26993393898010254,
|
3143 |
+
"learning_rate": 0.00018855023327838983,
|
3144 |
+
"loss": 1.2035,
|
3145 |
+
"step": 448
|
3146 |
+
},
|
3147 |
+
{
|
3148 |
+
"epoch": 0.07004816786598803,
|
3149 |
+
"grad_norm": 0.27148422598838806,
|
3150 |
+
"learning_rate": 0.00018848996543317982,
|
3151 |
+
"loss": 1.5843,
|
3152 |
+
"step": 449
|
3153 |
+
},
|
3154 |
+
{
|
3155 |
+
"epoch": 0.07020417714854034,
|
3156 |
+
"grad_norm": 0.2631765305995941,
|
3157 |
+
"learning_rate": 0.00018842954907300236,
|
3158 |
+
"loss": 1.2641,
|
3159 |
+
"step": 450
|
3160 |
+
},
|
3161 |
+
{
|
3162 |
+
"epoch": 0.07036018643109265,
|
3163 |
+
"grad_norm": 0.2621013820171356,
|
3164 |
+
"learning_rate": 0.00018836898429925585,
|
3165 |
+
"loss": 1.2167,
|
3166 |
+
"step": 451
|
3167 |
+
},
|
3168 |
+
{
|
3169 |
+
"epoch": 0.07051619571364497,
|
3170 |
+
"grad_norm": 0.25064215064048767,
|
3171 |
+
"learning_rate": 0.0001883082712135877,
|
3172 |
+
"loss": 1.2631,
|
3173 |
+
"step": 452
|
3174 |
+
},
|
3175 |
+
{
|
3176 |
+
"epoch": 0.07067220499619728,
|
3177 |
+
"grad_norm": 0.2558056712150574,
|
3178 |
+
"learning_rate": 0.00018824740991789415,
|
3179 |
+
"loss": 0.9964,
|
3180 |
+
"step": 453
|
3181 |
+
},
|
3182 |
+
{
|
3183 |
+
"epoch": 0.07082821427874958,
|
3184 |
+
"grad_norm": 0.2675093412399292,
|
3185 |
+
"learning_rate": 0.00018818640051432035,
|
3186 |
+
"loss": 1.4953,
|
3187 |
+
"step": 454
|
3188 |
+
},
|
3189 |
+
{
|
3190 |
+
"epoch": 0.07098422356130189,
|
3191 |
+
"grad_norm": 0.2550821006298065,
|
3192 |
+
"learning_rate": 0.0001881252431052599,
|
3193 |
+
"loss": 1.1283,
|
3194 |
+
"step": 455
|
3195 |
+
},
|
3196 |
+
{
|
3197 |
+
"epoch": 0.0711402328438542,
|
3198 |
+
"grad_norm": 0.24893717467784882,
|
3199 |
+
"learning_rate": 0.00018806393779335483,
|
3200 |
+
"loss": 1.1725,
|
3201 |
+
"step": 456
|
3202 |
+
},
|
3203 |
+
{
|
3204 |
+
"epoch": 0.07129624212640652,
|
3205 |
+
"grad_norm": 0.24471914768218994,
|
3206 |
+
"learning_rate": 0.00018800248468149543,
|
3207 |
+
"loss": 1.19,
|
3208 |
+
"step": 457
|
3209 |
+
},
|
3210 |
+
{
|
3211 |
+
"epoch": 0.07145225140895883,
|
3212 |
+
"grad_norm": 0.27745166420936584,
|
3213 |
+
"learning_rate": 0.00018794088387282,
|
3214 |
+
"loss": 1.6347,
|
3215 |
+
"step": 458
|
3216 |
+
},
|
3217 |
+
{
|
3218 |
+
"epoch": 0.07160826069151115,
|
3219 |
+
"grad_norm": 0.2930917739868164,
|
3220 |
+
"learning_rate": 0.00018787913547071484,
|
3221 |
+
"loss": 1.5139,
|
3222 |
+
"step": 459
|
3223 |
+
},
|
3224 |
+
{
|
3225 |
+
"epoch": 0.07176426997406346,
|
3226 |
+
"grad_norm": 0.2656380534172058,
|
3227 |
+
"learning_rate": 0.00018781723957881372,
|
3228 |
+
"loss": 1.1726,
|
3229 |
+
"step": 460
|
3230 |
+
},
|
3231 |
+
{
|
3232 |
+
"epoch": 0.07192027925661577,
|
3233 |
+
"grad_norm": 0.27983731031417847,
|
3234 |
+
"learning_rate": 0.0001877551963009982,
|
3235 |
+
"loss": 1.3818,
|
3236 |
+
"step": 461
|
3237 |
+
},
|
3238 |
+
{
|
3239 |
+
"epoch": 0.07207628853916809,
|
3240 |
+
"grad_norm": 0.2744976580142975,
|
3241 |
+
"learning_rate": 0.0001876930057413971,
|
3242 |
+
"loss": 1.2756,
|
3243 |
+
"step": 462
|
3244 |
+
},
|
3245 |
+
{
|
3246 |
+
"epoch": 0.07223229782172039,
|
3247 |
+
"grad_norm": 0.2684760093688965,
|
3248 |
+
"learning_rate": 0.00018763066800438636,
|
3249 |
+
"loss": 1.2302,
|
3250 |
+
"step": 463
|
3251 |
+
},
|
3252 |
+
{
|
3253 |
+
"epoch": 0.0723883071042727,
|
3254 |
+
"grad_norm": 0.25079357624053955,
|
3255 |
+
"learning_rate": 0.00018756818319458907,
|
3256 |
+
"loss": 1.1575,
|
3257 |
+
"step": 464
|
3258 |
+
},
|
3259 |
+
{
|
3260 |
+
"epoch": 0.07254431638682501,
|
3261 |
+
"grad_norm": 0.2802796959877014,
|
3262 |
+
"learning_rate": 0.000187505551416875,
|
3263 |
+
"loss": 1.3711,
|
3264 |
+
"step": 465
|
3265 |
+
},
|
3266 |
+
{
|
3267 |
+
"epoch": 0.07270032566937733,
|
3268 |
+
"grad_norm": 0.7640414237976074,
|
3269 |
+
"learning_rate": 0.0001874427727763607,
|
3270 |
+
"loss": 1.3431,
|
3271 |
+
"step": 466
|
3272 |
+
},
|
3273 |
+
{
|
3274 |
+
"epoch": 0.07285633495192964,
|
3275 |
+
"grad_norm": 0.265717089176178,
|
3276 |
+
"learning_rate": 0.0001873798473784092,
|
3277 |
+
"loss": 1.1778,
|
3278 |
+
"step": 467
|
3279 |
+
},
|
3280 |
+
{
|
3281 |
+
"epoch": 0.07301234423448195,
|
3282 |
+
"grad_norm": 0.23273074626922607,
|
3283 |
+
"learning_rate": 0.00018731677532862976,
|
3284 |
+
"loss": 1.02,
|
3285 |
+
"step": 468
|
3286 |
+
},
|
3287 |
+
{
|
3288 |
+
"epoch": 0.07316835351703427,
|
3289 |
+
"grad_norm": 0.248812735080719,
|
3290 |
+
"learning_rate": 0.00018725355673287778,
|
3291 |
+
"loss": 1.1423,
|
3292 |
+
"step": 469
|
3293 |
+
},
|
3294 |
+
{
|
3295 |
+
"epoch": 0.07332436279958658,
|
3296 |
+
"grad_norm": 0.24919858574867249,
|
3297 |
+
"learning_rate": 0.00018719019169725472,
|
3298 |
+
"loss": 1.2377,
|
3299 |
+
"step": 470
|
3300 |
+
},
|
3301 |
+
{
|
3302 |
+
"epoch": 0.07348037208213888,
|
3303 |
+
"grad_norm": 0.25503799319267273,
|
3304 |
+
"learning_rate": 0.00018712668032810768,
|
3305 |
+
"loss": 1.3236,
|
3306 |
+
"step": 471
|
3307 |
+
},
|
3308 |
+
{
|
3309 |
+
"epoch": 0.0736363813646912,
|
3310 |
+
"grad_norm": 0.28893566131591797,
|
3311 |
+
"learning_rate": 0.00018706302273202943,
|
3312 |
+
"loss": 1.4662,
|
3313 |
+
"step": 472
|
3314 |
+
},
|
3315 |
+
{
|
3316 |
+
"epoch": 0.07379239064724351,
|
3317 |
+
"grad_norm": 0.2384706735610962,
|
3318 |
+
"learning_rate": 0.00018699921901585813,
|
3319 |
+
"loss": 1.2817,
|
3320 |
+
"step": 473
|
3321 |
+
},
|
3322 |
+
{
|
3323 |
+
"epoch": 0.07394839992979582,
|
3324 |
+
"grad_norm": 0.2527397572994232,
|
3325 |
+
"learning_rate": 0.0001869352692866772,
|
3326 |
+
"loss": 1.1766,
|
3327 |
+
"step": 474
|
3328 |
+
},
|
3329 |
+
{
|
3330 |
+
"epoch": 0.07410440921234814,
|
3331 |
+
"grad_norm": 0.25340378284454346,
|
3332 |
+
"learning_rate": 0.00018687117365181512,
|
3333 |
+
"loss": 1.1876,
|
3334 |
+
"step": 475
|
3335 |
+
},
|
3336 |
+
{
|
3337 |
+
"epoch": 0.07426041849490045,
|
3338 |
+
"grad_norm": 0.2570219039916992,
|
3339 |
+
"learning_rate": 0.00018680693221884517,
|
3340 |
+
"loss": 1.3472,
|
3341 |
+
"step": 476
|
3342 |
+
},
|
3343 |
+
{
|
3344 |
+
"epoch": 0.07441642777745276,
|
3345 |
+
"grad_norm": 0.25267085433006287,
|
3346 |
+
"learning_rate": 0.00018674254509558544,
|
3347 |
+
"loss": 1.5048,
|
3348 |
+
"step": 477
|
3349 |
+
},
|
3350 |
+
{
|
3351 |
+
"epoch": 0.07457243706000508,
|
3352 |
+
"grad_norm": 0.24603790044784546,
|
3353 |
+
"learning_rate": 0.00018667801239009846,
|
3354 |
+
"loss": 1.276,
|
3355 |
+
"step": 478
|
3356 |
+
},
|
3357 |
+
{
|
3358 |
+
"epoch": 0.07472844634255738,
|
3359 |
+
"grad_norm": 0.2434520423412323,
|
3360 |
+
"learning_rate": 0.00018661333421069113,
|
3361 |
+
"loss": 1.3999,
|
3362 |
+
"step": 479
|
3363 |
+
},
|
3364 |
+
{
|
3365 |
+
"epoch": 0.07488445562510969,
|
3366 |
+
"grad_norm": 0.27032792568206787,
|
3367 |
+
"learning_rate": 0.00018654851066591448,
|
3368 |
+
"loss": 1.3909,
|
3369 |
+
"step": 480
|
3370 |
+
},
|
3371 |
+
{
|
3372 |
+
"epoch": 0.075040464907662,
|
3373 |
+
"grad_norm": 0.26559844613075256,
|
3374 |
+
"learning_rate": 0.00018648354186456348,
|
3375 |
+
"loss": 1.2931,
|
3376 |
+
"step": 481
|
3377 |
+
},
|
3378 |
+
{
|
3379 |
+
"epoch": 0.07519647419021432,
|
3380 |
+
"grad_norm": 0.2563202679157257,
|
3381 |
+
"learning_rate": 0.000186418427915677,
|
3382 |
+
"loss": 1.2773,
|
3383 |
+
"step": 482
|
3384 |
+
},
|
3385 |
+
{
|
3386 |
+
"epoch": 0.07535248347276663,
|
3387 |
+
"grad_norm": 0.2463751882314682,
|
3388 |
+
"learning_rate": 0.00018635316892853741,
|
3389 |
+
"loss": 1.4017,
|
3390 |
+
"step": 483
|
3391 |
+
},
|
3392 |
+
{
|
3393 |
+
"epoch": 0.07550849275531894,
|
3394 |
+
"grad_norm": 0.26452189683914185,
|
3395 |
+
"learning_rate": 0.00018628776501267052,
|
3396 |
+
"loss": 1.2236,
|
3397 |
+
"step": 484
|
3398 |
+
},
|
3399 |
+
{
|
3400 |
+
"epoch": 0.07566450203787126,
|
3401 |
+
"grad_norm": 0.48540955781936646,
|
3402 |
+
"learning_rate": 0.0001862222162778454,
|
3403 |
+
"loss": 1.1676,
|
3404 |
+
"step": 485
|
3405 |
+
},
|
3406 |
+
{
|
3407 |
+
"epoch": 0.07582051132042357,
|
3408 |
+
"grad_norm": 0.2931404411792755,
|
3409 |
+
"learning_rate": 0.0001861565228340742,
|
3410 |
+
"loss": 1.3877,
|
3411 |
+
"step": 486
|
3412 |
+
},
|
3413 |
+
{
|
3414 |
+
"epoch": 0.07597652060297588,
|
3415 |
+
"grad_norm": 0.2707270383834839,
|
3416 |
+
"learning_rate": 0.00018609068479161182,
|
3417 |
+
"loss": 1.2828,
|
3418 |
+
"step": 487
|
3419 |
+
},
|
3420 |
+
{
|
3421 |
+
"epoch": 0.07613252988552818,
|
3422 |
+
"grad_norm": 0.25902295112609863,
|
3423 |
+
"learning_rate": 0.00018602470226095603,
|
3424 |
+
"loss": 1.2393,
|
3425 |
+
"step": 488
|
3426 |
+
},
|
3427 |
+
{
|
3428 |
+
"epoch": 0.0762885391680805,
|
3429 |
+
"grad_norm": 0.27907291054725647,
|
3430 |
+
"learning_rate": 0.00018595857535284692,
|
3431 |
+
"loss": 1.1944,
|
3432 |
+
"step": 489
|
3433 |
+
},
|
3434 |
+
{
|
3435 |
+
"epoch": 0.07644454845063281,
|
3436 |
+
"grad_norm": 0.3079850375652313,
|
3437 |
+
"learning_rate": 0.00018589230417826697,
|
3438 |
+
"loss": 1.3686,
|
3439 |
+
"step": 490
|
3440 |
+
},
|
3441 |
+
{
|
3442 |
+
"epoch": 0.07660055773318512,
|
3443 |
+
"grad_norm": 0.250303715467453,
|
3444 |
+
"learning_rate": 0.00018582588884844084,
|
3445 |
+
"loss": 1.2497,
|
3446 |
+
"step": 491
|
3447 |
+
},
|
3448 |
+
{
|
3449 |
+
"epoch": 0.07675656701573744,
|
3450 |
+
"grad_norm": 0.260257750749588,
|
3451 |
+
"learning_rate": 0.00018575932947483502,
|
3452 |
+
"loss": 1.4186,
|
3453 |
+
"step": 492
|
3454 |
+
},
|
3455 |
+
{
|
3456 |
+
"epoch": 0.07691257629828975,
|
3457 |
+
"grad_norm": 0.2537723481655121,
|
3458 |
+
"learning_rate": 0.00018569262616915784,
|
3459 |
+
"loss": 1.28,
|
3460 |
+
"step": 493
|
3461 |
+
},
|
3462 |
+
{
|
3463 |
+
"epoch": 0.07706858558084206,
|
3464 |
+
"grad_norm": 0.21861004829406738,
|
3465 |
+
"learning_rate": 0.00018562577904335912,
|
3466 |
+
"loss": 0.9705,
|
3467 |
+
"step": 494
|
3468 |
+
},
|
3469 |
+
{
|
3470 |
+
"epoch": 0.07722459486339438,
|
3471 |
+
"grad_norm": 0.322566956281662,
|
3472 |
+
"learning_rate": 0.00018555878820963013,
|
3473 |
+
"loss": 1.4941,
|
3474 |
+
"step": 495
|
3475 |
+
},
|
3476 |
+
{
|
3477 |
+
"epoch": 0.07738060414594668,
|
3478 |
+
"grad_norm": 0.24904873967170715,
|
3479 |
+
"learning_rate": 0.00018549165378040327,
|
3480 |
+
"loss": 1.2277,
|
3481 |
+
"step": 496
|
3482 |
+
},
|
3483 |
+
{
|
3484 |
+
"epoch": 0.07753661342849899,
|
3485 |
+
"grad_norm": 0.2692057490348816,
|
3486 |
+
"learning_rate": 0.00018542437586835202,
|
3487 |
+
"loss": 1.3786,
|
3488 |
+
"step": 497
|
3489 |
+
},
|
3490 |
+
{
|
3491 |
+
"epoch": 0.0776926227110513,
|
3492 |
+
"grad_norm": 0.27876508235931396,
|
3493 |
+
"learning_rate": 0.00018535695458639056,
|
3494 |
+
"loss": 1.3822,
|
3495 |
+
"step": 498
|
3496 |
+
},
|
3497 |
+
{
|
3498 |
+
"epoch": 0.07784863199360362,
|
3499 |
+
"grad_norm": 0.2497495859861374,
|
3500 |
+
"learning_rate": 0.00018528939004767376,
|
3501 |
+
"loss": 1.1872,
|
3502 |
+
"step": 499
|
3503 |
+
},
|
3504 |
+
{
|
3505 |
+
"epoch": 0.07800464127615593,
|
3506 |
+
"grad_norm": 0.28155678510665894,
|
3507 |
+
"learning_rate": 0.00018522168236559695,
|
3508 |
+
"loss": 1.2253,
|
3509 |
+
"step": 500
|
3510 |
+
},
|
3511 |
+
{
|
3512 |
+
"epoch": 0.07800464127615593,
|
3513 |
+
"eval_loss": 1.3168833255767822,
|
3514 |
+
"eval_runtime": 110.9584,
|
3515 |
+
"eval_samples_per_second": 38.51,
|
3516 |
+
"eval_steps_per_second": 4.822,
|
3517 |
+
"step": 500
|
3518 |
+
}
|
3519 |
+
],
|
3520 |
+
"logging_steps": 1,
|
3521 |
+
"max_steps": 2500,
|
3522 |
+
"num_input_tokens_seen": 0,
|
3523 |
+
"num_train_epochs": 1,
|
3524 |
+
"save_steps": 500,
|
3525 |
+
"stateful_callbacks": {
|
3526 |
+
"TrainerControl": {
|
3527 |
+
"args": {
|
3528 |
+
"should_epoch_stop": false,
|
3529 |
+
"should_evaluate": false,
|
3530 |
+
"should_log": false,
|
3531 |
+
"should_save": true,
|
3532 |
+
"should_training_stop": false
|
3533 |
+
},
|
3534 |
+
"attributes": {}
|
3535 |
+
}
|
3536 |
+
},
|
3537 |
+
"total_flos": 2.0723785343901696e+16,
|
3538 |
+
"train_batch_size": 1,
|
3539 |
+
"trial_name": null,
|
3540 |
+
"trial_params": null
|
3541 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:839f2fc339cb5a7bf1b4d97030548a0af80cf4a1f7f0ce195c4516eef9f3eca4
|
3 |
+
size 5496
|